Статті в журналах з теми "EDGE DETECTION MODELS"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: EDGE DETECTION MODELS.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "EDGE DETECTION MODELS".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Eom, K. B., and R. L. Kashyap. "Composite edge detection with random field models." IEEE Transactions on Systems, Man, and Cybernetics 20, no. 1 (1990): 81–93. http://dx.doi.org/10.1109/21.47811.
Повний текст джерела
2
Luo, Shan, and Zehua Chen. "Edge detection in sparse Gaussian graphical models." Computational Statistics & Data Analysis 70 (February 2014): 138–52. http://dx.doi.org/10.1016/j.csda.2013.09.002.
Повний текст джерела
3
Yang, Chang Niu, and Xing Bo Sun. "Research on Jumper and Connector Detection of Silk Products." Applied Mechanics and Materials 716-717 (December 2014): 851–53. http://dx.doi.org/10.4028/www.scientific.net/amm.716-717.851.
Повний текст джерелаАнотація:
An improved morphological edge detection algorithm for silk products jumpers and connectors’ test was proposed. With structure elements of different models, we detect the edge information in different directions of silk products respectively; using the proposed adaptive fusion method based on histogram matching, we can obtain ideal image edge, while enhance the blurred edges, and effectively eliminate the silk products inherent texture and noise, then detect the clear jumpers and connectors.
4
Gong, Rong Fen, and Mao Xiang Chu. "An Edge Detection Method Based on Adaptive Differential Operator." Applied Mechanics and Materials 713-715 (January 2015): 415–19. http://dx.doi.org/10.4028/www.scientific.net/amm.713-715.415.
Повний текст джерелаАнотація:
An edge detection method based on adaptive differential operator is proposed in this paper. Firstly, standard local edge models are built. And these edge models are described with four-bit-binary code (FBBC) which is obtained from weighted mean values in four directions. Then, based on weighted gray values in four directions, different differential operator templates are defined. And FBBC is used to build the matching between differential operator templates and edge models. Experiments show that this edge detection method with adaptive differential operator can smooth noise and has satisfactory edge detection result.
5
Daoud, Mohammad I., Aamer Al-Ali, Rami Alazrai, Mahasen S. Al-Najar, Baha A. Alsaify, Mostafa Z. Ali, and Sahel Alouneh. "An Edge-Based Selection Method for Improving Regions-of-Interest Localizations Obtained Using Multiple Deep Learning Object-Detection Models in Breast Ultrasound Images." Sensors 22, no. 18 (September 6, 2022): 6721. http://dx.doi.org/10.3390/s22186721.
Повний текст джерелаАнотація:
Computer-aided diagnosis (CAD) systems can be used to process breast ultrasound (BUS) images with the goal of enhancing the capability of diagnosing breast cancer. Many CAD systems operate by analyzing the region-of-interest (ROI) that contains the tumor in the BUS image using conventional texture-based classification models and deep learning-based classification models. Hence, the development of these systems requires automatic methods to localize the ROI that contains the tumor in the BUS image. Deep learning object-detection models can be used to localize the ROI that contains the tumor, but the ROI generated by one model might be better than the ROIs generated by other models. In this study, a new method, called the edge-based selection method, is proposed to analyze the ROIs generated by different deep learning object-detection models with the goal of selecting the ROI that improves the localization of the tumor region. The proposed method employs edge maps computed for BUS images using the recently introduced Dense Extreme Inception Network (DexiNed) deep learning edge-detection model. To the best of our knowledge, our study is the first study that has employed a deep learning edge-detection model to detect the tumor edges in BUS images. The proposed edge-based selection method is applied to analyze the ROIs generated by four deep learning object-detection models. The performance of the proposed edge-based selection method and the four deep learning object-detection models is evaluated using two BUS image datasets. The first dataset, which is used to perform cross-validation evaluation analysis, is a private dataset that includes 380 BUS images. The second dataset, which is used to perform generalization evaluation analysis, is a public dataset that includes 630 BUS images. For both the cross-validation evaluation analysis and the generalization evaluation analysis, the proposed method obtained the overall ROI detection rate, mean precision, mean recall, and mean F1-score values of 98%, 0.91, 0.90, and 0.90, respectively. Moreover, the results show that the proposed edge-based selection method outperformed the four deep learning object-detection models as well as three baseline-combining methods that can be used to combine the ROIs generated by the four deep learning object-detection models. These findings suggest the potential of employing our proposed method to analyze the ROIs generated using different deep learning object-detection models to select the ROI that improves the localization of the tumor region.
6
Ledalla, Sukanya, Vijendar Reddy Gurram, Gopala Krishna P, Saiteja Vodnala, Maroof Md, and Raviteja Reddy Annapuredddy. "Density based smart traffic control system using canny edge detection algorithm along with object detection." E3S Web of Conferences 391 (2023): 01061. http://dx.doi.org/10.1051/e3sconf/202339101061.
Повний текст джерелаАнотація:
It is urgently necessary to combine current advancements to work on the cutting edge inrush hour jam the executives, as urban congestion is one of the world’s biggest concerns. Existing methodologies, for example, traffic police and traffic lights are neither fulfilling nor viable. Consequently, a traffic management system that utilizes sophisticated edge detection and digital image processing to measure vehicle density in real time is developed in this setting. Computerizedimage processing should be used to detect edges. To extract significant traffic data from CCTV images, the edge recognition method is required. The astute edge finder outperforms other processes in terms of accuracy, entropy, PSNR (peak signal to noise ratio), MSE (mean square error), and execution time. There are a number of possible edge recognition calculations. In terms of reaction time, vehicle the board, mechanization, dependability, and overall productivity, this framework performs significantly better than previous models. Utilizing a few model images of various traffic scenarios, appropriate schematics are also provided for a comprehensive approach that includes image collection, edge distinguishing evidence, and green sign classification. Also recommended is a system with object identification and priority for ambulances stuck in traffic.
7
De Borba, Anderson A., Arnab Muhuri, Mauricio Marengoni, and Alejandro C. Frery. "Feature Selection for Edge Detection in PolSAR Images." Remote Sensing 15, no. 9 (May 8, 2023): 2479. http://dx.doi.org/10.3390/rs15092479.
Повний текст джерелаАнотація:
Edge detection is one of the most critical operations for moving from data to information. Finding edges between objects is relevant for image understanding, classification, segmentation, and change detection, among other applications. The Gambini Algorithm is a good choice for finding evidence of edges. It finds the point at which a function of the difference of properties is maximized. This algorithm is very general and accepts many types of objective functions. We use an objective function built with likelihoods. Imaging with active microwave sensors has a revolutionary role in remote sensing. This technology has the potential to provide high-resolution images regardless of the Sun’s illumination and almost independently of the atmospheric conditions. Images from PolSAR sensors are sensitive to the target’s dielectric properties and structures in several polarization states of the electromagnetic waves. Edge detection in polarimetric synthetic-aperture radar (PolSAR) imagery is challenging because of the low signal-to-noise ratio and the data format (complex matrices). There are several known marginal models stemming from the complex Wishart model for the full complex format. Each of these models renders a different likelihood. This work generalizes previous studies by incorporating the ratio of intensities as evidence for edge detection. We discuss solutions for the often challenging problem of parameter estimation. We propose a technique which rejects edge estimates built with thin evidence. Using this idea of discarding potentially irrelevant evidence, we propose a technique for fusing edge pieces of evidence from different channels that only incorporate those likely to contribute positively. We use this approach for both edge and change detection in single- and multilook images from three different sensors.
