Optimal Matching Tracking Algorithm Based on Discriminant Appearance Model
LIU Wanjun1,2 , LIU Daqian2, FEI Bowen3
1.School of Software, Liaoning Technical University, Huludao 125105 2.School of Electronics and Information Engineering, Liaoning Technical University, Huludao 125105 3.School of Business Administration, Liaoning Technical University, Huludao 125105
Abstract Traditional model matching and tracking algorithms are easily influenced by the occlusion of other targets and the complex background. To solve these problems, an optimal matching tracking algorithm based on discriminant appearance model is proposed. Firstly, the local feature blocks of the previous 5 frames of the image sequences are extracted by sampling, and the training sample set consisting of a number of feature blocks is established. Then, the feature blocks with the same color and texture features are clustered to build a discriminant appearance model. Secondly, the bi-directional optimal similarity matching method is adopted for target detection. To avoid complex background interference, a method of foreground partition is proposed to acquire more accurate matching results. Finally, the tracking results are periodically added to the clustering collection to update the appearance model. The experimental results indicate that the proposed approach provides higher tracking accuracy under the conditions of partial occlusion and complex background by using the discriminant appearance model of multi-frame training and the bi-directional optimal similarity matching method.
About author:: (LIU Wanjun, born in 1959, master, professor. His research interests include image and vision computing, target detection and tracking.) (LIU Daqian(Corresponding author), born in 1992, Ph.D. candidate. His research interests include image and vision computing, target detection and tracking.) (FEI Bowen, born in 1991, Ph.D. candidate. Her research interests include data mi-ning and intelligent data processing.)
[1] VATAVU A, DANESCU R, NEDEVSCHI S. Stereovision-Based Multiple Object Tracking in Traffic Scenarios Using Free-Form Obstacle Delimiters and Particle Filters. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(1): 498-511. [2] 张焕龙,胡士强,杨国胜.基于外观模型学习的视频目标跟踪方法综述.计算机研究与发展, 2015, 52(1): 177-190. (ZHANG H L, HU S Q, YANG G S. Video Object Tracking Based on Appearance Models Learning. Journal of Computer Research and Development, 2015, 52(1): 177-190.) [3] 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, CHAI Y, et al. Vision-Based Object Detection and Tracking: A Review. Acta Automatica Sinica, 2016, 42(10): 1466-1489.) [4] 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.) [5] 李庆武,朱国庆,周 妍,等.基于特征在线选择的目标压缩跟踪算法.自动化学报, 2015, 41(11): 1961-1970. (LI Q W, ZHU G Q, ZHOU Y, et al. Object Compressive Tracking via Online Feature Selection. Acta Automatica Sinica, 2015, 41(11): 1961-1970.) [6] CHIVERTON J, XIE X H, MIRMEHDI M. Automatic Bootstra-pping and Tracking of Object Contours. IEEE Transactions on Image Processing, 2012, 21(3): 1231-1245. [7] WANG S, LU H C, YANG F, et al. Superpixel Tracking // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2011: 1323-1330. [8] MEI X, LING H B. Robust Visual Tracking and Vehicle Classification via Sparse Representation. IEEE Transactions on Pattern Ana-lysis and Machine Intelligence, 2011, 33(11): 2259-2272. [9] BAO C L, WU Y, LING H B, et al. Real Time Robust L1 Tracker Using Accelerated Proximal Gradient Approach // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 1830-1837. [10] 匡金骏,柴 毅,熊庆宇.基于时空约束和稀疏表示分类的目标跟踪算法.控制与决策, 2013, 28(9): 1355-1360. (KUANG J J, CHAI Y, XIONG Q Y. Visual Object Tracking via Time-Space Constraints and Sparse Representation Classification. Control and Decision, 2013, 28(9): 1355-1360.) [11] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-Learning-Detection. IEEE Transactions on Pattern Analysis and Machine Inte-lligence, 2012, 34(7): 1409-1422. [12] 李 俊,谢维信,李良群.基于空时线索的TLD 视频跟踪算法.信号处理, 2015, 31(10): 1287-1293. (LI J, XIE W X, LI L Q. TLD Visual Target Tracking Algorithm Based on Spatio-Temporal Cues. Journal of Signal Processing, 2015, 31(10): 1287-1293.) [13] ORON S, BAR-HILLEL A, LEVI D. Locally Orderless Tracking. International Journal of Computer Vision, 2015, 111(2): 213-228. [14] 刘大千,刘万军,费博雯.前景判别的局部模型匹配目标跟踪.中国图象图形学报, 2016, 21(5): 616-627. (LIU D Q, LIU W J, FEI B W. Foreground Discrimination in Local Model-Matching Tracking. Journal of Image and Graphics, 2016, 21(5): 616-627.) [15] DEKEL T, ORON S, RUBINSTEIN M, et al. Best-Buddies Similarity for Robust Template Matching // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 2021-2029. [16] WU Y, LIM J, YANG M H. Online Object Tracking: A Benchmark // Proc of the IEEE International Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2013: 2411-2418. [17] KWON J, LEE K M. Visual Tracking Decomposition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2010: 1269-1276. [18] ZHONG W, LU H C, YANG M H. Robust Object Tracking via Sparsity-Based Collaborative Model // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 1838-1845. [19] ADAM A, RIVLIN E, SHIMSHONI I. Robust Fragments-Based Tracking Using the Integral Histogram // Proc of the IEEE Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2006: 798-805. [20] 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. [21] WANG N Y, YEUNG D Y. Learning a Deep Compact Image Re-presentation for Visual Tracking[C/OL]. [2017-02-21]. http://winsty.net/papers/dlt.pdf. [22] 胡正平,谢荣路,王 蒙,等.基于全局与局部结构反稀疏外观模型的目标跟踪算法.模式识别与人工智能, 2016, 29(12): 1065-1074. (HU Z P, XIE R L, WANG M, et al. Object Tracking via Global and Local Structural Inverse Sparse Appearance Model. Pattern Recognition and Artificial Intelligence, 2016, 29(12): 1065-1074.)
2017, Vol. 30 
