检索结果-南通市图书馆

Parts-probability-based vehicle detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2014年第11期57卷 110-120页

作者： CHEN Long JIANG ZhiGuo FENG Hao Image Processing Center School of Astronautics Beihang University Beijing Key Laboratory of Digital Media

Detecting vehicles is important in aerial surveillance. Traditional methods used classifiers to detect vehicles, but a single classifier was limited to detecting vehicles of only one intensity and orientation. Therefore,the task required the use of multiple classifiers of different intensities and orientations. To solve this problem, we first used a latent Dirichlet allocation(LDA) model that improved the previous approaches to vehicle *** text modeling approaches have been generative. They could be used to build probability models of vehicles in different intensities and from various orientations simultaneously using unlabeled data. Using a probability model, we can detect vehicles in a region with high probability. Next, we used a parts-probability model that improves the LDA model. The model effectively encodes spatial structure among visual words by adding spatial relationships among vehicle parts as priors of words. A parts probability model represents a vehicle hierarchically according to parts appearances and a vehicle’s features within the parts to enforce spatial coherency. Then, we used our model to detect vehicles from a collection of images and demonstrate its performs more effectively.

关键词： LDA vehicle detection parts probability model aerial surveillance spatial structure

Optimal Deep Convolutional Neural Network for vehicle detection in Remote Sensing Images

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第2期74卷 3117-3131页

作者： Saeed Masoud Alshahrani Saud S.Alotaibi Shaha Al-Otaibi Mohamed Mousa Anwer Mustafa Hilal Amgad Atta Abdelmageed Abdelwahed Motwakel Mohamed I.Eldesouki Department of Computer Science College of Computing and Information TechnologyShaqra UniversityShaqraSaudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Electrical Engineering Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam Bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Information System College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAlKharjSaudi Arabia

Object detection(OD)in remote sensing images(RSI)acts as a vital part in numerous civilian and military application areas,like urban planning,geographic information system(GIS),and search and rescue *** recognition from RSIs remained a challenging process because of the difficulty of background data and the redundancy of recognition *** latest advancements in deep learning(DL)approaches permit the design of effectual OD *** study develops an Artificial Ecosystem Optimizer with Deep Convolutional Neural Network for vehicle detection(AEODCNN-VD)model on Remote Sensing *** proposed AEODCNN-VD model focuses on the identification of vehicles accurately and *** detect vehicles,the presented AEODCNN-VD model employs single shot detector(SSD)with Inception network as a baseline *** addition,Multiway Feature Pyramid Network(MFPN)is used for handling objects of varying sizes in *** features from the Inception model are passed into theMFPNformultiway andmultiscale feature ***,the fused features are passed into bounding box and class prediction *** enhancing the detection efficiency of the AEODCNN-VD approach,AEO based hyperparameter optimizer is used,which is stimulated by the energy transfer strategies such as production,consumption,and decomposition in an *** performance validation of the presentedmethod on benchmark datasets showed promising performance over recent DL models.

关键词： Object detection remote sensing vehicle detection artificial ecosystem optimizer convolutional neural network

Using deep learning in an embedded system for real-time target detection based on images from an unmanned aerial vehicle: vehicle detection as a case study

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2023年第1期16卷 910-936页

作者： Fang Huang Shengyi Chen Qi Wang Yingjie Chen Dandan Zhang School of Recourses and Environment University of Electronic Science and Technology of China(UESTC)ChengduPeople’s Republic of China Aerospace Information Research Institute(AIR) Chinese Academy of Sciences(CAS)BeijingPeople’s Republic of China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijingPeople’s Republic of China

For a majority of remote sensing applications of unmanned aerial vehicles(UAVs),the data need to be downloaded to ground devices for processing,but this procedure cannot satisfy the demands of real-time target *** objective in this study is to develop a real-time system based on an embedded technology for image acquisition,target detection,the transmission and display of the results,and user interaction while providing support for the interactions between multiple UAVs and *** work is divided into three parts:(1)We design the technical procedure and the framework for the implementation of a real-time target detection system according to application requirements.(2)We develop an efficient and reliable data transmission module to realize real-time cross-platform communication between airborne embedded devices and ground-side servers.(3)We optimize the YOLOv4 algorithm by using the K-Means algorithm and TensorRT inference to improve the accuracy and speed of the NVIDIA Jetson *** experiments involving static detection,it had an overall confidence of 89.6%and a rate of missed detection of 3.8%;in experiments involving dynamic detection,it had an overall confidence and a rate of missed detection of 88.2%and 4.6%,respectively.

