Journal articles on the topic 'Vehicle color recognition'
To see the other types of publications on this topic, follow the link: Vehicle color recognition.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Vehicle color recognition.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Yaba, Hawar Hussein, and Hemin Omer Latif. "Plate Number Recognition based on Hybrid Techniques." UHD Journal of Science and Technology 6, no. 2 (September 1, 2022): 39–48. http://dx.doi.org/10.21928/uhdjst.v6n2y2022.pp39-48.
Full textAbstract:
Globally and locally, the number of vehicles is on the rise. It is becoming more and more challenging for authorities to track down specific vehicles. Automatic License Plate Recognition becomes an addition to transportation systems automation. Where the extraction of the vehicle license plate is done without human intervention. Identifying the precise place of a vehicle through its license plate number from moving images of the vehicle image is among the crucial activities for vehicle plate discovery systems. Artificial intelligence systems are connecting the gap between the physical world and digital world of automatic license plate detection. The proposed research uses machine learning to recognizing Arabic license plate numbers. An image of the vehicle number plate is captured and the detection is done by image processing, character segmentation which locates Arabic numeric characters on a number plate. The system recognizes the license plate number area and extracts the plate area from the vehicle image. The background color of the number plate identifies the vehicle types: (1) White color for private vehicle; (2) red color for bus and taxi; (3) blue color for governmental vehicle; (4) yellow color for trucks, tractors, and cranes; (5) black color for temporary license; and (6) green color for army. The recognition of Arabic numbers from license plates is achieved by two methods as (1) Google Tesseract OCR based recognition and (2) Machine Learning-based training and testing Arabic number character as K-nearest neighbors (kNN). The system has been tested on 90 images downloaded from the internet and captured from CCTV. Empirical outcomes show that the proposed system finds plate numbers as well as recognizes background color and Arabic number characters successfully. The overall success rates of plate localization and background color detection have been done. The overall success rate of plate localization and background color detection is 97.78%, and Arabic number detection in OCR is 45.56 % as well as in KNN is 92.22%.
2
Gmiterko, Alexander. "LINE RECOGNITION SENSORS." TECHNICAL SCIENCES AND TECHNOLOGIES, no. 4 (14) (2018): 194–200. http://dx.doi.org/10.25140/2411-5363-2018-4(14)-194-200.
Full textAbstract:
Urgency of the research. There is a need from industrial practice for developing of methods for linefollowing navigation of automated guided vehicle (AGV) for logistic task in factories without operators. Target setting. Various types of navigation methods are used for vehicles. Actual scientific researches and issues analysis. Navigation of this automated guided vehicle can be made through the color line on ground or through the inductive sensed cable located underground. Also magnetically guided method is used. Various types of optical markers can be also used. Nowadays this type of autonomous robot applications grows up, because there is a need from industry. Uninvestigated parts of general matters defining. Next generation of automated guided vehicle is navigated via using laser scanners and they are also called LGV – Laser Guided Vehicle. This type is not covered in this paper. The research objective. The main aim of paper is to design the sensing system for color line sensing. There are several problems in using of these types of sensors. Manufacturer notes that there is placed daylight filter, but first experiments shows sensitivity to daylight. This problem can occurs when vehicle goes to tunnel. Next problem is when vehicle moves uphill and downhill on a bridge. The statement of basic materials. The color of sensor can be sensed with sensor - reflection optocoupler working in infrared light range. The optocoupler includes the infrared LED transmitter and infrared phototransistor, which senses the reflected light. Optocouplers are placed on bottom side of vehicle. Navigation line is black and other ground area is white. Optocoupler located over the navigation black line has no infrared reflection. Conclusions. The selected sensor system has been adapted for line detection application. Also ramp problems have been solved. Sensors have been successfully installed on linefollower vehicle. Results shows visible difference between the voltage levels related to black and white color line. Future plans is to add camera vision system for automatic recognition of line before vehicle and continuously path planning. Vision systems are also frequently used for obstacle detection and mapping of environment and consequently for path planning.
3
Hu, Mingdi, Yi Wu, Jiulun Fan, and Bingyi Jing. "Joint Semantic Intelligent Detection of Vehicle Color under Rainy Conditions." Mathematics 10, no. 19 (September 26, 2022): 3512. http://dx.doi.org/10.3390/math10193512.
Full textAbstract:
Color is an important feature of vehicles, and it plays a key role in intelligent traffic management and criminal investigation. Existing algorithms for vehicle color recognition are typically trained on data under good weather conditions and have poor robustness for outdoor visual tasks. Fine vehicle color recognition under rainy conditions is still a challenging problem. In this paper, an algorithm for jointly deraining and recognizing vehicle color, (JADAR), is proposed, where three layers of UNet are embedded into RetinaNet-50 to obtain joint semantic fusion information. More precisely, the UNet subnet is used for deraining, and the feature maps of the recovered clean image and the extracted feature maps of the input image are cascaded into the Feature Pyramid Net (FPN) module to achieve joint semantic learning. The joint feature maps are then fed into the class and box subnets to classify and locate objects. The RainVehicleColor-24 dataset is used to train the JADAR for vehicle color recognition under rainy conditions, and extensive experiments are conducted. Since the deraining and detecting modules share the feature extraction layers, our algorithm maintains the test time of RetinaNet-50 while improving its robustness. Testing on self-built and public real datasets, the mean average precision (mAP) of vehicle color recognition reaches 72.07%, which beats both sate-of-the-art algorithms for vehicle color recognition and popular target detection algorithms.
4
Park, Sun-Mi, and Ku-Jin Kim. "PCA-SVM Based Vehicle Color Recognition." KIPS Transactions:PartB 15B, no. 4 (August 29, 2008): 285–92. http://dx.doi.org/10.3745/kipstb.2008.15-b.4.285.
Full text
5
Hou, Dong Liang, and Xiao Lin Feng. "A New Quick Recognition Method Based on RGB Color Space." Advanced Materials Research 1049-1050 (October 2014): 1581–85. http://dx.doi.org/10.4028/www.scientific.net/amr.1049-1050.1581.
Full textAbstract:
Automatic Guided vehicle (AGV) can free drivers from boring work. Previously AGV guided by black conduction band, as the color is single, it can only used for a kind of vehicle navigation.When there are several kind of vehicles need to be guided, the black conduction band becomes powerless. Color conduction bands can overcome this problem. Usually RGB image should be converted to other image space, and then identifies the bands,but it costs lots of time. This paper proposes a quick recognition method which can be used in RGB color space. It effectively improved the recognition speed, and realized real-time identification.
6
WU, JUI-CHEN, JUN-WEI HSIEH, SIN-YU CHEN, CHENG-MIN TU, and YUNG-SHENG CHEN. "VEHICLE ORIENTATION ANALYSIS USING EIGEN COLOR, EDGE MAP, AND NORMALIZED CUT CLUSTERING." International Journal of Pattern Recognition and Artificial Intelligence 24, no. 05 (August 2010): 823–46. http://dx.doi.org/10.1142/s0218001410008111.
