计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 221000172-6.doi: 10.11896/jsjkx.221000172

• 图像处理&多媒体技术 • 上一篇    下一篇

基于自适应搜索范围调整的视觉目标跟踪

王超1,2, 王凯1   

  1. 1 河北工程大学信息与电气工程学院 河北 邯郸 056038
    2 河北省安防信息感知与处理重点实验室 河北 邯郸 056000
  • 发布日期:2023-11-09
  • 通讯作者: 王超(wangchao@hebeu.edu.cn)
  • 基金资助:
    国家自然科学基金(62071071);邯郸市科技计划项目(21422031251)

Visual Object Tracking Based on Adaptive Search Range Adjustment

WANG Chao1,2, WANG Kai1   

  1. 1 School of Information and Electrical Engineering,Hebei University of Engineering,HeBei,Handan 056000,China
    2 Hebei Key Laboratory of Security & Protection Information Sensing and Processing,HeBei,Handan 056000,China
  • Published:2023-11-09
  • About author:WANG Chao,born in 1983,Ph.D,lecturer,master supervisor,is a member of China Computer Federation.His main research interests include video/image processing and computer vision.
  • Supported by:
    National Natural Science Foundation of China(62071071)and Science and Technology Plan Project of Handan(21422031251).

PDF (PC)

171

摘要： 当前主流的视觉目标跟踪算法检测目标时,其搜索范围是以前一帧目标位置为中心设定的。然而目标可能由于运动而偏离设定的搜索中心,其在当前帧的检测响应易受到余弦窗惩罚机制的抑制,导致跟踪失败。为解决上述问题,提出了自适应搜索范围调整(Adaptive Search Range Adjustment,ASRA)方法。该方法采用了基于循环神经网络的运动预测模型来预测当前帧目标位置,并与相关滤波响应相结合来对搜索中心进行调整,进一步根据目标的运动矢量对搜索范围尺寸进行调整。将ASRA方法应用于当前先进的基于孪生网络的目标跟踪算法,在OTB2015和VOT2018数据集上进行的实验结果表明ASRA方法可以改善跟踪算法的准确率和鲁棒性。

关键词: 视觉目标跟踪, 搜索范围, 运动预测, 相关滤波, 孪生网络

Abstract: The mainstream visual object tracking algorithms generally set the position of object that tracked in the last frame as the center of a search range,which is used to detect the object in current frame.However,the tracking object may deviate from the center of search range due to its motion,thus its detection response in current frame can be easily inhibited by the cosine window penalty mechanism,which leads to tracking failure.To solve this problem,an adaptive search range adjustment(ASRA) method is proposed.In this method,a motion prediction model based on recurrent neural network(RNN) is used to predict the object position in current frame,and it is combined with the correlation filtering response to adjust the center of search range.The size of search range is further adjusted according to the motion vector of the tracking object.The proposed ASRA method is applied to current state-of-the-art object tracking algorithms based on Siamese networks.Experiments on OTB2015 and VOT2018 datasets show that ASRA can improve the accuracy and robustness of these algorithms.

Key words: Visual object tracking, Search range, Motion prediction, Correlation filtering, Siamese networks

中图分类号: 

  • TP391
[1]MENG Y,YANG X.Overview of target tracking algorithms[J].Journal of Automation,2019,45(7):1244-1260.
[2]ZHANG S P,YAO H X,SUN X,et al.Sparse coding based visual tracking:review and experimental comparison[J].Pattern Recognition,2013,46(7):1772-1788.
[3]ZHE C,HONG Z,TAO D.An Experimental Survey on Correlation Filter-based Tracking[J].Computer Science,2015,53(6025):68-83.
[4]LI B,WU W,WANG Q,et al.SiamRPN++:Evolution of Siamese Visual Tracking With Very Deep Networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach,CA,USA,2019:4277-4286.
[5]FAN H,LING H B.Siamese cascaded region proposal networks for real-time visual tracking[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition.Long Beach,USA:IEEE,2019:7952-7961.
[6]WANG S,WANG H,ZHOU Y,et al.Automatic Laser Profile Recognition and Fast Tracking for Structured Light Measurement Using Deep Learning and Template Matching[J].Mea-surement,2020,169:108362.
[7]ZHANG Y,WANG L,WANG D,et al.Learning Regression and Verification Networks for Robust Long-term Tracking[J].International Journal of Computer Vision,2021,129:2536-2547.
[8]LI J,YAN B,LIN C,et al.JROTM:Jointly Reinforced ObjectTracking with Temporal Content Reference and Motion Gui-dance[J].Neurocomputing,2021,434:285-294.
[9]ALAHI A,GOEL K,RAMANATHAN V,et al.Social LSTM:Human Trajectory Prediction in Crowded Spaces[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2016:961-971.
[10]BHUJEL N,TEOH E K,YAU W Y.Pedestrian Trajectory Prediction Using RNN Encoder-Decoder with Spatio-Temporal Attentions[C]//2019 IEEE 5th International Conference on Mechatronics System and Robots(ICMSR).IEEE,2019.
[11]FEREDE S,XIE X,ZHANG C,et al.Small Ball Tracking with Trajectory Prediction[C]//2020 IEEE 5th International Confe-rence on Signal and Image Processing(ICSIP).IEEE,2020.
[12]ZHU Z,WANG Q,LI B,et al.DistractorAware Siamese Net-works for Visual Object Tracking[C]//Computer Vision(ECCV 2018).Lecture Notes in Computer Science,Cham:Springer,2018:103-119.
[13]LI S,CHU J,ZHONG G,et al.Robust Visual Tracking with Occlusion Judgment and Re-Detection[J].IEEE Access,2020,8:122772-122781.
[14]WANG J,YANG H,XU N,et al.Long-term target trackingcombined with re-detection[J].EURASIP Journal on Advances in Signal Processing,2021,2021(1):1-16.
[15]CHEN Y,WANG P,ZHONG B,et al.Coarse-to-fine visualtracking with PSR and scale driven expert-switching[J].Neurocomputing,2018,275(JAN.31):1456-1467.
[16]WANG Y,DING L,LAGANIERE R.Real-Time UAV Tra-cking Based on PSR Stability[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop(ICCVW).IEEE,2019.
[17]WANG M,SU D,SHI L,et al.Real-time 3D human tracking for mobile robots with multisensors[C]//2017 IEEE International Conference on Robotics and Automation(ICRA).2017:5081-5087.
[18]KRISTAN M,MATAS J,LEONARDIS A,et al.A Novel Performance Evaluation Methodology for Single-Target Trackers[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence.2016:2137-2155.
[19]WU Y,LIM J,YANG M.Object Tracking Benchmark[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence.2015:1834-1848.
[20]LAO Y W,ZHUJ D,ZHENG Y F.Sequential particle generationfor visual tracking[J].IEEE Transactions on Circuits andSystems for VideoTechnology,2009,19(9):1365-1378.
[21]LI B,YAN J J,WU W,et al.High performance visual tracking with siamese region proposal network[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake City,USA:IEEE,2018:8971-8980.
[22]ZHANG Z,PENG H.Deeper and wider siamese networks for real-time visual tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:4591-4600.
[23]WANG Q,ZHANG L,BERTINETTO L,et al.Fast Online Object Tracking and Segmentation:A Unifying Approach[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:1328-1338.
[24]CHEN Z,ZHONG B,LI G,et al.Siamese box adaptive network for visual tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:6668-6677.
[25]GUO D,WANG J,CUI Y,et al.SiamCAR:Siamese fully convolutional classification and regression for visual tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:6269-6277.
[26]VOIGTLAENDER P,LUITEN J,TORR P H S,et al.Siam r-cnn:Visual tracking by re-detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:6578-6588.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发