Um die anderen Arten von Veröffentlichungen zu diesem Thema anzuzeigen, folgen Sie diesem Link: Joint coordinates estimation.
Zeitschriftenartikel zum Thema „Joint coordinates estimation“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit Top-50 Zeitschriftenartikel für die Forschung zum Thema "Joint coordinates estimation" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Sehen Sie die Zeitschriftenartikel für verschiedene Spezialgebieten durch und erstellen Sie Ihre Bibliographie auf korrekte Weise.
1
Rong, Dang, und Feng Gang. „Coordinate-Corrected and Graph-Convolution-Based Hand Pose Estimation Method“. Sensors 24, Nr. 22 (14.11.2024): 7289. http://dx.doi.org/10.3390/s24227289.
Der volle Inhalt der QuelleAnnotation:
To address the problem of low accuracy in joint point estimation in hand pose estimation methods due to the self-similarity of fingers and easy self-obscuration of hand joints, a hand pose estimation method based on coordinate correction and graph convolution is proposed. First, the standard coordinate encoding is improved by generating an unbiased heat map, and the distribution-aware method is used for decoding coordinates to reduce the error in decoding the coordinate encoding of joints. Then, the complex dependency relationship between the joints and the relationship between pixels and joints of the hand are modeled by using graph convolution, and the feature information of the hand joints is enhanced by determining the relationship between the hand joints. Finally, the skeletal constraint loss function is used to impose constraints on the joints, and a natural and undistorted hand skeleton structure is generated. Training tests are conducted on the public gesture interaction dataset STB, and the experimental results show that the method in this paper can reduce errors in hand joint point detection and improve the estimation accuracy.
2
Goldenberg, A. A., J. A. Apkarian und H. W. Smith. „A New Approach to Kinematic Control of Robot Manipulators“. Journal of Dynamic Systems, Measurement, and Control 109, Nr. 2 (01.06.1987): 97–103. http://dx.doi.org/10.1115/1.3143843.
Der volle Inhalt der QuelleAnnotation:
A new approach for solving the inverse kinematics problem iteratively is presented. The solution is based on the recursive estimation of a kinematics operator which maps the task space coordinates into joint coordinates. The recursive estimation is based on least square approximation. For controlling the robot, the solution (Joint coordinates) must be compensated to achieve an arbitrarily small error (in least square sense) of the desired task space coordinates. The compensation is provided by closed loop feedback of task space coordinates using an optimal control approach.
3
Liu, Tiexin, und Jianhui Deng. „Photogrammetry-Based 3D Textured Point Cloud Models Building and Rock Structure Estimation“. Applied Sciences 13, Nr. 8 (15.04.2023): 4977. http://dx.doi.org/10.3390/app13084977.
Der volle Inhalt der QuelleAnnotation:
Trace lines on the outcrop of a rock mass are usually the primary data source for the estimation of rock structure. It is important to obtain the data of trace lines precisely. Photogrammetry is well suited to finish this task. However, this is mainly conducted by commercial software, and not every researcher has easy access to the method of digital photogrammetry. This study aims to provide researchers with a low-cost method of building a photogrammetry-based textured 3D point cloud model (FMBPM) and display the applicability of the method to estimating the rock structure of rock masses. In the FMBPM, a digital single-lens reflex camera with a prime lens and a total station are the necessary hardware employed to capture images and measure the coordinates of feature points. A coordinate transformation means of converting model coordinates to physical coordinates was introduced. A program for calculating a joint orientation based on the coordinates of inflection points on the trace line of the joint was developed. A section of a rock slope was selected as a case to show the procedures and the practicability of the FMBPM. The textured 3D point cloud model of the rock slope was successfully built, and the rock structure of the rock slope was analyzed using the joint disk model generated based on the trace lines extracted from the point cloud model. The results show that: (1) the precision of the point coordinates of the textured 3D point cloud model could achieve 3.96 mm, taking the data of the total station as the reference; (2) the rock structure of the slope is good, according to the value of the rock quality designation; (3) the new method is applicable in engineering practices.
4
Choi, Seoung Wook, Jin Young Lee und Gye Young Kim. „Multi-View 3D Human Pose Estimation Based on Transformer“. Korean Institute of Smart Media 12, Nr. 11 (31.12.2023): 48–56. http://dx.doi.org/10.30693/smj.2023.12.11.48.
Der volle Inhalt der QuelleAnnotation:
The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.
5
万, 云翀, Yunpeng Song und Ligang Liu. „3D Human Pose Estimation Based on Volumetric Joint Coordinates“. Journal of Computer-Aided Design & Computer Graphics 34, Nr. 09 (01.09.2022): 1411–19. http://dx.doi.org/10.3724/sp.j.1089.2022.19167.
Der volle Inhalt der Quelle
6
Wang, Ziao, Weixing Wang, Jingxi Chen, Xuzhuang Zhang und Ziheng Miao. „Posture Risk Assessment and Workload Estimation for Material Handling by Computer Vision“. International Journal of Intelligent Systems 2023 (25.10.2023): 1–19. http://dx.doi.org/10.1155/2023/2085251.
Der volle Inhalt der QuelleAnnotation:
Workers in material handling tasks often suffer from work-related musculoskeletal disorders (WMSDs) caused by inaccurate work postures or the lifting of excessively heavy loads. Therefore, effective ergonomic assessment of workers is needed to improve worker productivity while reducing the risk of musculoskeletal disorders. This paper proposes a noninvasive method for evaluating posture risks and load analysis in manual material handling tasks. The study focuses on three main aspects: first, using 3D pose recognition technology to extract the 3D coordinates and joint angles of the human body. Second, the REBA method was improved by using fuzzy logic theory to more effectively capture the slow transition features of continuous movement by humans without abruptly altering risk scores, as well as to increase the accuracy and consistency of posture risk evaluation. Third, joint torque and workloads were estimated using biomechanical calculations by integrating pressure insoles and 3D joint coordinate data. Experiments show that this method can effectively evaluate posture risks and workloads in manual material handling tasks, with a correlation coefficient of 0.817 ( p < 0.01 ) between fuzzy logic REBA and REBA and an error rate of 15% in estimating workloads of eight joints. This method can help reduce occupational health risks for workers and industries and improve work efficiency.
7
Wu, Xiaoming, Yu Cao, Yu Wang, Bing Li, Haitao Yang und S. P. Raja. „Posture Estimation of Curve Running Motion Using Nano-Biosensor and Machine Learning“. International Journal of Interactive Multimedia and Artificial Intelligence In Press, In Press (2024): 1–9. http://dx.doi.org/10.9781/ijimai.2024.07.001.
Der volle Inhalt der QuelleAnnotation:
Curve running is a common form of training and competition. Conducting research on posture estimation during curve running can provide more accurate training and competition data for athletes. However, due to the unique nature of curve running, traditional posture estimation methods neglect the temporal changes in athlete posture, resulting in a decrease in estimation accuracy. Therefore, a posture estimation method for curve running motion using nano-biosensor and machine learning is proposed. First, the motion parameters of humans are collected by nano-biosensor, and the posture coordinates are obtained preliminarily. Second, the posture coordinates are established according to the human motion parameters, and the curve running posture data is obtained and filtered to obtain more accurate data. Finally, the Bayesian network in machine learning is used to continuously track the posture, and a nonlinear equation is established to fuse the posture angle obtained by the sensor and the posture tracked by the Bayesian network, to realize the posture estimation of curve running motion. The results show that the proposed estimation method has a good motion posture estimation effect, and the hip joint estimation error, knee joint estimation error and ankle joint estimation error are all less than 5°, and the endpoint displacement estimation offset rate is less than 2%. It can realize accurate motion posture estimation of curve running motion, and has important application value in the field of track training.
8
Tsareva, Olga, Ivan Dmitriev und Yuriy Kornilov. „Estimation of absolute deformations by changes in distances between the reference points and deformation marks“. MATEC Web of Conferences 245 (2018): 04013. http://dx.doi.org/10.1051/matecconf/201824504013.
