免锚检测的行人多目标跟踪算法

doi:10.3778/j.issn.1002-8331.2011-0050

摘要/Abstract

摘要： 针对复杂环境下行人目标因检测器漏检和频繁遮挡而导致的数据关联不正确、跟踪实时性差的问题，提出了一种基于免锚检测的多目标跟踪算法。算法采用预测目标中心点热力图的方法实现目标检测定位，改善了因锚点框回归歧义所导致的漏检问题。同时在检测模型中嵌入深度表观特征提取分支，构建联合检测与跟踪的多任务网络用于提升实时性。为解决跟踪阶段行人因遮挡而引起的数据关联错误和轨迹丢失问题，提出加权多特征融合的相似性度量算法，综合多种关键特征评估检测与轨迹的匹配程度，显著提升数据关联正确性；提出基于存活期的跟踪状态更新方法，有效找回丢失轨迹，提升跟踪鲁棒性。在MOT数据集上对跟踪性能进行测试，实验结果表明，算法能够有效应对遮挡，并实现长时间稳定跟踪，兼顾了实时性与准确性。

关键词: 多目标跟踪, 深度表观特征, 多特征融合, 数据关联

Abstract: A multi-object tracking algorithm based on anchor-free detection is proposed to solve the problems of incorrect data correlation and poor tracking real-time due to detector omission and frequent occlusion in complex environment. The algorithm uses the method of predicting the thermal diagram of the target center to realize the target detection and location, and improves the problem of missing detection caused by the ambiguity of anchor frame regression. At the same time, the depth apparent feature extraction branch is embedded in the detection model, and the multi-task network of joint detection and tracking is built to improve the real-time performance. In order to solve the problem of data association error and track loss caused by occlusion of pedestrians in the tracking stage, a similarity measurement algorithm based on weighted multi-feature fusion is proposed to evaluate the matching degree of detection and tracking based on a variety of key features to significantly improve the accuracy of data association. A survival based tracking status update method is proposed to effectively recover lost track and improve tracking robustness. The tracking performance is tested on the MOT dataset. The experimental results show that the algorithm can effectively deal with occlusion and realize long-term stable tracking, taking into account both real-time and accuracy.

Key words: multi-object tracking, depth appearance characteristics, multi-feature fusion, data association

单兆晨, 黄丹丹, 耿振野, 刘智. 免锚检测的行人多目标跟踪算法[J]. 计算机工程与应用, 2022, 58(10): 145-152.

SHAN Zhaochen, HUANG Dandan, GENG Zhenye, LIU Zhi. Pedestrian Multi-Object Tracking Algorithm of Anchor-Free Detection[J]. Computer Engineering and Applications, 2022, 58(10): 145-152.

参考文献

[1] 戴凤智，魏宝昌，欧阳育星，等.基于深度学习的视频跟踪研究进展综述[J].计算机工程与应用，2019，55（10）：16-29.
DAI F Z，WEI B C，OUYANG Y X，et al.Survey of research progress of video tracking based on deep learning[J].Computer Engineering and Applications，2019，55（10）：16-29.
[2] 王思奎，刘云鹏，亓琳，等.基于背景约束与卷积特征的目标跟踪方法[J].计算机工程与应用，2020，56（8）：205-214.
WANG S K，LIU Y P，QI L，et al.Object tracking method based on background constraints and convolution features[J].Computer Engineering and Applications，2020，56（8）：205-214.
[3] BEWLEY A，GE Z，OTT L，et al.Simple online and realtime tracking[C]//2016 IEEE International Conference on Image Processing，2016：3464-3468.
[4] WOJKE N，BEWLEY A，PAULUS D.Simple online and realtime tracking with a deep association metric[C]//2017 IEEE International Conference on Image Processing，2017：3645-3649.
[5] 罗浩，姜伟，范星，等.基于深度学习的行人重识别研究进展[J].自动化学报，2019，45（11）：2032-2049.
LUO H，JIANG W，FAN X，et al.A survey on deep learning based person re-identification[J].Acta Automatica Sinica，2019，45（11）：2032-2049.
[6] 罗元，王薄宇，陈旭.基于深度学习的目标检测技术的研究综述[J].半导体光电，2020，41（1）：1-10.
LUO Y，WANG B Y，CHEN X，et al.A review of target detection technology based on deep learning[J].Semiconductor Optoelectronics，2020，41（1）：1-10.
[7] 童靖然，毛力，孙俊.特征金字塔融合的多模态行人检测算法[J].计算机工程与应用，2019，55（19）：214-222.
TONG J R，MAO L，SUN J.Multimodal pedestrian detection algorithm based on fusion feature pyramids[J].Computer Engineering and Applications，2019，55（19）：214-222.
[8] NEWELL A，YANG K，DENG J，et al.Stacked hourglass networks for human pose estimation[C]//14th European Conference on Computer Vision，2016：483-499.
[9] YU F，WANG D，SHELHAMER E，et al.Deep layer aggregation[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition，2018：2403-2412.
[10] ZHANG Y，WANG C，WANG X，et al.FairMOT：on the fairness of detection and re-identification in multiple object tracking[J].arXiv：2004.01888，2020.
[11] WANG Z，ZHENG L，LIU Y，et al.Towards real-time multi-object tracking[C]//16th European Conference on Computer Vision，2020：107-122.
[12] DALAL N，TRIGGS B.Histograms of oriented gradients for human detection[C]//2005 IEEE Conference on Computer Vision and Pattern Recognition，2005：886-893.
[13] MA L，LIU H，HU L，et al.Orientation driven bag of appearances for person re-identification[J].arXiv：1605.02464，2016.
[14] ZHENG L，ZHANG H，SUN S，et al.Person re-identification in the wild[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition，2017：3346-3355.
[15] LI W，ZHAO R，XIAO T，et al.DeepReID：deep filter pairing neural network for person re-identification[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition，2014：152-159.
[16] REN S，HE K，GIRSHICK R，et al.Faster R-CNN：towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems 28：Annual Conference on Neural Information Processing Systems，2015：91-99.
[17] LIN T，GOYAL P，GIRSHICK R，et al.Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision，2017：2999-3007.
[18] REDMON J，FARHADI A.YOLOv3：an incremental improvement[J].arXiv：1804.02767，2018.
[19] KENI B，RAINER S.Evaluating multiple object tracking performance：the CLEAR MOT metrics[J].EURASIP Journal on Image & Video Processing，2008（1）：246309.