动态时空异常感知的相关滤波目标跟踪算法

doi:10.16182/j.issn1004731x.joss.22-1047

摘要/Abstract

摘要：

针对背景感知算法未与目标的时空域特性建立联系，以及无法准确处理遮挡、形变等异常跟踪情况的问题，提出了能够动态感知时空异常的目标跟踪算法。在相关滤波器训练过程中引入动态空间正则项，使其与样本的时空域特性建立联系；结合响应图的峰值唯一性和锐利信息，提出异常感知方法；利用历史滤波器具有不同置信度的特点以及目标在时域中的连续性，通过异常感知方法自适应选择高置信度的历史滤波器作为时间正则化的参考模板，降低滤波器退化的风险。在OTB50、OTB100和TC128测试基准上进行仿真实验，该算法能够适应外观变化、画面杂乱等复杂条件下的跟踪任务，具有较强的鲁棒性和实用性。

Abstract:

In view of the fact that the background perception algorithm does not establish a relationship with the spatio-temporal domain characteristics of the target, and cannot accurately deal with the occlusion, deformation and other abnormal tracking, a object tracking algorithm which can adaptively perceive the spatio-temporal anomalies is proposed. In the training stage of correlation filter, the adaptive spatial regularization term is introduced to establish a relationship with the spatio-temporal characteristics of sample. The abnormal perception method is proposed according to the peak value of response map. Taking advantage of the different confidence of historical filter and the continuity of target in the time domain, the historical filter with high confidence is adaptively selected as the reference template of time regularization through the abnormal perception method, which reduces the risk of filter degradation. Simulation experiments carried out on OTB50, OTB100 and TC128 test benchmarks show that the algorithm can adapt to the tracking tasks under complex scenarios such as appearance changes and messy pictures, and has strong robustness and practicability.

Key words: object tracking, correlation filter, abnormal perception, filter degradation, adaptive spatio-temporal regularization

中图分类号:

TP391.4

邱云飞,卜祥蕊,张博强 . 动态时空异常感知的相关滤波目标跟踪算法[J]. 系统仿真学报, 2024, 36(2): 338-351.

Qiu Yunfei,Bu Xiangrui,Zhang Boqiang . Dynamic Spatio-temporal Anomaly-aware Correlation Filtering Object Tracking Algorithm[J]. Journal of System Simulation, 2024, 36(2): 338-351.

图/表 10

图1

表1

图2

图3

图4

图5

表2

表 3

图6

表4

参考文献 28

1	孟晓燕, 段建民. 基于相关滤波的目标跟踪算法研究综述[J]. 北京工业大学学报, 2020, 46(12): 1393-1416.
	Meng Xiaoyan, Duan Jianmin. Advances in Correlation Filter-based Object Tracking Algorithms: A Review[J]. Journal of Beijing University of Technology, 2020, 46(12): 1393-1416.
2	张可, 杨灿坤, 周春平, 等. 无人机视频图像运动目标检测算法综述[J]. 液晶与显示, 2019, 34(1): 98-109.
	Zhang Ke, Yang Cankun, Zhou Chunping, et al. Review of Moving Target Detection Algorithms for UAV Video Images[J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(1): 98-109.
3	常立博, 杜慧敏, 毛智礼, 等. 面向视频监控的TLD改进目标跟踪算法研究[J]. 计算机工程与应用, 2018, 54(14): 191-198.
	Chang Libo, Du Huimin, Mao Zhili, et al. Research on TLD Improved Target Tracking Algorithm for Video Surveillance[J]. Computer Engineering and Applications, 2018, 54(14): 191-198.
4	G S Amorim Thulio, Souto Leonardo A, P Do Nascimento Tiago, et al. Multi-robot Sensor Fusion Target Tracking with Observation Constraints[J]. IEEE Access, 2021, 9: 52557-52568.
5	刘艺, 李蒙蒙, 郑奇斌, 等. 视频目标跟踪算法综述[J]. 计算机科学与探索, 2022, 16(7): 1504-1515.
	Liu Yi, Li Mengmeng, Zheng Qibin, et al. Survey on Video Object Tracking Algorithms[J]. Journal of Frontiers of Computer Science & Technology, 2022, 16(7): 1504-1515.
6	孟琭, 杨旭. 目标跟踪算法综述[J]. 自动化学报, 2019, 45(7): 1244-1260.
	Meng Lu, Yang Xu. A Survey of Object Tracking Algorithms[J]. Acta Automatica Sinica, 2019, 45(7): 1244-1260.
7	柳有权, 裴雪, 李婉, 等. 基于邻近目标置信度评估的视觉目标跟踪与定位[J]. 系统仿真学报, 2020, 32(7): 1294-1300.
	Liu Youquan, Pei Xue, Li Wan, et al. Visual Tracking and Localization Based on Confidence Evaluation of Adjacent Targets[J]. Journal of System Simulation, 2020, 32(7): 1294-1300.
8	王科平, 朱朋飞, 杨艺. 双重背景感知相关滤波算法[J]. 传感器与微系统, 2021, 40(5): 154-156, 160.
	Wang Keping, Zhu Pengfei, Yang Yi. Dual Background-aware Correlation Filtering Algorithm[J]. Transducer and Microsystem Technologies, 2021, 40(5): 154-156, 160.
9	彭子通. 基于深度学习的抗遮挡目标跟踪技术研究[D]. 成都: 电子科技大学, 2022.
	Peng Zitong. Anti-occlusion Object Tracking Based on Deep Learning[D]. Chengdu: University of Electronic Science and Technology, 2022.
10	Li Yang, Zhang Yafei, Xu Yulong, et al. Robust Scale Adaptive Kernel Correlation Filter Tracker with Hierarchical Convolutional Features[J]. IEEE Signal Processing Letters, 2016, 23(8): 1136-1140.
11	张思贤, 杨艺, 张猛, 等. 高效的多特征自适应相关滤波跟踪器[J]. 系统仿真学报, 2022, 34(8): 1864-1873.
	Zhang Sixian, Yang Yi, Zhang Meng, et al. An Efficient Tracker via Multi-feature Adaptive Correlation Filter[J]. Journal of System Simulation, 2022, 34(8): 1864-1873.
12	Bolme D S, Beveridge J R, Draper B A, et al. Visual Object Tracking Using Adaptive Correlation Filters[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2010: 2544-2550.
13	Henriques João F, Rui Caseiro, Martins Pedro, et al. High-speed Tracking with Kernelized Correlation Filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596.
14	Li Yang, Zhu Jianke. A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration[C]//Computer Vision-ECCV 2014 Workshops. Cham: Springer International Publishing, 2015: 254-265.
15	Danelljan Martin, Häger Gustav, Fahad Shahbaz Khan, et al. Accurate Scale Estimation for Robust Visual Tracking[C]//Proceedings of the British Machine Vision Conference 2014. [S.l.]: [s.n.], 2014: 65.1-65.11.
16	Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). Piscataway, NJ, USA: IEEE, 2005: 886-893.
17	Danelljan Martin, Fahad Shahbaz Khan, Felsberg Michael, et al. Adaptive Color Attributes for Real-time Visual Tracking[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2014: 1090-1097.
18	Bertinetto L, Valmadre J, Golodetz S, et al. Staple: Complementary Learners for Real-time Tracking[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2016: 1401-1409.
19	Hamed Kiani Galoogahi, Sim Terence, Lucey S. Correlation Filters with Limited Boundaries[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2015: 4630-4638.
20	Danelljan Martin, Häger Gustav, Fahad Shahbaz Khan, et al. Learning Spatially Regularized Correlation Filters for Visual Tracking[C]//2015 IEEE International Conference on Computer Vision (ICCV). Piscataway, NJ, USA: IEEE, 2015: 4310-4318.
21	Galoogahi H K, Fagg Ashton, Lucey S. Learning Background-aware Correlation Filters for Visual Tracking[C]//2017 IEEE International Conference on Computer Vision (ICCV). Piscataway, NJ, USA: IEEE, 2017: 1144-1152.
22	Dai Kenan, Wang Dong, Lu Huchuan, et al. Visual Tracking via Adaptive Spatially-regularized Correlation Filters[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2019: 4665-4674.
23	Li Feng, Tian Cheng, Zuo Wangmeng, et al. Learning Spatial-temporal Regularized Correlation Filters for Visual Tracking[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2018: 4904-4913.
24	Wu Yi, Lim Jongwoo, Yang M H. Online Object Tracking: A Benchmark[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ, USA: IEEE, 2013: 2411-2418.
25	Wu Yi, Lim Jongwoo, Yang M H. Object Tracking Benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834-1848.
26	Liang Pengpeng, Blasch E, Ling Haibin. Encoding Color Information for Visual Tracking: Algorithms and Benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5630-5644.
27	Li Yiming, Fu Changhong, Ding Fangqiang, et al. AutoTrack: Towards High-performance Visual Tracking for UAV with Automatic Spatio-temporal Regularization[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ, USA: IEEE, 2020: 11920-11929.
28	Huang Ziyuan, Fu Changhong, Li Yiming, et al. Learning Aberrance Repressed Correlation Filters for Real-time UAV Tracking[C]//2019 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway, NJ, USA: IEEE, 2019: 2891-2900.

属性	说明
BC	目标邻近区域杂乱
DEF	目标外观改变
FM	快速运动
IPR	面内旋转
IV	光照变化
LR	低分辨率
MB	运动模糊
OCC	遮挡
OPR	面外旋转
OV	超出视野
SV	尺度变化

