[1]张国印,王传博,高伟.抗遮挡的行人多目标跟踪算法[J].智能系统学报,2024,19(5):1248-1256.[doi:10.11992/tis.202307002]
ZHANG Guoyin,WANG Chuanbo,GAO Wei.Pedestrian multiobject tracking algorithm with anti-occlusion[J].CAAI Transactions on Intelligent Systems,2024,19(5):1248-1256.[doi:10.11992/tis.202307002]
点击复制
ZHANG Guoyin,WANG Chuanbo,GAO Wei.Pedestrian multiobject tracking algorithm with anti-occlusion[J].CAAI Transactions on Intelligent Systems,2024,19(5):1248-1256.[doi:10.11992/tis.202307002]
抗遮挡的行人多目标跟踪算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
19
期数:
2024年第5期
页码:
1248-1256
栏目:
学术论文—智能系统
出版日期:
2024-09-05
- Title:
- Pedestrian multiobject tracking algorithm with anti-occlusion
- Keywords:
- computer vision; pedestrian tracking; target detection; re-identification; association algorithm; anti-occlusion; self-attention; feature extraction
- 分类号:
- TP391
- 文献标志码:
- 2024-08-29
- 摘要:
- 为了解决在复杂场景下行人相互遮挡导致跟踪系统精度降低的问题，提出了基于FairMOT的抗遮挡多目标跟踪算法(multiple obeject tracking algorithm with anti-occlusions, AOMOT)。首先通过轻量化平衡模块，解耦不同层次的语义信息，减少检测任务和重识别任务的语义冲突，降低重识别任务的性能提升对检测任务的影响。其次应用自注意力结构提取行人的外观特征，加强局部窗口下的类内特征的区分度，增强行人身份信息的匹配一致性并减少身份标识的频繁切换。最后优化身份关联算法，挖掘低置信度目标中的被遮挡对象，将其重新纳入目标身份关联并更新其重识别特征。实验结果表明，AOMOT相比原有FairMOT在MOT17数据集中高阶跟踪精度提升1.5百分点，身份F1分数提升3百分点，身份切换数量降低32%。
- Abstract:
- A multiobject tracking algorithm with anti-occlusion (referred to as AOMOT), which is based on the FairMOT framework, is proposed to improve the accuracy of tracking systems in crowded pedestrian scenes. First, the lightweight balance module decouples semantic information at different levels to minimize semantic conflicts between detection and recognition tasks and decrease the impact of performance improvement in re-identification tasks. Second, the self-attention structure is adopted to extract pedestrian appearance features and improve the discrimination of intra-class features under local windows. The matching consistency of pedestrian identity information is enhanced, and frequent switching of identity signs is reduced. Finally, the identity association algorithm is optimized to mine occluded objects in low-confidence targets, reincorporate them into the target identity association, and update their recognition features. Experimental results show that, compared with the original model in the MOT17 dataset, the improved model enhances the higher-order tracking accuracy by 1.5 percentage points, improves identity F1 score by 3 percentage points, and reduces identity switching by 32%.
- 参考文献/References:
-
[1] 魏旋旋, 黄子健, 曹乐, 等. 采用轻量级姿态估计网络的脊柱侧弯筛查方法[J]. 智能系统学报, 2023, 18(5): 1039-1046.
WEI Xuanxuan, HUANG Zijian, CAO Le, et al. Scoliosis screening method using lightweight pose estimation network[J]. CAAI transactions on intelligent systems, 2023, 18(5): 1039-1046.
[2] DAVID R, S?FFKER D. A review on machine learning-based models for lane-changing behavior prediction and recognition[J]. Frontiers in future transportation, 2023, 4: 950429.
[3] 高尚兵, 黄子赫, 耿璇, 等. 视觉协同的违规驾驶行为分析方法[J]. 智能系统学报, 2021, 16(6): 1158-1165.
GAO Shangbing, HUANG Zihe, GENG Xuan, et al. A visual collaborative analysis method for detecting illegal driving behavior[J]. CAAI transactions on intelligent systems, 2021, 16(6): 1158-1165.
[4] 胡硕, 王洁, 孙妍等. 无人机视角下的多车辆跟踪算法研究[J]. 智能系统学报, 2022, 17(4): 798-805.
HU Shuo, WANG Jie, SUN Yan, et al. Research on multi-vehicle tracking algorithm from the perspective of UAV[J]. CAAI transactions on intelligent systems, 2022, 17(4): 798-805.
[5] BASHAR M, ISLAM S, HUSSAIN K K, et al. Multiple object tracking in recent times: a literature review[EB/OL]. (2022-09-11)[2023-07-10]. https://arxiv.org/abs/2209.04796.
[6] ZHOU Xingyi, YIN Tianwei, KOLTUN V, et al. Global tracking transformers[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 8761-8770.
