期刊文献+

二次检索

题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到1,906篇文章
< 1 2 96 >
每页显示 20 50 100
WiFi Indoor Positioning and Tracking Algorithm Based on Compressive Sensing and Sage-Husa Adaptive Kalman Filter
1
作者 Yingjie Sun Yi Zhong +2 位作者 Congwei Hu Ao Xiong Hu Zhao 《Open Journal of Applied Sciences》 2024年第2期379-390,共12页
Aiming at the problem that the positioning accuracy of WiFi indoor positioning technology based on location fingerprint has not reached the requirements of practical application, a WiFi indoor positioning and tracking... Aiming at the problem that the positioning accuracy of WiFi indoor positioning technology based on location fingerprint has not reached the requirements of practical application, a WiFi indoor positioning and tracking algorithm combining adaptive affine propagation (AAPC), compressed sensing (CS) and Kalman filter is proposed. In the off-line phase, AAPC algorithm is used to generate clustering fingerprints with optimal clustering effect performance;In the online phase, CS and nearest neighbor algorithm are used for position estimation;Finally, the Kalman filter and physical constraints are combined to perform positioning and tracking. By collecting a large number of real experimental data, it is proved that the developed algorithm has higher positioning accuracy and more accurate trajectory tracking effect. 展开更多
关键词 WiFi Indoor positioning CLUSTER Signal Recovery Trajectory tracking
下载PDF
Strong Tracking Particle Filter Based on the Chi-Square Test for Indoor Positioning 被引量:2
2
作者 Lingwu Qian Jianxiang Li +3 位作者 Qi Tang Mengfei Liu Bingjie Yuan Guoli Ji 《Computer Modeling in Engineering & Sciences》 SCIE EI 2023年第8期1441-1455,共15页
In recent years,a number of wireless indoor positioning(WIP),such as Bluetooth,Wi-Fi,and Ultra-Wideband(UWB)technologies,are emerging.However,the indoor environment is complex and changeable.Walls,pillars,and even ped... In recent years,a number of wireless indoor positioning(WIP),such as Bluetooth,Wi-Fi,and Ultra-Wideband(UWB)technologies,are emerging.However,the indoor environment is complex and changeable.Walls,pillars,and even pedestrians may block wireless signals and produce non-line-of-sight(NLOS)deviations,resulting in decreased positioning accuracy and the inability to provide people with real-time continuous indoor positioning.This work proposed a strong tracking particle filter based on the chi-square test(SPFC)for indoor positioning.SPFC can fuse indoor wireless signals and the information of the inertial sensing unit(IMU)in the smartphone and detect the NLOS deviation through the chi-square test to avoid the influence of the NLOS deviation on the final positioning result.Simulation experiment results show that the proposed SPFC can reduce the positioning error by 15.1%and 12.3% compared with existing fusion positioning systems in the LOS and NLOS environment. 展开更多
关键词 NLOS strong tracking filter particle filter CST pedestrian dead reckoning indoor positioning
下载PDF
Dynamic Visible Light Positioning Based on Enhanced Visual Target Tracking
3
作者 Xiangyu Liu Jingyu Hao +1 位作者 Lei Guo Song Song 《China Communications》 SCIE CSCD 2023年第10期276-291,共16页
In visible light positioning systems,some scholars have proposed target tracking algorithms to balance the relationship among positioning accuracy,real-time performance,and robustness.However,there are still two probl... In visible light positioning systems,some scholars have proposed target tracking algorithms to balance the relationship among positioning accuracy,real-time performance,and robustness.However,there are still two problems:(1)When the captured LED disappears and the uncertain LED reappears,existing tracking algorithms may recognize the landmark in error;(2)The receiver is not always able to achieve positioning under various moving statuses.In this paper,we propose an enhanced visual target tracking algorithm to solve the above problems.First,we design the lightweight recognition/demodulation mechanism,which combines Kalman filtering with simple image preprocessing to quickly track and accurately demodulate the landmark.Then,we use the Gaussian mixture model and the LED color feature to enable the system to achieve positioning,when the receiver is under various moving statuses.Experimental results show that our system can achieve high-precision dynamic positioning and improve the system’s comprehensive performance. 展开更多
关键词 visible light positioning visual target tracking gaussian mixture model kalman filtering system performance
下载PDF
FGAs-Based Data Association Algorithm for Multi-sensor Multi-target Tracking 被引量:4
4
作者 朱力立 张焕春 经亚枝 《Chinese Journal of Aeronautics》 SCIE EI CAS CSCD 2003年第3期177-181,共5页