Der volle Inhalt der QuelleAnnotation:
The article considers the definition of absolute types of deformations, such as transfer and rotation of a building, using linear spatial intersection. In particular, knowing the distances between strong points and deformation marks, the coordinates of the marks located on the building in the initial and current observation cycles are obtained. Knowing the coordinates of the marks, calculate the displacement vectors of the marks for a certain period of time. The definition of absolute deformations is based on the estimation of the projections of the displacement vectors on the coordinate axes, as well as the direction cosines of the vectors with the coordinate axes. The determination of the direction of displacement is shown for the transference deformation. And how to determine the axis, the distance to this axis and the angle of rotation is shown for rotation deformation. We show for joint deformation of the transfer and rotation how divide it into components and then determine the direction of displacement and the axis of rotation. The results can be used in assessing of absolute deformations buildings of monuments of cultural heritage.
9
Rutkovskiy, V. Yu, V. M. Glumov und A. S. Ermilov. „Angular Motion Control of a Large Space Structure with Elastic Elements“. Avtomatika i telemehanika, Nr. 8 (15.12.2023): 122–37. http://dx.doi.org/10.31857/s0005231023080081.
Der volle Inhalt der QuelleAnnotation:
The task of angular orientation and stabilization of a space structure during its assembly in orbit is solved. The structure includes elastic elements that are installed during the assembly process. The elastic elements of the structure have no sensors to obtain information about their deformation parameters. Control algorithms are proposed to ensure the stability of the angular motion of the structure. A nonlinear extended Kalman filter is used to obtain the necessary information. A joint estimation algorithm for the coordinates of the angular motion of the considered mechanical system and the coordinates of the elastic vibration tones, as well as an algorithm for the identification of their unobservable parameters are developed. The results of mathematical modeling of a variant of the mechanical system of a space structure are presented, which confirm the operability and efficiency of the developed algorithms for estimating coordinates and parameters.
10
Seo, Jiho, Jonghyeok Lee, Jaehyun Park, Hyungju Kim und Sungjin You. „Distributed Two-Dimensional MUSIC for Joint Range and Angle Estimation with Distributed FMCW MIMO Radars“. Sensors 21, Nr. 22 (16.11.2021): 7618. http://dx.doi.org/10.3390/s21227618.
Der volle Inhalt der QuelleAnnotation:
To estimate range and angle information of multiple targets, FMCW MIMO radars have been exploited with 2D MUSIC algorithms. To improve estimation accuracy, received signals from multiple FMCW MIMO radars are collected at the data fusion center and processed coherently, which increases data communication overhead and implementation complexity. To resolve them, we propose the distributed 2D MUSIC algorithm with coordinate transformation, in which 2D MUSIC algorithm is operated with respect to the reference radar’s coordinate at each radar in a distributed way. Rather than forwarding the raw data of received signal to the fusion center, each radar performs 2D MUSIC with its own received signal in the transformed coordinates. Accordingly, the distributed radars do not need to report all their measured signals to the data fusion center, but they forward their local cost function values of 2D MUSIC for the radar image region of interest. The data fusion center can then estimate the range and angle information of targets jointly from the aggregated cost function. By applying the proposed scheme to the experimentally measured data, its performance is verified in the real environment test.
11
Li, Moran, Yuan Gao und Nong Sang. „Exploiting Learnable Joint Groups for Hand Pose Estimation“. Proceedings of the AAAI Conference on Artificial Intelligence 35, Nr. 3 (18.05.2021): 1921–29. http://dx.doi.org/10.1609/aaai.v35i3.16287.
Der volle Inhalt der QuelleAnnotation:
In this paper, we propose to estimate 3D hand pose by recovering the 3D coordinates of joints in a group-wise manner, where less-related joints are automatically categorized into different groups and exhibit different features. This is different from the previous methods where all the joints are considered holistically and share the same feature. The benefits of our method are illustrated by the principle of multi-task learning (MTL), i.e., by separating less-related joints into different groups (as different tasks), our method learns different features for each of them, therefore efficiently avoids the negative transfer (among less related tasks/groups of joints). The key of our method is a novel binary selector that automatically selects related joints into the same group. We implement such a selector with binary values stochastically sampled from a Concretedistribution, which is constructed using Gumbel softmax on trainable parameters. This enables us to preserve the differentiable property of the whole network. We further exploit features from those less-related groups by carrying out an additional feature fusing scheme among them, to learn more discriminative features. This is realized by implementing multiple 1x1 convolutions on the concatenated features, where each joint group contains a unique 1x1convolution for feature fusion. The detailed ablation analysis and the extensive experiments on several benchmark datasets demonstrate the promising performance of the proposed method over the state-of-the-art (SOTA) methods. Besides, our method achieves top-1 among all the methods that do not exploit the dense 3D shape labels on the most recently released FreiHAND competition at the submission date. The source code and models are available at https://github.com/moranli-aca/LearnableGroups-Hand.
12
Nechaev, Yury Borisovich, Ilia Vladimirovich Peshkov, Nataliya Alexandrovna Fortunova, Irina Nikolaevna Zaitseva und Eugene Alexandrovich Arnautov. „Improving the shapes of planar antenna arrays to improve accuracy of radar with super-resolution“. Vestnik of Astrakhan State Technical University. Series: Management, computer science and informatics 2022, Nr. 3 (29.07.2022): 38–50. http://dx.doi.org/10.24143/2072-9502-2022-3-38-50.
Der volle Inhalt der QuelleAnnotation:
A promising way to increase the bandwidth and noise immunity of modern wireless information transmission systems is the use of antenna arrays equipped with a digital signal processing unit, which include MIMO systems (Multiple Input Multiple Output), as well as adaptive (smart) antennas. The main advantage of this approach is the antenna’s spacing, which makes it possible to assess the angular coordinates of radio signals with further developing
a radiation pattern. Gaps in studying the influence of the lattice geometry together with various kinds of antenna elements are known to be one of the factors of inaccuracy of such systems. The work is aimed at obtaining the shape
of a planar antenna array with a higher direction finding accuracy. There is described an algorithm for calculating such an arrangement of antenna elements of flat antenna arrays, in which the standard deviation of the estimates of the angular coordinates of one and two radio signal sources is reduced. The proposed approach is based on the analysis
of the influence of antenna location on the variance of estimates described by the lower boundary of Kramer-Rao. This value shows the influence of the location of antenna elements on the accuracy of estimating the direction of arrival of a joint assessment with two signal sources. It has been shown that the accuracy of the direction-of-arrival non-joint estimation is determined as the sum of squared differences between all coordinates of omnidirectional elements along the X- and Y-axis if one signal arrives. If two signals arrive, the accuracy of the direction-of-arrival joint estimation depends on the sum of cosines having the argument with the difference between sensor coordinates and signals radius-vectors. The optimal location of the antenna elements using the obtained expressions can be calculated very easily to reduce the direction-finding errors near particular sectors. In order to confirm the proposed method, there were studied the antenna arrays built after minimizing the boundary of Kramer-Rao, where the target functions are the new expressions. It is found out that the new shapes of antenna arrays based on the analytical expressions have better direction-of-arrival accuracy in comparison with the circular ones.
13
Cai, Qingyuan, Xuecai Hu, Saihui Hou, Li Yao und Yongzhen Huang. „Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser“. Proceedings of the AAAI Conference on Artificial Intelligence 38, Nr. 2 (24.03.2024): 882–90. http://dx.doi.org/10.1609/aaai.v38i2.27847.
