Vehicle Recognition Research Articles

Vehicle recognition based on Haar features and Adaboost cascade classifier

With the progress of world science and economic development, more and more industries are developing towards intelligence and automation. In the field of intelligent driving, the intelligent vehicle environment perception method based on machine vision has become a hot research topic. Based on monocular vision system, aiming at the requirements of different target features and detection accuracy and efficiency, this paper improves the Haar feature and Adaboost cascade classifier recognition algorithm combined with gray symmetry method to adapt to the recognition environment required by vehicles. The measured results show that the improved vehicle identification method combined with the tracking method based on Kalman filter can reduce the misjudgment rate of vehicles and has good real-time performance.

Vehicle Recognition from Unmanned Aerial Vehicle Videos Based on Fusion of Target Pre-Detection and Deep Learning

For accurate and effective automatic vehicle identification, morphological detection and deep convolutional networks were combined to propose a method for locating and identifying vehicle models from unmanned aerial vehicle (UAV) videos. First, the region of interest of the video frame image was sketched and grey-scale processing was performed; sub-pixel-level skeleton images were generated based on the Canny edge detection results of the region of interest; then, the image skeletons were decomposed and reconstructed. Second, a combination of morphological operations and connected domain morphological features were applied for vehicle target recognition, and a deep learning image benchmark library containing 244,520 UAV video vehicle samples was constructed. Third, we improved the AlexNet model by adding convolutional layers, pooling layers, and adjusting network parameters, which we named AlexNet*. Finally, a vehicle recognition method was established based on a candidate target extraction algorithm with AlexNet*. The validation analysis revealed that AlexNet* achieved a mean F1 of 85.51% for image classification, outperforming AlexNet (82.54%), LeNet (63.88%), CaffeNet (46.64%), VGG16 (16.67%), and GoogLeNet (14.38%). The mean values of Pcor, Pre, and Pmiss for cars and buses reached 94.63%, 6.87%, and 4.40%, respectively, proving that this method can effectively identify UAV video targets.

(Retracted) Laser radar-based intelligent vehicle target recognition and detection system using image detection technology

In recent years, with the progress of society and the development of the economy, the number of cars in China has been increasing. In wireless communication networks, the choice of wireless nodes has a greater impact on the improvement of system performance (such as channel capacity, coverage area, etc.). The intelligent vehicle target detection system can perceive and recognize the surrounding objects such as pedestrians and vehicles through sensors, which is the basis for realizing the unmanned driving of intelligent vehicles. In a wireless environment where multiple wireless nodes coexist, current research focuses on how long it takes to re-plan the selection of wireless nodes (for mobile environments) and how to allocate and manage wireless nodes, such as where under the conditions of wireless, who will wireless with whom, and in what way (such as auto focus, digital fusion, or other) wireless, etc.; the dedicated centralized controller (such as the base station of the infrastructure-based wireless access network) determines the wireless partner (i.e., centralized type selection), or the wireless node decides by itself (i.e., distributed selection); select the appropriate number of wireless nodes to take into account the system performance gain and implementation complexity. The popularity of automobiles has brought great convenience to people’s lives, but it has also brought greater traffic pressure. At present, the amount of domestic automobile traffic has increased exponentially, and urban traffic congestion has become more serious, and even caused serious traffic accidents, directly affecting people’s quality of life. The emergence of intelligent transportation systems has effectively alleviated road traffic pressure and reduced the incidence of traffic accidents. As an important part of the intelligent transportation system, the research of intelligent vehicles has received extensive attention. Intelligent vehicles use a variety of sensors installed on the body to sense the environment, and realize intelligent driving functions such as lane line detection, obstacle detection, dynamic cruise control, and unmanned driving, which is conducive to reducing the incidence of traffic accidents and improving the safety of vehicle driving. At present, in the research of target recognition and tracking of intelligent vehicles, the traditional target detection method is mainly based on artificial feature extraction, which is difficult to describe more complex or higher-order image features, and the tracking effect is not good, which limits the target detection. An intelligent vehicle is an intelligent system with functions such as environment perception, planning decision-making, and operation control, and is an important part of the intelligent transportation system. Identify the effect. In response to these problems, we present a study of the target recognition and tracking of intelligent vehicles based on grid map and lidar sensor technology. To verify the proposed method in the actual scene, we identify and track the vehicle ahead on the road through a car equipped with a lidar sensor. The meaning of target detection: target detection, also called target extraction, is an image segmentation based on target geometric and statistical features. The results show that the proposed research method can accurately identify the vehicle in front and detect the moving targets such as pedestrians. The tracking trajectory is also consistent with the expected route. The results show that the laser radar-based vehicle target recognition and tracking in this study is effective. In the 10 frames of images, the average time taken for the recognition of one frame of image is 9.8 ms, while the traditional method is 12.9 ms. Technology can improve reliable road information for intelligent vehicle driving and improve the transportation efficiency and safety performance of intelligent vehicles. There are two main target detection methods for lidar: detection methods based on feature extraction and detection methods based on grid maps.