A novel data association algorithm is developed based on fuzzy geneticalgorithms (FGAs). The static part of data association uses one FGA to determine both the lists ofcomposite measurements and the solutions of m-bes... A novel data association algorithm is developed based on fuzzy geneticalgorithms (FGAs). The static part of data association uses one FGA to determine both the lists ofcomposite measurements and the solutions of m-best S-D assignment. In the dynamic part of dataassociation, the results of the m-best S-D assignment are then used in turn, with a Kalman filterstate estimator, in a multi-population FGA-based dynamic 2D assignment algorithm to estimate thestates of the moving targets over time. Such an assignment-based data association algorithm isdemonstrated on a simulated passive sensor track formation and maintenance problem. The simulationresults show its feasibility in multi-sensor multi-target tracking. Moreover, algorithm developmentand real-time problems are briefly discussed. 展开更多
关键词 multi-target tracking data association FGA assignment problem kalmanfilter
下载PDF
Dynamic cluster member selection method for multi-target tracking in wireless sensor network 被引量:8
5
作者 蔡自兴 文莎 刘丽珏 《Journal of Central South University》 SCIE EI CAS 2014年第2期636-645,共10页
Multi-target tracking(MTT) is a research hotspot of wireless sensor networks at present.A self-organized dynamic cluster task allocation scheme is used to implement collaborative task allocation for MTT in WSN and a s... Multi-target tracking(MTT) is a research hotspot of wireless sensor networks at present.A self-organized dynamic cluster task allocation scheme is used to implement collaborative task allocation for MTT in WSN and a special cluster member(CM) node selection method is put forward in the scheme.An energy efficiency model was proposed under consideration of both energy consumption and remaining energy balance in the network.A tracking accuracy model based on area-sum principle was also presented through analyzing the localization accuracy of triangulation.Then,the two models mentioned above were combined to establish dynamic cluster member selection model for MTT where a comprehensive performance index function was designed to guide the CM node selection.This selection was fulfilled using genetic algorithm.Simulation results show that this method keeps both energy efficiency and tracking quality in optimal state,and also indicate the validity of genetic algorithm in implementing CM node selection. 展开更多
关键词 wireless sensor networks multi-target tracking collaborative task allocation dynamic cluster comprehensive performance index function
下载PDF
Multi-target tracking algorithm based on PHD filter against multi-range-false-target jamming 被引量:11
6
作者 TIAN Chen PEI Yang +1 位作者 HOU Peng ZHAO Qian 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2020年第5期859-870,共12页
Multi-range-false-target(MRFT) jamming is particularly challenging for tracking radar due to the dense clutter and the repeated multiple false targets. The conventional association-based multi-target tracking(MTT) met... Multi-range-false-target(MRFT) jamming is particularly challenging for tracking radar due to the dense clutter and the repeated multiple false targets. The conventional association-based multi-target tracking(MTT) methods suffer from high computational complexity and limited usage in the presence of MRFT jamming.In order to solve the above problems, an efficient and adaptable probability hypothesis density(PHD) filter is proposed. Based on the gating strategy, the obtained measurements are firstly classified into the generalized newborn target and the existing target measurements. The two categories of measurements are independently used in the decomposed form of the PHD filter. Meanwhile,an amplitude feature is used to suppress the dense clutter. In addition, an MRFT jamming suppression algorithm is introduced to the filter. Target amplitude information and phase quantization information are jointly used to deal with MRFT jamming and the clutter by modifying the particle weights of the generalized newborn targets. Simulations demonstrate the proposed algorithm can obtain superior correct discrimination rate of MRFT, and high-accuracy tracking performance with high computational efficiency in the presence of MRFT jamming in the dense clutter. 展开更多
关键词 multi-range-false-target(MRFT)jamming multi-target tracking(MTT) probability hypothesis density(PHD) target amplitude feature gating strategy
下载PDF
The linear position tracking servo systemusing a linear voice-coil motor 被引量:2
7
作者 褚立新 林辉 《Journal of Pharmaceutical Analysis》 SCIE CAS 2008年第3期164-167,共4页
More and more linear servo systems have been used in servo applications. Direct drive technology can greatly increase the bandwidth and the tracking accuracy. A position servo-system based on linear voice-coil motor w... More and more linear servo systems have been used in servo applications. Direct drive technology can greatly increase the bandwidth and the tracking accuracy. A position servo-system based on linear voice-coil motor was designed for one linear oscillation movement application. Besides the conventional position, speed and current control loops, the speed and acceleration feed-forward control of command position signal were also used. The experimental test proved the correctness of the design, and the system can track the given periodic sinusoid position command signal of 15Hz with high accuracy. The linear voice-coil motor is very suitable for short stroke position tracking application with high dynamic response. 展开更多