Der volle Inhalt der QuelleAnnotation:
Recently, diffusion-based methods for monocular 3D human pose estimation have achieved state-of-the-art (SOTA) performance by directly regressing the 3D joint coordinates from the 2D pose sequence. Although some methods decompose the task into bone length and bone direction prediction based on the human anatomical skeleton to explicitly incorporate more human body prior constraints, the performance of these methods is significantly lower than that of the SOTA diffusion-based methods. This can be attributed to the tree structure of the human skeleton. Direct application of the disentangled method could amplify the accumulation of hierarchical errors, propagating through each hierarchy. Meanwhile, the hierarchical information has not been fully explored by the previous methods. To address these problems, a Disentangled Diffusion-based 3D human Pose Estimation method with Hierarchical Spatial and Temporal Denoiser is proposed, termed DDHPose. In our approach: (1) We disentangle the 3d pose and diffuse the bone length and bone direction during the forward process of the diffusion model to effectively model the human pose prior. A disentanglement loss is proposed to supervise diffusion model learning. (2) For the reverse process, we propose Hierarchical Spatial and Temporal Denoiser (HSTDenoiser) to improve the hierarchical modelling of each joint. Our HSTDenoiser comprises two components: the Hierarchical-Related Spatial Transformer (HRST) and the Hierarchical-Related Temporal Transformer (HRTT). HRST exploits joint spatial information and the influence of the parent joint on each joint for spatial modeling, while HRTT utilizes information from both the joint and its hierarchical adjacent joints to explore the hierarchical temporal correlations among joints. Extensive experiments on the Human3.6M and MPI-INF-3DHP datasets show that our method outperforms the SOTA disentangled-based, non-disentangled based, and probabilistic approaches by 10.0%, 2.0%, and 1.3%, respectively.
14
Ferretti, G., C. Maffezzoni, G. Magnani und P. Rocco. „Joint Stiffness Estimation Based on Force Sensor Measurements in Industrial Manipulators“. Journal of Dynamic Systems, Measurement, and Control 116, Nr. 1 (01.03.1994): 163–67. http://dx.doi.org/10.1115/1.2900673.
Der volle Inhalt der QuelleAnnotation:
The problem of estimating the stiffness constants of the joints in industrial manipulators is addressed in this paper. It is shown that the model of the robot constrained by a rigid environment yields a simple relationship between variations of the motor coordinates and the forces arising at the contact with the environment. By exploiting the measurements of the motor positions sensors and of a force sensor located at the end effector a method is proposed to simply compute good estimates of the stiffness constants. Experiments have been made on the industrial robot SMART and the results are given and discussed.
15
Wenjing Ma, Wenjing Ma, Jianguang Zhao Wenjing Ma und Guangquan Zhu Jianguang Zhao. „Estimation on Human Motion Posture using Improved Deep Reinforcement Learning“. 電腦學刊 34, Nr. 4 (August 2023): 097–110. http://dx.doi.org/10.53106/199115992023083404008.
Der volle Inhalt der QuelleAnnotation:
<p>Estimating human motion posture can provide important data for intelligent monitoring systems, human-computer interaction, motion capture, and other fields. However, the traditional human motion posture estimation algorithm is difficult to achieve the goal of fast estimation of human motion posture. To address the problems of traditional algorithms, in the paper, we propose an estimation algorithm for human motion posture using improved deep reinforcement learning. First, the double deep Q network is constructed to improve the deep reinforcement learning algorithm. The improved deep reinforcement learning algorithm is used to locate the human motion posture coordinates and improve the effectiveness of bone point calibration. Second, the human motion posture analysis generative adversarial networks are constructed to realize the automatic recognition and analysis of human motion posture. Finally, using the preset human motion posture label, combined with the undirected graph model of the human, the human motion posture estimation is completed, and the precise estimation algorithm of the human motion posture is realized. Experiments are performed based on MPII Human Pose data set and HiEve data set. The results show that the proposed algorithm has higher positioning accuracy of joint nodes. The recognition effect of bone joint points is better, and the average is about 1.45%. The average posture accuracy is up to 98.2%, and the average joint point similarity is high. Therefore, it is proved that the proposed method has high application value in human-computer interaction, human motion capture and other fields.</p> <p> </p>
16
Huang, Weiting, Pengfei Ren, Jingyu Wang, Qi Qi und Haifeng Sun. „AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation“. Proceedings of the AAAI Conference on Artificial Intelligence 34, Nr. 07 (03.04.2020): 11061–68. http://dx.doi.org/10.1609/aaai.v34i07.6761.
Der volle Inhalt der QuelleAnnotation:
In this paper, we propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based and regression-based method. Hand joint coordinates are estimated as discrete integration of all pixels in dense representation, guided by adaptive weight maps. This learnable aggregation process introduces both dense and joint supervision that allows end-to-end training and brings adaptability to weight maps, making network more accurate and robust. Comprehensive exploration experiments are conducted to validate the effectiveness and generality of AWR under various experimental settings, especially its usefulness for different types of dense representation and input modality. Our method outperforms other state-of-the-art methods on four publicly available datasets, including NYU, ICVL, MSRA and HANDS 2017 dataset.
17
Park, Byung-Seo, Woosuk Kim, Jin-Kyum Kim, Eui Seok Hwang, Dong-Wook Kim und Young-Ho Seo. „3D Static Point Cloud Registration by Estimating Temporal Human Pose at Multiview“. Sensors 22, Nr. 3 (31.01.2022): 1097. http://dx.doi.org/10.3390/s22031097.
Der volle Inhalt der QuelleAnnotation:
This paper proposes a new technique for performing 3D static-point cloud registration after calibrating a multi-view RGB-D camera using a 3D (dimensional) joint set. Consistent feature points are required to calibrate a multi-view camera, and accurate feature points are necessary to obtain high-accuracy calibration results. In general, a special tool, such as a chessboard, is used to calibrate a multi-view camera. However, this paper uses joints on a human skeleton as feature points for calibrating a multi-view camera to perform calibration efficiently without special tools. We propose an RGB-D-based calibration algorithm that uses the joint coordinates of the 3D joint set obtained through pose estimation as feature points. Since human body information captured by the multi-view camera may be incomplete, a joint set predicted based on image information obtained through this may be incomplete. After efficiently integrating a plurality of incomplete joint sets into one joint set, multi-view cameras can be calibrated by using the combined joint set to obtain extrinsic matrices. To increase the accuracy of calibration, multiple joint sets are used for optimization through temporal iteration. We prove through experiments that it is possible to calibrate a multi-view camera using a large number of incomplete joint sets.
18
Izadbakhsh, Alireza, und Saeed Khorashadizadeh. „Robust task-space control of robot manipulators using differential equations for uncertainty estimation“. Robotica 35, Nr. 9 (08.09.2016): 1923–38. http://dx.doi.org/10.1017/s0263574716000588.
Der volle Inhalt der QuelleAnnotation:
SUMMARYMost control algorithms for rigid-link electrically driven robots are given in joint coordinates. However, since the task to be accomplished is expressed in Cartesian coordinates, inverse kinematics has to be computed in order to implement the control law. Alternatively, one can develop the necessary theory directly in workspace coordinates. This has the disadvantage of a more complex robot model. In this paper, a robust control scheme is given to achieve exact Cartesian tracking without the knowledge of the manipulator kinematics and dynamics, actuator dynamics and nor computing inverse kinematics. The control design procedure is based on a new form of universal approximation theory and using Stone–Weierstrass theorem, to mitigate structured and unstructured uncertainties associated with external disturbances and actuated manipulator dynamics. It has been assumed that the lumped uncertainty can be modeled by linear differential equations. As the method is Model-Free, a broad range of manipulators can be controlled. Numerical case studies are developed for an industrial robot manipulator.
19
Qin, Yuemei, Yang Han, Shuying Li und Jun Li. „An Iteratively Extended Target Tracking by Using Decorrelated Unbiased Conversion of Nonlinear Measurements“. Sensors 24, Nr. 5 (20.02.2024): 1362. http://dx.doi.org/10.3390/s24051362.
Der volle Inhalt der QuelleAnnotation:
Extended target tracking (ETT) based on random matrices typically assumes that the measurement model is linear. However, nonlinear measurements (such as range and azimuth) depending on locations of a series of unknown scattering centers always exist in many practical tracking applications. To address this issue, this paper proposes an iteratively extended target tracking based on random matrices by using decorrelated unbiased conversion of nonlinear measurements (ETT-IDUCM). First, we utilize a decorrelated unbiased converted measurement (DUCM) method to convert nonlinear measurements depending on unknown scatters of target extent in polar coordinates into the ones in Cartesian coordinates with equivalent measurement noise covariances. Subsequently, a novel method, combining iteratively extended Kalman filter (IEKF) updates with variational Bayesian (VB) cycles is developed for precise estimation of the target’s kinematic state and extension. This method leverages the synergy between external IEKF iterations, which use the estimated state as a new prediction and input for DUCM, and internal VB iterations, which realize a closed-form approximation of the joint posterior probability. This approach progressively enhances estimation accuracy. Simulation results demonstrate the ETT-IDUCM algorithm’s superior precision in estimating the target’s kinematic state and extension compared to existing methods.
