动态模板匹配的孪生网络长时目标跟踪算法

doi:10.3778/j.issn.1002-8331.2205-0444

摘要/Abstract

摘要： 近年来备受关注的长时目标跟踪更接近实际应用场景，许多算法通过目标重检测机制来解决目标消失与重现问题，但跟踪速度无法满足实时目标跟踪需求，因此提出一种基于模板匹配的孪生网络长时目标跟踪算法。改进算法引入快速动态模板匹配的全局搜索重检测机制，当检测到目标丢失情况，则利用模板匹配进行预测粗定位，再通过孪生网络目标跟踪算法进一步获得目标准确位置。目标外观形变会严重影响模板匹配预测定位的准确度，因此引入动态匹配模板更新策略进一步提高抗干扰性能。在四个数据集上与当前先进的长时目标跟踪算法相比较，实验结果显示改进算法不仅跟踪性能显著提高，并且跟踪速度达到40?FPS左右，能满足实时目标跟踪需求。

关键词: 机器视觉, 长时目标跟踪, 深度学习, 孪生网络, 目标重检测, 模板匹配

Abstract: Due to closing to practical application scenarios, long-term object tracking has attracted much attention in recent years. Many long-term tracking algorithms use the object re-detection mechanism to solve the problem of out-of-view and reappearance, but the tracking speed cannot meet the real-time requirements. In the paper a Siamese network long-term object tracking algorithm based on dynamic template matching is proposed. A re-detection mechanism using fast dynamic template matching is designed. When the target loss is detected, template matching method is utilized to roughly predict the object location, and then the accurate target position is further obtained using Siamese network object tracking algorithm. The deformation of the target appearance will seriously affect the template matching positioning accuracy, so the dynamic matching template update strategy is proposed to improve the anti-interference performance. Compared with the state-of-the-art long-term target tracking algorithm on four datasets, the experimental results show that the improved algorithm can not only significantly improve the object tracking performance, but also obtain 40?FPS tracking speed, which can meet the needs of real-time target tracking.

Key words: machine vision, long-term object tracking, deep learning, Siamese network, target re-detection, template matching

李阳, 侯颖, 李娇, 杨林, 石欢, 贺顺, 张释如. 动态模板匹配的孪生网络长时目标跟踪算法[J]. 计算机工程与应用, 2023, 59(17): 159-168.

LI Yang, HOU Ying, LI Jiao, YANG Lin, SHI Huan, HE Shun, ZHANG Shiru. Siamese Network Long-Term Object Tracking Algorithm Based on Dynamic Template Matching[J]. Computer Engineering and Applications, 2023, 59(17): 159-168.