关键词 voice-coil motor position tracking linear movement
下载PDF
An Iterative Pose Estimation Algorithm Based on Epipolar Geometry With Application to Multi-Target Tracking 被引量:3
8
作者 Jacob H.White Randal W.Beard 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2020年第4期942-953,共12页
This paper introduces a new algorithm for estimating the relative pose of a moving camera using consecutive frames of a video sequence. State-of-the-art algorithms for calculating the relative pose between two images ... This paper introduces a new algorithm for estimating the relative pose of a moving camera using consecutive frames of a video sequence. State-of-the-art algorithms for calculating the relative pose between two images use matching features to estimate the essential matrix. The essential matrix is then decomposed into the relative rotation and normalized translation between frames. To be robust to noise and feature match outliers, these methods generate a large number of essential matrix hypotheses from randomly selected minimal subsets of feature pairs, and then score these hypotheses on all feature pairs. Alternatively, the algorithm introduced in this paper calculates relative pose hypotheses by directly optimizing the rotation and normalized translation between frames, rather than calculating the essential matrix and then performing the decomposition. The resulting algorithm improves computation time by an order of magnitude. If an inertial measurement unit(IMU) is available, it is used to seed the optimizer, and in addition, we reuse the best hypothesis at each iteration to seed the optimizer thereby reducing the number of relative pose hypotheses that must be generated and scored. These advantages greatly speed up performance and enable the algorithm to run in real-time on low cost embedded hardware. We show application of our algorithm to visual multi-target tracking(MTT) in the presence of parallax and demonstrate its real-time performance on a 640 × 480 video sequence captured on a UAV. Video results are available at https://youtu.be/Hh K-p2 h XNn U. 展开更多
关键词 Aerial robotics epipolar geometry multi-target tracking pose estimation unmanned aircraft systems vision-based flight
下载PDF
A new algorithm of bearings-only multi-target tracking of bistatic system 被引量:2
9
作者 Benlian XU Zhiquan WANG 《控制理论与应用(英文版)》 EI 2006年第4期331-337,共7页
Much research mainly focuses on the batch processing method (e.g. maximum likelihood method) when bearings-only multiple targets tracking of bistatic sonar system is considered. In this paper, the idea of recursive ... Much research mainly focuses on the batch processing method (e.g. maximum likelihood method) when bearings-only multiple targets tracking of bistatic sonar system is considered. In this paper, the idea of recursive processing method is presented and employed, and corresponding data association algorithms, i.e. a multi-objective ant-colony-based optimization algorithm and an easy fast assignment algorithm are developed to solve the measurements-to-measurements and measurements-to-tracks data association problems of bistatic sonar system, respectively. Monte-Carlo simulations are induced to evaluate the effectiveness of the proposed methods. 展开更多
关键词 BEARINGS-ONLY multi-target tracking Data association Ant colony optimization
下载PDF
METHOD OF MULTI-TARGET TRACKING IN WIDE AREA SURVEILLANCE AIRBORNE RADAR SYSTEM BASING ON CLUSTERING ANALYSIS 被引量:3
10
作者 Wu Kun Zhao Fengjun +2 位作者 Hui Zhou Zheng Shichao Zheng Mingjie 《Journal of Electronics(China)》 2014年第3期208-213,共6页
This paper proposed a robust method based on the definition of Mahalanobis distance to track ground moving target. The feature and the geometry of airborne ground moving target tracking systems are studied at first. B... This paper proposed a robust method based on the definition of Mahalanobis distance to track ground moving target. The feature and the geometry of airborne ground moving target tracking systems are studied at first. Based on this feature, the assignment relation of time-nearby target is calculated via Mahalanobis distance, and then the corresponding transformation formula is deduced. The simulation results show the correctness and effectiveness of the proposed method. 展开更多
关键词 Airborne radar Wide Area Surveillance(WAS) Moving target detect multi-target tracking(MTT)
下载PDF
Joint target assignment and power allocation in the netted C-MIMO radar when tracking multi-targets in the presence of self-defense blanket jamming 被引量:1
11
作者 Zhengjie Li Junwei Xie +1 位作者 Haowei Zhang Jiahao Xie 《Defence Technology(防务技术)》 SCIE EI CAS CSCD 2023年第6期414-427,共14页