20
Chen, Jian, Hui Zhao, Xiaoying Sun und Guohong Liu. „Joint 2D Direction-of-Arrival and Range Estimation for Nonstationary Sources“. International Journal of Antennas and Propagation 2014 (2014): 1–7. http://dx.doi.org/10.1155/2014/849039.
Der volle Inhalt der QuelleAnnotation:
Passive localization of nonstationary sources in the spherical coordinates (azimuth, elevation, and range) is considered, and a parallel factor analysis based method is addressed for the near-field parameter estimation problem. In this scheme, a parallel factor analysis model is firstly constructed by computing five time-frequency distribution matrices of the properly chosen observation data. In addition, the uniqueness of the constructed model is proved, and both the two-dimensional (2D) direction-of-arrival (DOA) and range can be jointly obtained via trilinear alternating least squares regression (TALS). The investigated algorithm is well suitable for near-field nonstationary source localization and does not require parameter-pairing or multidimensional search. Several simulation examples confirm the effectiveness of the proposed algorithm.
21
Xue, Feng, Fuli Bian und Shujie Li. „Attention fusion network for estimation of 3D joint coordinates and rotation of human pose“. Journal of Image and Graphics 29, Nr. 10 (2024): 3116–29. http://dx.doi.org/10.11834/jig.230502.
Der volle Inhalt der Quelle
22
Huang, Xin, Yuanping Zhu und Shuqin Wang. „An Efficient Dynamic Regulated Fuzzy Neural Network for Human Motion Retrieval and Analysis“. Symmetry 13, Nr. 8 (22.07.2021): 1317. http://dx.doi.org/10.3390/sym13081317.
Der volle Inhalt der QuelleAnnotation:
Human motion retrieval and analysis is a useful means of activity recognition to 3D human bodies. An efficient method is proposed to estimate human motion by using symmetric joint points and limb features of various limb parts based on regression task. We primarily obtain the 3D coordinates of symmetric joint points based on the located waist and hip points. By introducing three critical feature points on torso and symmetric joint points’ matching on motion video sequences, the 3D coordinates of symmetric joint points and its asymmetric limb features will not be affected by shading and interference of limb on different postures. With the asymmetric limb features of various human parts, a dynamic regulated Fuzzy neural network (DRFNN) is proposed to estimate human motion for different asymmetric postures using learning algorithm of network parameters and weights. Finally, human sequential actions corresponding to different asymmetric postures are presented according to the best retrieval results by DRFNN based on 3D human action database. Experiments show that compared with the traditional adaptive self-organizing fuzzy neural network (SOFNN) model, the proposed algorithm has higher estimation accuracy and better presentation results compared with the existing human motion analysis algorithms.
23
Pagnon, David, Mathieu Domalain und Lionel Reveret. „Pose2Sim: An End-to-End Workflow for 3D Markerless Sports Kinematics—Part 2: Accuracy“. Sensors 22, Nr. 7 (01.04.2022): 2712. http://dx.doi.org/10.3390/s22072712.
Der volle Inhalt der QuelleAnnotation:
Two-dimensional deep-learning pose estimation algorithms can suffer from biases in joint pose localizations, which are reflected in triangulated coordinates, and then in 3D joint angle estimation. Pose2Sim, our robust markerless kinematics workflow, comes with a physically consistent OpenSim skeletal model, meant to mitigate these errors. Its accuracy was concurrently validated against a reference marker-based method. Lower-limb joint angles were estimated over three tasks (walking, running, and cycling) performed multiple times by one participant. When averaged over all joint angles, the coefficient of multiple correlation (CMC) remained above 0.9 in the sagittal plane, except for the hip in running, which suffered from a systematic 15° offset (CMC = 0.65), and for the ankle in cycling, which was partially occluded (CMC = 0.75). When averaged over all joint angles and all degrees of freedom, mean errors were 3.0°, 4.1°, and 4.0°, in walking, running, and cycling, respectively; and range of motion errors were 2.7°, 2.3°, and 4.3°, respectively. Given the magnitude of error traditionally reported in joint angles computed from a marker-based optoelectronic system, Pose2Sim is deemed accurate enough for the analysis of lower-body kinematics in walking, cycling, and running.
24
Yadav, Santosh Kumar, Kamlesh Tiwari, Hari Mohan Pandey und Shaik Ali Akbar. „Skeleton-based human activity recognition using ConvLSTM and guided feature learning“. Soft Computing 26, Nr. 2 (01.10.2021): 877–90. http://dx.doi.org/10.1007/s00500-021-06238-7.
Der volle Inhalt der QuelleAnnotation:
AbstractHuman activity recognition aims to determine actions performed by a human in an image or video. Examples of human activity include standing, running, sitting, sleeping, etc. These activities may involve intricate motion patterns and undesired events such as falling. This paper proposes a novel deep convolutional long short-term memory (ConvLSTM) network for skeletal-based activity recognition and fall detection. The proposed ConvLSTM network is a sequential fusion of convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and fully connected layers. The acquisition system applies human detection and pose estimation to pre-calculate skeleton coordinates from the image/video sequence. The ConvLSTM model uses the raw skeleton coordinates along with their characteristic geometrical and kinematic features to construct the novel guided features. The geometrical and kinematic features are built upon raw skeleton coordinates using relative joint position values, differences between joints, spherical joint angles between selected joints, and their angular velocities. The novel spatiotemporal-guided features are obtained using a trained multi-player CNN-LSTM combination. Classification head including fully connected layers is subsequently applied. The proposed model has been evaluated on the KinectHAR dataset having 130,000 samples with 81 attribute values, collected with the help of a Kinect (v2) sensor. Experimental results are compared against the performance of isolated CNNs and LSTM networks. Proposed ConvLSTM have achieved an accuracy of 98.89% that is better than CNNs and LSTMs having an accuracy of 93.89 and 92.75%, respectively. The proposed system has been tested in realtime and is found to be independent of the pose, facing of the camera, individuals, clothing, etc. The code and dataset will be made publicly available.
25
Dumas, R., E. Nicol und L. Chèze. „Influence of the 3D Inverse Dynamic Method on the Joint Forces and Moments During Gait“. Journal of Biomechanical Engineering 129, Nr. 5 (19.04.2007): 786–90. http://dx.doi.org/10.1115/1.2768114.
Der volle Inhalt der QuelleAnnotation:
The joint forces and moments are commonly used in gait analysis. They can be computed by four different 3D inverse dynamic methods proposed in the literature, either based on vectors and Euler angles, wrenches and quaternions, homogeneous matrices, or generalized coordinates and forces. In order to analyze the influence of the inverse dynamic method, the joint forces and moments were computed during gait on nine healthy subjects. A ratio was computed between the relative dispersions (due to the method) and the absolute amplitudes of the gait curves. The influence of the inverse dynamic method was negligible at the ankle (2%) but major at the knee and the hip joints (40%). This influence seems to be due to the dynamic computation rather than the kinematic computation. Compared to the influence of the joint center location, the body segment inertial parameter estimation, and more, the influence of the inverse dynamic method is at least of equivalent importance. This point should be confirmed with other subjects, possibly pathologic, and other movements.
26
Li, Shaobo, Xingxing Zhang, Jing Yang, Qiang Bai, Jianjun Hu, Qisong Song und Zhiang Li. „Real-time motion tracking of cognitive Baxter robot based on differential inverse kinematics“. International Journal of Advanced Robotic Systems 18, Nr. 3 (01.05.2021): 172988142110240. http://dx.doi.org/10.1177/17298814211024052.