Full textAbstract:
This paper proposes a novel approach for estimating vehicles' orientations from still images using "eigen color" and edge map through a clustering framework. To extract the eigen color, a novel color transform model is used for roughly segmenting a vehicle from its background. The model is invariant to various situations like contrast changes, background, and lighting. It does not need to be re-estimated for any new vehicles. In this eigen color space, different vehicle regions can be easily identified. However, since the problem of object segmentation is still ill-posed, only with this model, the shape of a vehicle cannot be well extracted from its background and thus affects the accuracy of orientation estimation. In order to solve this problem, the distributions of vehicle edges and colors are then integrated together to form a powerful but high-dimensional feature space. Since the feature dimension is high, the normalized cut spectral clustering (Ncut) is then used for feature reduction and orientation clustering. The criterion in Ncut tries to minimize the ratio of the total dissimilarity between groups to the total similarity within the groups. Then, the vehicle orientation can be analyzed using the eigenvectors derived from the Ncut result. The proposed framework needs only one still image and is thus very different to traditional methods which need motion features to determine vehicle orientations. Experimental results reveal the superior performances in vehicle orientation analysis.
7
Panetta, Karen, Landry Kezebou, Victor Oludare, James Intriligator, and Sos Agaian. "Artificial Intelligence for Text-Based Vehicle Search, Recognition, and Continuous Localization in Traffic Videos." AI 2, no. 4 (December 6, 2021): 684–704. http://dx.doi.org/10.3390/ai2040041.
Full textAbstract:
The concept of searching and localizing vehicles from live traffic videos based on descriptive textual input has yet to be explored in the scholarly literature. Endowing Intelligent Transportation Systems (ITS) with such a capability could help solve crimes on roadways. One major impediment to the advancement of fine-grain vehicle recognition models is the lack of video testbench datasets with annotated ground truth data. Additionally, to the best of our knowledge, no metrics currently exist for evaluating the robustness and performance efficiency of a vehicle recognition model on live videos and even less so for vehicle search and localization models. In this paper, we address these challenges by proposing V-Localize, a novel artificial intelligence framework for vehicle search and continuous localization captured from live traffic videos based on input textual descriptions. An efficient hashgraph algorithm is introduced to compute valid target information from textual input. This work further introduces two novel datasets to advance AI research in these challenging areas. These datasets include (a) the most diverse and large-scale Vehicle Color Recognition (VCoR) dataset with 15 color classes—twice as many as the number of color classes in the largest existing such dataset—to facilitate finer-grain recognition with color information; and (b) a Vehicle Recognition in Video (VRiV) dataset, a first of its kind video testbench dataset for evaluating the performance of vehicle recognition models in live videos rather than still image data. The VRiV dataset will open new avenues for AI researchers to investigate innovative approaches that were previously intractable due to the lack of annotated traffic vehicle recognition video testbench dataset. Finally, to address the gap in the field, five novel metrics are introduced in this paper for adequately accessing the performance of vehicle recognition models in live videos. Ultimately, the proposed metrics could also prove intuitively effective at quantitative model evaluation in other video recognition applications. T One major advantage of the proposed vehicle search and continuous localization framework is that it could be integrated in ITS software solution to aid law enforcement, especially in critical cases such as of amber alerts or hit-and-run incidents.
8
Che, Sheng Bing, and Jin Kai Luo. "Vehicle License Plate Recognition with Intelligent Materials Based on Color Division." Advanced Materials Research 485 (February 2012): 592–95. http://dx.doi.org/10.4028/www.scientific.net/amr.485.592.
Full textAbstract:
With the development and progress of the economic and technology, transportation has become more and more important in human’s usual life. Intelligent transportation system can be used in many areas. Images in RGB color space are very sensitive to the environment light intensity, and what’s more, there may be some pollution appeared on the plate and so on, these made it difficult to locate the plate area. In this paper, we proposed some new algorithms. In the first stage, car image preprocess, a new algorithm named color division was proposed. Experiments show that, influences from the environment as well as some inevitably differences of colors in the plate into standard color, so the performance of whole system was improved. In the period of license location, a new algorithm based on license color pairs was proposed, and it has good performance after experiments.
9
Hu, Mingdi, Chenrui Wang, Jingbing Yang, Yi Wu, Jiulun Fan, and Bingyi Jing. "Rain Rendering and Construction of Rain Vehicle Color-24 Dataset." Mathematics 10, no. 17 (September 5, 2022): 3210. http://dx.doi.org/10.3390/math10173210.
Full textAbstract:
The fine identification of vehicle color can assist in criminal investigation or intelligent traffic management law enforcement. Since almost all vehicle-color datasets that are used to train models are collected in good weather, the existing vehicle-color recognition algorithms typically show poor performance for outdoor visual tasks. In this paper we construct a new RainVehicleColor-24 dataset by rain-image rendering using PS technology and a SyRaGAN algorithm based on the VehicleColor-24 dataset. The dataset contains a total of 40,300 rain images with 125 different rain patterns, which can be used to train deep neural networks for specific vehicle-color recognition tasks. Experiments show that the vehicle-color recognition algorithms trained on the new dataset RainVehicleColor-24 improve accuracy to around 72% and 90% on rainy and sunny days, respectively. The code is available at humingdi2005@github.com.
10
Hou, Dong Liang, and Xiao Lin Feng. "A Kind of Design of Automatic Guided Vehicle Based on RGB Color Space." Applied Mechanics and Materials 687-691 (November 2014): 3844–48. http://dx.doi.org/10.4028/www.scientific.net/amm.687-691.3844.
Full textAbstract:
Automatic Guided vehicle (AGV) can free drivers from boring work. Previously AGV guided by black conduction band, as the color is single, it can only used for a kind of vehicle navigation.When there are several kind of vehicles need to be guided, the black conduction band becomes powerless. Color conduction bands can overcome this problem. Usually RGB image should be converted to other image space, and then identified the bands,but it costs lots of time. This paper proposes the design of AGV and intruduces the hardware, also proposes a quick recognition method which can be used in RGB color space. It effectively improved the recognition speed, and realized real-time identification.
11
Ayaz, Muhammad, Dr Said Khalid Shah, Dr Muhammad Javed, Muhammad Assam, Wasiat Khan, and Fahad Najeeb. "Automatic Vehicle Number Plate Recognition Approach Using Color Detection Technique." Vol 3 Issue 5 3, no. 5 (January 8, 2022): 166–76. http://dx.doi.org/10.33411/ijist/2021030513.
Full textAbstract:
An Automatic Vehicle Number Plate Recognition System (AVNPR) is a key research area in image processing. Various techniques are developed and tested by researchers to improve the detection and recognition rate of AVNPR system but faced problems due to issues such as variation in format, lighting conditions, scales, and colors of number plates in different countries or states or even provinces of a country. Douglas Peucker Algorithm for shape approximation has been used in this research to detect the rectangular contours and the most prominent rectangular contour is extracted as a number plate (NP) and the connected component analysis is used to segment the characters followed by optical character recognition (OCR) to recognize the number plate characters. A custom dataset of 210 vehicle images with different colors at various distances and lighting conditions was used for the proposed method captured on my smart phone Galaxy J7 Model SM-j700F at roads and parking. The dataset contains various types of vehicles (i.e. Trucks, motorcars, mini-buses, tractors, pick-ups etc). The proposed method shows an average result of 95.5%. The novelty used in this method is that it works for different colors simultaneously because in Pakistan, several colors are used for vehicle NPs.
