面向路侧视角目标检测的轻量级YOLOv7-R算法

doi:10.19562/j.chinasae.qcgc.2023.10.006

Abstract

Abstract:

A lightweight detection algorithm YOLOV7-R based on the YOLOv7 algorithm is proposed to solve the problems of model deployment difficulty， multi-scale problem of the measured target and occlusion problem between targets in the detection process of the road side sensing unit in V2X. Firstly， the backbone of YOLOv7 is rebuilt using the improved EfficientNetv2-s to reduce the model parameters and improve the model detection speed. Secondly， CA coordinate attention mechanism is adopted to retain accurate location information to enhance the performance of the model for multi-scale targets. At the same time， Focal-EIoU loss function is utilized to enhance the accuracy of the algorithm. Finally， GridMask image enhancement is used in the pre-processing stage to improve the learning ability of the algorithm for the blocked target. The experimental results show that compared with the baseline algorithm YOLOv7， the map@0.5 and map@0.5：0.95 value of the proposed algorithm on the DAIR-V2X-I dataset is increased by 3% and 4.8%， respectively， with the detection rate reaching 96.3 f/s， which can meet the requirements of lightweight and obtain better detection accuracy， and effectively implement the detection task of the road side unit for traffic participants.

Key words: deep learning, roadside perception, YOLOv7, lightweight, attention mechanism, IVICS

Xiaojun Zhang,Jingzhe Xi,Yanlei Shi,Anlu Yuan. Lightweight YOLOv7-R Algorithm for Road-Side View Target Detection[J].Automotive Engineering, 2023, 45(10): 1833-1844.

Figures/Tables 14

模型	EfficientNetv2-e	Coordinate Attention	Focal-EIoULoss	mAP@0.5/%	mAP@0.5：0.95/%	AP_small	AP_medium	P_arams/M	FPS/（ $f · s - 1$ ）
（1）				89.3	59.1	23.7	58.6	36.9	77.3
（2）	√			87.7	56.9	22.9	58.1	17.1	95.6
（3）	√	√		90	59.6	25.3	63.5	17.4	92.5
（4）			√	90.4	62.1	23.8	59	37.2	80.9
本文	√	√	√	92.3	63.9	25.7	64.3	17.6	96.3

模型	mAP@0.5/%	AP_small	P_arams/M	FPS/（ $f · s - 1$ ）
SSD	72.1	18.1	25.0	56.6
EfficientDet	86.3	18.5	18.2	88.5
YOLOv4	86.6	19.4	50.5	55.2
YOLOv5-m	88.0	21.0	18.4	74.0
YOLOv5-s	85.3	19.1	9.5	86.3
YOLOv7	89.3	23.7	36.9	77.3
YOLOX-s	86.1	21.2	10.1	61.0
YOLOv8	90.7	23.7	25.9	79.2
Ours	92.3	25.7	17.6	96.3