A novel part-level feature extraction method for fine-grained vehicle recognition

In this paper, we propose a novel part-level feature extraction method to enhance the discriminative ability of deep convolutional features for the task of fine-grained vehicle recognition. Generally, the challenges for fine-grained vehicle recognition are mainly caused by the subtle visual differences between part regions of vehicles. Therefore, it is essential to extract discriminative features from part regions. Many existing methods, especially deep convolutional neural networks (D-CNNs), tend to detect the discriminative part regions explicitly or learn the part information implicitly through network restructuring and neglect the abundant part-level information contained in the high-level features generated by CNNs. In light of this, we propose a simple and effective part-level feature extraction method to enhance the representation of part-level features within the global features of target object generated by the backbone networks. The proposed method is built on the deep convolutional layers from which the discriminative part features could be integrated and extracted accordingly. More specifically, a basic feature grouping module is adopted to integrate the feature maps of deep convolutional layers into groups in each of which the related discriminative parts are assembled. The feature grouping process is performed in a multi-stage manner to ensure the integration process. Then a fusion module follows to model the coarse-to-fine relationship of the part features and further ensure the integrity and effectiveness of the part features. We conduct comparison experiments on public datasets, and the results show that the proposed method achieves comparable performance with state-of-the-art algorithms.

Accuracy Improvement of Vehicle Recognition by Using Smart Device Sensors.

This paper explores the utilization of smart device sensors for the purpose of vehicle recognition. Currently a ubiquitous aspect of people’s lives, smart devices can conveniently record details about walking, biking, jogging, and stepping, including physiological data, via often built-in phone activity recognition processes. This paper examines research on intelligent transportation systems to uncover how smart device sensor data may be used for vehicle recognition research, and fit within its growing body of literature. Here, we use the accelerometer and gyroscope, which can be commonly found in a smart phone, to detect the class of a vehicle. We collected data from cars, buses, trains, and bikes using a smartphone, and we designed a 1D CNN model leveraging the residual connection for vehicle recognition. The model achieved more than 98% accuracy in prediction. Moreover, we also provide future research directions based on our study.

Research on Deep Learning Automatic Vehicle Recognition Algorithm Based on RES-YOLO Model.

With the introduction of concepts such as ubiquitous mapping, mapping-related technologies are gradually applied in autonomous driving and target recognition. There are many problems in vision measurement and remote sensing, such as difficulty in automatic vehicle discrimination, high missing rates under multiple vehicle targets, and sensitivity to the external environment. This paper proposes an improved RES-YOLO detection algorithm to solve these problems and applies it to the automatic detection of vehicle targets. Specifically, this paper improves the detection effect of the traditional YOLO algorithm by selecting optimized feature networks and constructing adaptive loss functions. The BDD100K data set was used for training and verification. Additionally, the optimized YOLO deep learning vehicle detection model is obtained and compared with recent advanced target recognition algorithms. Experimental results show that the proposed algorithm can automatically identify multiple vehicle targets effectively and can significantly reduce missing and false rates, with the local optimal accuracy of up to 95% and the average accuracy above 86% under large data volume detection. The average accuracy of our algorithm is higher than all five other algorithms including the latest SSD and Faster-RCNN. In average accuracy, the RES-YOLO algorithm for small data volume and large data volume is 1.0% and 1.7% higher than the original YOLO. In addition, the training time is shortened by 7.3% compared with the original algorithm. The network is then tested with five types of local measured vehicle data sets and shows satisfactory recognition accuracy under different interference backgrounds. In short, the method in this paper can complete the task of vehicle target detection under different environmental interferences.