关键词： Unmanned aerial vehicle(UAV) embedded system deep learning YOLOv4 algorithm data transmission vehicle detection

A New vehicle detection Framework Based on Feature-Guided in the Road Scene

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第1期78卷 533-549页

作者： Tianmin Deng Xiyue Zhang Xinxin Cheng School of Traffic and Transportation Chongqing Jiaotong UniversityChongqing400074China

vehicle detection plays a crucial role in the field of autonomous driving ***,directly applying deep learning-based object detection algorithms to complex road scene images often leads to subpar performance and slow inference speeds in vehicle *** a balance between accuracy and detection speed is crucial for real-time object detection in real-world road *** paper proposes a high-precision and fast vehicle detector called the feature-guided bidirectional pyramid network(FBPN).Firstly,to tackle challenges like vehicle occlusion and significant background interference,the efficient feature filtering module(EFFM)is introduced into the deep network,which amplifies the disparities between the features of the vehicle and the ***,the proposed global attention localization module(GALM)in the model neck effectively perceives the detailed position information of the target,improving both the accuracy and inference speed of ***,the detection accuracy of small-scale vehicles is further enhanced through the utilization of a four-layer feature pyramid *** results show that FBPN achieves an average precision of 60.8% and 97.8% on the BDD100K and KITTI datasets,respectively,with inference speeds reaching 344.83 frames/s and 357.14 frames/*** demonstrates its effectiveness and superiority by striking a balance between detection accuracy and inference speed,outperforming several state-of-the-art methods.

关键词： Driverless car vehicle detection channel attention mechanism deep learning

Image and Feature Space Based Domain Adaptation for vehicle detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2020年第12期65卷 2397-2412页

作者： Ying Tian Libing Wang Hexin Gu Lin Fan School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China School of Mechanical Engineering and Automation University of Science and Technology LiaoningAnshan114051China Faculty of Business Economics&LawThe University of QueenslandBrisbaneQLD 4072Australia

The application of deep learning in the field of object detection has experienced much ***,due to the domain shift problem,applying an off-the-shelf detector to another domain leads to a significant performance drop.A large number of ground truth labels are required when using another domain to train models,demanding a large amount of human and financial *** order to avoid excessive resource requirements and performance drop caused by domain shift,this paper proposes a new domain adaptive approach to cross-domain vehicle *** approach improves the cross-domain vehicle detection model from image space and feature *** employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image *** feature space,we align feature distributions between the source domain and the target domain to improve the detection *** are carried out using the method with two different datasets,proving that this technique effectively improves the accuracy of vehicle detection in the target domain.

关键词： Deep learning cross-domain vehicle detection

vehicle detection and Tracking Based on Fast Wavelet Transform and Kalman Filter

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

微计算机信息 2008年第33期 278-280+268页

作者： LIN Pei-qun XU Jian-min

A new approach for vehicle detection is proposed in this ***,fast wavelet transform(FWT)designed for discrete signal is proposed to extract image texture,while grey level co-occurrence matrix(GLCM)is employed to measure and analyze the extracted ***,vehicles can be extracted since the vehicle sections and the shadow sections have different textures in the combined foreground ***,we put forward in this work the state and observation matrixes of Kalman filter which has been employed to track vehicles under complicated traffic *** results in real traffic scenes reveal that the proposed techniques are effective and efficient for vehicle detection and tracking.

关键词： Intelligent transportation systems vehicle detection vehicle tracking Fast wavelet transform Kalman filter

Efficient and Cost-Effective vehicle detection in Foggy Weather for Edge/Fog-Enabled Traffic Surveillance and Collision Avoidance Systems

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第10期81卷 911-931页

作者： Naeem Raza Muhammad Asif Habib Mudassar Ahmad Qaisar Abbas Mutlaq BAldajani Muhammad Ahsan Latif Department of Computer Science National Textile UniversityFaisalabad37610Pakistan College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia Department of Computer Science University of AgricultureFaisalabad38000Pakistan