[7] SUN Peize, CAO Jinkun, JIANG Yi, et al. Transtrack: multiple object tracking with transformer[EB/OL]. (2020-12-01)[2023-07-10]. https://arxiv.org/abs/2012.15460.
[8] MEINHARDT T, KIRILLOV A, LEAL-TAIXé L, et al. TrackFormer: multi-object tracking with transformers[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 8834-8844.
[9] WU Jialian, CAO Jiale, SONG Liangchen, et al. Track to detect and segment: an online multi-object tracker[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 12347-12356.
[10] ZHOU Xingyi, KOLTUN V, KR?HENBüHL P. Tracking objects as points[C]//European Conference on Computer Vision. Cham: Springer, 2020: 474-490.
[11] HYUN J, KANG M, WEE D, et al. Detection recovery in online multi-object tracking with sparse graph tracker[C]//2023 IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa: IEEE, 2023: 4839-4848.
[12] ZHANG Yifu, WANG Chunyu, WANG Xinggang, et al. FairMOT: on the fairness of detection and re-identification in multiple object tracking[J]. International journal of computer vision, 2021, 129(11): 3069-3087.
[13] DUAN Kaiwen, BAI Song, XIE Lingxi, et al. CenterNet: keypoint triplets for object detection[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 6568-6577.
[14] WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric[C]//2017 IEEE International Conference on Image Processing. Beijing: IEEE, 2017: 3645-3649.
[15] 王凯, 戴芳, 郭文艳, 等. 融合目标相似性和作用力的多目标跟踪[J]. 中国图象图形学报, 2024, 29(7): 1984-1997.
WANG Kai, DAI Fang, GUO Wenyan, et al. Integrating similarity and interaction force between objects for multiple object tracking[J]. Journal of image and graphics, 2024, 29(7): 1984-1997.
[16] YU En, LI Zhuoling, HAN Shoudong, et al. RelationTrack: relation-aware multiple object tracking with decoupled representation[J]. IEEE transactions on multimedia, 2023, 25: 2686-2697.
[17] 张英俊, 白小辉, 谢斌红. CNN-Transformer特征融合多目标跟踪算法[J]. 计算机工程与应用, 2024, 60(2): 180-190.
ZHANG Yingjun, BAI Xiaohui, XIE Binhong. Multi-object tracking algorithm based on CNN-transformer feature fusion[J]. Computer engineering and applications, 2024, 60(2): 180-190.
[18] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//European conference on computer vision. Cham: Springer, 2018: 3-19.
[19] LIU Ze, LIN Yutong, CAO Yue, et al. Swin transformer: hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2021: 9992-10002.
[20] ZHANG Yifu, SUN Peize, JIANG Yi, et al. ByteTrack: multi-object tracking by associating every detection box[C]//Lecture Notes in Computer Science. Cham: Springer, 2022: 1-21.
[21] LAURA LEAL-TAIXé, MILAN A , REID I , et al. MOTChallenge 2015: towards a benchmark for multi-target tracking[EB/OL]. (2015-04-08) [2023-07-10]. https://arxiv.org/abs/1504.01942.
[22] MILAN A , LEAL-TAIXE L , REID I , et al. MOT16: a benchmark for multi-object tracking[EB/OL]. (2016-03-02)[2023-07-10]. https://arxiv.org/pdf/1603.00831.
[23] LUITEN J, OS?EP A, DENDORFER P, et al. HOTA: a higher order metric for evaluating multi-object tracking[J]. International journal of computer vision, 2021, 129(2): 548-578.
[24] SHAO Shuai, ZHAO Zijian, LI Boxun, et al. Crowdhuman: a benchmark for detecting human in a crowd[EB/OL]. (2018-04-30)[2023-07-10]. https://arxiv.org/abs/1805.00123.
[25] ESS A, LEIBE B, SCHINDLER K, et al. A mobile vision system for robust multi-person tracking[C]//2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008: 1-8.
[26] ZHANG Shanshan, BENENSON R, SCHIELE B. CityPersons: a diverse dataset for pedestrian detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 4457-4465.
[27] DOLLAR P, WOJEK C, SCHIELE B, et al. Pedestrian detection: a benchmark[C]//2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami: IEEE, 2009: 304-311.
[28] XIAO Tong, LI Shuang, WANG Bochao, et al. Joint detection and identification feature learning for person search[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 3376-3385.
[29] ZHENG Liang, ZHANG Hengheng, SUN Shaoyan, et al. Person re-identification in the wild[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 3346-3355.
[30] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//European conference on computer vision. Cham: Springer, 2020: 213-229.
[31] XU Yihong, BAN Yutong, DELORME G, et al. TransCenter: transformers with dense representations for multiple-object tracking[J]. IEEE transactions on pattern analysis and machine intelligence, 2023, 45(6): 7820-7835.