Research on Vehicle Detection and Recognition Based on Infrared Image and Feature Extraction

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.

Structure-guided attention network for fine-grained vehicle model recognition

In view of the difficulty in accurately recognizing vehicle models due to the wide variety of vehicle models and little differentiation between some models, a structure-guided attention network for weakly supervised learning fine-grained vehicle model recognition is proposed. First, we utilize the structure-guided attention location module to locate key features of images, extracting the strong and weak attention areas of the image by generating attention maps. Second, we investigate multichannel convolutional neural network for the learning of the strong-weak feature pairs and solve the problem of different network feature maps with different sizes by using feature map alignment. Third, an adaptive weighting method is proposed to balance the loss function. The experimental results show that our algorithm effectively improves the accuracy of the fine-grained vehicle recognition dataset and has universal applicability in other fine-grained recognition datasets.

Detection of Logos of Moving Vehicles under Complex Lighting Conditions

This study proposes a method for vehicle logo detection and recognition to detect missing and inaccurate vehicle marks under complex lighting conditions. For images acquired in complex light conditions, adaptive image enhancement is used to improve the accuracy of car sign detection by more than 2%; for the problems of multi-scale and detection speed of vehicle logo recognition in different images, the paper improves the target detection algorithm to improve the detection accuracy by more than 3%. The adaptive image enhancement algorithm and improved You Only Look One-level Feature (YOLOF) detection algorithm proposed in this study can effectively improve the correct identification rate under complex lighting conditions.

Intelligent Intersection Vehicle and Pedestrian Detection Based on Convolutional Neural Network

The preprocessed images are input to a pretrained neural network to obtain the corresponding feature mapping, and the corresponding region of interest is set for each point in the feature mapping to obtain multiple candidate feature regions; subsequently, these candidate feature regions are fed into a region proposal network and a deep residual network for binary classification and BB regression, and some of the candidate feature regions are filtered out, and the remaining feature regions are subjected to ROIAIign operation; finally, classification, BB regression, and mask generation are performed on these feature regions, and full convolutional nerve network operation is performed in each feature region and output. To further identify the specific model of the vehicle, this paper proposes a multifeature model recognition method that fuses the improved model with the optimized Mask R-CNN algorithm. A vehicle local feature dataset including vehicle badges, lights, air intake grille, and whole vehicle outline is established to simplify the network structure of model. Meanwhile, its detection frame generation process and the adjustment rules of overlapping frame confidence in nonmaximum suppression are improved for coarse vehicle localization. Then, the generated vehicle detection frames after localization are output to the Mask R-CNN algorithm after further optimizing the RPN structure. The localized vehicle detection frames are then output to the Mask R-CNN algorithm after further optimization of the RPN structure for local feature recognition, and good recognition results are achieved. Finally, this paper establishes a distributed server-based vehicle recognition system, which mainly includes database module, file module, feature extraction and matching module, message queue module, WEB module, and vehicle detection module. Due to the limitations of traditional region generation methods, this paper provides a brief analysis of the region generation network in the Faster R-CNN algorithm and details the loss calculation principle of the output layer.

Traffic Flow Detection Using Camera Images and Machine Learning Methods in ITS for Noise Map and Action Plan Optimization.

Noise maps and action plans represent the main tools in the fight against citizens’ exposure to noise, especially that produced by road traffic. The present and the future in smart traffic control is represented by Intelligent Transportation Systems (ITS), which however have not yet been sufficiently studied as possible noise-mitigation tools. However, ITS dedicated to traffic control rely on models and input data that are like those required for road traffic noise mapping. The present work developed an instrumentation based on low-cost cameras and a vehicle recognition and counting methodology using modern machine learning techniques, compliant with the requirements of the CNOSSOS-EU noise assessment model. The instrumentation and methodology could be integrated with existing ITS for traffic control in order to design an integrated method, which could also provide updated data over time for noise maps and action plans. The test was carried out as a follow up of the L.I.S.T. Port project, where an ITS was installed for road traffic management in the Italian port city of Piombino. The acoustic efficacy of the installation is evaluated by looking at the difference in the acoustic impact on the population before and after the ITS installation by means of the distribution of noise exposure, the evaluation of Gden and Gnight, and the calculation of the number of highly annoyed and sleep-disturbed citizens. Finally, it is shown how the ITS system represents a valid solution to be integrated with targeted and more specific sound mitigation, such as the laying of low-emission asphalts.