12
Hu, Chuanping, Xiang Bai, Li Qi, Pan Chen, Gengjian Xue, and Lin Mei. "Vehicle Color Recognition With Spatial Pyramid Deep Learning." IEEE Transactions on Intelligent Transportation Systems 16, no. 5 (October 2015): 2925–34. http://dx.doi.org/10.1109/tits.2015.2430892.
Full text
13
Zang, Di, Zhihua Wei, Maomao Bao, Jiujun Cheng, Dongdong Zhang, Keshuang Tang, and Xin Li. "Deep learning–based traffic sign recognition for unmanned autonomous vehicles." Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering 232, no. 5 (March 4, 2018): 497–505. http://dx.doi.org/10.1177/0959651818758865.
Full textAbstract:
Being one of the key techniques for unmanned autonomous vehicle, traffic sign recognition is applied to assist autopilot. Colors are very important clues to identify traffic signs; however, color-based methods suffer performance degradation in the case of light variation. Convolutional neural network, as one of the deep learning methods, is able to hierarchically learn high-level features from the raw input. It has been proved that convolutional neural network–based approaches outperform the color-based ones. At present, inputs of convolutional neural networks are processed either as gray images or as three independent color channels; the learned color features are still not enough to represent traffic signs. Apart from colors, temporal constraint is also crucial to recognize video-based traffic signs. The characteristics of traffic signs in the time domain require further exploration. Quaternion numbers are able to encode multi-dimensional information, and they have been employed to describe color images. In this article, we are inspired to present a quaternion convolutional neural network–based approach to recognize traffic signs by fusing spatial and temporal features in a single framework. Experimental results illustrate that the proposed method can yield correct recognition results and obtain better performance when compared with the state-of-the-art work.
14
Chen, Pan, Xiang Bai, and Wenyu Liu. "Vehicle Color Recognition on Urban Road by Feature Context." IEEE Transactions on Intelligent Transportation Systems 15, no. 5 (October 2014): 2340–46. http://dx.doi.org/10.1109/tits.2014.2308897.
Full text
15
Wang, Zhenzhou, Wei Huo, Pingping Yu, Lin Qi, Shanshan Geng, and Ning Cao. "Performance Evaluation of Region-Based Convolutional Neural Networks Toward Improved Vehicle Taillight Detection." Applied Sciences 9, no. 18 (September 8, 2019): 3753. http://dx.doi.org/10.3390/app9183753.
Full textAbstract:
Increasingly serious traffic jams and traffic accidents pose threats to the social economy and human life. The lamp semantics of driving is a major way to transmit the driving behavior information between vehicles. The detection and recognition of the vehicle taillights can acquire and understand the taillight semantics, which is of great significance for realizing multi-vehicle behavior interaction and assists driving. It is a challenge to detect taillights and identify the taillight semantics on real traffic road during the day. The main research content of this paper is mainly to establish a neural network to detect vehicles and to complete recognition of the taillights of the preceding vehicle based on image processing. First, the outlines of the preceding vehicles are detected and extracted by using convolutional neural networks. Then, the taillight area in the Hue-Saturation-Value (HSV) color space are extracted and the taillight pairs are detected by correlations of histograms, color and positions. Then the taillight states are identified based on the histogram feature parameters of the taillight image. The detected taillight state of the preceding vehicle is prompted to the driver to reduce traffic accidents caused by the untimely judgement of the driving intention of the preceding vehicle. The experimental results show that this method can accurately identify taillight status during the daytime and can effectively reduce the occurrence of confused judgement caused by light interference.
16
Yibing, Zhao, Xu Hongbin, Guo Lie, Li Linhui, and Zhang Mingheng. "Research of Obstacle Recognition Technology in Cross-Country Environment for Unmanned Ground Vehicle." Mathematical Problems in Engineering 2014 (2014): 1–13. http://dx.doi.org/10.1155/2014/531681.
Full textAbstract:
Being aimed at the obstacle recognition problem of unmanned ground vehicles in cross-country environment, this paper uses monocular vision sensor to realize the obstacle recognition of typical obstacles. Firstly, median filtering algorithm is applied during image preprocessing that can eliminate the noise. Secondly, image segmentation method based on the Fisher criterion function is used to segment the region of interest. Then, morphological method is used to process the segmented image, which is preparing for the subsequent analysis. The next step is to extract the color featureS, color featureaand edge feature “verticality” of image are extracted based on the HSI color space, the Lab color space, and two value images. Finally multifeature fusion algorithm based on Bayes classification theory is used for obstacle recognition. Test results show that the algorithm has good robustness and accuracy.
17
Rehman, Saif Ur, Moiz Ahmad, Asif Nawaz, and Tariq Ali. "An Efficient Approach for Vehicle Number Plate Recognition in Pakistan." Open Artificial Intelligence Journal 06, no. 1 (May 9, 2020): 12–21. http://dx.doi.org/10.2174/1874061802006010012.
Full textAbstract:
Introduction: Recognition of Vehicle License Number Plates (VLNP) is an important task. It is valuable in numerous applications, such as entrance admission, security, parking control, road traffic control, and speed control. An ANPR (Automatic Number Plate Recognition) is a system in which the image of the vehicle is captured through high definition cameras. The image is then used to detect vehicles of any type (car, van, bus, truck, and bike, etc.), its’ color (white, black, blue, etc.), and its’ model (Toyota Corolla, Honda Civic etc.). Furthermore, this image is processed using segmentation and OCR techniques to get the vehicle registration number in form of characters. Once the required information is extracted from VLNP, this information is sent to the control center for further processing. Aim: ANPR is a challenging problem, especially when the number plates have varying sizes, the number of lines, fonts, background diversity, etc. Different ANPR systems have been suggested for different countries, including Iran, Malaysia, and France. However, only a limited work exists for Pakistan vehicles. Therefore, in this study, we aim to propose a novel ANPR framework for Pakistan VLNP recognition. Methods: The proposed ANPR system functions in three different steps: (i) - Number Plate Localization (NPL); (ii)- Character Segmentation (CS); and (iii)- Optical Character Recognition (OCR), involving template-matching mechanism. The proposed ANPR approach scans the number plate and instantly checks against database records of vehicles of interest. It can further extract the real=time information of driver and vehicle, for instance, license of the driver and token taxes of vehicles are paid or not, etc. Results: Finally, the proposed ANPR system has been evaluated on several real-time images from various formats of number plates practiced in Pakistan territory. In addition to this, the proposed ANPR system has been compared with the existing ANPR systems proposed specifically for Pakistani licensed number plates. Conclusion: The proposed ANPR Model has both time and money-saving profit for law enforcement agencies and private organizations for improving homeland security. There is a need to expand the types of vehicles that can be detected: trucks, buses, scooters, bikes. This technology can be further improved to detect the crashed vehicle’s number plate in an accident and alert the closest hospital and police station about the accident, thus saving lives.
18
Xu, Mei Hua, Chen Jun Xia, and Huai Meng Zheng. "A Study of Self-Adaptive Front Vehicle Recognition Algorithm Based on Multi-Features." Advanced Materials Research 945-949 (June 2014): 1815–19. http://dx.doi.org/10.4028/www.scientific.net/amr.945-949.1815.