References 24

1	GIRSHICK R， DONAHUE J， DARRELL T， et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus， USA， 2014： 580-587.
2	REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once：unified， real-time object detection［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas， USA， 2016： 779-788.
3	LIU W， DRAGOMIR A， DUMITRU E， et al. Ssd： single shot multibox detector［C］. European Conference on Computer Vision. Amsterdam， Netherlands， 2016：21-37.
4	WU T H， WANG T W， LIU Y Q. Real-time vehicle and distance detection based on improved YOLOv5 network［C］. 2021 3rd World Symposium on Artificial Intelligence（WSAI）， Guangzhou， China， 18-20 June 2021：24-28.
5	LIU S S， GENG Y N， SONG Y H， et al. Research on small target pedestrian detection algorithm based on improved YOLOv3［C］.International Conference on Genetic and Evolutionary Computing. Springer， Singapore， 2021： 203-214.
6	ZHOU S Y， YIN J. YOLO-Ship：a visible light ship detection method［C］. Proceedings of the 2022 2nd International Conference on Consumer Electronics and Computer Engineering. Piscataway：IEEE， Guangzhou， China， 2022： 113-118.
7	张舜然. 基于深度学习的路侧视角下多目标检测模型研究［D］. 长春：吉林大学，2022.
	ZHANG S R. Research on multiple object detection model from the roadside perspective based on deep learning［D］. Changchun： Jilin University， 2022.
8	皮任东. 基于路侧激光雷达和摄像头融合的目标轨迹追踪方法研究［D］. 济南：山东大学，2022.
	PI R D. Research on object tracking method based on fusion of roadside LiDAR and camera［D］. Jinan： Shandong University， 2022.
9	TAN M X， LE Q. Efficientnetv2：smaller models and faster training［C］. Proceedings of the 38th International Conference on Machine Learning. Vienna， Austria， 2021：10096-10106.
10	WANG C Y， ALEXEY B， LIAO H Y. YOLOv7：trainable bag-of-freebies sets new state-of-the-art for real-time object detectors［J］. arXiv Preprint arXiv：， 2022.
11	HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition， Salt Lake City， USA， 2018： 7132－7141.
12	HOU Q B， ZHOU D Q， FENG J S. Coordinate attention for efficient mobile network design［J］. arXiv Preprint arXiv： 2103. 02907， 2021.
13	ZHANG Y F， REN W Q， ZHANG Z， et al. Focal and efficient iou loss for accurate bounding box regression ［J］. arXiv Preprint arXiv： 2101. 08158， 2021.
14	ZHANG X D， ZENG H， GUO S， et al. Efficient long-range attention network for image super-resolution ［J］. arXiv Preprint arXiv：， 2022.
15	WANG C Y， BOCHKOVSKIY A， LIAO H Y M. Scaled-YOLOv4： scaling cross stage partial network［C］. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York： IEEE Press， 2021： 13024-13033.
16	DING X H， ZHANG X Y， MA N N， et al. RepVGG： making VGG-style ConvNets great again［C］.2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York： IEEE Press， 2021： 13728-13737.
17	STEFAN E， EIJI U， KENJI D. Sigmoid-weighted linear units for neural network function approximation in reinforcement learning ［J］. arXiv Preprint arXiv：， 2017.
18	MELEKHO V， I，TIULPIN A， SATTLER T，et al. DGC-Net： dense geometric correspondence network［C］. 2019 IEEE Winter Conference on Applications of Computer Vision， Waikoloa Village， Hawaii 2019： 1034-1042.
19	ZHENG Z H. Distance-IoU loss： faster and better learning for bounding box regression［C］. Proceedings of the AAAI Conference on Artificial Intelligence， San Francisco， USA， 2020， 34（7）： 12993-13000.
20	HE K M， GOYAL P， LIN S Y， et al. Focal loss for dense object detection ［J］. arXiv Preprint arXiv：， 2017.
21	CHEN P G， LIU S， ZHAO H S， et al. GridMask data augmentation ［J］. arXiv Preprint arXiv：， 2020.
22	TAN M X， PANG R M， LE Q. EfficientDet： scalable and efficient object detection［C］. IEEE Conference on Computer Vision and Pattern Recognition， Seattle， USA， 2020： 10778-10787.
23	WANG C Y， BOCHKOVSKIY A， LIAO H Y M. YOLOv4： optimal speed and accuracy of object detection［J］. arXiv Preprint arXiv：， 2020.
24	GE Z， LIU S T， WANG F， et al. YOLOX： exceeding YOLO series in 2021［J］. arXiv Preprint arXiv：， 2021.