REAL-TIME MOVING VEHICLE COUNTER SYSTEM USING OPENCV AND PYTHON

— In view of highway management, intelligent vehicle recognition, and counting is becoming increasingly crucial. In highway monitoring, it is a crucial part that every vehicle should be observed and should go through vehicle monitoring and detection system. With today’s technology have great effect on this area the road surveillance camera gives a large library of traffic video footage has been available for examination. By taking these video footage from the cameras the paper will present a system that will achieve to calculate the vehicle their direction with using image subtractor and counters. The computer vision will advance the capability of the system to process on the videos and give desired output. The main idea behind using computer vision and open CV is that they will not disturb the traffic and monitoring part will be done smoothly. The vehicle counter-offered in this study is primarily based totally on an aggregate of image processing algorithms which includes item detection, edges detection, and frames differentiation. The machine has been applied with the use of Python. This paper explains how to use multiple libraries for real-time image processing to achieve traffic flow counting and classification. The proposed system differs the existing system by providing the feature to count the cars in the day and night mode.

Anomalous Vehicle Recognition in Smart Urban Traffic Monitoring as an Edge Service

The past decades witnessed an unprecedented urbanization and the proliferation of modern information and communication technologies (ICT), which makes the concept of Smart City feasible. Among various intelligent components, smart urban transportation monitoring is an essential part of smoothly operational smart cities. Although there is fast development of Smart Cities and the growth of Internet of Things (IoT), real-time anomalous behavior detection in Intelligent Transportation Systems (ITS) is still challenging. Because of multiple advanced features including flexibility, safety, and ease of manipulation, quadcopter drones have been widely adopted in many areas, from service improvement to urban surveillance, and data collection for scientific research. In this paper, a Smart Urban traffic Monitoring (SurMon) scheme is proposed employing drones following an edge computing paradigm. A dynamic video stream processing scheme is proposed to meet the requirements of real-time information processing and decision-making at the edge. Specifically, we propose to identify anomalous vehicle behaviors in real time by creatively applying the multidimensional Singular Spectrum Analysis (mSSA) technique in space to detect the different vehicle behaviors on roads. Multiple features of vehicle behaviors are fed into channels of the mSSA procedure. Instead of trying to create and define a database of normal activity patterns of vehicles on the road, the anomaly detection is reformatted as an outlier identifying problem. Then, a cascaded Capsules Network is designed to predict whether the behavior is a violation. An extensive experimental study has been conducted and the results have validated the feasibility and effectiveness of the SurMon scheme.

MASFF: Multiscale Adaptive Spatial Feature Fusion Method for Vehicle Recognition

<p>Traditional vehicle recognition methods have the disadvantages such as low efficiency and time-consuming due to the complex background and overlapping situation. In this paper, we propose a multiscale adptive spatial feature fusion (ASFF) method for vehicle recognition. First, it calculates the difference hash values of images. Then the hash value is used to judge the similarity between the current frame and the previous frame. When the similarity is less than the threshold value, it is input to ResNet18 model for detection. Using ResNet18 as the base network can reduce network parameters. Then, aiming at the problem that the detection effect of ASFF for vehicle recognition is not ideal, the offset loss and width-height loss are replaced by the intersection ratio loss. Meanwhile, multi-scale adaptive spatial feature fusion method is adopted to fuse the multi-level features of the network. The experimental results show that the average accuracy with proposed methed is increased by 2.1%. For BDD100K and Pascal VOC datasets, the average accuracy of predicted borders is increased by 5.5%, when the IoU is greater than 0.5. With the GTX1060Ti, the recognition speed can reach 149 frames per second. The multiscale ASFF in this paper can significantly improve the vehicle recognition accuracy.</p> <p> </p>

Real-time Vehicle Detection implementing Deep Convolutional Neural Network features Data Augmentation Technique