[32] CAI Jiarui, XU Mingze, LI Wei, et al. MeMOT: multi-object tracking with memory[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 8080-8090.
[33] LIANG Chao, ZHANG Zhipeng, ZHOU Xue, et al. Rethinking the competition between detection and ReID in multiobject tracking[J]. IEEE transactions on image processing, 2022, 31: 3182-3196.
- 相似文献/References:
-
[1]夏 凡,王 宏.基于局部异常行为检测的欺骗识别研究[J].智能系统学报,2007,2(5):12.
XIA Fan,WANG Hong.Methodologies for deception detection based on abnormal b ehavior[J].CAAI Transactions on Intelligent Systems,2007,2():12.
[2]杨 戈,刘 宏.视觉跟踪算法综述[J].智能系统学报,2010,5(2):95.
YANG Ge,LIU Hong.Survey of visual tracking algorithms[J].CAAI Transactions on Intelligent Systems,2010,5():95.
[3]刘宏,李哲媛,许超.视错觉现象的分类和研究进展[J].智能系统学报,2011,6(1):1.
LIU Hong,LI Zheyuan,XU Chao.The categories and research advances of visual illusions[J].CAAI Transactions on Intelligent Systems,2011,6():1.
[4]叶果,程洪,赵洋.电影中吸烟活动识别[J].智能系统学报,2011,6(5):440.
YE Guo,CHENG Hong,ZHAO Yang.moking recognition in movies[J].CAAI Transactions on Intelligent Systems,2011,6():440.
[5]史晓鹏,何为,韩力群.采用Hough变换的道路边界检测算法[J].智能系统学报,2012,7(1):81.
SHI Xiaopeng,HE Wei,HAN Liqun.A road edge detection algorithm based on the Hough transform[J].CAAI Transactions on Intelligent Systems,2012,7():81.
[6]顾照鹏,刘宏.单目视觉同步定位与地图创建方法综述[J].智能系统学报,2015,10(4):499.[doi:10.3969/j.issn.1673-4785.201503003]
GU Zhaopeng,LIU Hong.A survey of monocular simultaneous localization and mapping[J].CAAI Transactions on Intelligent Systems,2015,10():499.[doi:10.3969/j.issn.1673-4785.201503003]
[7]赵军,於俊,汪增福.基于改进逆向运动学的人体运动跟踪[J].智能系统学报,2015,10(4):548.[doi:10.3969/j.issn.1673-4785.201403032]
ZHAO Jun,YU Jun,WANG Zengfu.Human motion tracking based on an improved inverse kinematics[J].CAAI Transactions on Intelligent Systems,2015,10():548.[doi:10.3969/j.issn.1673-4785.201403032]
[8]姬晓飞,王昌汇,王扬扬.分层结构的双人交互行为识别方法[J].智能系统学报,2015,10(6):893.[doi:10.11992/tis.201505006]
JI Xiaofei,WANG Changhui,WANG Yangyang.Human interaction behavior-recognition method based on hierarchical structure[J].CAAI Transactions on Intelligent Systems,2015,10():893.[doi:10.11992/tis.201505006]
[9]方鹏,李贤,汪增福.运用核聚类和偏最小二乘回归的歌唱声音转换[J].智能系统学报,2016,11(1):55.[doi:10.11992/tis.201506022]
FANG Peng,LI Xian,WANG Zengfu.Conversion of singing voice based on kernel clustering and partial least squares regression[J].CAAI Transactions on Intelligent Systems,2016,11():55.[doi:10.11992/tis.201506022]
[10]刘翠君,赵才荣,苗夺谦,等.粒化的Mean Shift行人跟踪算法[J].智能系统学报,2016,11(4):433.[doi:10.11992/tis.201605033]
LIU Cuijun,ZHAO Cairong,MIAO Duoqian,et al.Granular mean shift pedestrian tracking algorithm[J].CAAI Transactions on Intelligent Systems,2016,11():433.[doi:10.11992/tis.201605033]
备注/Memo
收稿日期:2023-7-10。
作者简介:张国印，教授，博士生导师，博士，主要研究方向为智能感知与决策。主持国家自然科学基金等各类科研项目20余项，发表学术论文100余篇。E-mail：zhangguoyin@hrbeu.edu.cn;王传博，硕士研究生，主要研究方向为计算机视觉。E-mail：694882809@qq.com;高伟，副教授，博士，中国计算机学会会员、中国计算机学会黑龙江省计算机网络专委会委员。主要研究方向为计算机网络、数据库和信息安全，发表学术论文30余篇。E-mail：gaowei@hrbeu.edu.cn。
通讯作者:高伟. E-mail：gaowei@hrbeu.edu.cn
更新日期/Last Update:
2024-09-05