Der volle Inhalt der QuelleAnnotation:
The tracking motion of the robot is realized based on a specific robot or relying on an expensive movement acquisition system. It has the problems of complex control procedures, lack of real-time performance, and difficulty in achieving secondary development. We propose a robot real-time tracking control method based on the control principle of differential inverse kinematics, which fuses the position and joint angle information of the robot’s actuators to realize the real-time estimation of the user’s movement during the tracking process. The motion coordinates of each joint of the robot are calculated and the coordinate conversion between man and machine is realized with the combination of the Kinect sensor and the robot operating system. We have demonstrated the robustness and accuracy of the tracking method through the real-time tracking experiment of the Baxter robot. Our research has a wide range of application value, such as automatic target recognition, demonstration teaching, and so on. It provides an important reference for the research in the field of cognitive robots.
27
Sahota, Herman, und Ratnesh Kumar. „Sensor Localization Using Time of Arrival Measurements in a Multi-Media and Multi-Path Application of In-Situ Wireless Soil Sensing“. Inventions 6, Nr. 1 (27.02.2021): 16. http://dx.doi.org/10.3390/inventions6010016.
Der volle Inhalt der QuelleAnnotation:
The problem of localization of nodes of a wireless sensor network placed in different physical media (anchor nodes above ground and sensor nodes underground) is addressed in this article. We use time of arrival of signals transmitted between neighboring sensor nodes and between satellite nodes and sensor nodes as the ranging measurement. The localization problem is formulated as a parameter estimation of the joint distribution of the time of arrival values. The probability distribution of the time of arrival of a signal is derived based on rigorous statistical analysis and its parameters are expressed in terms of the location coordinates of the sensor nodes. Maximum likelihood estimates of the nodes’ location coordinates as parameters of the joint distribution of the various time of arrival variables in the network are computed. Sensitivity analysis to study the variation in the estimates with respect to error in measured soil complex permittivity and magnetic permeability is presented to validate the model and methodology.
28
Nenashev, Vadim, und Alexander Shepeta. „Accuracy characteristics of object location in a two-position system of small onboard radars“. Information and Control Systems, Nr. 2 (20.04.2020): 31–36. http://dx.doi.org/10.31799/1684-8853-2020-2-31-36.
Der volle Inhalt der QuelleAnnotation:
Introduction: The search for physical objects in a given area is often performed in automatic mode using small unmanned aerial vehicles equipped with radars. Airborne radar antennas, due to size restrictions, have a small aperture and, accordingly, a wide directional pattern, decreasing the accuracy of determining the angular coordinates of the objects. The increase in the angular coordinate estimation accuracy leads to the increase in the informativeness of such automatic search systems and, consequently, to the increase in the efficiency of their practical use. Purpose: Developing a technique for calculating the parameters of a two-position radar system consisting of two small airborne radars placed on small unmanned aerial vehicles, in order to increase the accuracy of determining the angular coordinates of radiocontrast physical objects. Results: An algorithm is proposed for integrating the data about the coordinates of physical objects detected in the joint coverage area of a two-position system of small airborne radars. It allows you, depending on the observation conditions, to increase the accuracy of determining the azimuthal coordinates by an order of magnitude or more. The aircraft trajectories are calculated on which the accuracy grows, and those on which there is almost no gain in accuracy. Practical relevance: Such two-position airborne small radars can be used in automated systems in order to detect physical object such as people in disaster areas, as well as in systems of collecting and processing data from sensors used for monitoring the state of the environment or man-made objects.
29
yuchi, atsushi, takahiko sato und akinori nagano. „Estimation Of Joint Torque During Countermovement Jump From Position Coordinates Using Deep Residual Recurrent Network“. Medicine & Science in Sports & Exercise 52, Nr. 7S (Juli 2020): 272. http://dx.doi.org/10.1249/01.mss.0000676520.42951.58.
Der volle Inhalt der Quelle
30
Martinez, Lucas, Matthieu Lalevée, Thomas Poirier, Helena Brunel, Jean Matsoukis, Stéphane Van Driessche und Fabien Billuart. „Influence of Skin Marker Positioning and Their Combinations on Hip Joint Center Estimation Using the Functional Method“. Bioengineering 11, Nr. 3 (21.03.2024): 297. http://dx.doi.org/10.3390/bioengineering11030297.
Der volle Inhalt der QuelleAnnotation:
Accurate estimation of hip joint center (HJC) position is crucial during gait analysis. HJC is obtained with predictive or functional methods. But in the functional method, there is no consensus on where to place the skin markers and which combination to use. The objective of this study was to analyze how different combinations of skin markers affect the estimation of HJC position relative to predictive methods. Forty-one healthy volunteers were included in this study; thirteen markers were placed on the pelvis and hip of each subject’s lower limbs. Various marker combinations were used to determine the HJC position based on ten calibration movement trials, captured by a motion capture system. The estimated HJC position for each combination was evaluated by focusing on the range and standard deviation of the mean norm values of HJC and the mean X, Y, Z coordinates of HJC for each limb. The combinations that produced the best estimates incorporated the markers on the pelvis and on proximal and easily identifiable muscles, with results close to predictive methods. The combination that excluded the markers on the pelvis was not robust in estimating the HJC position.
31
Takigami, Shunsaku, Atsuyuki Inui, Yutaka Mifune, Hanako Nishimoto, Kohei Yamaura, Tatsuo Kato, Takahiro Furukawa et al. „Estimation of Shoulder Joint Rotation Angle Using Tablet Device and Pose Estimation Artificial Intelligence Model“. Sensors 24, Nr. 9 (02.05.2024): 2912. http://dx.doi.org/10.3390/s24092912.
Der volle Inhalt der QuelleAnnotation:
Traditionally, angle measurements have been performed using a goniometer, but the complex motion of shoulder movement has made these measurements intricate. The angle of rotation of the shoulder is particularly difficult to measure from an upright position because of the complicated base and moving axes. In this study, we attempted to estimate the shoulder joint internal/external rotation angle using the combination of pose estimation artificial intelligence (AI) and a machine learning model. Videos of the right shoulder of 10 healthy volunteers (10 males, mean age 37.7 years, mean height 168.3 cm, mean weight 72.7 kg, mean BMI 25.6) were recorded and processed into 10,608 images. Parameters were created using the coordinates measured from the posture estimation AI, and these were used to train the machine learning model. The measured values from the smartphone’s angle device were used as the true values to create a machine learning model. When measuring the parameters at each angle, we compared the performance of the machine learning model using both linear regression and Light GBM. When the pose estimation AI was trained using linear regression, a correlation coefficient of 0.971 was achieved, with a mean absolute error (MAE) of 5.778. When trained with Light GBM, the correlation coefficient was 0.999 and the MAE was 0.945. This method enables the estimation of internal and external rotation angles from a direct-facing position. This approach is considered to be valuable for analyzing motor movements during sports and rehabilitation.
32
Wierzcholski, Krzysztof, und Ryszard Maciołek. „A NEW CONTRIBUTION IN STOCHASTIC HYDRODYNAMIC LUBRICATION FOR ARBITRARY BIO-SURFACES“. Tribologia 291, Nr. 3 (30.06.2020): 63–76. http://dx.doi.org/10.5604/01.3001.0014.4766.
Der volle Inhalt der QuelleAnnotation:
This paper shows a recent progress described in curvilinear, orthogonal coordinates of the method of estimation of stochastic bio-hydrodynamic lubrication parameters. Here are discussed real arbitrary movable, non-rotational living biological surfaces coated with phospholipid bi-layers and lubricated with biological liquids. Non-rotational, curvilinear cooperating biological surfaces take the place in various biological nods for example in sacra bone, femoral bone, knee cap, calf bone and hip joint, elbow joint, knee joint, jump joint. Moreover are assumed biological non-rotational friction nods between human skin and tightly sport dress lubricated with the sweat. The main focus of the paper was to demonstrate the influence of expected values variations and standard deviation of the human joint gap height on the hydrodynamic lubrication parameters occurring during the friction process. It is very important to notice that the random gap height variations imply on the apparent dynamic viscosity of biological fluid or synovial fluid.
33
Shiao, Yaojung, Guan-Yu Chen und Thang Hoang. „Three-Dimensional Human Posture Recognition by Extremity Angle Estimation with Minimal IMU Sensor“. Sensors 24, Nr. 13 (02.07.2024): 4306. http://dx.doi.org/10.3390/s24134306.