Background/Objectives: In this progressive Hi-Tech ecosystem, the cuttingedge technologies in the Deep Learning techniques for Vehicle Detection and Classification engendered swift paradigm shifts in diverse operations through the deployment of convolutional neural models in the Traffic Surveillance System. The fundamental element of the Traffic management system constitutes a real-time dynamic image, which forms the base input for vehicle recognition systems. The deep model functionalities on these base static images are highly pragmatic, and a radical approach leads to its successful applicability. Methods: This study proposes Faster Region-based Convolutional Neural Network (R-CNN) technique for image-based vehicle detection with significant performance benefits. Essentially, the base network of a pre-trained deep model, fine-tuned VGG-16 is transformed into Faster R-CNN. At this stage, the framework is constructed for a customized finitecapacity vehicle dataset. Subsequently, it is applied to train and test the system. From the performance lens, for further system enhancement, the speedup Bottleneck, and Data Augmentation implementation improve training speed and accuracy. Findings: The Experiments demonstrate that the sensitivity factor is 93.5% which provides acceptable results of 87.6% with 0.42s in vehicle detection in aspects of accuracy and execution time. Novelty : For our customized dataset, the performance-enhanced detection framework shows an increase of 4% in sensitivity and 3.23s with respect to time as compared to the other existing models. The proposed research is designed for a novel Faster RCNN algorithm that is fine-tuned detection algorithm of vehicles integrating sophisticated approaches for dynamic transformation of the live traffic video stream recording by transposing these real-time traffic videos to image inputs to this optimized detection framework achieving a high sensitivity factor with an efficient computation stack benefiting cost and time. Keywords: Data Augmentation; Deep Learning; Faster RegionConvolutional Neural Network; Traffic Surveillance System; VGG16 pretrained model; Vehicle Detection

Experimental investigation on all-target electromagnetic scattering characteristics of hypervelocity HTV2-like flight model

According to the requirements for target detection and recognition of hypervelocity vehicles in near space, the simulation and measurement of corresponding electromagnetic scattering characteristics of non-uniform plasma generated by hypervelocity targets are conducted. A numerical calculation method with dynamic plasma parameters is developed and hypervelocity HTV2-like models launched by the ballistic ranges are used to simulate complex shape target flying at a hypervelocity velocity. The high-precision shadow imaging systems and radar measurement systems of the ballistic range are used to measure the model postures, the electromagnetic scattering characteristics of the whole targets and their flow fields in both C band and X band. The experimental measurement results of the radar cross section (RCS) of the models and their flow fields under different experimental conditions are obtained. The results show that the numerical simulation methods of unsteady high-temperature ionized air flow can be used to simulate the unsteady thermal chemical flow fields around the head and body of the simplified hypervelocity HTV2-like flight models. The electromagnetic scattering characteristics of the models and their plasma sheath differ by more than one order of magnitude under different experimental conditions. The total RCS of the model’s wake in the C band is much smaller than that of the model, and the total RCS of the model’s wake in the X band is significantly enhanced. The attitude angles of the models have great influence on their electromagnetic scattering characteristics and their RCSs with different attitude angles can differ by one order of magnitude. The electromagnetic scattering energy of the model in the C band is distributed mainly around the targets and their flow fields surrounding them. The X band electromagnetic scattering energy of the model is distributed mainly in the regions around the targets, surrounding flow fields and the wake flow fields. According to the experimental conditions of the ballistic range, the numerical simulation analyses of the electromagnetic scattering characteristics of the models and flow fields around them are carried out, and the maximum error between simulation and experimental results is less than 4 dB, verifying the effectiveness of the modeling methods of simulating electromagnetic scattering characteristics of non-uniform plasma coated targets.

Performance Analysis of Deep Learning YOLO models for South Asian Regional Vehicle Recognition

For years, humans have pondered the possibility of combining human and machine intelligence. The purpose of this research is to recognize vehicles from media and while there are multiple models associated with this, models that can detect vehicles commonly used in developing countries like Bangladesh, India, etc. are scarce. Our focus was to assimilate the largest dataset of vehicles exclusive to South Asia in addition to the more common universal vehicles and apply it to track and recognize these vehicles, even in motion. To develop this, we increased the class variations and quantity of the data and used multiple variations of the YOLOv5 model. We trained different versions of the model with our dataset to properly measure the degree of accuracy between the models in detecting the more unique vehicles. If vehicle detection and tracking are adopted and implemented in live traffic camera feeds, the information can be used to create smart traffic systems that can regulate congestion and routing by identifying and separating fast and slow-moving vehicles on the road. The comparison between the three different YOLOv5 models led to an analysis that indicates that the large variant of the YOLOv5 architecture outperforms the rest.