参考文献

[1] MOUDGIL A，GANDHI V.Long-term visual object tracking benchmark[C]//Asian Conference on Computer Vision ACCV 2018.Cham：Springer，2018：629-645.
[2] LUKEŹIČ A，ZAJC L Č，VOJÍŘ T，et al.Performance evaluation methodology for long-term single-object tracking[J].IEEE Transactions on Cybernetics，2021，51（12）：6305-6318.
[3] 赵德明.基于深度学习的长时目标跟踪[D].成都：电子科技大学，2021.
ZHAO D M.Long-term object tracking based on deep learning[D].Chengdu：University of Electronic Science and Technology of China，2021.
[4] BERTINETTO L，VALMADRE J，HENRIQUES J F，et al.Fully-convolutional siamese networks for object tracking[C]//European Conference on Computer Vision.Switzerland：Springer Press，2016：850-865.
[5] ZHANG Z，PENG H.Deeper and wider siamese networks for real-time visual tracking[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.USA：IEEE Press，2019：4591-4600.
[6] ZHU Z，WANG Q，LI B，et al.Distractor-aware siamese networks for visual object tracking[C]//European Conference on Computer Vision.Germany：Springer Press，2018：101-117.
[7] LI B，WU W，WANG Q，et al.SiamRPN++：evolution of Siamese visual tracking with very deep networks[C]// IEEE Conference on Computer Vision and Pattern Recognition.USA：IEEE Press，2019：4282-4291.
[8] XU Y D，WANG Z Y，LI Z X，et al.SiamFC++：towards robust and accurate visual tracking with target estimation guidelines[C]//AAAI Conference on Artificial Intelligence.USA：AAAI Press，2020：12549-12556.
[9] ZHANG Y，WANG L，WANG D，et al.Learning regression and verification networks for robust long-term tracking[J].International Journal of Computer Vision，2021，129（9）：2536-2547.
[10] VALMADRE J，BERTINETTO L，HENRIQUES J F，et al.Long-term tracking in the wild：a benchmark[C]//European Conference on Computer Vision.Germany：Springer Press，2018：670-685.
[11] YAN B，ZHAO H，WANG D，et al.Skimming-perusal tracking：a framework for real-time and robust long-term tracking[C]//IEEE/CVF International Conference on Computer Vision.USA：IEEE Press，2019：2385-2393.
[12] HUANG L，ZHAO X，HUANG K.Globaltrack：a simple and strong baseline for long-term tracking[C]//AAAI Conference on Artificial Intelligence.USA：AAAI Press，2020：11037-11044.
[13] DAI K，ZHANG Y，WANG D，et al.High-performance long-term tracking with meta-updater[C]//IEEE/CVF Conference on Computer Vision and Pattern Recognition.USA：IEEE Press，2020：6297-6306.
[14] YAN B，PENG H，FU J，et al.Learning spatio-temporal transformer for visual tracking[C]//IEEE/CVF International Conference on Computer Vision.USA：IEEE Press，2021：10448-10457.
[15] 邓文浩.长时目标跟踪算法的研究与应用[D].成都：电子科技大学，2021.
DENG W H.Research and application of long-term object tracking algorithm[D].Chengdu：University of Electronic Science and Technology of China，2021.
[16] 马珺，王昱皓.结合自适应更新策略和再检测技术的跟踪算法[J].计算机工程与应用，2021，57（9）：217-224.
MA J，WANG Y H.Object tracking algorithm based on adaptive update strategy and re-detection technology[J].Computer Engineering and Applications，2021，57（9）：217-224.
[17] 王林，郑有玲.结合孪生网络重检的长期目标跟踪算法[J].计算机系统应用，2022，31（4）：188-195.
WANG L，ZHENG Y L.Long-term target tracking algorithm based on twin network rechecking[J].Computer Systems and Applications，2022，31（4）：188-195.
[18] REN Q，ZHENG Y，SUN P，et al.A robust and accurate end-to-end template matching method based on the siamese network[J].IEEE Geoscience and Remote Sensing Letters，2021，19：1-5.
[19] 贾迪，朱宁丹，杨宁华，等.图像匹配方法研究综述[J].中国图象图形学报，2019，24（5）：677-699.
JIA D，ZHU N D，YANG N H，et al.Image matching methods[J].Journal of Image and Graphics，2019，24（5）：677-699.
[20] 任立成，杨嘉棋，魏宇星，等.基于特征融合与双模板嵌套更新的孪生网络跟踪算法[J].计算机工程，2021，47（7）：239-248.
REN L C，YANG J Q，WEI Y X，et al.Tracking algorithm using siamese network based on feature fusion and dual-template nested update[J].Computer Engineering，2021，47（7）：239-248.
[21] 沈玉玲，伍忠东，赵汝进，等.基于模型更新与快速重检测的长时目标跟踪[J].光学学报，2020，40（3）：121-130.
SHEN Y L，WU Z D，ZHAO R J，et al.Long-term object tracking based-on model updating and fast re-detection[J].Acta Optica Sinica，2020，40（3）：121-130.
[22] 杨哲，孙力帆，付主木，等.基于孪生网络融合多模板的目标跟踪算法[J].计算机工程与应用，2022，58（4）：212-220.
YANG Z，SUN L F，FU Z M，et al.Object tracking algorithm based on siamese network with multiple templates[J].Computer Engineering and Applications，2022，58（4）：212-220.
[23] 陈志良，石繁槐.结合双模板融合与孪生网络的鲁棒视觉目标跟踪[J].中国图象图形学报，2022，27（4）：1191-1203.
CHEN Z L，SHI F H.Double template fusion based siamese network for robust visual object tracking[J].Journal of Image and Graphics，2022，27（4）：1191-1203.
[24] FAN H，LIN L，YANG F，et al.Lasot：a high-quality benchmark for large-scale single object tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition（CVPR），Long Beach，CA，USA，2019：5374-5383.
[25] KRISTAN M，MATAS J，LEONARDIS A，et al.The seventh visual object tracking vot2019 challenge results[C]// IEEE/CVF International Conference on Computer Vision.USA：IEEE Press，2019：2206-2241.
[26] MUELLER M，SMITH N，GHANEM B.A benchmark and simulator for uav tracking[C]//European Conference on Computer Vision.Cham：Springer，2016：445-461.