Der volle Inhalt der QuelleAnnotation:
Recently, posture recognition technology has advanced rapidly. Herein, we present a novel posture angle calculation system utilizing a single inertial measurement unit and a spatial geometric equation to accurately identify the three-dimensional (3D) motion angles and postures of both the upper and lower limbs of the human body. This wearable system facilitates continuous monitoring of body movements without the spatial limitations or occlusion issues associated with camera-based methods. This posture-recognition system has many benefits. Providing precise posture change information helps users assess the accuracy of their movements, prevent sports injuries, and enhance sports performance. This system employs a single inertial sensor, coupled with a filtering mechanism, to calculate the sensor’s trajectory and coordinates in 3D space. Subsequently, the spatial geometry equation devised herein accurately computed the joint angles for changing body postures. To validate its effectiveness, the joint angles estimated from the proposed system were compared with those from dual inertial sensors and image recognition technology. The joint angle discrepancies for this system were within 10° and 5° when compared with dual inertial sensors and image recognition technology, respectively. Such reliability and accuracy of the proposed angle estimation system make it a valuable reference for assessing joint angles.
34
Woo, Yeong Ju, Ji-Yong Joo, Young-Kwan Kim und He Yong Jeong. „Analysis of Pitching Motions by Human Pose Estimation Based on RGB Images“. Korean Institute of Smart Media 13, Nr. 4 (30.04.2024): 16–22. http://dx.doi.org/10.30693/smj.2024.13.4.16.
Der volle Inhalt der QuelleAnnotation:
Pitching is a major part of baseball, so much so that it can be said to be the beginning of baseball. Analysis of accurate pitching motions is very important in terms of performance improvement and injury prevention. When analyzing the correct pitching motion, the currently used motion capture method has several critical environmental drawbacks. In this paper, we propose analysis of pitching motion using the RGB-based Human Pose Estimation (HPE) model to replace motion capture, which has these shortcomings, and use motion capture data and HPE data to verify its reliability. The similarity of the two data was verified by comparing joint coordinates using the Dynamic Time Warping (DTW) algorithm.
35
Zhang, Siqi, Jie Jin, Chaofang Wang, Wenlong Dong und Bin Fan. „Quality Evaluation Algorithm for Chest Compressions Based on OpenPose Model“. Applied Sciences 12, Nr. 10 (11.05.2022): 4847. http://dx.doi.org/10.3390/app12104847.
Der volle Inhalt der QuelleAnnotation:
Aiming at the problems of the low evaluation efficiency of the existing traditional cardiopulmonary resuscitation (CPR) training mode and the considerable development of machine vision technology, a quality evaluation algorithm for chest compressions (CCs) based on the OpenPose human pose estimation (HPE) model is proposed. Firstly, five evaluation criteria are proposed based on major international CPR guidelines along with our experimental study on elbow straightness. Then, the OpenPose network is applied to obtain the coordinates of the key points of the human skeleton. The algorithm subsequently calculates the geometric angles and displacement of the selected joint key points using the detected coordinates. Finally, it determines whether the compression posture is standard, and it calculates the depth, frequency, position and chest rebound, which are the critical evaluation metrics of CCs. Experimental results show that the average accuracy of network behavior detection reaches 94.85%, and detection speed reaches 25 fps.
36
Wang, Dianjun, zilong wang, Ya Chen, Zhiguo Cui, Yadong Zhu und Chao Wu. „Kinematics analysis and calibration of a 6-degree of freedom light load collaborative robot“. Cobot 1 (15.09.2022): 18. http://dx.doi.org/10.12688/cobot.17568.1.
Der volle Inhalt der QuelleAnnotation:
Background: In the process of carrying small forgings and other materials, the trajectory error of the 6-degree of freedom light-load collaborative robot will lead to the deviation of forgings placement position. The kinematics analysis and calibration of 6-degree of freedom light load collaborative robot are performed to solve the problem of trajectory error. Methods: The quaternion and cubic spline interpolation methods are adopted to plan the trajectory of the 6-degree of freedom light load collaborative robot. Based on the kinematic error model, the least squares estimation method is adopted to estimate the parameter error of the robot's connecting rod, and the parameter compensation values of each joint are obtained. Results: The kinematic calibration experiment shows that the coordinates of the robot end center are basically consistent with the actual coordinates after compensation, which verifies the rationality of the kinematic model and calibration method. Conclusions: The study lays the theoretical foundation for the trajectory error correction of the light load collaborative robot.
37
Shin, Jungpil, Akitaka Matsuoka, Md Al Mehedi Hasan und Azmain Yakin Srizon. „American Sign Language Alphabet Recognition by Extracting Feature from Hand Pose Estimation“. Sensors 21, Nr. 17 (31.08.2021): 5856. http://dx.doi.org/10.3390/s21175856.
Der volle Inhalt der QuelleAnnotation:
Sign language is designed to assist the deaf and hard of hearing community to convey messages and connect with society. Sign language recognition has been an important domain of research for a long time. Previously, sensor-based approaches have obtained higher accuracy than vision-based approaches. Due to the cost-effectiveness of vision-based approaches, researchers have been conducted here also despite the accuracy drop. The purpose of this research is to recognize American sign characters using hand images obtained from a web camera. In this work, the media-pipe hands algorithm was used for estimating hand joints from RGB images of hands obtained from a web camera and two types of features were generated from the estimated coordinates of the joints obtained for classification: one is the distances between the joint points and the other one is the angles between vectors and 3D axes. The classifiers utilized to classify the characters were support vector machine (SVM) and light gradient boosting machine (GBM). Three character datasets were used for recognition: the ASL Alphabet dataset, the Massey dataset, and the finger spelling A dataset. The results obtained were 99.39% for the Massey dataset, 87.60% for the ASL Alphabet dataset, and 98.45% for Finger Spelling A dataset. The proposed design for automatic American sign language recognition is cost-effective, computationally inexpensive, does not require any special sensors or devices, and has outperformed previous studies.
38
Kitajima, Eiji, Takashi Sato, Koji Kurata und Ryota Miyata. „Automatic feature selection for performing Unit 2 of vault in wheel gymnastics“. PLOS ONE 18, Nr. 6 (23.06.2023): e0287095. http://dx.doi.org/10.1371/journal.pone.0287095.
Der volle Inhalt der QuelleAnnotation:
We propose a framework to analyze the relationship between the movement features of a wheel gymnast around the mounting phase of Unit 2 of the vault event and execution (E-score) deductions from a machine-learning perspective. We first developed an automation system from a video of a wheel gymnast performing a tuck-front somersault to extract the four frames highlighting its Unit 2 performance of the vault event, such as take-off, pike-mount, the starting point of time on the wheel, and final position before the thrust. We implemented this automation using recurrent all-pairs field transforms (RAFT) and XMem, i.e., deep network architectures respectively for optical flow estimation and video object segmentation. We then used a markerless pose-estimation system called OpenPose to acquire the coordinates of the gymnast’s body joints, such as shoulders, hips, and knees then calculate the joint angles at the extracted video frames. Finally, we constructed a regression model to estimate the E-score deductions during Unit 2 on the basis of the joint angles using an ensemble learning algorithm called Random Forests, with which we could automatically select a small number of features with the nonzero values of feature importances. By applying our framework of markerless motion analysis to videos of male wheel gymnasts performing the vault, we achieved precise estimation of the E-score deductions during Unit 2 with a determination coefficient of 0.79. We found the two movement features of particular importance for them to avoid significant deductions: time on the wheel and angles of knees at the pike-mount position. The selected features well reflected the maturity of the gymnast’s skills related to the motions of riding the wheel, easily noticeable to the judges, and their branching conditions were almost consistent with the general vault regulations.
39
Bao, Wenxia, Zhongyu Ma, Dong Liang, Xianjun Yang und Tao Niu. „Pose ResNet: 3D Human Pose Estimation Based on Self-Supervision“. Sensors 23, Nr. 6 (12.03.2023): 3057. http://dx.doi.org/10.3390/s23063057.