The netted radar system(NRS)has been proved to possess unique advantages in anti-jamming and improving target tracking performance.Effective resource management can greatly ensure the combat capability of the NRS.In t... The netted radar system(NRS)has been proved to possess unique advantages in anti-jamming and improving target tracking performance.Effective resource management can greatly ensure the combat capability of the NRS.In this paper,based on the netted collocated multiple input multiple output(CMIMO)radar,an effective joint target assignment and power allocation(JTAPA)strategy for tracking multi-targets under self-defense blanket jamming is proposed.An architecture based on the distributed fusion is used in the radar network to estimate target state parameters.By deriving the predicted conditional Cramer-Rao lower bound(PC-CRLB)based on the obtained state estimation information,the objective function is formulated.To maximize the worst case tracking accuracy,the proposed JTAPA strategy implements an online target assignment and power allocation of all active nodes,subject to some resource constraints.Since the formulated JTAPA is non-convex,we propose an efficient two-step solution strategy.In terms of the simulation results,the proposed algorithm can effectively improve tracking performance in the worst case. 展开更多
关键词 Netted radar system MIMO Target assignment Power allocation multi-targets tracking Self-defense blanket jamming
下载PDF
A novel maneuvering multi-target tracking algorithm based on multiple model particle filter in clutters 被引量:2
12
作者 胡振涛 Pan Quan Yang Feng 《High Technology Letters》 EI CAS 2011年第1期19-24,共6页
To solve the problem of strong nonlinear and motion model switching of maneuvering target tracking system in clutter environment, a novel maneuvering multi-target tracking algorithm based on multiple model particle fi... To solve the problem of strong nonlinear and motion model switching of maneuvering target tracking system in clutter environment, a novel maneuvering multi-target tracking algorithm based on multiple model particle filter is presented in this paper. The algorithm realizes dynamic combination of multiple model particle filter and joint probabilistic data association algorithm. The rapid expan- sion of computational complexity, caused by the simple combination of the interacting multiple model algorithm and particle filter is solved by introducing model information into the sampling process of particle state, and the effective validation and utilization of echo is accomplished by the joint proba- bilistic data association algorithm. The concrete steps of the algorithm are given, and the theory analysis and simulation results show the validity of the method. 展开更多
关键词 maneuvering multi-target tracking multiple model particle filter interacting multiple model IMM) joint probabilistic data association
下载PDF
MULTI-TARGET VISUAL TRACKING AND OCCLUSION DETECTION BY COMBINING BHATTACHARYYA COEFFICIENT AND KALMAN FILTER INNOVATION 被引量:1
13
作者 Chen Ken Chul Gyu Jhun 《Journal of Electronics(China)》 2013年第3期275-282,共8页
This paper introduces an approach for visual tracking of multi-target with occlusion occurrence. Based on the author's previous work in which the Overlap Coefficient (OC) is used to detect the occlusion, in this p... This paper introduces an approach for visual tracking of multi-target with occlusion occurrence. Based on the author's previous work in which the Overlap Coefficient (OC) is used to detect the occlusion, in this paper a method of combining Bhattacharyya Coefficient (BC) and Kalman filter innovation term is proposed as the criteria for jointly detecting the occlusion occurrence. Fragmentation of target is introduced in order to closely monitor the occlusion development. In the course of occlusion, the Kalman predictor is applied to determine the location of the occluded target, and the criterion for checking the re-appearance of the occluded target is also presented. The proposed approach is put to test on a standard video sequence, suggesting the satisfactory performance in multi-target tracking. 展开更多
关键词 Visual tracking multi-target occlusion Bhattacharyya Coefficient (BC) Kalman filter
下载PDF
Adaptive resource management for multi-target tracking in co-located MIMO radar based on time-space joint allocation 被引量:1
14
作者 SU Yang CHENG Ting +2 位作者 HE Zishu LI Xi LU Yanxi 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2020年第5期916-927,共12页
Compared with the traditional phased array radar, the co-located multiple-input multiple-output(MIMO) radar is able to transmit orthogonal waveforms to form different illuminating modes, providing a larger freedom deg... Compared with the traditional phased array radar, the co-located multiple-input multiple-output(MIMO) radar is able to transmit orthogonal waveforms to form different illuminating modes, providing a larger freedom degree in radar resource management. In order to implement the effective resource management for the co-located MIMO radar in multi-target tracking,this paper proposes a resource management optimization model,where the system resource consumption and the tracking accuracy requirements are considered comprehensively. An adaptive resource management algorithm for the co-located MIMO radar is obtained based on the proposed model, where the sub-array number, sampling period, transmitting energy, beam direction and working mode are adaptively controlled to realize the time-space resource joint allocation. Simulation results demonstrate the superiority of the proposed algorithm. Furthermore, the co-located MIMO radar using the proposed algorithm can satisfy the predetermined tracking accuracy requirements with less comprehensive cost compared with the phased array radar. 展开更多