Full textAbstract:
With the development of intelligent driving technology, recognition the vehicle in front of our cars became the hotspot in the field of intelligent driving research. This paper presents a self-adaptive front vehicle recognition algorithm with some unique improved method on the basis of analyzing and comparing the popular vehicle detection algorithm of domestic and foreign. Using the gray feature, vehicle shadow feature, taillights feature, license plate color domain feature and other features, the recognition algorithm can detect the vehicle in front of cars effectively, find out the safe passage area and avoid the potential risks. Finally, the feasibility of the algorithm is verified by experiment results with MATLAB tools.
19
Zhao, Dongxin. "Application of Neural Network Based on Visual Recognition in Color Perception Analysis of Intelligent Vehicle HMI Interactive Interface under User Experience." Computational Intelligence and Neuroscience 2022 (October 12, 2022): 1–10. http://dx.doi.org/10.1155/2022/3929110.
Full textAbstract:
As a bridge of human-computer communication, the color design of intelligent vehicle HMI interactive interface is particularly important. It is also the first guide to the driver during the driving process. The quality of its design will also directly affect the driver’s senses and the driving safety of the vehicle. Therefore, this paper introduces the current situation, design principle, and future development of the vehicle interaction interface from multiple perspectives. Through the neural network system (condition generation countermeasure network model) of visual recognition, the color of the intelligent vehicle HMI interactive interface under the user experience is analyzed. According to the analysis of the psychological cognition and behavior operation of the automobile user, the correlation analysis of the human, vehicle, environment, and various elements of the interface is carried out, and how the vehicle interactive interface can meet the expected physiological and psychological needs of the user more and improve the operability is discussed in order to design an on-board HMI interactive interface that can be intelligently perceived according to weather, driver’s interests, and other factors and then improve the current backward operation mode of the on-board interactive interface, so that the interaction between people and vehicles is more smooth and pleasant.
20
Cheng, Sining, Jiaxian Qin, Yuanyuan Chen, and Mingzhu Li. "Moving Target Detection Technology Based on UAV Vision." Wireless Communications and Mobile Computing 2022 (July 22, 2022): 1–13. http://dx.doi.org/10.1155/2022/5443237.
Full textAbstract:
The detection of moving objects by machine vision is a hot research direction in recent years. It is widely used in military, medical, transportation, and agriculture. With the rapid development of UAV technology, as well as the high mobility of UAVs and the wide range of high-altitude vision, the target detection technology based on UAV vision is applied to traffic management such as vehicle tracking and detection of vehicle violations. The moving target detection technology in this study is based on the YOLOv3 algorithm. It implements moving vehicle tracking by means of Mean-Shift and Kalman filtering. In this paper, the Gaussian background difference technology is used to analyze the illegal behavior of the vehicle, and the color feature extraction technology is used to identify and locate the license plate, and the information of the illegal vehicle is entered into the database. The experiment compares the moving target detection of UAV vision and the traditional target detection in four aspects: recognition accuracy, recognition speed, manual time, and divergent results. The results show that the average accuracy rates of UAV vision-based moving target detection and traditional pattern recognition are 98.4% and 87.8%, respectively. The recognition speeds are 24.9 (vehicles/sec) and 10.6 (vehicles/sec), respectively. However, the artificial time and divergence results of moving target detection based on UAV vision are only 1/3 of the traditional mode. The moving target detection based on UAV vision has a better moving target detection ability.
21
Geng, Keke, Wei Zou, Guodong Yin, Yang Li, Zihao Zhou, Fan Yang, Yuan Wu, and Cheng Shen. "Low-observable targets detection for autonomous vehicles based on dual-modal sensor fusion with deep learning approach." Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 233, no. 9 (August 2019): 2270–83. http://dx.doi.org/10.1177/0954407019859821.
Full textAbstract:
Environment perception is a basic and necessary technology for autonomous vehicles to ensure safety and reliable driving. A lot of studies have focused on the ideal environment, while much less work has been done on the perception of low-observable targets, features of which may not be obvious in a complex environment. However, it is inevitable for autonomous vehicles to drive in environmental conditions such as rain, snow and night-time, during which the features of the targets are not obvious and detection models trained by images with significant features fail to detect low-observable target. This article mainly studies the efficient and intelligent recognition algorithm of low-observable targets in complex environments, focuses on the development of engineering method to dual-modal image (color–infrared images) low-observable target recognition and explores the applications of infrared imaging and color imaging for an intelligent perception system in autonomous vehicles. A dual-modal deep neural network is established to fuse the color and infrared images and detect low-observable targets in dual-modal images. A manually labeled color–infrared image dataset of low-observable targets is built. The deep learning neural network is trained to optimize internal parameters to make the system capable for both pedestrians and vehicle recognition in complex environments. The experimental results indicate that the dual-modal deep neural network has a better performance on the low-observable target detection and recognition in complex environments than traditional methods.
22
Li, Ke, Rongchun Deng, Yongkang Cheng, Rongqun Hu, and Keyong Shen. "Research on Vehicle Detection and Recognition Based on Infrared Image and Feature Extraction." Mobile Information Systems 2022 (April 22, 2022): 1–10. http://dx.doi.org/10.1155/2022/6154614.
Full textAbstract:
Vehicle detection and identification and safe distance keeping technology have become the main content of current intelligent transportation system research. Among them, vehicle detection and recognition is one of the most important research contents, and it is also crucial to the safe driving of vehicles. Real-time detection and recognition of current vehicles can effectively prevent the occurrence of malignant traffic accidents such as rear-end collision. Because the infrared image has some shortcomings such as poor contrast, loud noise, and blurred edge, this paper mainly studies the color space preprocessing of the image and uses threshold segmentation method and infrared image enhancement to segment the front vehicle and background. That is to say, by analyzing the infrared image captured by infrared CCD, we use median filter to remove noise from the collected infrared image and then use the improved histogram equalization to enhance the contrast of the image. Vertical Sobel operator is selected to enhance the vertical edge of the image, and the image is segmented by binary segmentation method. Finally, vehicle detection and recognition are realized by vertical edge symmetry, aspect ratio, and gray-scale symmetry. The experimental image and experimental data analysis results show that the image processing technology studied in this paper has achieved the intended research purpose.
23
Thammarak, Karanrat, Prateep Kongkla, Yaowarat Sirisathitkul, and Sarun Intakosum. "Comparative analysis of Tesseract and Google Cloud Vision for Thai vehicle registration certificate." International Journal of Electrical and Computer Engineering (IJECE) 12, no. 2 (April 1, 2022): 1849. http://dx.doi.org/10.11591/ijece.v12i2.pp1849-1858.
