基于动态自适应相关滤波的复杂场景目标跟踪算法
|
摘要
为解决目标变化、场景非均匀照明等复杂场景下的目标跟踪问题,提出了一种复杂场景下基于动态自适应相关滤波的目标跟踪算法。该算法首先构造一组几何失真的目标参考图像的版本,然后基于组合滤波器的思想,将构造的适用于每个图的最优模板组合起来;同时为避免下一帧中预先指定目标预期位置的需要,算法采用基于时间序列的预测机制,通过考虑目标的运动学来提高跟踪精度;最后该算法设计了重新初始化机制,在系统发生故障时算法进行重启。仿真结果表明,所提的算法的跟踪精度和跟踪效率上优于现有的算法,从而验证了所提算法的有效性和可行性。
In order to solve the target tracking problem in complex scenes such as target changes and non-uniform illumination of the scene, this paper proposes a target tracking algorithm based on dynamic adaptive correlation filtering in complex scenes. The algorithm first constructs a set of geometrically distorted target reference images, and then combines the constructed optimal templates for each graph based on the idea of the combined filter. At the same time, in order to avoid the need to pre-specify the target expected position in the next frame, the algorithm uses a time series-based prediction mechanism to improve the tracking accuracy by considering the kinematics of the target. Finally, the algorithm is designed with a re-initialization mechanism to restart the system in the event of a system failure. The simulation results show that the proposed algorithm has better tracking accuracy and tracking efficiency than the existing ones, which verifies the effectiveness and feasibility of the proposed algorithm.
In order to solve the target tracking problem in complex scenes such as target changes and non-uniform illumination of the scene, this paper proposes a target tracking algorithm based on dynamic adaptive correlation filtering in complex scenes. The algorithm first constructs a set of geometrically distorted target reference images, and then combines the constructed optimal templates for each graph based on the idea of the combined filter. At the same time, in order to avoid the need to pre-specify the target expected position in the next frame, the algorithm uses a time series-based prediction mechanism to improve the tracking accuracy by considering the kinematics of the target. Finally, the algorithm is designed with a re-initialization mechanism to restart the system in the event of a system failure. The simulation results show that the proposed algorithm has better tracking accuracy and tracking efficiency than the existing ones, which verifies the effectiveness and feasibility of the proposed algorithm.
引文
[1] 侯志强,韩崇昭.视觉跟踪技术综述[J].自动化学报, 2006, 32(4):603-617.HOU ZH Q,HAN CH ZH. A Survey of visual tracking[J].Acta Automatica Sinice, 2006, 32(4):603-617.
[2] 郭鹏宇,苏昂,张红良.结合纹理和形状特征的在线混合朴素贝叶斯视觉跟踪器[J].光学学报,2015,35(3):0315002-1-11.GUO P Y, SU H, ZHANG H L. Online hybrid naive Bayesian visual tracker combining texture and shape features [J]. Journal of Optics, 2015,35(3):0315002-1-11.
[3] 刘威,赵文杰,李成.时空上下文学习长时目标跟踪[J].光学学报,2016,36(1):0115001-1-8.LIU W, ZHAO W J.LI CH. Spatio-temporal context learning long-term target tracking[J]. Journal of Optics, 2016,36(1):0115001-1-8.
[4] WU Y, LIM J, YANG M H. Online object tracking: A benchmark[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013: 2411-2418.
[5] WU Y, LIM J, YANG M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(12): 1834- 1848.
[6] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(9):1409-1422.
[7] BABENKO B, YANG M H, BELONGIE S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(8):1619-1632.
[8] HARE S, SAFFARI A, TORR P H. Struck:Structuredoutput tracking with kernels[C]. IEEE International Conference on Computer Vision (ICCV), 2011:263-270.
[9] DIAZ-RAMIREZ V H, KOBER V. Adaptive phase-input joint transform correlator[J]. Applied Optics, 2007,46(9): 6543- 6551.
[10] MANZUR T, ZELLER J, SERATI S. Optical correlator based target detection, recognition, classification, and tracking[J]. Applied Optics, 2012,51(21): 4976-4983.
[11] BEN W, ARSENAULT H, GARCíA P. Intensity invariant nonlinear correlation filtering in spatially disjoint noise[J]. Applied Optics, 2010,49(5): 4284-4289.
[12] DIAZ-RAMIREZ V, KOBER V. Target recognition under nonuniform illumination conditions[J]. Applied Optics, 2009, 48(11):1408-1418.
[13] GARCíA-MARTíNEZ P, TEJERA M, FERREIRA C, et al. Optical implementation of the weighted sliced orthogonal nonlinear generalized correlation for nonuniform illumination conditions[J]. Applied Optics, 2002,41(12): 6867- 6874.
[14] OUERHANI Y, JRIDI M, ALFALOU A, et al.Optimized pre-processing input plane GPU implementation of an optical face recognition technique using a segmented phase only composite filter[J]. Optics Communications, 2013, 289(9): 33-44.
[15] BOLME D, BEVERIDGE J, DRAPER B. Visual object tracking using adaptive correlation filters[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010: 2544-2550.
[2] 郭鹏宇,苏昂,张红良.结合纹理和形状特征的在线混合朴素贝叶斯视觉跟踪器[J].光学学报,2015,35(3):0315002-1-11.GUO P Y, SU H, ZHANG H L. Online hybrid naive Bayesian visual tracker combining texture and shape features [J]. Journal of Optics, 2015,35(3):0315002-1-11.
[3] 刘威,赵文杰,李成.时空上下文学习长时目标跟踪[J].光学学报,2016,36(1):0115001-1-8.LIU W, ZHAO W J.LI CH. Spatio-temporal context learning long-term target tracking[J]. Journal of Optics, 2016,36(1):0115001-1-8.
[4] WU Y, LIM J, YANG M H. Online object tracking: A benchmark[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013: 2411-2418.
[5] WU Y, LIM J, YANG M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(12): 1834- 1848.
[6] KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(9):1409-1422.
[7] BABENKO B, YANG M H, BELONGIE S. Robust object tracking with online multiple instance learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011,33(8):1619-1632.
[8] HARE S, SAFFARI A, TORR P H. Struck:Structuredoutput tracking with kernels[C]. IEEE International Conference on Computer Vision (ICCV), 2011:263-270.
[9] DIAZ-RAMIREZ V H, KOBER V. Adaptive phase-input joint transform correlator[J]. Applied Optics, 2007,46(9): 6543- 6551.
[10] MANZUR T, ZELLER J, SERATI S. Optical correlator based target detection, recognition, classification, and tracking[J]. Applied Optics, 2012,51(21): 4976-4983.
[11] BEN W, ARSENAULT H, GARCíA P. Intensity invariant nonlinear correlation filtering in spatially disjoint noise[J]. Applied Optics, 2010,49(5): 4284-4289.
[12] DIAZ-RAMIREZ V, KOBER V. Target recognition under nonuniform illumination conditions[J]. Applied Optics, 2009, 48(11):1408-1418.
[13] GARCíA-MARTíNEZ P, TEJERA M, FERREIRA C, et al. Optical implementation of the weighted sliced orthogonal nonlinear generalized correlation for nonuniform illumination conditions[J]. Applied Optics, 2002,41(12): 6867- 6874.
[14] OUERHANI Y, JRIDI M, ALFALOU A, et al.Optimized pre-processing input plane GPU implementation of an optical face recognition technique using a segmented phase only composite filter[J]. Optics Communications, 2013, 289(9): 33-44.
[15] BOLME D, BEVERIDGE J, DRAPER B. Visual object tracking using adaptive correlation filters[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010: 2544-2550.