关键词 co-located multiple-input multiple-output(MIMO)radar adaptive resource management multi-target tracking sub-array division time-space joint allocation
下载PDF
Kernel density estimation and marginalized-particle based probability hypothesis density filter for multi-target tracking 被引量:3
15
作者 张路平 王鲁平 +1 位作者 李飚 赵明 《Journal of Central South University》 SCIE EI CAS CSCD 2015年第3期956-965,共10页
In order to improve the performance of the probability hypothesis density(PHD) algorithm based particle filter(PF) in terms of number estimation and states extraction of multiple targets, a new probability hypothesis ... In order to improve the performance of the probability hypothesis density(PHD) algorithm based particle filter(PF) in terms of number estimation and states extraction of multiple targets, a new probability hypothesis density filter algorithm based on marginalized particle and kernel density estimation is proposed, which utilizes the idea of marginalized particle filter to enhance the estimating performance of the PHD. The state variables are decomposed into linear and non-linear parts. The particle filter is adopted to predict and estimate the nonlinear states of multi-target after dimensionality reduction, while the Kalman filter is applied to estimate the linear parts under linear Gaussian condition. Embedding the information of the linear states into the estimated nonlinear states helps to reduce the estimating variance and improve the accuracy of target number estimation. The meanshift kernel density estimation, being of the inherent nature of searching peak value via an adaptive gradient ascent iteration, is introduced to cluster particles and extract target states, which is independent of the target number and can converge to the local peak position of the PHD distribution while avoiding the errors due to the inaccuracy in modeling and parameters estimation. Experiments show that the proposed algorithm can obtain higher tracking accuracy when using fewer sampling particles and is of lower computational complexity compared with the PF-PHD. 展开更多
关键词 particle filter with probability hypothesis density marginalized particle filter meanshift kernel density estimation multi-target tracking
下载PDF
Speed-assigned Position Tracking Control of SRM With Adaptive Backstepping Control 被引量:2
16
作者 Jiajun Wang 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2018年第6期1128-1135,共8页
A novel speed-assigned method is applied to the position tracking control of switched reluctance motor(SRM).A speed control freedom can be drawn into the position control through speed assignment. Adaptive backsteppin... A novel speed-assigned method is applied to the position tracking control of switched reluctance motor(SRM).A speed control freedom can be drawn into the position control through speed assignment. Adaptive backstepping control is used to design the position controller for the SRM. The accuracy of position tracking of the SRM can be enhanced with speed assignment. A disturbance observer is further designed to enhance the estimation accuracy of the unknown load torque. Simulation results certify that the design scheme is right and effective. 展开更多
关键词 Backstepping control direct torque control (DTC) disturbance observer speed-assigned position tracking control switched reluctance motor (SRM)
下载PDF
Research and Application of Multi-Target Tracking Based on GM-PHD Filter 被引量:2
17
作者 Yanyi Li Limin Guo Xiangsong Huang 《Optics and Photonics Journal》 2020年第6期125-133,共9页
<div style="text-align:justify;"> In recent years, multi-target tracking technology based on Gaussian Mixture- Probability Hypothesis Density (GM-PHD) filtering has become a hot field of information fu... <div style="text-align:justify;"> In recent years, multi-target tracking technology based on Gaussian Mixture- Probability Hypothesis Density (GM-PHD) filtering has become a hot field of information fusion research. This article outlines the generation and development of multi-target tracking methods based on GM-PHD filtering, and the principle and implementation method of GM-PHD filtering are explained, and the application status based on GM-PHD filtering is summarized, and the key issues of the development of GM-PHD filtering technology are analyzed. </div> 展开更多
关键词 GM-PHD multi-target tracking Random Finite Set
下载PDF
VIDEO MULTI-TARGET TRACKING BASED ON PROBABILISTIC GRAPHICAL MODEL
18
作者 Xu Feng Huang Chenrong +1 位作者 Wu Zhengjun Xu Lizhong 《Journal of Electronics(China)》 2011年第4期548-557,共10页