Der volle Inhalt der QuelleAnnotation:
The accurate estimation of a 3D human pose is of great importance in many fields, such as human–computer interaction, motion recognition and automatic driving. In view of the difficulty of obtaining 3D ground truth labels for a dataset of 3D pose estimation techniques, we take 2D images as the research object in this paper, and propose a self-supervised 3D pose estimation model called Pose ResNet. ResNet50 is used as the basic network for extract features. First, a convolutional block attention module (CBAM) was introduced to refine selection of significant pixels. Then, a waterfall atrous spatial pooling (WASP) module is used to capture multi-scale contextual information from the extracted features to increase the receptive field. Finally, the features are input into a deconvolution network to acquire the volume heat map, which is later processed by a soft argmax function to obtain the coordinates of the joints. In addition to the two learning strategies of transfer learning and synthetic occlusion, a self-supervised training method is also used in this model, in which the 3D labels are constructed by the epipolar geometry transformation to supervise the training of the network. Without the need for 3D ground truths for the dataset, accurate estimation of the 3D human pose can be realized from a single 2D image. The results show that the mean per joint position error (MPJPE) is 74.6 mm without the need for 3D ground truth labels. Compared with other approaches, the proposed method achieves better results.
40
Zhou, Yuting, und Hongjie Wan. „Joint Measurement of Multi-channel Sound Event Detection and Localization Using Deep Neural Network“. Journal of Physics: Conference Series 2216, Nr. 1 (01.03.2022): 012101. http://dx.doi.org/10.1088/1742-6596/2216/1/012101.
Der volle Inhalt der QuelleAnnotation:
Abstract For joint sound event localization and detection (SELD), a multi-channel sound event method based on deep learning is proposed. This paper uses CRNN model training with datasets of maximum two overlapping sound events. The difficulty of the polyphonic SELD is the combination of SED and DOA estimation in the same network. Using multi-channel audio can better identify these overlapping sound events. The input of the proposed model is a series of continuous spectrograms, which are then output to two branches respectively. As the first branch, SED performs multi-label classification in each time segment. As the second branch, 3-D Cartesian coordinates are used to represent the DOA estimate of each sound event. This paper extracts the phase feature and amplitude feature of the sound spectrum from each audio channel, avoiding feature extraction limited by other microphone arrays.
41
Xu, Chenxin, Siheng Chen, Maosen Li und Ya Zhang. „Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation“. Proceedings of the AAAI Conference on Artificial Intelligence 35, Nr. 4 (18.05.2021): 3013–21. http://dx.doi.org/10.1609/aaai.v35i4.16409.
Der volle Inhalt der QuelleAnnotation:
We propose a novel method based on teacher-student learning framework for 3D human pose estimation without any 3D annotation or side information. To solve this unsupervised-learning problem, the teacher network adopts pose-dictionary-based modeling for regularization to estimate a physically plausible 3D pose. To handle the decomposition ambiguity in the teacher network, we propose a cycle-consistent architecture promoting a 3D rotation-invariant property to train the teacher network. To further improve the estimation accuracy, the student network adopts a novel graph convolution network for flexibility to directly estimate the 3D coordinates. Another cycle-consistent architecture promoting 3D rotation-equivariant property is adopted to exploit geometry consistency, together with knowledge distillation from the teacher network to improve the pose estimation performance. We conduct extensive experiments on Human3.6M and MPI-INF-3DHP. Our method reduces the 3D joint prediction error by 11.4% compared to state-of-the-art unsupervised methods and also outperforms many weakly-supervised methods that use side information on Human3.6M. Code will be available at https://github.com/sjtuxcx/ITES.
42
Yuan, Chunmiao, Pengju Zhang, Qingyong Yang und Jianming Wang. „Fall Detection and Direction Judgment Based on Posture Estimation“. Discrete Dynamics in Nature and Society 2022 (15.06.2022): 1–12. http://dx.doi.org/10.1155/2022/8372291.
Der volle Inhalt der QuelleAnnotation:
For the problem of elderly people falling easily, it is very necessary to correctly detect the occurrence of falls and provide early warning, which can greatly reduce the injury caused by falls. Most of the existing fall detection algorithms require the monitored persons to carry wearable devices, which will bring inconvenience to their lives and few algorithms pay attention to the direction of the fall. Therefore, we propose a video-based fall detection and direction judgment method based on human posture estimation for the first time. We predict the joint point coordinates of each human body through the posture estimation network, and then use the SVM classifier to detect falls. Next, we will use the three-dimensional human posture information to judge the direction of the fall. Compared to the existing methods, our method has a great improvement in sensitivity, specificity, and accuracy which reaches 95.86, 99.5, and 97.52 on the Le2i fall dataset, respectively, whereas on the UR fall dataset, they are 95.45, 100, and 97.43, respectively.
43
Kondo, Tamon, Sakura Narumi, Zixun He, Duk Shin und Yousun Kang. „A Performance Comparison of Japanese Sign Language Recognition with ViT and CNN Using Angular Features“. Applied Sciences 14, Nr. 8 (11.04.2024): 3228. http://dx.doi.org/10.3390/app14083228.
Der volle Inhalt der QuelleAnnotation:
In recent years, developments in deep learning technology have driven significant advancements in research aimed at facilitating communication with individuals who have hearing impairments. The focus has been on enhancing automatic recognition and translation systems for sign language. This study proposes a novel approach using a vision transformer (ViT) for recognizing Japanese Sign Language. Our method employs a pose estimation library, MediaPipe, to extract the positional coordinates of each finger joint within video frames and generate one-dimensional angular feature data from these coordinates. Then, the code arranges these feature data in a temporal sequence to form a two-dimensional input vector for the ViT model. To determine the optimal configuration, this study evaluated recognition accuracy by manipulating the number of encoder layers within the ViT model and compared against traditional convolutional neural network (CNN) models to evaluate its effectiveness. The experimental results showed 99.7% accuracy for the method using the ViT model and 99.3% for the results using the CNN. We demonstrated the efficacy of our approach through real-time recognition experiments using Japanese sign language videos.
44
Galkin, P. S., und V. N. Lagutkin. „METHOD OF COMPENSATION OF IONOSPHERE ERRORS OF SPACE OBJECTS COORDINATES DEFINITION BY MEANS OF TWO POSITION RADAR OBSERVATION“. Issues of radio electronics, Nr. 3 (20.03.2018): 45–49. http://dx.doi.org/10.21778/2218-5453-2018-3-45-49.
Der volle Inhalt der QuelleAnnotation:
The algorithm of estimation and compensation of ionosphere influence on the measurement of parameters of the motion of space objects in two-position radar system with account of radio physical effects depending on elevation angles and the operating frequency is developed. It is assumed that the observed space object is traсked object, the orbital parameters which are well known, including the dependence of the velocity of the point on the orbit, and the uncertainty of the current coordinates of the object is caused mainly by forecast error of its position of in orbit (longitudinal error). To estimate the true position of space object in the orbit and the parameter, determining the influence of the ionosphere, a joint optimal processing of measurement of ranges to the object, obtained by two separated radars, taking into account the relevant ionospheric propagation delays and available a priori data on observable object trajectory. Estimation of unknown parameters are obtained on the basis of the criterion of maximum a posteriori probability density for these parameters, taking into account the measured and a priori data. The task of searching for maximum a posteriori probability density is reduced to task of searching of minimum weighted sum of squares, for the solution of which the cascade algorithm of iteration through is implemented in the work. Estimation accuracy of the position of space objects in orbit after compensation of ionosphere influence have been studied by Monte-Carlo method. Dependencies of mean square error of the position estimation of space objects upon elevation angles, operation frequency and solar activity have been obtained. It is shown that the effectiveness of the algorithm increases with the spatial base of measurements (for a fixed orbit of the object).
45
Lekova, A., A. Krastev und I. Chavdarov. „Wireless Kinect-NAO Framework Based on Takagi-Sugeno Fuzzy Inference System“. Information Technologies and Control 15, Nr. 2 (01.06.2017): 14–24. http://dx.doi.org/10.1515/itc-2017-0023.