Full textAbstract:
Optical character recognition (OCR) is a technology to digitize a paper-based document to digital form. This research studies the extraction of the characters from a Thai vehicle registration certificate via a Google Cloud Vision API and a Tesseract OCR. The recognition performance of both OCR APIs is also examined. The 84 color image files comprised three image sizes/resolutions and five image characteristics. For suitable image type comparison, the greyscale and binary image are converted from color images. Furthermore, the three pre-processing techniques, sharpening, contrast adjustment, and brightness adjustment, are also applied to enhance the quality of image before applying the two OCR APIs. The recognition performance was evaluated in terms of accuracy and readability. The results showed that the Google Cloud Vision API works well for the Thai vehicle registration certificate with an accuracy of 84.43%, whereas the Tesseract OCR showed an accuracy of 47.02%. The highest accuracy came from the color image with 1024×768 px, 300dpi, and using sharpening and brightness adjustment as pre-processing techniques. In terms of readability, the Google Cloud Vision API has more readability than the Tesseract. The proposed conditions facilitate the possibility of the implementation for Thai vehicle registration certificate recognition system.
24
Wakamiya, Atsushi, Naoki Suganuma, In Soo Kweon, and Naofumi Fujiwara. "Obstacle Recognition and Position Measurement for Night Driving by Image Processing." Journal of Robotics and Mechatronics 13, no. 4 (August 20, 2001): 371–80. http://dx.doi.org/10.20965/jrm.2001.p0371.
Full textAbstract:
The reduced driving visibility at night makes it important in driver support to improve recognize obstacle recognition. We propose detecting vehicle tail lights by us bright color information issued at night and measuring the relative distance to the vehicle from its image position using stereo vision. We conducted experiments to determine the effectiveness of our proposed technique.
25
AĞGÜL, Burak, and Gökhan ERDEMİR. "Development of a Counterfeit Vehicle License Plate Detection System by Using Deep Learning." Balkan Journal of Electrical and Computer Engineering 10, no. 3 (July 30, 2022): 252–57. http://dx.doi.org/10.17694/bajece.1093158.
Full textAbstract:
In this study, a deep learning-based counterfeit plate detection system that compares and detects vehicles with the make, model, color, and license plate is designed. As known that the relevant government institutions are responsible for keeping all detailed information about all motor vehicles in their database. All registration details are stored in the database. It is possible to find unregistered vehicles by comparing database records with detected details. In general, vehicles with counterfeit license plates are used in illegal actions. Therefore, it is of great importance to detect them. Generally, license plate recognition systems successfully detect counterfeit license plates that are randomly generated. Security units typically use such systems at toll roads, bridge crossings, parking lot entrances and exits, sites, customs gates, etc. This kind of system only checks the plate is exists or not in the database. But it is unsuccessful if the vehicle uses existing plate numbers such as stolen ones. In this study, the developed system can detect not only vehicles' plate numbers but also make, model, year, and color information by using deep learning. Thus, the system can also detect randomly generated plates and stolen plates that belong to another vehicle.
26
Dai, Zhi Tao, Yi Wen Wang, Shu Sun, and Pan Zhang. "The Research and Implementation of Parallel In-Vehicle Vision System Based on Multi-Core Processors." Applied Mechanics and Materials 224 (November 2012): 529–32. http://dx.doi.org/10.4028/www.scientific.net/amm.224.529.
Full textAbstract:
This paper introduces a novel implementation of in-vehicle traffic signs and traffic lights recognition system based on FPGA multi-core processers. Images could be processed with multi-core parallel processor using the corresponding relationships of traffic signs’ color and shape. We implement this vehicle vision system on SOPC hardware platform.
27
Shao, Jian Chao, Xue Mei Guo, and Bing Qi Chen. "Study on Vehicle License Plate Automatic Recognition System for Exit and Entrance." Applied Mechanics and Materials 58-60 (June 2011): 2115–21. http://dx.doi.org/10.4028/www.scientific.net/amm.58-60.2115.
Full textAbstract:
A new algorithm of vehicle license plate automatic recognition for exit and entrance was proposed in this research. Firstly, using the gray information of vehicle license plate to locate plate roughly, and secondly using the color characteristics of the plate for accurate positioning in the rough location region, and then correcting the horizontal tilt of the plate by the method of Hough transform. After above processing, we adopt template matching method to recognize the plate characters. Experimental results indicated that the developed method can adapt to a variety of complex backgrounds and achieve the correct recognition of the vehicle license plate.
28
Gashnikov, M. V., A. V. Chernov, and N. V. Chupshev. "Color correction of vehicle images during the sequential registration of color channels." Pattern Recognition and Image Analysis 19, no. 1 (March 2009): 106–8. http://dx.doi.org/10.1134/s1054661809010192.
Full text
29
Li, Qingwu, Haisu Cheng, Yan Zhou, and Guanying Huo. "Road Vehicle Monitoring System Based on Intelligent Visual Internet of Things." Journal of Sensors 2015 (2015): 1–16. http://dx.doi.org/10.1155/2015/720308.
Full textAbstract:
In recent years, with the rapid development of video surveillance infrastructure, more and more intelligent surveillance systems have employed computer vision and pattern recognition techniques. In this paper, we present a novel intelligent surveillance system used for the management of road vehicles based on Intelligent Visual Internet of Things (IVIoT). The system has the ability to extract the vehicle visual tags on the urban roads; in other words, it can label any vehicle by means of computer vision and therefore can easily recognize vehicles with visual tags. The nodes designed in the system can be installed not only on the urban roads for providing basic information but also on the mobile sensing vehicles for providing mobility support and improving sensing coverage. Visual tags mentioned in this paper consist of license plate number, vehicle color, and vehicle type and have several additional properties, such as passing spot and passing moment. Moreover, we present a fast and efficient image haze removal method to deal with haze weather condition. The experiment results show that the designed road vehicle monitoring system achieves an average real-time tracking accuracy of 85.80% under different conditions.
30
Lin, Yueh-lung, and Conghua Wen. "Vehicle Vision Robust Detection and Recognition Method." International Journal of Pattern Recognition and Artificial Intelligence 34, no. 10 (December 31, 2019): 2055020. http://dx.doi.org/10.1142/s0218001420550204.
Full textAbstract:
With the rapid growth of the global economy, the global car ownership is also increasing year by year, which has caused a series of problems, the most prominent of which is traffic congestion and traffic accidents. In order to solve the traffic problem, all countries are actively studying the intelligent transportation system, and one of the important research contents of the intelligent transportation system is vehicle detection. Vehicle detection based on vision is to capture vehicle images in the driving environment through a camera, and then use computer vision recognition technology for vehicle detection and recognition. Although computer vision recognition technology has made great progress, how to improve the detection accuracy of the image to be detected is still an important content of visual recognition technology research. Intelligent vehicle visual robust detection and identification of methods of research to reduce the growing incidence of traffic accidents, improve the existing road traffic safety and transportation efficiency, alleviate the degree of driver fatigue problem are of great significance. This paper considers the intelligent vehicle environmental awareness of the key technology to the goal of robust detection and recognition based on machine vision problems for further research. The particle filter is used to extract the local energy of the image to realize the fast segmentation of the region of interest (ROI). In order to further verify the ROI, a measure learning method based on multi-core embedding is proposed, and the semantic classification of ROI is realized by integrating the color, shape and geometric features of ROI. Experimental results show that the algorithm can effectively eliminate false sexy ROI interest, and the algorithm is robust to complex background, illumination changes, perspective changes and other conditions.
31
Chávez-Aragón, Alberto, Rizwan Macknojia, Pierre Payeur, and Robert Laganière. "Rapid 3D Modeling and Parts Recognition on Automotive Vehicles Using a Network of RGB-D Sensors for Robot Guidance." Journal of Sensors 2013 (2013): 1–16. http://dx.doi.org/10.1155/2013/832963.