属性	Ours	ARCF	AutoTrack	BACF	DSST	KCF	SRDCF	STRCF	Staple
BC	0.856	0.820	0.758	0.830	0.704	0.713	0.748	0.870	0.684
DEF	0.833	0.785	0.737	0.773	0.547	0.691	0.723	0.781	0.644
FM	0.783	0.755	0.769	0.808	0.576	0.622	0.725	0.810	0.575
IPR	0.802	0.783	0.779	0.795	0.702	0.701	0.719	0.825	0.670
IV	0.815	0.793	0.784	0.826	0.722	0.724	0.757	0.848	0.685
LR	0.741	0.710	0.763	0.739	0.602	0.560	0.662	0.758	0.592
MB	0.808	0.750	0.759	0.766	0.575	0.601	0.714	0.803	0.571
OCC	0.804	0.738	0.728	0.740	0.601	0.632	0.710	0.776	0.628
OPR	0.842	0.777	0.759	0.787	0.659	0.677	0.743	0.811	0.640
OV	0.784	0.623	0.703	0.765	0.478	0.501	0.554	0.735	0.558
SV	0.826	0.762	0.746	0.771	0.644	0.635	0.739	0.819	0.665

属性	Ours	ARCF	AutoTrack	BACF	DSST	KCF	SRDCF	STRCF	Staple
BC	0.655	0.624	0.563	0.625	0.523	0.498	0.585	0.665	0.515
DEF	0.612	0.590	0.557	0.581	0.426	0.438	0.542	0.573	0.484
FM	0.617	0.582	0.594	0.606	0.461	0.459	0.574	0.630	0.459
IPR	0.596	0.572	0.560	0.584	0.508	0.469	0.533	0.604	0.493
IV	0.650	0.622	0.603	0.642	0.560	0.482	0.603	0.662	0.529
LR	0.544	0.503	0.537	0.530	0.395	0.307	0.497	0.545	0.390
MB	0.643	0.594	0.600	0.585	0.474	0.459	0.574	0.628	0.454
OCC	0.617	0.564	0.551	0.574	0.459	0.445	0.547	0.595	0.484
OPR	0.628	0.570	0.551	0.584	0.480	0.453	0.552	0.604	0.473
OV	0.599	0.479	0.533	0.552	0.386	0.393	0.434	0.561	0.430
SV	0.625	0.563	0.548	0.575	0.473	0.395	0.560	0.611	0.490

算法	跟踪速度	算法	跟踪速度
Ours	29.04	BACF	34.89
STRCF	32.36	ARCF	30.78
DSST	93.09	Staple	65.59
SRDCF	6.89	AutoTrack	31.42
KCF	478.91

[1]	李盈萱, 王中训, 董云龙. 两种新的机动目标仿真模型[J]. 系统仿真学报, 2023, 35(7): 1581-1589.
[2]	焦嵩鸣, 丁辉, 钟宇飞, 姚鑫, 郑家豪. 一种基于SiamRPN的无人机目标跟踪及控制算法[J]. 系统仿真学报, 2023, 35(6): 1372-1380.
[3]	张思贤, 杨艺, 张猛, 米鹏博. 高效的多特征自适应相关滤波跟踪器[J]. 系统仿真学报, 2022, 34(8): 1864-1873.
[4]	周维, 刘宇翔, 廖广平, 马鑫. 结合交并比损失的孪生网络目标跟踪算法研究[J]. 系统仿真学报, 2022, 34(09): 1956-1967.
[5]	李琪, 墨瀚林, 王向东, 李华. 短道速滑场景下的多目标跟踪与运动仿真[J]. 系统仿真学报, 2021, 33(5): 1039-1050.
[6]	柳有权, 裴雪, 李婉, 刘正雄. 基于邻近目标置信度评估的视觉目标跟踪与定位[J]. 系统仿真学报, 2020, 32(7): 1294-1300.
[7]	张良, 郝凯锋. 基于RSSI变化序列的MAC地址与目标匹配方法[J]. 系统仿真学报, 2020, 32(1): 113-121.
[8]	孙永侃, 张萍萍. 基于横向地球坐标系的极区超视距目标跟踪[J]. 系统仿真学报, 2018, 30(9): 3502-3513.
[9]	李菊, 曹明伟, 余烨, 夏瑜, 周立凡. 抗遮挡自适应的粒子滤波算法[J]. 系统仿真学报, 2018, 30(9): 3552-3557.
[10]	姜明新, 潘志庚, 王兰芳, 胡铸鑫. 基于深度去噪自编码器的RGB-D视频目标跟踪[J]. 系统仿真学报, 2018, 30(11): 4276-4283.
[11]	张志利, 王超, 龙勇, 王韶迪. 基于核相关滤波器无标识AR的目标跟踪仿真[J]. 系统仿真学报, 2018, 30(11): 4462-4468.
[12]	牛为华, 梁贵书, 赵鹏. 基于稀疏表示和M-ELM的断路器故障诊断模型[J]. 系统仿真学报, 2017, 29(11): 2828-2839.
[13]	陈金广, 江梦茜, 马丽丽. 存在目标交叉情形的扩展目标跟踪算法[J]. 系统仿真学报, 2017, 29(1): 7-13.
[14]	周彦, 胡岚, 王冬丽. 基于IMM-UKF-CS的混合环境目标跟踪[J]. 系统仿真学报, 2017, 29(1): 43-48.
[15]	马丽丽, 秦晓姗, 陈金广. 一种状态与杂波相关条件下的GM-CPHD算法[J]. 系统仿真学报, 2016, 28(7): 1637-1643.