Der volle Inhalt der QuelleAnnotation:
Abstract In the context of learning new skills by imitation for children with special educational needs, we propose Wireless Kinect-NAO Framework (WKNF) for robot teleoperation in real time based on Takagi-Sugeno (T-S) Fuzzy Inference System. The new solutions here are related to complex whole-body motion retargeting, standing body stabilization, view invariance and smoothness of robot motions. The raw depth Kinect data are fuzzified and processed by median filter. The joint angles estimation for motion mapping of Human to NAO movements is based on fuzzy logic and featured angles rather than direct angles are calculated by Inverse Kinematics due to differences in the human and robot kinematics. During the joint angles calculation nonlinearities are observed as a result of ambiguity of Kinect 3D joint coordinates in different offsets. NAO kinematic limitations and nonlinearities in workspace are decomposed and linearly approximated by T-S fuzzy rules of zero and first order that have local support in 2D projections. To prevent the robot to fall down, the center of mass is considered in order NAO to stay within a support and safe polygon. The feasibility of the proposed framework has been proven by real experiments.
46
Zhao, Jingjing, Yongxiang Liu, Kai Huo, Jiaxi Ye und Bo Xiao. „Three-Dimensional High-Resolution MIMO Radar Imaging via OFDM Modulation and Unitary ESPRIT“. Mathematical Problems in Engineering 2020 (27.06.2020): 1–16. http://dx.doi.org/10.1155/2020/2308389.
Der volle Inhalt der QuelleAnnotation:
Imaging and recognition of targets with complex maneuvers bring a new challenge to conventional radar applications. In this paper, the three-dimensional (3D) high-resolution image is attained in real-time by a Multiple-Input-Multiple-Output (MIMO) radar system with single Orthogonal-Frequency-Division-Multiplexing (OFDM) pulse. First, to build the orthogonal transmit waveform set for MIMO transmission, we utilize complex orthogonal designs (CODs) for OFDM subcarrier modulation. Based on the OFDM modulation, a preprocessing method is developed for transmit waveform separation without conventional matched filtering. The result array manifold is the Kronecker product of the steering vectors of subcarrier/transmit antenna/receive antenna uniform linear arrays (ULAs). Then, the high-resolution image of target is attained by the Multidimensional Unitary Estimation of Signal Parameters via Rotational Invariant Techniques (MD-UESPRIT) algorithm. The proposed imaging procedures include the multidimensional spatial smoothing, the unitary transform via backward-forward averaging, and the joint eigenvalue decomposition (JEVD) algorithm for automatically paired coordinates estimation. Simulation tests compare the reconstruction results with the conventional methods and analyze the estimation precision relative to signal-to-noise ratio (SNR), system parameters, and errors.
47
Zhang, Shaobo, Qinxiang Xia, Mingxing Chen und Sizhu Cheng. „Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning“. Sensors 23, Nr. 13 (27.06.2023): 5974. http://dx.doi.org/10.3390/s23135974.
Der volle Inhalt der QuelleAnnotation:
This study investigated the trajectory-planning problem of a six-axis robotic arm based on deep reinforcement learning. Taking into account several characteristics of robot motion, a multi-objective optimization approach is proposed, which was based on the motivations of deep reinforcement learning and optimal planning. The optimal trajectory was considered with respect to multiple objectives, aiming to minimize factors such as accuracy, energy consumption, and smoothness. The multiple objectives were integrated into the reinforcement learning environment to achieve the desired trajectory. Based on forward and inverse kinematics, the joint angles and Cartesian coordinates were used as the input parameters, while the joint angle estimation served as the output. To enable the environment to rapidly find more-efficient solutions, the decaying episode mechanism was employed throughout the training process. The distribution of the trajectory points was improved in terms of uniformity and smoothness, which greatly contributed to the optimization of the robotic arm’s trajectory. The proposed method demonstrated its effectiveness in comparison with the RRT algorithm, as evidenced by the simulations and physical experiments.
48
Lafayette, Thiago Buarque de Gusmão, Victor Hugo de Lima Kunst, Pedro Vanderlei de Sousa Melo, Paulo de Oliveira Guedes, João Marcelo Xavier Natário Teixeira, Cínthia Rodrigues de Vasconcelos, Veronica Teichrieb und Alana Elza Fontes da Gama. „Validation of Angle Estimation Based on Body Tracking Data from RGB-D and RGB Cameras for Biomechanical Assessment“. Sensors 23, Nr. 1 (20.12.2022): 3. http://dx.doi.org/10.3390/s23010003.
Der volle Inhalt der QuelleAnnotation:
Motion analysis is an area with several applications for health, sports, and entertainment. The high cost of state-of-the-art equipment in the health field makes it unfeasible to apply this technique in the clinics’ routines. In this vein, RGB-D and RGB equipment, which have joint tracking tools, are tested with portable and low-cost solutions to enable computational motion analysis. The recent release of Google MediaPipe, a joint inference tracking technique that uses conventional RGB cameras, can be considered a milestone due to its ability to estimate depth coordinates in planar images. In light of this, this work aims to evaluate the measurement of angular variation from RGB-D and RGB sensor data against the Qualisys Tracking Manager gold standard. A total of 60 recordings were performed for each upper and lower limb movement in two different position configurations concerning the sensors. Google’s MediaPipe usage obtained close results compared to Kinect V2 sensor in the inherent aspects of absolute error, RMS, and correlation to the gold standard, presenting lower dispersion values and error metrics, which is more positive. In the comparison with equipment commonly used in physical evaluations, MediaPipe had an error within the error range of short- and long-arm goniometers.
49
Kudriashov, Volodymyr V., Artem Y. Garbar, Konstantin A. Lukin, Lukasz Maslikowski, Piotr Samczynski und Krzysztof S. Kulpa. „Fusion of Images Generated by Radiometric and Active Noise SAR“. Cybernetics and Information Technologies 15, Nr. 7 (01.12.2015): 58–66. http://dx.doi.org/10.1515/cait-2015-0089.
Der volle Inhalt der QuelleAnnotation:
Abstract The work is devoted to fusion of radar and radiometer images. Noise waveform SAR generates radar images of reflective objects of its field of view. A bistatic radiometer with synthetic aperture estimates the thermal radio emissions of the objects along their angular coordinates and even range. The estimated brightness temperatures of rough and smooth surfaces are different, as well as the radar responses from them. Identification of the parameters of objects surfaces may be done using results of joint processing of images generated by both sensors. The optimum and quasi-optimum criteria for fusion of the images were obtained. The latter was experimentally checked. It approves the opportunity to fuse the images for further estimation of some parameters of objects surfaces. The results obtained may be used in environmental and security applications.
50
Iversen, Einar, und Martin Tygel. „Image-ray tracing for joint 3D seismic velocity estimation and time-to-depth conversion“. GEOPHYSICS 73, Nr. 3 (Mai 2008): S99—S114. http://dx.doi.org/10.1190/1.2907736.
Der volle Inhalt der QuelleAnnotation:
Seismic time migration is known for its ability to generate well-focused and interpretable images, based on a velocity field specified in the time domain. A fundamental requirement of this time-migration velocity field is that lateral variations are small. In the case of 3D time migration for symmetric elementary waves (e.g., primary PP reflections/diffractions, for which the incident and departing elementary waves at the reflection/diffraction point are pressure [P] waves), the time-migration velocity is a function depending on four variables: three coordinates specifying a trace point location in the time-migration domain and one angle, the so-called migration azimuth. Based on a time-migration velocity field available for a single azimuth, we have developed a method providing an image-ray transformation between the time-migration domain and the depth domain. The transformation is obtained by a process in which image rays and isotropic depth-domain velocity parameters for their propagation are esti-mated simultaneously. The depth-domain velocity field and image-ray transformation generated by the process have useful applications. The estimated velocity field can be used, for example, as an initial macrovelocity model for depth migration and tomographic inversion. The image-ray transformation provides a basis for time-to-depth conversion of a complete time-migrated seismic data set or horizons interpreted in the time-migration domain. This time-to-depth conversion can be performed without the need of an a priori known velocity model in the depth domain. Our approach has similarities as well as differences compared with a recently published method based on knowledge of time-migration velocity fields for at least three migration azimuths. We show that it is sufficient, as a minimum, to give as input a time-migration velocity field for one azimuth only. A practical consequence of this simplified input is that the image-ray transformation and its corresponding depth-domain velocity field can be generated more easily.