8
Pitas, I. "Markovian image models for image labeling and edge detection." Signal Processing 15, no. 4 (December 1988): 365–74. http://dx.doi.org/10.1016/0165-1684(88)90057-6.
Повний текст джерела
9
Naraghi, Mahdi Ghasemi. "Satellite images edge detection based on morphology models fusion." Indian Journal of Science and Technology 5, no. 7 (July 20, 2012): 1–4. http://dx.doi.org/10.17485/ijst/2012/v5i7.5.
Повний текст джерела
10
Ahmed, Awa, and Osman Sharif. "Image Processing Techniques-based fire detection." Sulaimani Journal for Engineering Sciences 8, no. 1 (August 1, 2021): 23–34. http://dx.doi.org/10.17656/sjes.10145.
Повний текст джерелаАнотація:
In this paper different fire detection systems and techniques has been reviewed, many techniques have been developed for the purpose of early fire detection in different scenarios. The most accurate technique used among all these methods is Image Processing based Techniques. Different color models like RGB, HSI, CIE L*a*b and YCbCr have been used along with different edge detection algorithms like Sobel and Novel edge detection, finally the color segmentation technique was discussed in the review paper. All the mentioned methods in these papers have significantly proved to detect fire and flame edges in digital images with a timely manner, which has a huge impact on saving life and reducing loss of life.
11
Li, Junqing, and Jiongyao Ye. "Edge-YOLO: Lightweight Infrared Object Detection Method Deployed on Edge Devices." Applied Sciences 13, no. 7 (March 30, 2023): 4402. http://dx.doi.org/10.3390/app13074402.
Повний текст джерелаАнотація:
Existing target detection algorithms for infrared road scenes are often computationally intensive and require large models, which makes them unsuitable for deployment on edge devices. In this paper, we propose a lightweight infrared target detection method, called Edge-YOLO, to address these challenges. Our approach replaces the backbone network of the YOLOv5m model with a lightweight ShuffleBlock and a strip depthwise convolutional attention module. We also applied CAU-Lite as the up-sampling operator and EX-IoU as the bounding box loss function. Our experiments demonstrate that, compared with YOLOv5m, Edge-YOLO is 70.3% less computationally intensive, 71.6% smaller in model size, and 44.4% faster in detection speed, while maintaining the same level of detection accuracy. As a result, our method is better suited for deployment on embedded platforms, making effective infrared target detection in real-world scenarios possible.
12
Waili, Abdul Rasul AL. "Using Convolutional Neural Networks for Edge Detection in Medical Images to Determine Surgery Instrument Tools." June-July 2023, no. 34 (May 25, 2023): 13–25. http://dx.doi.org/10.55529/jaimlnn.34.13.25.
Повний текст джерелаАнотація:
Edge detection plays a crucial role in medical image analysis, particularly in surgical settings where accurate identification of surgical instrument tools is essential. In this paper, we explore the use of Convolutional Neural Networks (CNNs) for edge detection in medical images to determine surgical instrument tools. We present a comprehensive study that includes dataset selection, preprocessing techniques, network architecture design, training procedures, evaluation metrics, and experimental results. The CNN models were trained on a diverse dataset of medical images with annotated ground truth edge maps. The models demonstrated superior performance compared to traditional edge detection algorithms and handcrafted feature-based approaches, achieving high accuracy and robustness in capturing surgical instrument boundaries. We evaluated the models using metrics such as Intersection over Union (IoU), Precision, Recall, F1-Score, and Mean Average Precision (mAP) on a separate test set. this study demonstrates the potential of CNNs for edge detection in medical images to determine surgical instrument tools. The achieved accuracy, robustness, and computational efficiency of the trained models validate their utility in assisting surgeons during surgical interventions.
13
Liang, Yan Bing, Xiao Li Meng, and Shu Jiang An. "Canny Edge Detection Method and its Application." Applied Mechanics and Materials 50-51 (February 2011): 483–87. http://dx.doi.org/10.4028/www.scientific.net/amm.50-51.483.
Повний текст джерелаАнотація:
Digital Cameras positioning has a wide range of application in the aspect of traffic monitoring (e-police).In this paper, the author builds and solves the mathematical model of positioning of monocular by edge detection methods and physical principles of optical imaging of Gauss, and offers a distortion error algorithm to test models, and finally sets up to solve the problem of relative position of multi-cameras. The introduction of distortion error algorithm, could be used to quantitatively examine the models in the first two steps. In accordance with the image situation of multi-image planes, the relative position between the cameras could be determined. This model of camera generates Multi-Vision Inspecting Technique of general distribution of the relative position. Relative position can be figured out if only the parameters of the pictures to be determined are available to determine the inner and outer parameters of the camera.
14
Cazorla, M., F. Escolano, D. Gallardo, and R. Rizo. "Junction detection and grouping with probabilistic edge models and Bayesian." Pattern Recognition 35, no. 9 (September 2002): 1869–81. http://dx.doi.org/10.1016/s0031-3203(01)00150-9.
Повний текст джерела
15
Cakic, Stevan, Tomo Popovic, Srdjan Krco, Daliborka Nedic, Dejan Babic, and Ivan Jovovic. "Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC." Sensors 23, no. 6 (March 10, 2023): 3002. http://dx.doi.org/10.3390/s23063002.
Повний текст джерелаАнотація:
This research describes the use of high-performance computing (HPC) and deep learning to create prediction models that could be deployed on edge AI devices equipped with camera and installed in poultry farms. The main idea is to leverage an existing IoT farming platform and use HPC offline to run deep learning to train the models for object detection and object segmentation, where the objects are chickens in images taken on farm. The models can be ported from HPC to edge AI devices to create a new type of computer vision kit to enhance the existing digital poultry farm platform. Such new sensors enable implementing functions such as counting chickens, detection of dead chickens, and even assessing their weight or detecting uneven growth. These functions combined with the monitoring of environmental parameters, could enable early disease detection and improve the decision-making process. The experiment focused on Faster R-CNN architectures and AutoML was used to identify the most suitable architecture for chicken detection and segmentation for the given dataset. For the selected architectures, further hyperparameter optimization was carried out and we achieved the accuracy of AP = 85%, AP50 = 98%, and AP75 = 96% for object detection and AP = 90%, AP50 = 98%, and AP75 = 96% for instance segmentation. These models were installed on edge AI devices and evaluated in the online mode on actual poultry farms. Initial results are promising, but further development of the dataset and improvements in prediction models is needed.
16
Yin, Zhenyu, Zisong Wang, Chao Fan, Xiaohui Wang, and Tong Qiu. "Edge Detection via Fusion Difference Convolution." Sensors 23, no. 15 (August 3, 2023): 6883. http://dx.doi.org/10.3390/s23156883.
Повний текст джерелаАнотація:
Edge detection is a crucial step in many computer vision tasks, and in recent years, models based on deep convolutional neural networks (CNNs) have achieved human-level performance in edge detection. However, we have observed that CNN-based methods rely on pre-trained backbone networks and generate edge images with unwanted background details. We propose four new fusion difference convolution (FDC) structures that integrate traditional gradient operators into modern CNNs. At the same time, we have also added a channel spatial attention module (CSAM) and an up-sampling module (US). These structures allow the model to better recognize the semantic and edge information in the images. Our model is trained from scratch on the BIPED dataset without any pre-trained weights and achieves promising results. Moreover, it generalizes well to other datasets without fine-tuning.
