基于改进YOLOv5的道路车辆跟踪算法

doi:10.16088/j.issn.1001-6600.2021081303

摘要/Abstract

摘要： 针对现有多目标跟踪算法参数量和计算量大,难以满足移动设备实时性要求的问题,本文通过改进JDE跟踪算法,提出了一种道路车辆多目标跟踪算法。首先,设计关联融合网络来解决JDE算法中多任务学习存在的竞争问题,提高算法的跟踪精度,减少身份切换次数;其次,使用改进的EfficientNetv2重新构建YOLOv5的特征提取网络,降低模型复杂度,提高模型实时检测速度;最后,使用改进的YOLOv5检测算法与JDE跟踪算法结合,实现道路车辆多目标跟踪。实验结果表明,提出的方法相比原JDE跟踪算法,MOTA提高0.3个百分点、跟踪速度提高约43.2%,可以满足实际自动驾驶场景中对车辆跟踪的速度要求。

关键词: 车辆跟踪, EfficientNet, 通道注意力, 关联融合网络, YOLOv5

Abstract: To solve the problem that it's difficult for the large amount of network parameters and calculations for existing multi-object tracking algorithm to meet the real-time requirements of mobile devices, a road vehicle multi-object tracking algorithm is proposed by improving the JDE tracking algorithm. Firstly, in order to improve the tracking accuracy of the algorithm and reduce the number of ID switching, the association fusion network is used to solve the competition problem of multi-task learning in the JDE algorithm. Secondly, in order to reduce the complexity of the model and improve the real-time detection speed of the model, the improved EfficientNetV2 is used to rebuild the feature extraction network in YOLOv5. Finally, the improved YOLOv5 detection algorithm is combined with the JDE tracking algorithm to achieve multi-object tracking of road vehicles. The experimental results show that compared with the original JDE tracking algorithm, the proposed method improves MOTA by 0.3percentage point and tracking speed by about 43.2%. It can meet the speed requirements for vehicle tracking in actual autonomous driving scenarios.

Key words: vehicle tracking, EfficientNet, channel attention, associative fusion network, YOLOv5

中图分类号:

TP391.41

张文龙, 南新元. 基于改进YOLOv5的道路车辆跟踪算法[J]. 广西师范大学学报（自然科学版）, 2022, 40(2): 49-57.

ZHANG Wenlong, NAN Xinyuan. Road Vehicle Tracking Algorithm Based on Improved YOLOv5[J]. Journal of Guangxi Normal University(Natural Science Edition), 2022, 40(2): 49-57.

参考文献

[1] 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. DOI: 10.3788/YJYXS20193401.0098.
[2] 张灿龙, 苏建才, 李志欣, 等. 基于AdaBoost置信图的红外与可见光目标跟踪[J]. 广西师范大学学报(自然科学版), 2018, 36(4): 42-50. DOI: 10.16088/j.issn.1001-6600.2018.04.006.
[3] 张灿龙, 李燕茹, 李志欣, 等. 基于核相关滤波与特征融合的分块跟踪算法[J]. 广西师范大学学报(自然科学版), 2020, 38(5): 12-23. DOI: 10.16088/j.issn.1001-6600.2020.05.002.
[4] 黄一凡, 杨建业, 戚国庆. 基于二自由度转台的双目视觉跟踪技术研究[J]. 电子设计工程, 2018, 26(14):181-185. DOI: 10.14022/j.cnki.dzsjgc.2018.14.039.
[5] 冯霞, 杜佳浩, 段仪浓, 等. 基于深度学习的行人重识别研究综述[J]. 计算机应用研究, 2020, 37(11): 3220-3226, 3240. DOI: 10.19734/j.issn.1001-3695.2019.09.0514.
[6] 尹梓睿, 张索非, 张磊, 等. 适于行人重识别的二分支EfficientNet网络设计[J]. 信号处理, 2020, 36(9): 1481-1488. DOI: 10.16798/j.issn.1003-0530.2020.09.013.
[7] WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric[C]// 2017 IEEE International Conference on Image Processing (ICIP). Piscataway, NJ: IEEE Press, 2017: 3645-3649. DOI: 10.1109/ICIP.2017.8296962.
[8] ZHOU Z W, XING J L, ZHANG M D, et al. Online multi-target tracking with tensor-based high-order graph matching[C]// 2018 24th International Conference on Pattern Recognition(ICPR). Piscataway, NJ: IEEE Press, 2018: 1809-1814. DOI: 10.1109/ICPR.2018.8545450.
[9] WANG Z D, ZHENG L, LIU Y X, et al. Towards real-time multi-object tracking[EB/OL]. (2020-07-14)[2021-08-13]. https://arxiv.org/abs/1909.12605.
[10] REDMON J, FARHADI A. YOLOv3: An incremental improvement[EB/OL]. (2018-04-08)[2021-08-13]. https://arxiv.org/abs/1804.02767v1.
[11] ZHANG Y F, WANG C Y, WANG X G, 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. DOI: 10.1007/s11263-021-01513-4.
[12] YU F, WANG D Q, SHELHAMER E, et al. Deep layer aggregation[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos, CA: IEEE Computer Society, 2018: 2403-2412. DOI: 10.1109/CVPR.2018.00255.
[13] ZHOU X Y, WANG D Q, KRÄHENBÜHL P. Objects as points[EB/OL]. (2019-04-25)[2021-08-13]. https://arxiv.org/abs/1904.07850.
[14] 晏康, 曾凤彩, 何宁, 等. 引入注意力机制的JDE多目标跟踪方法[J/OL]. 计算机工程与应用, 2021[2021-08-13]. http://kns.cnki.net/kcms/detail/11.2127.TP.20210524.0920.004.html. DOI: 10.3778/j.issn.1002-8331.2104-0049.
[15] 薛俊韬, 马若寒, 胡超芳. 基于MobileNet的多目标跟踪深度学习算法[J]. 控制与决策, 2021, 36(8): 1991-1996. DOI: 10.13195/j.kzyjc.2019.1424.
[16] SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos, CA: IEEE Computer Society, 2018: 4510-4520. DOI: 10.1109/CVPR.2018.00474.
[17] 马永杰, 马芸婷, 程时升, 等. 基于改进YOLO v3模型与Deep-SORT算法的道路车辆检测方法[J]. 交通运输工程学报, 2021, 21(2): 222-231. DOI: 10.19818/j.cnki.1671-1637.2021.02.019.
[18] HU J, SHEN L, AIBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(8): 2011-2023. DOI: 10.1109/TPAMI.2019.2913372.
[19] WANG Q L, WU B G, ZHU P F, et al. ECA-Net: efficient channel attention for deep convolutional neural networks[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2020: 11531-11539. DOI: 10.1109/CVPR42600.2020.01155.
[20] QIN Z Q, ZHANG P Y, WU F, et al. FCANet: frequency channel attention networks[EB/OL]. (2021-07-23)[2021-08-13]. https://arxiv.org/abs/2012.11879.
[21] WOO S H, PARK J C, LEE J Y, et al. CBAM: convolutional block attention module[C]// Computer Vision-ECCV 2018: LNCS volume 11211. Cham: Springer Nature Switzerland AG, 2018: 3-19. DOI: 10.1007/978-3-030-01234-2_1.
[22] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2017: 936-944. DOI: 10.1109/CVPR.2017.106.
[23] TAN M X, LE Q V. EfficientNetV2: smaller models and faster training[EB/OL]. (2021-06-23)[2021-08-13]. https://arxiv.org/abs/2104.00298.
[24] FU J, LIU J, TIAN H J, et al. Dual attention network for scene segmentation[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Los Alamitos, CA: IEEE Computer Society, 2019: 3141-3149. DOI: 10.1109/CVPR.2019.00326.
[25] XU D,OUYANG W L, WANG X G, et al. PAD-Net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos, CA: IEEE Computer Society, 2018: 675-684. DOI: 10.1109/CVPR.2018.00077.
[26] LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Los Alamitos, CA: IEEE Computer Society, 2018: 8759-8768. DOI: 10.1109/CVPR.2018.00913.