Vision-based vehicle detection in adverse weather conditions such as fog,haze,and mist is a challenging research area in the fields of autonomous vehicles,collision avoidance,and Internet of Things(IoT)-enabled edge/fog computing traffic surveillance and monitoring *** and cost-effective vehicle detection at high accuracy and speed in foggy weather is essential to avoiding road traffic collisions in *** evaluate vision-based vehicle detection performance in foggy weather conditions,state-of-the-art vehicle detection in Adverse Weather Nature(DAWN)and Foggy Driving(FD)datasets are self-annotated using the YOLO LABEL tool and customized to four vehicle detection classes:cars,buses,motorcycles,and *** state-of-the-art single-stage deep learning algorithms YOLO-V5,and YOLO-V8 are considered for the task of vehicle ***,YOLO-V5s is enhanced by introducing attention modules Convolutional Block Attention Module(CBAM),Normalized-based Attention Module(NAM),and Simple Attention Module(SimAM)after the SPPF module as well as YOLO-V5l with *** vehicle detection accuracy parameters and running speed is validated on cloud(Google Colab)and edge(local)*** mAP50 score of YOLO-V5n is 72.60%,YOLOV5s is 75.20%,YOLO-V5m is 73.40%,and YOLO-V5l is 77.30%;and YOLO-V8n is 60.20%,YOLO-V8s is 73.50%,YOLO-V8m is 73.80%,and YOLO-V8l is 72.60%on DAWN *** mAP50 score of YOLO-V5n is 43.90%,YOLO-V5s is 40.10%,YOLO-V5m is 49.70%,and YOLO-V5l is 57.30%;and YOLO-V8n is 41.60%,YOLO-V8s is 46.90%,YOLO-V8m is 42.90%,and YOLO-V8l is 44.80%on FD *** vehicle detection speed of YOLOV5n is 59 Frame Per Seconds(FPS),YOLO-V5s is 47 FPS,YOLO-V5m is 38 FPS,and YOLO-V5l is 30 FPS;and YOLO-V8n is 185 FPS,YOLO-V8s is 109 FPS,YOLO-V8m is 72 FPS,and YOLO-V8l is 63 FPS on DAWN *** vehicle detection speed of YOLO-V5n is 26 FPS,YOLO-V5s is 24 FPS,YOLO-V5m is 22 FPS,and YOLO-V5l is 17 FPS;and YOLO-V8n is 313 FPS,YOLO-V8s is 182 FPS,YOLO

关键词： vehicle detection YOLO-V5 YOLO-V5s variants YOLO-V8 DAWN dataset foggy driving dataset IoT cloud/edge/fog computing

A review of vehicle detection methods based on computer vision

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Intelligent and Connected vehicles 2024年第1期7卷 1-18页

作者： Changxi Ma Fansong Xue School of Traffic and Transportation Lanzhou Jiaotong UniversityLanzhou 730070China Key Laboratory of Railway Industry on Plateau Railway Transportation Intelligent Management and Control Lanzhou 730070China

With the increasing number of vehicles,there has been an unprecedented pressure on the operation and maintenance of intelligent transportation systems and transportation *** order to achieve faster and more accurate identification of traffic vehicles,computer vision and deep learning technology play a vital role and have made significant *** study summarizes the current research status,latest findings,and future development trends of traditional detection algorithms and deep learning-based detection *** the detection algorithms based on deep learning,this study focuses on the representative convolutional neural network ***,it examines the two-stage and one-stage detection algorithms,which have been extensively utilized in the field of intelligent transportation *** to traditional detection algorithms,deep learning-based detection algorithms can achieve higher accuracy and *** single-stage detection algorithm is more efficient for real-time detection,while the two-stage detection algorithm is more accurate than the single-stage detection *** the follow-up research,it is important to consider the balance between detection efficiency and detection ***,vehicle missed detection and false detection in complex scenes,such as bad weather and vehicle overlap,should be taken into *** will ensure better application of the research findings in engineering practice.

关键词： intelligent transportation system computer vision deep learning vehicle detection object detection algorithm

Part-based on-road vehicle detection using hidden random field

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2011年第12期54卷 2542-2549页

作者： ZHANG XueTao 1 , HE YongJian 1,2 & WANG Fei 1 1 Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China 2 Xi’an Communication Institute, Xi’an 710049, China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Xi’an Communication Institute Xi’an China

This paper addresses the problem of detecting on-road vehicles in still images captured by the on-board cameras. We model this as a labelling inference procedure and incorporate the part-based representation of the rear-ends of vehicle within a hidden random field based probabilistic model. Representing objects with parts inherently good for dealing with occlusions. In the proposed model, the part labels form a hidden layer in the graphical model. Our approaches can automatically find the latent parts without explicit indication during training. The experiment is performed on the database with real images with a promising result.

关键词： vehicle detection hidden random field part-based model