17
Yadav, Dhirendra Prasad, Ashish Sharma, Senthil Athithan, Abhishek Bhola, Bhisham Sharma, and Imed Ben Dhaou. "Hybrid SFNet Model for Bone Fracture Detection and Classification Using ML/DL." Sensors 22, no. 15 (August 4, 2022): 5823. http://dx.doi.org/10.3390/s22155823.
Повний текст джерелаАнотація:
An expert performs bone fracture diagnosis using an X-ray image manually, which is a time-consuming process. The development of machine learning (ML), as well as deep learning (DL), has set a new path in medical image diagnosis. In this study, we proposed a novel multi-scale feature fusion of a convolution neural network (CNN) and an improved canny edge algorithm that segregate fracture and healthy bone image. The hybrid scale fracture network (SFNet) is a novel two-scale sequential DL model. This model is highly efficient for bone fracture diagnosis and takes less computation time compared to other state-of-the-art deep CNN models. The innovation behind this research is that it works with an improved canny edge algorithm to obtain edges in the images that localize the fracture region. After that, grey images and their corresponding canny edge images are fed to the proposed hybrid SFNet for training and evaluation. Furthermore, the performance is also compared with the state-of-the-art deep CNN models on a bone image dataset. Our results showed that SFNet with canny (SFNet + canny) achieved the highest accuracy, F1-score and recall of 99.12%, 99% and 100%, respectively, for bone fracture diagnosis. It showed that using a canny edge algorithm improves the performance of CNN.
18
Sadjadi, Ebrahim Navid, Danial Sadrian Zadeh, Behzad Moshiri, Jesús García Herrero, Jose Manuel Molina López, and Roemi Fernández. "Application of Smooth Fuzzy Model in Image Denoising and Edge Detection." Mathematics 10, no. 14 (July 11, 2022): 2421. http://dx.doi.org/10.3390/math10142421.
Повний текст джерелаАнотація:
In this paper, the bounded variation property of fuzzy models with smooth compositions have been studied, and they have been compared with the standard fuzzy composition (e.g., min–max). Moreover, the contribution of the bounded variation of the smooth fuzzy model for the noise removal and edge preservation of the digital images has been investigated. Different simulations on the test images have been employed to verify the results. The performance index related to the detected edges of the smooth fuzzy models in the presence of both Gaussian and Impulse (also known as salt-and-pepper noise) noises of different densities has been found to be higher than the standard well-known fuzzy models (e.g., min–max composition), which demonstrates the efficiency of smooth compositions in comparison to the standard composition.
19
Bathiany, Sebastian, Johan Hidding, and Marten Scheffer. "Edge Detection Reveals Abrupt and Extreme Climate Events." Journal of Climate 33, no. 15 (August 1, 2020): 6399–421. http://dx.doi.org/10.1175/jcli-d-19-0449.1.
Повний текст джерелаАнотація:
AbstractThe most discernible and devastating impacts of climate change are caused by events with temporary extreme conditions (“extreme events”) or abrupt shifts to a new persistent climate state (“tipping points”). The rapidly growing amount of data from models and observations poses the challenge to reliably detect where, when, why, and how these events occur. This situation calls for data-mining approaches that can detect and diagnose events in an automatic and reproducible way. Here, we apply a new strategy to this task by generalizing the classical machine-vision problem of detecting edges in 2D images to many dimensions (including time). Our edge detector identifies abrupt or extreme climate events in spatiotemporal data, quantifies their abruptness (or extremeness), and provides diagnostics that help one to understand the causes of these shifts. We also publish a comprehensive toolset of code that is documented and free to use. We document the performance of the new edge detector by analyzing several datasets of observations and models. In particular, we apply it to all monthly 2D variables of the RCP8.5 scenario of the Coupled Model Intercomparison Project (CMIP5). More than half of all simulations show abrupt shifts of more than 4 standard deviations on a time scale of 10 years. These shifts are mostly related to the loss of sea ice and permafrost in the Arctic. Our results demonstrate that the edge detector is particularly useful to scan large datasets in an efficient way, for example multimodel or perturbed-physics ensembles. It can thus help to reveal hidden “climate surprises” and to assess the uncertainties of dangerous climate events.
20
Prochazkova, Jana, David Procházka, and Jaromír Landa. "Sharp Feature Detection as a Useful Tool in Smart Manufacturing." ISPRS International Journal of Geo-Information 9, no. 7 (June 30, 2020): 422. http://dx.doi.org/10.3390/ijgi9070422.
Повний текст джерелаАнотація:
Industry 4.0 comprises a wide spectrum of developmental processes within the management of manufacturing and chain production. Presently, there is a huge effort to automate manufacturing and have automatic control of the production. This intention leads to the increased need for high-quality methods for digitization and object reconstruction, especially in the area of reverse engineering. Commonly used scanning software based on well-known algorithms can correctly process smooth objects. Nevertheless, they are usually not applicable for complex-shaped models with sharp features. The number of the points on the edges is extremely limited due to the principle of laser scanning and sometimes also low scanning resolution. Therefore, a correct edge reconstruction problem occurs. The same problem appears in many other laser scanning applications, i.e., in the representation of the buildings from airborne laser scans for 3D city models. We focus on a method for preservation and reconstruction of sharp features. We provide a detailed description of all three key steps: point cloud segmentation, edge detection, and correct B-spline edge representation. The feature detection algorithm is based on the conventional region-growing method and we derive the optimal input value of curvature threshold using logarithmic least square regression. Subsequent edge representation stands on the iterative algorithm of B-spline approximation where we compute the weighted asymmetric error using the golden ratio. The series of examples indicates that our method gives better or comparable results to other methods.
21
Horrocks, Tom, Eun-Jung Holden, Daniel Wedge, and Chris Wijns. "A nonparametric boundary detection technique applied to 3D inverted surveys of the Kevitsa Ni-Cu-PGE deposit." GEOPHYSICS 83, no. 1 (January 1, 2018): IM1—IM13. http://dx.doi.org/10.1190/geo2017-0085.1.
Повний текст джерелаАнотація:
Geophysical inversion can produce 3D models of the subsurface’s physical properties. The smoothness of property variations in these models makes it challenging to automatically find boundaries of homogeneous regions, where these boundaries may have implications for petrophysical transition and are significant for geologic interpretation. We have developed a new boundary detection technique that nonparametrically identifies and subtracts homogeneous regions from the 3D model, leaving exposed edges. The method is based on kernel density estimation of local property variations, in which the number of modes in the kernel density estimates (i.e., the local mode cardinality [MC]) is used to identify edge voxels within the model. Two edge detection operators were developed: one using local values exclusively and the other incorporating the spatial distribution of local values into the local MC, which is more sensitive to local variations. To assist in the geologic interpretation, continuous boundary surfaces are generated from the identified edge voxels using a gradient-based 3D image morphological operation. The technique was evaluated on synthetic rock property models and effectively identified the lithologic boundaries, even with non-Gaussian noise. The proposed operators were also applied to visualize edges in density, conductivity, magnetic susceptibility, and seismic tomography models of the Kevitsa Ni-Cu-PGE deposit (Lapland, Finland) generated by geophysical inversion. The boundaries detected via the proposed technique can be used for visualization and may be useful in further geostatistical computation due to their statistical foundation.