Full textAbstract:
This paper presents an approach for the automatic detection and fast 3D profiling of lateral body panels of vehicles. The work introduces a method to integrate raw streams from depth sensors in the task of 3D profiling and reconstruction and a methodology for the extrinsic calibration of a network of Kinect sensors. This sensing framework is intended for rapidly providing a robot with enough spatial information to interact with automobile panels using various tools. When a vehicle is positioned inside the defined scanning area, a collection of reference parts on the bodywork are automatically recognized from a mosaic of color images collected by a network of Kinect sensors distributed around the vehicle and a global frame of reference is set up. Sections of the depth information on one side of the vehicle are then collected, aligned, and merged into a global RGB-D model. Finally, a 3D triangular mesh modelling the body panels of the vehicle is automatically built. The approach has applications in the intelligent transportation industry, automated vehicle inspection, quality control, automatic car wash systems, automotive production lines, and scan alignment and interpretation.
32
Zhang, Qiang, Li Zhuo, Jiafeng Li, Jing Zhang, Hui Zhang, and Xiaoguang Li. "Vehicle color recognition using Multiple-Layer Feature Representations of lightweight convolutional neural network." Signal Processing 147 (June 2018): 146–53. http://dx.doi.org/10.1016/j.sigpro.2018.01.021.
Full text
33
XU, YUANYUAN, BIN KONG, HU WEI, and QIANG TIAN. "LANE-BASED DIRECTION MARKING RECOGNITION USING HU MOMENTS." International Journal of Information Acquisition 09, no. 03n04 (September 2013): 1350016. http://dx.doi.org/10.1142/s0219878913500162.
Full textAbstract:
In intelligent vehicle system, it is significant to detect and identify road markings for vehicles to follow traffic regulation. This paper proposes a method to recognize direction markings on road surface, which is on the basis of detected lanes and uses Hu moments. First of all, the detection of lanes is based on horizontal luminance difference, which converts the RGB color image to the luminance image, calculates the horizontal luminance difference, obtains the candidate points of lanes' edge and uses least square method to fit the lanes. Secondly, with the detected lines as guide for the search of candidate marking, the paper extracts Hu moments of candidate marking, calculates its Mahalanobis distance to every marking type and classifies it to the type which has the minimal distance with the candidate marking. From the simulation results, the method to detect lanes is more effective and time-efficient than canny or sobel edge detection methods; the method to recognize direction marking is effective and has a high accuracy.
34
Pan, Hao, and Bailing Zhang. "An Integrative Approach to Accurate Vehicle Logo Detection." Journal of Electrical and Computer Engineering 2013 (2013): 1–12. http://dx.doi.org/10.1155/2013/391652.
Full textAbstract:
Vehicle logo detection from images captured by surveillance cameras is an important step towards the vehicle recognition that is required for many applications in intelligent transportation systems and automatic surveillance. The task is challenging considering the small target of logos and the wide range of variability in shape, color, and illumination. A fast and reliable vehicle logo detection approach is proposed following visual attention mechanism from the human vision. Two prelogo detection steps, that is, vehicle region detection and a small RoI segmentation, rapidly focalize a small logo target. An enhanced Adaboost algorithm, together with two types of features of Haar and HOG, is proposed to detect vehicles. An RoI that covers logos is segmented based on our prior knowledge about the logos’ position relative to license plates, which can be accurately localized from frontal vehicle images. A two-stage cascade classier proceeds with the segmented RoI, using a hybrid of Gentle Adaboost and Support Vector Machine (SVM), resulting in precise logo positioning. Extensive experiments were conducted to verify the efficiency of the proposed scheme.
35
Hussein, Khalid Ali, and Ziad Tariq A. Al-Ani. "Iraqi License Plate Recognition Based on Neural Network Technique." Journal of Physics: Conference Series 2322, no. 1 (August 1, 2022): 012025. http://dx.doi.org/10.1088/1742-6596/2322/1/012025.
Full textAbstract:
Abstract License Plate (LP) is the unique identification of a vehicle. License Plate Recognition (LPR) is considered as one of the promising aspects of applying computer seeing technology across intelligent transportation system. We used mathematical morphology and edge detection as a method for segmentation and extracting the vehicle license plate character, in Location of the vehicle plate. Initially, the color image was changed to a gray image, and by calculating the difference between the pixels and their neighbors in order to build the edge of the image. This makes the license panel appear clearly. The Sobel operator is applied to extract the edge of objects in the image. In order to obtain a smooth image, we apply the mathematical morphology of the images for dilation and erosion, and then we improve the efficiency of segmentation processing by using the images that are sent to the LP recognition stage. Multi-layer perceptron neural network will be used to recognize the license plate. Characters can be accurately extracted from the license plate due to the accurate extraction of the plate region.
36
Yu, Hong, Alex Pyankov, and Marcus Perla. "A Developed Sensor for Color Identification, Sorting and Counting Automation Control System." European Journal of Engineering and Technology Research 6, no. 2 (February 15, 2021): 75–80. http://dx.doi.org/10.24018/ejers.2021.6.2.2363.
Full textAbstract:
Knowing how to manipulate the data from environment to automation control systems in industry can innovate and improve a quality of the products effectively. In plastic manufacturing, there is a need of automated control system that can recognize color and sort, count and sequentially control processing since the certain quantity of color billets mix into a batch in order to produce desired colorful products. In this paper, a color recognition sensor based on the principle of LEDs energy harvest corresponding actuator has been designed. The derivational voltage due to red, green and blue color shift in color recognition, sorting and counting automation control system is measured as a signal input of the controller that works with the reflected light properties such as the reflective harmonic energy. Sequentially, the automation control system with human machine interface (HMI) and supervisory control and data acquisition (SCADA) will monitor the quantity of diversity color products in intuitive and remote supervisory, customization or adjustments in automation processing. Furthermore, the designed device will integrate into artificial intelligent (AI) and unmanned aerial vehicle (UAV).
37
Yu, Hong, Alex Pyankov, and Marcus Perla. "A Developed Sensor for Color Identification, Sorting and Counting Automation Control System." European Journal of Engineering and Technology Research 6, no. 2 (February 15, 2021): 75–80. http://dx.doi.org/10.24018/ejeng.2021.6.2.2363.
Full textAbstract:
Knowing how to manipulate the data from environment to automation control systems in industry can innovate and improve a quality of the products effectively. In plastic manufacturing, there is a need of automated control system that can recognize color and sort, count and sequentially control processing since the certain quantity of color billets mix into a batch in order to produce desired colorful products. In this paper, a color recognition sensor based on the principle of LEDs energy harvest corresponding actuator has been designed. The derivational voltage due to red, green and blue color shift in color recognition, sorting and counting automation control system is measured as a signal input of the controller that works with the reflected light properties such as the reflective harmonic energy. Sequentially, the automation control system with human machine interface (HMI) and supervisory control and data acquisition (SCADA) will monitor the quantity of diversity color products in intuitive and remote supervisory, customization or adjustments in automation processing. Furthermore, the designed device will integrate into artificial intelligent (AI) and unmanned aerial vehicle (UAV).