相关文章 15

[1]	万黎明, 张小乾, 刘知贵, 宋林, 周莹, 李理. 基于高效通道注意力的UNet肺结节CT图像分割[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 66-75.
[2]	张萍, 徐巧枝. 基于多感受野与分组混合注意力机制的肺结节分割研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 76-87.
[3]	李永杰, 周桂红, 刘博. 基于YOLOv3模型的人脸检测与头部姿态估计融合算法[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 95-103.
[4]	马铖旭, 曾上游, 赵俊博, 陈红阳. 基于卷积神经网络的逆光图像增强研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(2): 81-90.
[5]	陈文康, 陆声链, 刘冰浩, 李帼, 刘晓宇, 陈明. 基于改进YOLOv4的果园柑橘检测方法研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(5): 134-146.
[6]	张伟彬, 吴军, 易见兵. 基于RFB网络的特征融合管制物品检测算法研究[J]. 广西师范大学学报（自然科学版）, 2021, 39(4): 34-46.
[7]	张灿龙, 李燕茹, 李志欣, 王智文. 基于核相关滤波与特征融合的分块跟踪算法[J]. 广西师范大学学报（自然科学版）, 2020, 38(5): 12-23.
[8]	肖逸群, 宋树祥, 夏海英. 基于多特征的快速行人检测方法及实现[J]. 广西师范大学学报（自然科学版）, 2019, 37(4): 61-67.
[9]	王勋, 李廷会, 潘骁, 田宇. 基于改进模糊C均值聚类与Otsu的图像分割方法[J]. 广西师范大学学报（自然科学版）, 2019, 37(4): 68-73.
[10]	蔡冰, 张灿龙, 李志欣. 基于联合直方图的红外与可见光目标融合跟踪[J]. 广西师范大学学报（自然科学版）, 2017, 35(3): 37-44.
[11]	何鹏, 刘高凯, 李静辉. 基于机器视觉的疲劳驾驶监测预警系统[J]. 广西师范大学学报（自然科学版）, 2015, 33(4): 25-29.
[12]	王冬旭, 宋树祥, 蒋品群. 基于BP神经网络的竹片正反面识别算法[J]. 广西师范大学学报（自然科学版）, 2014, 32(2): 14-19.
[13]	马先兵, 孙水发, 覃音诗, 郭青, 夏平. 基于粒子滤波的on-line boosting目标跟踪算法[J]. 广西师范大学学报（自然科学版）, 2013, 31(3): 100-105.
[14]	孙水发, 李乐鹏, 董方敏, 邹耀斌, 陈鹏. 基于迭代阈值的子块部分重叠双直方图均衡算法[J]. 广西师范大学学报（自然科学版）, 2013, 31(3): 119-126.
[15]	唐振军, 戴玉敏, 张显全, 张师超. 基于DCT特征点的感知图像Hash函数[J]. 广西师范大学学报（自然科学版）, 2012, 30(3): 135-141.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed