Long-Term Tracking Algorithm Based on Correlation Filter
LI Na1,2,3, WU Lingfeng1,2,3, LI Daxiang1,2,3
1.Center for Image and Information Processing, Xi′an University of Posts and Telecommunications, Xi′an 710121 2.Key Laboratory of Electronic Information Application Technology for Scene Investigation, Ministry of Public Security, Xi′an 710121 3.International Joint Research Center for Wireless Communication and Information Processing, Xi′an 710121
Abstract Based on the kernelized correlation filter(KCF) algorithm, a long-term tracking algorithm combining target re-detection is proposed. Firstly, the histogram of oriented gradient features and LAB color information are fused, the appearance model is established and scale estimation is added to cope with the changes of object scale. Then, the peak ratio is introduced to control the start of re-detection module and a correlation filter model is re-learned by extracting Harris corners. Finally, the occluded object is continuously tracked with the proposed model updating strategy. Comparison experiments on OTB datasets show that the proposed algorithm produces higher tracking accuracy and is suitable for long-term tracking with occlusion.
Fund:Supported by Shaanxi International Cooperation Exchange Funded Projects(No.2017KW-013), Education Department of Shaanxi Provincial Government Special Research Program Funded Projects(No.17JK0692), Graduate Creative Funds of Xi′an University of Posts and Telecommunications(No.CXJJ2017004)
[1] 尹宏鹏,陈 波,柴 毅,等.基于视觉的目标检测与跟踪综述.自动化学报, 2016, 42(10): 1466-1489. (YIN H P, CHEN B, CAI Y, et al. Vision-Based Object Detection and Tracking: A Review. Acta Automatica Sinica, 2016, 42(10): 1466-1489.) [2] XU Y, DONG J X, ZHANG B, et al. Background Modeling Me-thods in Video Analysis: A Review and Comparative Evaluation. CAAI Transactions on Intelligence Technology, 2016, 1(1): 43-60. [3] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual Object Tracking Using Adaptive Correlation Filters // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2010: 2544-2550. [4] HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploiting the Circulant Structure of Tracking-by-Detection with Kernels // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2012: 702-715. [5] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-Speed Tracking with Kernelized Correlation Filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596. [6] LI Y, ZHU J K. A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2014: 254-265. [7] DANELLJAN M, HGER G, KHAN F S, et al. Accurate Scale Estimation for Robust Visual Tracking // Proc of the British Machine Vision Conference. Berlin, Germany: Springer, 2014: 65.1-65.11. [8] 王宇霞,赵清杰,蔡艺明,等.基于自重构粒子滤波算法的目标跟踪.计算机学报, 2016, 39(7): 1294-1306. (WANG Y X, ZHAO Q J, CAI Y M, et al. Tracking by Auto-Reconstructing Particle Filter Trackers. Chinese Journal of Computers, 2016, 39(7): 1294-1306.) [9] 姜文涛,刘万军,袁 姮.基于软特征理论的目标跟踪研究.计算机学报, 2016, 39(7): 1334-1355. (JIANG W T, LIU W J, YUAN H. Research of Object Tracking Based on Soft Feature Theory. Chinese Journal of Computers, 2016, 39(7): 1334-1355.) [10] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-Learning-Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422. [11] 童 源,费树岷,沈 捷.基于TLD框架的快速目标跟踪方法.计算机应用研究, 2018, 35(1): 317-320. (TONG Y, FEI S M, SHEN J. Fast Object Tracking Method Based on TLD Algorithm. Application Research of Computers, 2018, 35(1): 317-320.) [12] ZHANG K H, ZHANG L, YANG M H, et al. Fast Tracking via Spatio-Temporal Context Learning[J/OL]. [2018-05-25]. https://arxiv.org/pdf/1311.1939.pdf. [13] 刘 威,赵文杰,李 成.时空上下文学习长时目标跟踪.光学学报, 2016, 36(1): 179-186. (LIU W, ZHAO W J, LI C. Long-Term Visual Tracking Based on Spatio-Temporal Context. Acta Optica Sinica, 2016, 36(1): 179-186.) [14] 张 雷,于凤芹.基于置信图特性的改进时空上下文目标跟踪.计算机工程, 2016, 42(8): 277-281, 288. (ZHANG L, YU F Q. Improved Object Tracking via Spatial-Temporal Context Based on Confidence Map Property. Computer Engineering, 2016, 42(8): 277-281, 288.) [15] MUELLER M, SMITH N, GHANEM B. Context-Aware Correlation Filter Tracking // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 1396-1404. [16] GALOOGAHI H K, FAGG A, LUCEY S. Learning Background-Aware Correlation Filters for Visual Tracking // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE. 2017: 1135-1143. [17] MA C, YANG X K, ZHANG C Y, et al. Long-Term Correlation Tracking // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 5388-5396. [18] 赵高鹏,沈玉鹏,王建宇.基于核循环结构的自适应特征融合目标跟踪.光学学报, 2017, 37(8): 201-210. (ZHAO G P, SHEN Y P, WANG J Y, et al. Adaptive Feature Fusion Object Tracking Based on Circulant Structure with Kernel. Acta Optica Sinica, 2017, 37(8): 201-210.) [19] ZHANG T Z, XU C S, YANG M H. Multi-task Correlation Particle Filter for Robust Object Tracking // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 4335-4343. [20] ASHA C S, NARASIMHADHAN A V. Adaptive Learning Rate for Visual Tracking Using Correlation Filters. Procedia Computer Science, 2016, 89: 614-622. [21] WU Y, LIM J, YANG M H. Online Object Tracking: A Benchmark // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2013: 2411-2418. [22] DANELLJAN M, KHAN F S, FELSBERG M, et al. Adaptive Co-lor Attributes for Real-Time Visual Tracking // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 1090-1097.
2018, Vol. 31 