22
Zhou, Liping, Wei-Bang Chen, and Chengcui Zhang. "Authorship Detection and Encoding for eBay Images." International Journal of Multimedia Data Engineering and Management 2, no. 1 (January 2011): 22–37. http://dx.doi.org/10.4018/jmdem.2011010102.
Повний текст джерелаАнотація:
This paper describes a framework to detect authorship of eBay images. It contains three modules: editing style summarization, classification and multi-account linking detection. For editing style summarization, three approaches, namely the edge-based approach, the color-based approach, and the color probability approach, are proposed to encode the common patterns inside a group of images with similar editing styles into common edge or color models. Prior to the summarization step, an edge-based clustering algorithm is developed. Corresponding to the three summarization approaches, three classification methods are developed accordingly to predict the authorship of an unlabeled test image. For multi-account linking detection, to detect the hidden owner behind multiple eBay seller accounts, two methods to measure the similarity between seller accounts based on similar models are presented.
23
Liu, Jing, and Yimin Shao. "An improved analytical model for a lubricated roller bearing including a localized defect with different edge shapes." Journal of Vibration and Control 24, no. 17 (June 22, 2017): 3894–907. http://dx.doi.org/10.1177/1077546317716315.
Повний текст джерелаАнотація:
Vibrations of a roller bearing (RB) with a localized defect (LOD) are determined by LOD edge shapes, which can be used to detect and diagnose the LODs. Therefore, it is very helpful to analyze the relationships between impulses and LOD edge shapes for detection and diagnosis of the early LODs. In this study, an improved analytical model for a lubricated RB with a LOD considering different edge shapes is proposed. The LOD edge propagation is determined by the size of small cylindrical surface at its edge. A time-varying impact force (TVIF) model for the LOD with different edge shapes is also presented depended on Hertzian contact theory. The time-varying displacement excitation (TVDE) and time-varying contact stiffness coefficient (TVSC) between the roller and LOD edges can be formulated by the presented model, which cannot be formulated by the previous models considering sharp edges in the literatures. Influences of LOD edge shapes on vibrations of the unlubricated and lubricated RB are investigated. The numerical results show that the amplitude and impulse waveform of the accelerations of the RB will be affected by the LOD edge shape and lubricated oil; however, the peak frequencies in the spectrum are slightly influenced by the LOD edge shape and lubricated oil. It seems that the presented numerical results can give some guidance for the incipient LOD detection and diagnosis for RBs.
24
Hou, Shuai, Jizhe Lu, Enguo Zhu, Hailong Zhang, and Aliaosha Ye. "A Federated Learning-Based Fault Detection Algorithm for Power Terminals." Mathematical Problems in Engineering 2022 (July 19, 2022): 1–10. http://dx.doi.org/10.1155/2022/9031701.
Повний текст джерелаАнотація:
Power terminal is an important part of the power grid, and fault detection of power terminals is essential for the safety of the power grid. Existing fault detection of power terminals is usually based on artificial intelligent or deep learning models in the cloud or edge servers to achieve high accuracy and low latency. However, these methods cannot protect the privacy of the terminals and update the detection model incrementally. A terminal-edge-server collaborative fault detection model based on federated learning is proposed in this study to improve the accuracy of fault detection, reduce the data transmission and protect the privacy of the terminals. The fault detection model is initially trained in the server using historical data and updated using the parameters of local models from edge servers according to different updating strategies, then the parameters will be sent to each edge server and further to all terminals. Each edge server updates the local model via the compressed system log from terminals in its coverage region, and each terminal uses the model to detect fault according to the system behavior in the log. Experiment results show that this fault detection algorithm has high accuracy and low latency, and the accuracy increases with more model updating.
25
Leeds, Daniel, and Michael Tarr. "Mixing hierarchical edge detection and medial axis models of object perception." Journal of Vision 15, no. 12 (September 1, 2015): 1095. http://dx.doi.org/10.1167/15.12.1095.
Повний текст джерела
26
Baştan, Muhammet, Syed Saqib Bukhari, and Thomas Breuel. "Active Canny: edge detection and recovery with open active contour models." IET Image Processing 11, no. 12 (December 1, 2017): 1325–32. http://dx.doi.org/10.1049/iet-ipr.2017.0336.
Повний текст джерела
27
Gerling, Gregory J., and Geb W. Thomas. "Two Dimensional Finite Element Modeling to Identify Physiological Bases for Tactile Gap Discrimination." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 49, no. 10 (September 2005): 891–95. http://dx.doi.org/10.1177/154193120504901004.
Повний текст джерелаАнотація:
Tactile edge and gap detection are fundamental to performing manual tasks. Because slowly adapting type I (SA-I) mechanoreceptors encode details pertinent to edge localization, understanding low-level encoding is critical to understanding edge perception. Solid mechanics models may help us understand how mechanoreceptors in the skin encode applied surface indentation into neural signals representing edges. Finite element models test whether an indenter separated by a gap creates unique stress/strain distributions in models based upon orientation to fingerprint lines. Results indicate that a gap axis parallel to ridge lines elicits a more pronounced signal than a gap axis perpendicular to ridge lines. The differences may be due to underlying intermediate ridge microstructure. The percentage differences for three derived stress metrics range from 30-87% greater when the indenter's gap axis parallels the ridges. This initial effort demonstrates that underlying skin microstructure may aid tactile perception of stimulus orientation.
28
Dinh, Duc-Liem, Hong-Nam Nguyen, Huy-Tan Thai, and Kim-Hung Le. "Towards AI-Based Traffic Counting System with Edge Computing." Journal of Advanced Transportation 2021 (June 27, 2021): 1–15. http://dx.doi.org/10.1155/2021/5551976.
Повний текст джерелаАнотація:
The recent years have witnessed a considerable rise in the number of vehicles, which has placed transportation infrastructure and traffic control under tremendous pressure. Yielding timely and accurate traffic flow information is essential in the development of traffic control strategies. Despite the continual advances and the wealth of literature available in intelligent transportation system (ITS), there is a lack of practical traffic counting system, which is readily deployable on edge devices. In this study, we introduce a low-cost and effective edge-based system integrating object detection models to perform vehicle detecting, tracking, and counting. First, a vehicle detection dataset (VDD) representing traffic conditions in Vietnam was created. Several deep learning models for VDD were then examined on two different edge device types. Using this detection, we presented a lightweight counting method seamlessly combining with a traditional tracking method to increase counting accuracy. Finally, the traffic flow information is obtained based on counted vehicle categories and their directions. The experiment results clearly indicate that the proposed system achieves the top inference speed at around 26.8 frames per second (FPS) with 92.1% accuracy on the VDD. This proves that our proposal is capable of producing high-accuracy traffic flow information and can be applicable to ITS in order to reduce labor-intensive tasks in traffic management.
29
Fan, Lili, Jiabin Yuan, Keke Zha, and Xunan Wang. "ELCD: Efficient Lunar Crater Detection Based on Attention Mechanisms and Multiscale Feature Fusion Networks from Digital Elevation Models." Remote Sensing 14, no. 20 (October 19, 2022): 5225. http://dx.doi.org/10.3390/rs14205225.