38
Zhuo, Li, and Qiang Zhang. "High-accuracy vehicle color recognition using hierarchical fine-tuning strategy for urban surveillance videos." Journal of Electronic Imaging 27, no. 05 (February 1, 2018): 1. http://dx.doi.org/10.1117/1.jei.27.5.051203.
Full text
39
Zhang, Zhi Bin, Zhan Liu, Yong Sheng Song, Hai Yue Wang, and Guo Jun Tang. "A License Plate Recognition System Based on HSV Space in Natural Lighting." Advanced Materials Research 590 (November 2012): 421–26. http://dx.doi.org/10.4028/www.scientific.net/amr.590.421.
Full textAbstract:
In recent years, with the development of modern traffic demand, the automobile license plate recognition technology has obtained more and more attentions. In this paper, the license plate in the vehicle image is located by extracting the color feature in HSV color space. And after binarizing the license plate image, the vertical scanning procedure is used to segment the license plate characters, and the template matching procedure are used to recognize the characters according to the similar degrees. Experimental results show that the system designed in this paper can effectively recognize the license plate in natural lighting, with the accuracy up to 95% for the Chinese characters, 90.4% for the numbers, 84.4% for the letters, and the time consumption being second level.
40
Xiao, Yong Hao, and Hong Zhen. "Pedestrian Crowd Detection Based Unmanned Aerial Vehicle Infrared Imagery." Applied Mechanics and Materials 873 (November 2017): 347–52. http://dx.doi.org/10.4028/www.scientific.net/amm.873.347.
Full textAbstract:
Human detection is a keyproblem in computer vision. Recently, some research has been focusing on the detection ofpedestrianusing infrared images. The infrared images have outstanding merit. It depends only on object's temperature, but not on color or texture. In this paper, the pedestrian crowd detection approach is proposed. The approach is compose of ROI blocks extraction and crowd block recognition. ROI blocks can be extracted with circle gradient operator and weighted geometric filtering. Crowd blocks are recognized by support vector machine, which combines histogram of oriented gradient and circle gradient. The experimental results show thatthe approach works effectively in different scenes.
41
Khudov, Hennadii, Oleksandr Makoveichuk, Dmytro Misiuk, Hennadii Pievtsov, Irina Khizhnyak, Yuriy Solomonenko, Iryna Yuzova, Volodymyr Cherneha, Valerii Vlasiuk, and Vladyslav Khudov. "Devising a method for processing the image of a vehicle's license plate when shooting with a smartphone camera." Eastern-European Journal of Enterprise Technologies 1, no. 2(115) (February 25, 2022): 6–21. http://dx.doi.org/10.15587/1729-4061.2022.252310.
Full textAbstract:
This paper reports an improved method for processing the image of a vehicle's license plate when shooting with a smartphone camera. The method for processing the image of a vehicle's license plate includes the following stages: – enter the source data; – split the video streaming into frames; – preliminary process the image of a vehicle's license plate; – find the area of a vehicle's license plate; – refine character recognition using the signature of a vehicle's license plate; – refine character recognition using the combined results from frames in the streaming video; – obtain the result of processing. Experimental studies were conducted on the processing of images of a vehicle's license plate. During the experimental studies, the license plate of a military vehicle (Ukraine) was considered. The original image was the color image of a vehicle. The results of experimental studies are given. A comparison of the quality of character recognition in a license plate has been carried out. It was established that the improved method that uses the combined results from streaming video frames works out efficiently at the end of the sequence. The improved method that employs the combined results from streaming video frames operates with numerical probability vectors. The assessment of errors of the first and second kind in processing the image of a license plate was carried out. The total accuracy of finding the area of a license plate by known method is 61 % while the improved method's result is 76 %. It has been established that the minimization of errors of the first kind is more important than reducing errors of the second kind. If a license plate is incorrectly identified, these results would certainly be discarded at the character recognition stage.
42
Ho Kwon, Tae, Jai Eun Kim, Ki Soo An, Rappy Saha, and Ki Doo Kim. "Visual-MIMO for Software-Defined Vehicular Networks." International Journal of Engineering & Technology 7, no. 4.4 (September 15, 2018): 13. http://dx.doi.org/10.14419/ijet.v7i4.4.19596.
Full textAbstract:
The paradigm of software-defined network (SDN) is being applied to vehicle scenarios in order to eliminate this heterogeneity of vehicular network infrastructure and to manage packet flow in an application- and user-centrically flexible and efficient manner. However, owing to the random mobility of vehicles and the unpredictable road communication environment, efficient vehicle-based SDN development needs further research. In this study, we propose the concept of a sub-control plane for supporting and backing up, at the data plane level, various functions of the control plane, which plays a key role in SDN. The sub-control plane can be intuitively understood through the image processing techniques used in color-independent visual-MIMO (multiple input multiple output) networking, and the function of the control plane can be backed up through various vehicle-based recognition and tracking algorithms under the situation of disconnection between the data plane and the control plane. The proposed sub-control plane is expected to facilitate efficient management of the software-defined vehicular network (SDVN) and improve vehicular communication performance and service quality.
43
Cao, Jingwei, Chuanxue Song, Silun Peng, Feng Xiao, and Shixin Song. "Improved Traffic Sign Detection and Recognition Algorithm for Intelligent Vehicles." Sensors 19, no. 18 (September 18, 2019): 4021. http://dx.doi.org/10.3390/s19184021.
Full textAbstract:
Traffic sign detection and recognition are crucial in the development of intelligent vehicles. An improved traffic sign detection and recognition algorithm for intelligent vehicles is proposed to address problems such as how easily affected traditional traffic sign detection is by the environment, and poor real-time performance of deep learning-based methodologies for traffic sign recognition. Firstly, the HSV color space is used for spatial threshold segmentation, and traffic signs are effectively detected based on the shape features. Secondly, the model is considerably improved on the basis of the classical LeNet-5 convolutional neural network model by using Gabor kernel as the initial convolutional kernel, adding the batch normalization processing after the pooling layer and selecting Adam method as the optimizer algorithm. Finally, the traffic sign classification and recognition experiments are conducted based on the German Traffic Sign Recognition Benchmark. The favorable prediction and accurate recognition of traffic signs are achieved through the continuous training and testing of the network model. Experimental results show that the accurate recognition rate of traffic signs reaches 99.75%, and the average processing time per frame is 5.4 ms. Compared with other algorithms, the proposed algorithm has remarkable accuracy and real-time performance, strong generalization ability and high training efficiency. The accurate recognition rate and average processing time are markedly improved. This improvement is of considerable importance to reduce the accident rate and enhance the road traffic safety situation, providing a strong technical guarantee for the steady development of intelligent vehicle driving assistance.
44
Bagirov, M. B., T. L. Borodina, T. D. Karklin, and D. V. Dmitriev. "ALGORITHMS FOR TRACKING OBJECTS ON A VIDEO STREAM." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 219 (September 2022): 3–13. http://dx.doi.org/10.14489/vkit.2022.09.pp.003-013.
