基于难例挖掘和自适应时间正则化的视觉目标跟踪算法

doi:10.13973/j.cnki.robot.200370

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (781 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
黄月平, 李小锋, 齐乃新, 卢瑞涛, 张胜修. 基于难例挖掘和自适应时间正则化的视觉目标跟踪算法[J]. 机器人, 2021, 43(3): 350-363.DOI: 10.13973/j.cnki.robot.200370. HUANG Yueping, LI Xiaofeng, QI Naixin, LU Ruitao, ZHANG Shengxiu. Visual Object Tracking Algorithm Based on Hard Negative Mining and Adaptive Temporal Regularization. ROBOT, 2021, 43(3): 350-363. DOI: 10.13973/j.cnki.robot.200370.

摘要针对复杂情况下视觉目标跟踪算法性能严重退化的问题，提出一种基于难例挖掘和自适应时间正则化的视觉目标跟踪算法．首先，该算法在Staple算法基础上，深度挖掘困难负样本用于相关滤波器训练，提高了跟踪算法的抗干扰能力；其次，加入自适应时间正则化约束，根据目标响应图的变化情况，自适应确定时间正则化系数及模型更新策略，增强了跟踪算法的鉴别能力．在数据集OTB-2015、TC-128和UAV123上的实验结果表明，该算法能够有效应对复杂情况下跟踪性能退化的问题，且运行速度超过30帧/秒，满足实时性需求，综合性能优于对比算法．

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	黄月平
	李小锋
	齐乃新
	卢瑞涛
	张胜修

关键词 ：目标跟踪, 相关滤波, 难例挖掘, 时间正则化

Abstract：To alleviate the severe performance degradation of visual object tracking algorithms in complex situations, a visual object tracking algorithm based on hard negative mining and adaptive temporal regularization is proposed. Firstly, hard negative samples are deeply mined based on the Staple algorithm to train the correlation filter, which improves the anti-jamming ability of the tracking algorithm. Secondly, the adaptive temporal regularization term is added, and the coefficient of temporal regularization term and the model updating strategy are adaptively determined by the response map variation, which improves the identification ability of the tracking algorithm. The experimental results on datasets OTB-2015, TC-128 and UAV123 show that the proposed algorithm can effectively deal with the tracking performance degradation in complex situations, and its running speed is more than 30 frames per second, which meets the real-time requirement. Its comprehensive performance is better than the comparative algorithms.

Key words： object tracking correlation filter hard negative mining temporal regularization

收稿日期: 2020-09-14 【基金专刊】 录用日期: 2021-01-21

TP391

基金资助:国家自然科学基金（61806209）；陕西省组合与智能导航重点实验室基金（SKLIIN-20180103）．

通讯作者: 李小锋，xiaofeng_li2006@126.com E-mail: xiaofeng_li2006@126.com

作者简介: 黄月平（1990–），女，博士生．研究领域：视觉目标跟踪
李小锋（1982–），男，博士，讲师．研究领域：飞行器制导与控制
齐乃新（1989–），男，博士．研究领域：视觉导航．

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.200370 或 https://robot.sia.cn/CN/Y2021/V43/I3/350

[1] Henriques J F, Caseiro R, Martins P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596.
[2] Li Y M, Fu C H, Ding F Q, et al. AutoTrack: Towards highperformance visual tracking for UAV with automatic spatiotemporal regularization[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2020: 11920-11929.
[3] Wang N, Zhou W G, Tian Q, et al. Multi-cue correlation filters for robust visual tracking[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2018: 4844-4853.
[4] Wang Q, Gao J, Xing J L, et al. DCFNet: Discriminant correlation filters network for visual tracking[DB/OL]. (2017-04-13) [2020-09-01]. https://arxiv.org/abs/1704.04057v1.
[5] Galoogahi H K, Fagg A, Lucey S. Learning backgroundaware correlation filters for visual tracking[C]//IEEE/CVF International Conference on Computer Vision. Piscataway, USA: IEEE, 2017: 1144-1152.
[6] Dai K N, Wang D, Lu H C, et al. Visual tracking via adaptive spatially-regularized correlation filters[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2019: 4665-4674.
[7] Danelljan M, Hager G, Khan F S, et al. Learning spatially regularized correlation filters for visual tracking[C]//IEEE International Conference on Computer Vision. Piscataway, USA: IEEE, 2015: 4310-4318.
[8] 葛宝义，左宪章，胡永江，等. 基于双步相关滤波的目标跟踪算法[J].红外与激光工程， 2018， 47(12)： 388-397. Ge B Y, Zuo X Z, Hu Y J, et al. Object tracking algorithm based on two-step correlation filter[J]. Infrared and Laser Engineering, 2018, 47(12): 388-397.
[9] Xu T Y, Feng Z H, Wu X J, et al. Learning adaptive discriminative correlation filters via temporal consistency preserving spatial feature selection for robust visual object tracking[J]. IEEE Transactions on Image Processing, 2019, 28(11): 5596-5609.
[10] Bertinetto L, Valmadre J, Golodetz S, et al. Staple: Complementary learners for real-time tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2016: 1401-1409.
[11] Danelljan M, Bhat G, Khan F S, et al. ECO: Efficient convolution operators for tracking[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2017: 6931-6939.
[12] Possegger H, Mauthner T, Bischof H. In defense of color-based model-free tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2015: 2113- 2120.
[13] Danelljan M, Häger G, Khan F, et al. Discriminative scale space tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(8): 1561-1575.
[14] Zhang S L, Lu W, Xing W W, et al. Learning scale-adaptive tight correlation filter for object tracking[J]. IEEE Transactions on Cybernetics, 2020, 50(1): 270-283.
[15] Xu T Y, Feng Z H, Wu X J, et al. Joint group feature selection and discriminative filter learning for robust visual object tracking[C]//IEEE/CVF International Conference on Computer Vision. Piscataway, USA: IEEE, 2019: 7949-7959.
[16] Wu Y, Lim J, Yang M H. Object tracking benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834-1848.
[17] Gray R M. Toeplitz and circulant matrices: A review[J]. Foundations and Trends in Communications and Information Theory, 2006, 2(3): 155-239.
[18] Mueller, M, Smith N, Ghanem B. Context-aware correlation filter tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2017: 1387-1395.
[19] Ryan R, Yeo G, Poggio T. Regularized least-squares classification[M]//Advances in Learning Theory: Methods, Model and Applications. Amsterdam, Netherlands: IOS Press, 2003: 131- 154.
[20] Wu Y, Lim J, Yang M H. Online object tracking: A benchmark[C]//IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, USA: IEEE, 2013: 2411-2418.
[21] Liang P P, Blasch E, Ling H B. Encoding color information for visual tracking: Algorithms and benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5630-5644.
[22] Mueller M, Smith N, Ghanem B. A benchmark and simulator for UAV tracking[C]//European Conference on Computer Vision. Cham, Switzerland: Springer, 2016: 445-461.
[23] Valmadre J, Bertinetto L, Henriques J F, et al. Long-term tracking in the wild: A benchmark[C]//European Conference on Computer Vision. Cham, Switzerland: Springer, 2018: 692- 707.
[24] Ma C, Huang J B, Yang X K, et al. Hierarchical convolutional features for visual tracking[C]//IEEE International Conference on Computer Vision. Piscataway, USA: IEEE, 2015: 3074-3082.