Повний текст джерелаАнотація:
The detection and counting of lunar impact craters are crucial for the selection of detector landing sites and the estimation of the age of the Moon. However, traditional crater detection methods are based on machine learning and image processing technologies. These are inefficient for situations with different distributions, overlaps, and crater sizes, and most of them mainly focus on the accuracy of detection and ignore the efficiency. In this paper, we propose an efficient lunar crater detection (ELCD) algorithm based on a novel crater edge segmentation network (AFNet) to detect lunar craters from digital elevation model (DEM) data. First, in AFNet, a lightweight attention mechanism module is introduced to enhance the feature extract capabilities of networks, and a new multiscale feature fusion module is designed by fusing different multi-level feature maps to reduce the information loss of the output map. Then, considering the imbalance in the classification and the distributions of the crater data, an efficient crater edge segmentation loss function (CESL) is designed to improve the network optimization performance. Lastly, the crater positions are obtained from the network output map by the crater edge extraction (CEA) algorithm. The experiment was conducted on the PyTorch platform using two lunar crater catalogs to evaluate the ELCD. The experimental results show that ELCD has a superior detection accuracy and inference speed compared with other state-of-the-art crater detection algorithms. As with most crater detection models that use DEM data, some small craters may be considered to be noise that cannot be detected. The proposed algorithm can be used to improve the accuracy and speed of deep space probes in detecting candidate landing sites, and the discovery of new craters can increase the size of the original data set.
30
Shi, Xuetao, Hongli Zhao, Hailin Jiang, Huijun Zuo, and Qiang Zhang. "Edge Intelligence-Based OCS Fault Detection in Rail Transit Systems." Wireless Communications and Mobile Computing 2023 (April 11, 2023): 1–11. http://dx.doi.org/10.1155/2023/8659679.
Повний текст джерелаАнотація:
The Overhead Contact System (OCS) is critical infrastructure for train power supply in rail transit systems. OCS state monitoring and fault detection are indispensable to guarantee the safety of railway operations. The existing human-based OCS state monitoring and fault diagnosing method has some inherent drawbacks, such as poor real-time capability, low detecting precision, and waste of human resources. Edge Intelligence (EI) can perform complex computing tasks offloaded from trains within a little delay, and it is believed to help empower the OCS. In this paper, we propose an EI-based OCS state monitoring and fault detecting system. The latest Computer Vision (CV) model YOLOv5s is used to detect the OCS faults using the collected images. Edge Computing (EC) is used to perform the CV model inference. The EC system receives the OCS images taken by the train cameras and calculates the real-time fault detection results. The consistency and scalability of running jobs on edge devices are also addressed in our approach. Extensive experimental results demonstrate that the proposed EI-based system can detect OCS faults in real-time. The adopted YOLOv5s achieves a high fault detection rate, outperforming other models.
31
Fishbach, Alon, Israel Nelken, and Yehezkel Yeshurun. "Auditory Edge Detection: A Neural Model for Physiological and Psychoacoustical Responses to Amplitude Transients." Journal of Neurophysiology 85, no. 6 (June 1, 2001): 2303–23. http://dx.doi.org/10.1152/jn.2001.85.6.2303.
Повний текст джерелаАнотація:
Primary segmentation of visual scenes is based on spatiotemporal edges that are presumably detected by neurons throughout the visual system. In contrast, the way in which the auditory system decomposes complex auditory scenes is substantially less clear. There is diverse physiological and psychophysical evidence for the sensitivity of the auditory system to amplitude transients, which can be considered as a partial analogue to visual spatiotemporal edges. However, there is currently no theoretical framework in which these phenomena can be associated or related to the perceptual task of auditory source segregation. We propose a neural model for an auditory temporal edge detector, whose underlying principles are similar to classical visual edge detector models. Our main result is that this model reproduces published physiological responses to amplitude transients collected at multiple levels of the auditory pathways using a variety of experimental procedures. Moreover, the model successfully predicts physiological responses to a new set of amplitude transients, collected in cat primary auditory cortex and medial geniculate body. Additionally, the model reproduces several published psychoacoustical responses to amplitude transients as well as the psychoacoustical data for amplitude edge detection reported here for the first time. These results support the hypothesis that the response of auditory neurons to amplitude transients is the correlate of psychoacoustical edge detection.
32
Wang, Dongcheng, Yanghuan Xu, Bowei Duan, Yongmei Wang, Mingming Song, Huaxin Yu, and Hongmin Liu. "Intelligent Recognition Model of Hot Rolling Strip Edge Defects Based on Deep Learning." Metals 11, no. 2 (January 27, 2021): 223. http://dx.doi.org/10.3390/met11020223.
Повний текст джерелаАнотація:
The edge of a hot rolling strip corresponds to the area where surface defects often occur. The morphologies of several common edge defects are similar to one another, thereby leading to easy error detection. To improve the detection accuracy of edge defects, the authors of this paper first classified the common edge defects and then made a dataset of edge defect images on this basis. Subsequently, edge defect recognition models were established on the basis of LeNet-5, AlexNet, and VggNet-16 by using a convolutional neural network as the core. Through multiple groups of training and recognition experiments, the model’s accuracy and recognition time of a single defect image were analyzed and compared with recognition models with different learning rates and sample batches. The experimental results showed that the recognition model based on the AlexNet had a maximum accuracy of 93.5%, and the average recognition time of a single defect image was 0.0035 s, which could meet the industry requirement. The research results in this paper provide a new method and thought for the fine detection of edge defects in hot rolling strips and have practical significance for improving the surface quality of hot rolling strips.
33
LYON, DOUGLAS A. "ON THE USE OF A VISUAL CORTICAL SUB-BAND MODEL FOR INTERACTIVE HEURISTIC EDGE DETECTION." International Journal of Pattern Recognition and Artificial Intelligence 18, no. 04 (June 2004): 583–606. http://dx.doi.org/10.1142/s0218001404003381.
Повний текст джерелаАнотація:
We present a novel interactive edge detection algorithm that combines A* search with low-level adaptive image processing. The algorithm models the semantically driven interpretation that we hypothesize to occur between the mind and visual cortex in the human brain. The basic idea is that oriented Gabor sub-bands are used to model grating cells in the mammalian visual system. These sub-bands are used during the search for a path to a marker in an image. A domain expert uses image markers to select edges of interest.We demonstrate the system in several image domains. Examples are shown in the areas of photo-interpretation, medical imaging, path planning and general edge finding. The A* search finds a suboptimal result, but executes in a time that is typically 10 to 1,000 times faster than the dynamic programming approach currently used for this type of edge detection.
34
Seo, Jihyun, Sumin Jang, Jaegeun Cha, Hyunhwa Choi, Daewon Kim, and Sunwook Kim. "MDED-Framework: A Distributed Microservice Deep-Learning Framework for Object Detection in Edge Computing." Sensors 23, no. 10 (May 12, 2023): 4712. http://dx.doi.org/10.3390/s23104712.
Повний текст джерелаАнотація:
The demand for deep learning frameworks capable of running in edge computing environments is rapidly increasing due to the exponential growth of data volume and the need for real-time processing. However, edge computing environments often have limited resources, necessitating the distribution of deep learning models. Distributing deep learning models can be challenging as it requires specifying the resource type for each process and ensuring that the models are lightweight without performance degradation. To address this issue, we propose the Microservice Deep-learning Edge Detection (MDED) framework, designed for easy deployment and distributed processing in edge computing environments. The MDED framework leverages Docker-based containers and Kubernetes orchestration to obtain a pedestrian-detection deep learning model with a speed of up to 19 FPS, satisfying the semi-real-time condition. The framework employs an ensemble of high-level feature-specific networks (HFN) and low-level feature-specific networks (LFN) trained on the MOT17Det dataset, achieving an accuracy improvement of up to AP50 and AP0.18 on MOT20Det data.