Full textAbstract:
Algorithms for monitoring moving objects are of great interest in the field of computer vision. The paper presents the results of the development and research of image analysis algorithms for monitoring vehicles in a video stream. Currently, the monitoring of vehicles, especially in production areas, is performed manually by operators. Developing practical applications of video analytics will reduce operator workload, increase speed and accuracy of decision making, and automate the process of collecting and generating reporting statistics on plant transportation. Research was conducted and a video analysis system was developed that includes detection algorithms, classifications by vehicle type, color, and model, and vehicle tracking in the video stream. It should be noted that the architecture of existing solutions, as a rule, is monolithic and does not allow to refine and embed new unique modules to solve emerging problems. In modern conditions, in order to cover new requirements in the field of object recognition and detection in large vehicle flows, it is necessary to develop and implement new solutions. The results of the work of the algorithms on real images of existing datasets and the developed own dataset are presented. In this case, the objects are under different lighting conditions, in different angles, are rebuilt in the stream, there is an overlap of objects. The developed system has a microservice architecture, which allows to adapt the solutions to specific tasks.
45
Mahmood, Zahid, Khurram Khan, Uzair Khan, Syed Hasan Adil, Syed Saad Azhar Ali, and Mohsin Shahzad. "Towards Automatic License Plate Detection." Sensors 22, no. 3 (February 7, 2022): 1245. http://dx.doi.org/10.3390/s22031245.
Full textAbstract:
Automatic License Plate Detection (ALPD) is an integral component of using computer vision approaches in Intelligent Transportation Systems (ITS). An accurate detection of vehicles’ license plates in images is a critical step that has a substantial impact on any ALPD system’s recognition rate. In this paper, we develop an efficient license plate detecting technique through the intelligent combination of Faster R-CNN along with digital image processing techniques. The proposed algorithm initially detects vehicle(s) in the input image through Faster R-CNN. Later, the located vehicle is analyzed by a robust License Plate Localization Module (LPLM). The LPLM module primarily uses color segmentation and processes the HSV image to detect the license plate in the input image. Moreover, the LPLM module employs morphological filtering and dimension analysis to find the license plate. Detailed trials on challenging PKU datasets demonstrate that the proposed method outperforms few recently developed methods by producing high license plates detection accuracy in much less execution time. The proposed work demonstrates a great feasibility for security and target detection applications.
46
Ahmed, Bhutto Jaseem, Qin Bo, Qu Jabo, Zhai Xiaowei, and Abdullah Maitlo. "Urban Road Traffic Sign Detection & Recognition with Time Space Relationship Model." Sukkur IBA Journal of Emerging Technologies 4, no. 1 (June 10, 2021): 22–33. http://dx.doi.org/10.30537/sjet.v4i1.860.
Full textAbstract:
Detection and recognition of urban road traffic signs is an important part of the Modern Intelligent Transportation System (ITS). It is a driver support function which can be used to notify and warn the driver for any possible incidence on the current stretch of road. This paper presents a robust and novel Time Space Relationship Model for high positive urban road traffic sign detection and recognition for a running vehicle. There are three main contributions of the proposed framework. Firstly, it applies fast color-segment algorithm based on color information to extract candidate areas of traffic signs and reduce the computation load. Secondly, it verifies the traffic sign candidate areas to decrease false positives and raise the accuracy by analysing the variation in preceding video-images sequence while implementing the proposed Time Space Relationship Model. Lastly, the classification is done with Support Vector Machine with dataset from real-time detection of TSRM. Experimental results indicate that the accuracy, efficiency, and the robustness of the framework are satisfied on urban road and detect road traffic sign in real time.
47
Fu, Huiyuan, Huadong Ma, Gaoya Wang, Xiaomou Zhang, and Yifan Zhang. "MCFF-CNN: Multiscale comprehensive feature fusion convolutional neural network for vehicle color recognition based on residual learning." Neurocomputing 395 (June 2020): 178–87. http://dx.doi.org/10.1016/j.neucom.2018.02.111.
Full text
48
Saraf, Samkit. "Use of Machine Learning in Automobile Industry to Improve Safety Using CNN." International Journal for Research in Applied Science and Engineering Technology 9, no. 10 (October 31, 2021): 1807–10. http://dx.doi.org/10.22214/ijraset.2021.38713.
Full textAbstract:
Abstract: Vision-based vehicle steering system cars can have three main roles: 1) road access; 2) an obstacle to find; and 3) signal recognition. The first two have already been taught many years and there have been many positive results, but a sign of traffic recognition is a less readable field. Road signs provide drivers with the most important information on the road, to do driving is safe and easy. We think road signs should play the same role of private cars. The color and shape are very different from the natural environment. The algorithm described in this paper uses this feature. It has two main parts. The first, to find, uses color range to separate image analysis and shapes to get symptoms. The second, in stages, uses the neural network. Some effects from natural forums are shown. On the other hand, the algorithm works to detect other types of marks can tell a moving robot to perform a specific task that place. Keywords: o Traffic signs o CNN o Cars o Image processing o Classification
49
Raza, Muhammad Ali, Chun Qi, Muhammad Rizwan Asif, and Muhammad Armoghan Khan. "An Adaptive Approach for Multi-National Vehicle License Plate Recognition Using Multi-Level Deep Features and Foreground Polarity Detection Model." Applied Sciences 10, no. 6 (March 22, 2020): 2165. http://dx.doi.org/10.3390/app10062165.
Full textAbstract:
License plate recognition system (LPR) plays a vital role in intelligent transport systems to build up smart environments. Numerous country specific methods have been proposed successfully for an LPR system, but there is a need to find a generalized solution that is independent of license plate layout. The proposed architecture is comprised of two important LPR stages: (i) License plate character segmentation (LPCS) and (ii) License plate character recognition (LPCR). A foreground polarity detection model is proposed by using a Red-Green-Blue (RGB) channel-based color map in order to segment and recognize the LP characters effectively at both LPCS and LPCR stages respectively. Further, a multi-channel CNN framework with layer aggregation module is proposed to extract deep features, and support vector machine is used to produce target labels. Multi-channel processing with merged features from different-level convolutional layers makes output feature map more expressive. Experimental results show that the proposed method is capable of achieving high recognition rate for multinational vehicles license plates under various illumination conditions.
50
Dr. Govind Shah. "An Efficient Traffic Control System and License Plate Detection Using Image Processing." International Journal of New Practices in Management and Engineering 6, no. 01 (March 31, 2017): 20–25. http://dx.doi.org/10.17762/ijnpme.v6i01.52.
Full textAbstract:
Automatic license plate recognition is extracted from license plate of the vehicle. It is taken as an image or a continuous image taken in sequence. The extracted information can be with or without a database in many applications like electronic payment systems and freeway and arterial monitoring devices for traffic surveillance. ALPR employs CC camera, advanced camera or black and white, color camera to capture the image. ALPR is fruitful if the captured images are of good quality. ALPR is a real time application that processes the images of license plates in various conditions like dark or bright times in a day. A general technique should be identified to process images in many different countries or states. We should know that the license plate generally consists of various colors, languages, fonts and others have images in the background. Also, these plates are obstructed by mud, light, some accessories especially on a car. Here, we discuss about methods for ALPR. We classify ALPR based on the features they are used in each method and knowing their advantages, disadvantages, recognition accuracy and processing speed. Managing the timing in traffic controlling by calculating the density of an image.