Hierarchical Dictionary Learning for Vehicle Classification Based on the Carrier-Free UWB Radar

As a promising technique, dictionary learning (DL) for target recognition has seen a recent surge in recent years. Although many methods have been proposed to obtain discriminative dictionaries or coefficients via incorporating various constraints into the objective function, there are still two issues. First, it is well known that kinds of discriminative criteria on the objective function often involve substantial optimized items, increasing computation cost. Second, noises in the real world inevitably degrade the classification performance, while most DL algorithms disregard that. Aiming at these two problems, a hierarchical DL model is proposed for vehicle recognition based on the carrier-free ultrawideband (UWB) radar. With the purpose of successfully determining the identity of targets, we first learn several class-specific subdictionaries. Then, considering that the actual environment is filled with noises, we divided the learned dictionary atoms into signal and disturbance atoms in accordance with sparse coefficients to establish the signal dictionary and noise dictionary, respectively. Finally, the clean data are recovered over the corresponding signal dictionary, and meanwhile, the classification task is achieved. This hierarchical DL method takes into account both the noise-robust ability and discriminative power of the learned dictionary, in which the “atom selection” mechanism dramatically speeds up calculations. What is more, rather than imposing discriminative restraints on the objective function, we improve the K-SVD-based optimization process to complete hierarchical DL. Experimental results on the measured and synthetic data corroborate the effectiveness of the proposed method even under low signal-to-noise ratio (SNR) values. Especially, to testify to the generalization ability of the proposed method, we evaluate our algorithm on a public synthetic aperture radar (SAR) dataset (MSTAR).

Domain Knowledge Powered Two-Stream Deep Network for Few-Shot SAR Vehicle Recognition

Synthetic aperture radar (SAR) target recognition faces the challenge that there are very little labeled data. Although few-shot learning methods are developed to extract more information from a small amount of labeled data to avoid overfitting problems, recent few-shot or limited-data SAR target recognition algorithms overlook the unique SAR imaging mechanism. Domain knowledge-powered two-stream deep network (DKTS-N) is proposed in this study, which incorporates SAR domain knowledge related to the azimuth angle, the amplitude, and the phase data of vehicles, making it a pioneering work in few-shot SAR vehicle recognition. The two-stream deep network, extracting the features of the entire image and image patches, is proposed for more effective use of the SAR domain knowledge. To measure the structural information distance between the global and local features of vehicles, the deep Earth mover’s distance is improved to cope with the features from a two-stream deep network. Considering the sensitivity of the azimuth angle in SAR vehicle recognition, the nearest neighbor classifier replaces the structured fully connected layer for <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -shot classification. All experiments are conducted under the configuration that the SARSIM and the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset work as a source and target task, respectively. Our proposed DKTS-N achieved 49.26% and 96.15% under ten-way one-shot and ten-way 25-shot, whose labeled samples are randomly selected from the training set. In standard operating condition (SOC) as well as three extended operating conditions (EOCs), DKTS-N demonstrated overwhelming advantages in accuracy and time consumption compared with other few-shot learning methods in <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -shot recognition tasks.

Target detection and recognition method based on embedded vision

Vehicles have become an essential means of transportation in people's daily life. A large number of vehicles need scientific and effective detection and management. The existing vehicle recognition technology may not be able to achieve good results when applied in the actual environment of the embedded platform. We proposed a vehicle detection and recognition model for embedded platform and applied it to the actual environment. Support Vector Machine (SVM) uses Histogram of Oriented Gradient (HOG) feature combined with window sliding detection to complete vehicle detection. Convolutional Neural Network (CNN) is used to realise licence plate recognition. Furthermore, oriented fast and rotated brief (ORB) feature extraction method is used to extract vehicle key information quickly and accurately. Licence plate information and vehicle ORB features are stored on the embedded device as the unique features of the vehicle to identify the recorded vehicles. The model has good timeliness, high accuracy and practical value.