35
Pandey, Amit, Aman Gupta, and Radhey Shyam. "FACIAL EMOTION DETECTION AND RECOGNITION." International Journal of Engineering Applied Sciences and Technology 7, no. 1 (May 1, 2022): 176–79. http://dx.doi.org/10.33564/ijeast.2022.v07i01.027.
Повний текст джерелаАнотація:
Facial emotional expression is a part of face recognition, it has always been an easy task for humans, but achieving the same with a computer algorithm is challenging. With the recent and continuous advancements in computer vision and machine learning, it is possible to detect emotions in images, videos, etc. A face expression recognition method based on the Deep Neural Networks especially the convolutional neural network (CNN) and an image edge detection is proposed. The edge of each layer of the image is retrieved in the convolution process after the facial expression image is normalized. To maintain the texture picture's edge structure information, the retrieved edge information is placed on each feature image. In this research, several datasets are investigated and explored for training expression recognition models. The purpose of this paper is to make a study on face emotion detection and recognition via Machine learning algorithms and deep learning. This research work will present deeper insights into Face emotion detection and Recognition. It will also highlight the variables that have an impact on its efficacy.
36
Kim, Youngpil, Shinuk Yi, Hyunho Ahn, and Cheol-Ho Hong. "Accurate Crack Detection Based on Distributed Deep Learning for IoT Environment." Sensors 23, no. 2 (January 11, 2023): 858. http://dx.doi.org/10.3390/s23020858.
Повний текст джерелаАнотація:
Defects or cracks in roads, building walls, floors, and product surfaces can degrade the completeness of the product and become an impediment to quality control. Machine learning can be a solution for detecting defects effectively without human experts; however, the low-power computing device cannot afford that. In this paper, we suggest a crack detection system accelerated by edge computing. Our system consists of two: Rsef and Rsef-Edge. Rsef is a real-time segmentation method based on effective feature extraction that can perform crack image segmentation by optimizing conventional deep learning models. Then, we construct the edge-based system, named Rsef-Edge, to significantly decrease the inference time of Rsef, even in low-power IoT devices. As a result, we show both a fast inference time and good accuracy even in a low-powered computing environment.
37
Liao, Xiaolian, Jun Li, Leyi Li, Caoxi Shangguan, and Shaoyan Huang. "RGBD Salient Object Detection, Based on Specific Object Imaging." Sensors 22, no. 22 (November 19, 2022): 8973. http://dx.doi.org/10.3390/s22228973.
Повний текст джерелаАнотація:
RGBD salient object detection, based on the convolutional neural network, has achieved rapid development in recent years. However, existing models often focus on detecting salient object edges, instead of objects. Importantly, detecting objects can more intuitively display the complete information of the detection target. To take care of this issue, we propose a RGBD salient object detection method, based on specific object imaging, which can quickly capture and process important information on object features, and effectively screen out the salient objects in the scene. The screened target objects include not only the edge of the object, but also the complete feature information of the object, which realizes the detection and imaging of the salient objects. We conduct experiments on benchmark datasets and validate with two common metrics, and the results show that our method reduces the error by 0.003 and 0.201 (MAE) on D3Net and JLDCF, respectively. In addition, our method can still achieve a very good detection and imaging performance in the case of the greatly reduced training data.
38
Freitas, Nuno, Daniel Silva, Carlos Mavioso, Maria J. Cardoso, and Jaime S. Cardoso. "Deep Edge Detection Methods for the Automatic Calculation of the Breast Contour." Bioengineering 10, no. 4 (March 24, 2023): 401. http://dx.doi.org/10.3390/bioengineering10040401.
Повний текст джерелаАнотація:
Breast cancer conservative treatment (BCCT) is a form of treatment commonly used for patients with early breast cancer. This procedure consists of removing the cancer and a small margin of surrounding tissue, while leaving the healthy tissue intact. In recent years, this procedure has become increasingly common due to identical survival rates and better cosmetic outcomes than other alternatives. Although significant research has been conducted on BCCT, there is no gold-standard for evaluating the aesthetic results of the treatment. Recent works have proposed the automatic classification of cosmetic results based on breast features extracted from digital photographs. The computation of most of these features requires the representation of the breast contour, which becomes key to the aesthetic evaluation of BCCT. State-of-the-art methods use conventional image processing tools that automatically detect breast contours based on the shortest path applied to the Sobel filter result in a 2D digital photograph of the patient. However, because the Sobel filter is a general edge detector, it treats edges indistinguishably, i.e., it detects too many edges that are not relevant to breast contour detection and too few weak breast contours. In this paper, we propose an improvement to this method that replaces the Sobel filter with a novel neural network solution to improve breast contour detection based on the shortest path. The proposed solution learns effective representations for the edges between the breasts and the torso wall. We obtain state of the art results on a dataset that was used for developing previous models. Furthermore, we tested these models on a new dataset that contains more variable photographs and show that this new approach shows better generalization capabilities as the previously developed deep models do not perform so well when faced with a different dataset for testing. The main contribution of this paper is to further improve the capabilities of models that perform the objective classification of BCCT aesthetic results automatically by improving upon the current standard technique for detecting breast contours in digital photographs. To that end, the models introduced are simple to train and test on new datasets which makes this approach easily reproducible.
39
BOTHOREL, CECILE, JUAN DAVID CRUZ, MATTEO MAGNANI, and BARBORA MICENKOVÁ. "Clustering attributed graphs: Models, measures and methods." Network Science 3, no. 3 (March 18, 2015): 408–44. http://dx.doi.org/10.1017/nws.2015.9.
Повний текст джерелаАнотація:
AbstractClustering a graph, i.e., assigning its nodes to groups, is an important operation whose best known application is the discovery of communities in social networks. Graph clustering and community detection have traditionally focused on graphs without attributes, with the notable exception of edge weights. However, these models only provide a partial representation of real social systems, that are thus often described using node attributes, representing features of the actors, and edge attributes, representing different kinds of relationships among them. We refer to these models asattributed graphs. Consequently, existing graph clustering methods have been recently extended to deal with node and edge attributes. This article is a literature survey on this topic, organizing, and presenting recent research results in a uniform way, characterizing the main existing clustering methods and highlighting their conceptual differences. We also cover the important topic of clustering evaluation and identify current open problems.
40
Golding, Vaughn Peter, Zahra Gharineiat, Hafiz Suliman Munawar, and Fahim Ullah. "Crack Detection in Concrete Structures Using Deep Learning." Sustainability 14, no. 13 (July 2, 2022): 8117. http://dx.doi.org/10.3390/su14138117.