In the technique of video multi-target tracking,the common particle filter can not deal well with uncertain relations among multiple targets.To solve this problem,many researchers use data association method to reduce... In the technique of video multi-target tracking,the common particle filter can not deal well with uncertain relations among multiple targets.To solve this problem,many researchers use data association method to reduce the multi-target uncertainty.However,the traditional data association method is difficult to track accurately when the target is occluded.To remove the occlusion in the video,combined with the theory of data association,this paper adopts the probabilistic graphical model for multi-target modeling and analysis of the targets relationship in the particle filter framework.Ex-perimental results show that the proposed algorithm can solve the occlusion problem better compared with the traditional algorithm. 展开更多
关键词 Video tracking multi-target tracking Data association Probabilistic graphical model Particle filter
下载PDF
Robust attitude control for rapid multi-target tracking in spacecraft formation flying
19
作者 袁长清 李俊峰 +1 位作者 王天舒 宝音贺西 《Applied Mathematics and Mechanics(English Edition)》 SCIE EI 2008年第2期185-198,共14页
A robust attitude tracking control scheme for spacecraft formation flying is presented. The leader spacecraft with a rapid mobile antenna and a camera is modeled. While the camera is tracking the ground target, the an... A robust attitude tracking control scheme for spacecraft formation flying is presented. The leader spacecraft with a rapid mobile antenna and a camera is modeled. While the camera is tracking the ground target, the antenna is tracking the follower spacecraft. By an angular velocity constraint and an angular constraint, two methods are proposed to compute the reference attitude profiles of the camera and antenna, respectively. To simplify the control design problem, this paper first derives the desired inverse system (DIS), which can convert the attitude tracking problem of 3D space into the regulator problem. Based on DIS and sliding mode control (SMC), a robust attitude tracking controller is developed in the presence of mass parameter uncertainties and external disturbance. By Lyapunov stability theory, the closed loop system stability can be achieved. The numerical simulations show that the proposed robust control scheme exhibits significant advantages for the multi-target attitude tracking of a two-spacecraft formation. 展开更多
关键词 attitude control formation flying multi-body spacecraft robust control multi-target tracking
下载PDF
Multi-Target Tracking of Person Based on Deep Learning
20
作者 Xujun Li Guodong Fang +1 位作者 Liming Rao Tengze Zhang 《Computer Systems Science & Engineering》 SCIE EI 2023年第11期2671-2688,共18页
To improve the tracking accuracy of persons in the surveillance video,we proposed an algorithm for multi-target tracking persons based on deep learning.In this paper,we used You Only Look Once v5(YOLOv5)to obtain pers... To improve the tracking accuracy of persons in the surveillance video,we proposed an algorithm for multi-target tracking persons based on deep learning.In this paper,we used You Only Look Once v5(YOLOv5)to obtain person targets of each frame in the video and used Simple Online and Realtime Tracking with a Deep Association Metric(DeepSORT)to do cascade matching and Intersection Over Union(IOU)matching of person targets between different frames.To solve the IDSwitch problem caused by the low feature extraction ability of the Re-Identification(ReID)network in the process of cascade matching,we introduced Spatial Relation-aware Global Attention(RGA-S)and Channel Relation-aware Global Attention(RGA-C)attention mechanisms into the network structure.The pre-training weights are loaded for Transfer Learning training on the dataset CUHK03.To enhance the discrimination performance of the network,we proposed a new loss function design method,which introduces the Hard-Negative-Mining way into the benchmark triplet loss.To improve the classification accuracy of the network,we introduced a Label-Smoothing regularization method to the cross-entropy loss.To facilitate the model’s convergence stability and convergence speed at the early training stage and to prevent the model from oscillating around the global optimum due to excessive learning rate at the later stage of training,this paper proposed a learning rate regulation method combining Linear-Warmup and exponential decay.The experimental results on CUHK03 show that the mean Average Precision(mAP)of the improved ReID network is 76.5%.The Top 1 is 42.5%,the Top 5 is 65.4%,and the Top 10 is 74.3%in Cumulative Matching Characteristics(CMC);Compared with the original algorithm,the tracking accuracy of the optimized DeepSORT tracking algorithm is improved by 2.5%,the tracking precision is improved by 3.8%.The number of identity switching is reduced by 25%.The algorithm effectively alleviates the IDSwitch problem,improves the tracking accuracy of persons,and has a high practical value. 展开更多
关键词 YOLOv5 DeepSORT deep learning attention mechanism person re-identification multi-target tracking
下载PDF
上一页 1 2 96 下一页 到第
使用帮助 返回顶部