Повний текст джерелаАнотація:
Infrastructure, such as buildings, bridges, pavement, etc., needs to be examined periodically to maintain its reliability and structural health. Visual signs of cracks and depressions indicate stress and wear and tear over time, leading to failure/collapse if these cracks are located at critical locations, such as in load-bearing joints. Manual inspection is carried out by experienced inspectors who require long inspection times and rely on their empirical and subjective knowledge. This lengthy process results in delays that further compromise the infrastructure’s structural integrity. To address this limitation, this study proposes a deep learning (DL)-based autonomous crack detection method using the convolutional neural network (CNN) technique. To improve the CNN classification performance for enhanced pixel segmentation, 40,000 RGB images were processed before training a pretrained VGG16 architecture to create different CNN models. The chosen methods (grayscale, thresholding, and edge detection) have been used in image processing (IP) for crack detection, but not in DL. The study found that the grayscale models (F1 score for 10 epochs: 99.331%, 20 epochs: 99.549%) had a similar performance to the RGB models (F1 score for 10 epochs: 99.432%, 20 epochs: 99.533%), with the performance increasing at a greater rate with more training (grayscale: +2 TP, +11 TN images; RGB: +2 TP, +4 TN images). The thresholding and edge-detection models had reduced performance compared to the RGB models (20-epoch F1 score to RGB: thresholding −0.723%, edge detection −0.402%). This suggests that DL crack detection does not rely on colour. Hence, the model has implications for the automated crack detection of concrete infrastructures and the enhanced reliability of the gathered information.
41
Berwo, Michael Abebe, Zhipeng Wang, Yong Fang, Jabar Mahmood, and Nan Yang. "Off-road Quad-Bike Detection Using CNN Models." Journal of Physics: Conference Series 2356, no. 1 (October 1, 2022): 012026. http://dx.doi.org/10.1088/1742-6596/2356/1/012026.
Повний текст джерелаАнотація:
Off-road vehicles are rapidly being employed for transportation, military activities, and sports racing. However, in monitoring and maintaining the race’s safety and reliability, quad-bike detection receives less attention than on-road vehicle recognition utilizing DL approaches. In this paper, we used transfer-learning approaches on pre-trained models of cutting-edge architectures, notably Yolov4, Yolov4-tiny, and Yolov5s, to detect quad-bikes from images and videos. A quad-bike dataset acquired from YouTube (https://youtu.be/ZyE3t3lG-vU. Accessed on April 10, 2022) was used to train and assess these designs. In this paper, we show that the Yolov4-tiny architecture outperforms the Yolov4, and Yolov5s in terms of mAP@50 and computing time per image.
42
Koay, Hong Vin, Joon Huang Chuah, Chee-Onn Chow, Yang-Lang Chang, and Keh Kok Yong. "YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices." Remote Sensing 13, no. 21 (October 20, 2021): 4196. http://dx.doi.org/10.3390/rs13214196.
Повний текст джерелаАнотація:
Object detection in aerial images has been an active research area thanks to the vast availability of unmanned aerial vehicles (UAVs). Along with the increase of computational power, deep learning algorithms are commonly used for object detection tasks. However, aerial images have large variations, and the object sizes are usually small, rendering lower detection accuracy. Besides, real-time inferencing on low-cost edge devices remains an open-ended question. In this work, we explored the usage of state-of-the-art deep learning object detection on low-cost edge hardware. We propose YOLO-RTUAV, an improved version of YOLOv4-Tiny, as the solution. We benchmarked our proposed models with various state-of-the-art models on the VAID and COWC datasets. Our proposed model can achieve higher mean average precision (mAP) and frames per second (FPS) than other state-of-the-art tiny YOLO models, especially on a low-cost edge device such as the Jetson Nano 2 GB. It was observed that the Jetson Nano 2 GB can achieve up to 12.8 FPS with a model size of only 5.5 MB.
43
Aw, Y. K., Robyn Owens, and John Ross. "An analysis of local energy and phase congruency models in visual feature detection." Journal of the Australian Mathematical Society. Series B. Applied Mathematics 40, no. 1 (July 1998): 97–122. http://dx.doi.org/10.1017/s0334270000012406.
Повний текст джерелаАнотація:
AbstractA variety of approaches have been developed for the detection of features such as edges, lines, and corners in images. Many techniques presuppose the feature type, such as a step edge, and use the differential properties of the luminance function to detect the location of such features. The local energy model provides an alternative approach, detecting a variety of feature types in a single pass by analysing order in the phase components of the Fourier transform of the image. The local energy model is usually implemented by calculating the envelope of the analytic signal associated with the image function. Here we analyse the accuracy of such an implementation, and show that in certain cases the feature location is only approximately given by the local energy model. Orientation selectivity is another aspect of the local energy model, and we show that a feature is only correctly located at a peak of the local energy function when local energy has a zero gradient in two orthogonal directions at the peak point.
44
Meyer, T., A. Brunn, and U. Stilla. "ACCURACY INVESTIGATION ON IMAGE-BASED CHANGE DETECTION FOR BIM COMPLIANT INDOOR MODELS." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-4-2021 (June 17, 2021): 105–12. http://dx.doi.org/10.5194/isprs-annals-v-4-2021-105-2021.
Повний текст джерелаАнотація:
Abstract. Construction progress documentation is currently of great interest for the AEC (Architecture, Engineering and Construction) branch and BIM (Building Information Modeling). Subject of this work is the geometric accuracy assessment of image-based change detection in indoor environments based on a BIM. Line features usually serve well as geodetic references in indoor scenes in order to solve for camera orientation. However, building edges are never perfectly built as planned and often geometrically generalized for BIM compliant representation. As a result, in this approach, line correspondences for image-to-model co-registration are considered as statistically uncertain entities as this is essential for dealing with metric confidences in the field of civil engineering and BIM. We present an estimation model for camera pose refinement which is based on the incidence condition between model edges and corresponding image lines. Geometric accuracies are assigned to the model edges according to the Level of Accuracy (LOA) specification for BIM. The approach is demonstrated in a series of tests using a synthetic image of an indoor BIM. The effects of varying edge detection accuracies on the estimation are investigated as well as the effects of using model edges with different geometric quality by adding Gaussian noise to the synthetic observations, each within 100 simulation runs. The results show that the camera orientation can be improved with the presented estimation model as long as the BIM compliant references meet the conditions of LOA 30 or higher (σ < 7.5 mm).
45
Song, Jinhai, and Zhiyong Zhang. "Industrial Internet Intrusion Detection Method based on Cloud-Edge Collaboration." Frontiers in Science and Engineering 3, no. 3 (March 20, 2023): 1–8. http://dx.doi.org/10.54691/fse.v3i3.4498.
Повний текст джерелаАнотація:
Industrial Internet security incidents occur frequently, and the amount of industrial data is increasing exponentially. Efficient and correct detection of attacks is critical to industrial Internet security. The method is based on the concept of cloud-edge collaboration to detect malicious behaviors. Firstly, the data is normalized and preprocessed to reduce the differences caused by different feature scales, then the deep neural network(DNN) is used to extract the features of massive data, and finally the softmax function is used for classification. In order to verify the effectiveness of the model, it is evaluated on the NSL-KDD dataset and the GAS dataset, and compared with other traditional models, the model has higher precision and recall. This method integrates edge-cloud collaboration and deep learning models, which can effectively reduce edge load and improve model performance, and has a good application prospect.
46
Xia, Liegang, Jun Chen, Jiancheng Luo, Junxia Zhang, Dezhi Yang, and Zhanfeng Shen. "Building Change Detection Based on an Edge-Guided Convolutional Neural Network Combined with a Transformer." Remote Sensing 14, no. 18 (September 10, 2022): 4524. http://dx.doi.org/10.3390/rs14184524.
Повний текст джерелаАнотація:
Change detection extracts change areas in bitemporal remote sensing images, and plays an important role in urban construction and coordination. However, due to image offsets and brightness differences in bitemporal remote sensing images, traditional change detection algorithms often have reduced applicability and accuracy. The development of deep learning-based algorithms has improved their applicability and accuracy; however, existing models use either convolutions or transformers in the feature encoding stage. During feature extraction, local fine features and global features in images cannot always be obtained simultaneously. To address these issues, we propose a novel end-to-end change detection network (EGCTNet) with a fusion encoder (FE) that combines convolutional neural network (CNN) and transformer features. An intermediate decoder (IMD) eliminates global noise introduced during the encoding stage. We noted that ground objects have clearer semantic information and improved edge features. Therefore, we propose an edge detection branch (EDB) that uses object edges to guide mask features. We conducted extensive experiments on the LEVIR-CD and WHU-CD datasets, and EGCTNet exhibits good performance in detecting small and large building objects. On the LEVIR-CD dataset, we obtain F1 and IoU scores of 0.9008 and 0.8295. On the WHU-CD dataset, we obtain F1 and IoU scores of 0.9070 and 0.8298. Experimental results show that our model outperforms several previous change detection methods.
47
Li, Boqiang, Liang Qin, Feng Zhao, Haofeng Liu, Jinyun Yu, Min He, Jing Wang, and Kaipei Liu. "Research on Edge Detection Model of Insulators and Defects Based on Improved YOLOv4-tiny." Machines 11, no. 1 (January 16, 2023): 122. http://dx.doi.org/10.3390/machines11010122.
Повний текст джерелаАнотація:
Edge computing can avoid the long-distance transmission of massive data and problems with large-scale centralized processing. Hence, defect identification for insulators with object detection models based on deep learning is gradually shifting from cloud servers to edge computing devices. Therefore, we propose a detection model for insulators and defects designed to deploy on edge computing devices. The proposed model is improved on the basis of YOLOv4-tiny, which is suitable for edge computing devices, and the detection accuracy of the model is improved on the premise of maintaining a high detection speed. First, in the neck network, the inverted residual module is introduced to perform feature fusion to improve the positioning ability of the insulators. Then, a high-resolution detection output head is added to the original model to enhance its ability to detect defects. Finally, the prediction boxes are post-processed to incorporate split object boxes for large-scale insulators. In an experimental evaluation, the proposed model achieved an mAP of 96.22% with a detection speed of 10.398 frames per second (FPS) on an edge computing device, which basically meets the requirements of insulator and defect detection scenarios in edge computing devices.
48
PARSE, Milind, and Dhanya PRAMOD. "EDGE DETECTION TECHNIQUE BASED ON BILATERAL FILTERING AND ITERATIVE THRESHOLD SELECTION ALGORITHM AND TRANSFER LEARNING FOR TRAFFIC SIGN RECOGNITION." Scientific Journal of Silesian University of Technology. Series Transport 119 (June 1, 2023): 199–222. http://dx.doi.org/10.20858/sjsutst.2023.119.12.
Повний текст джерелаАнотація:
The traffic sign identification and recognition system (TSIRS) is an essential component for autonomous vehicles to succeed. The TSIRS helps to collect and provide helpful information for autonomous driving systems. The information may include limits on speed, directions for driving, signs to stop or lower the speed, and many more essential things for safe driving. Recently, incidents have been reported regarding autonomous vehicle crashes due to traffic sign identification and recognition system failures. The TSIRS fails to recognize the traffic signs in challenging conditions such as skewed signboards, scratches on traffic symbols, discontinuous or damaged traffic symbols, etc. These challenging conditions are presented for various reasons, such as accidents, storms, artificial damage, etc. Such traffic signs contain an ample amount of noise, because of which traffic sign identification and recognition become a challenging task for automated TSIRS systems. The proposed method in this paper addresses these challenges. The sign edge is a helpful feature for the recognition of traffic signs. A novel traffic sign edge detection algorithm is introduced based on bilateral filtering with adaptive thresholding and varying aperture size that effectively detects the edges from such noisy images. The proposed edge detection algorithm and transfer learning is used to train the Convolutional Neural Network (CNN) models and recognize the traffic signs. The performance of the proposed method is evaluated and compared with existing edge detection methods. The results show that the proposed algorithm achieves optimal Mean Square Error (MSE) and Root Mean Square Error (RMSE) error rates and has a better Signal to Noise Ratio (SNR) and Peak Signal to Noise Ratio (PSNR) ratio than the traditional edge detection algorithms. Furthermore, the precision rate, recall rate, and F1 scores are evaluated for the CNN models. With the German Traffic Sign Benchmark database (GTSRB), the proposed algorithm and Inception V3 CNN model gives promising results when it receives the edge-detected images for training and testing.
49
Kim, Young Jae, Chan-Hyeok Park, and MyungKeun Yoon. "FILM: Filtering and Machine Learning for Malware Detection in Edge Computing." Sensors 22, no. 6 (March 10, 2022): 2150. http://dx.doi.org/10.3390/s22062150.
Повний текст джерелаАнотація:
Machine learning with static-analysis features extracted from malware files has been adopted to detect malware variants, which is desirable for resource-constrained edge computing and Internet-of-Things devices with sensors; however, this learned model suffers from a misclassification problem because some malicious files have almost the same static-analysis features as benign ones. In this paper, we present a new detection method for edge computing that can utilize existing machine learning models to classify a suspicious file into either benign, malicious, or unpredictable categories while existing models make only a binary decision of either benign or malicious. The new method can utilize any existing deep learning models developed for malware detection after appending a simple sigmoid function to the models. When interpreting the sigmoid value during the testing phase, the new method determines if the model is confident about its prediction; therefore, the new method can take only the prediction of high accuracy, which reduces incorrect predictions on ambiguous static-analysis features. Through experiments on real malware datasets, we confirm that the new scheme significantly enhances the accuracy, precision, and recall of existing deep learning models. For example, the accuracy is enhanced from 0.96 to 0.99, while some files are classified as unpredictable that can be entrusted to the cloud for further dynamic or human analysis.
50
Stathopoulou, E. K., S. Rigon, R. Battisti, and F. Remondino. "ENHANCING GEOMETRIC EDGE DETAILS IN MVS RECONSTRUCTION." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B2-2021 (June 28, 2021): 391–98. http://dx.doi.org/10.5194/isprs-archives-xliii-b2-2021-391-2021.
Повний текст джерелаАнотація:
Abstract. Mesh models generated by multi view stereo (MVS) algorithms often fail to represent in an adequate manner the sharp, natural edge details of the scene. The harsh depth discontinuities of edge regions are eventually a challenging task for dense reconstruction, while vertex displacement during mesh refinement frequently leads to smoothed edges that do not coincide with the fine details of the scene. Meanwhile, 3D edges have been used for scene representation, particularly man-made built environments, which are dominated by regular planar and linear structures. Indeed, 3D edge detection and matching are commonly exploited either to constrain camera pose estimation, or to generate an abstract representation of the most salient parts of the scene, and even to support mesh reconstruction. In this work, we attempt to jointly use 3D edge extraction and MVS mesh generation to promote edge detail preservation in the final result. Salient 3D edges of the scene are reconstructed with state-of-the-art algorithms and integrated in the dense point cloud to be further used in order to support the mesh triangulation step. Experimental results on benchmark dataset sequences using metric and appearance-based measures are performed in order to evaluate our hypothesis.