[1]	ZHOU Wei, ZHANG Cheng-Ning, LI Jun-Qiu. [J]. , 2016, 38(12): 1407 -1414 .
[2]	HAO Han, WANG Si-南, LI Xiao, LIU Zong-Wei, ZHAO Fu-Quan. [J]. , 2017, 39(1): 1 -8 .
[3]	XU Cheng-Shan, JIANG Fa-Chao, SONG Sen-Nan, TIAN Guang-Yu. [J]. , 2017, 39(1): 9 -14 .
[4]	ZENG Bi-Qiang, GAO Ji-Dong, PENG Wei, SUN Zhen-Dong. [J]. , 2016, 38(12): 1446 -1451 .
[5]	WANG Guo-Chun, LI Qi-Qi, DAI Jiang-Lu, CHENG Ai-Guo, LI Tie-Zhu. [J]. , 2017, 39(2): 168 -173 .
[6]	CAO Li-Bo, CHEN Zheng, YAN Ling-Bo, QIN Qin, ZHANG Rui-Feng. [J]. , 2017, 39(2): 225 -231 .
[7]	HONG Qiu-Cai, LIU Wei-Guo, ZHOU Da-Yong. [J]. , 2017, 39(2): 232 -236 .
[8]	XU Feng-Xiang, TIAN Xuan-Yi. [J]. , 2017, 39(2): 237 -242 .
[9]	LI Jun, SU Yan-Zhao, KUI Han-Bing, HU Ming-Hui, ZHANG Sheng-Gen, LIU Heng-Shuo. [J]. , 2017, 39(3): 296 -303 .
[10]	. [J]. , 0, (): 0 .

[1]	Libin Duan,Yu Zhang,Zhanpeng Du,Yegang Liu,Xiangxin Meng,Guannan Tian,Haiyang Zheng,Chuang Wu. Research on Lightweight Design of CTB Battery Pack Cover Assembly Based on VRB/OW-GFRP Hybrid Structure [J]. Automotive Engineering, 2024, 46(2): 290-299.
[2]	Ze Gao, Zunkang Chu, Jiasheng Shi, Fu Lin, Weixiong Rao, Haiyan Yu. Research on Fast Prediction Method of Stress Field of Automotive Parts Based on Graph Network [J]. Automotive Engineering, 2024, 46(1): 170-178.
[3]	Xianguang Gu, Honglin Chen, Luxin Yu, Daisheng Zhang. Integrated Design of Precision Aluminum Castings Parts and Its Application in Lightweight Vehicle Body [J]. Automotive Engineering, 2024, 46(1): 179-186.
[4]	Lei Ma, Shunqing Yang, Huanhuan Wang, Jiachen Zhai, Jianao Xu. Lightweight Object Detection Algorithm Based on Image Saliency Feature Fusion [J]. Automotive Engineering, 2024, 46(1): 84-91.
[5]	Yongtao Li,Chenxu Sun,Weiguang Zheng,Enyong Xu,Yufang Li,Shanchao Wang. Collision Warning Based on Fusion of Millimeter Wave Radar and Vision [J]. Automotive Engineering, 2023, 45(9): 1666-1676.
[6]	Weiguo Liu,Zhiyu Xiang,Rui Liu,Guodong Li,Zixu Wang. Research on End-to-End Vehicle Motion Planning Method Based on Deep Learning [J]. Automotive Engineering, 2023, 45(8): 1343-1352.
[7]	Dongyu Zhao, Shuen Zhao. Autonomous Driving 3D Object Detection Based on Cascade YOLOv7 [J]. Automotive Engineering, 2023, 45(7): 1112-1122.
[8]	Jiahao Zhao,Zhiquan Qi,Zhifeng Qi,Hao Wang,Lei He. Calculation of Heading Angle of Parallel Large Vehicle Based on Tire Feature Points [J]. Automotive Engineering, 2023, 45(6): 1031-1039.
[9]	Xia Zhao,Zhao Li,Rui Fu,Zhenzhen Ge,Chang Wang. Real-Time Detection of Distracted Driving Behavior Based on Deep Convolution-Tokens Dimensionality Reduction Optimized Visual Transformer Model [J]. Automotive Engineering, 2023, 45(6): 974-988.
[10]	Lisheng Jin,Bingdong Ji,Baicang Guo. Driver’s Attention Prediction Based on Multi-Level Temporal-Spatial Fusion Network [J]. Automotive Engineering, 2023, 45(5): 759-767.
[11]	Chunning Jin,Yan Gao,Shizhe Gao,Tianxia Zou,Yang Liu,Zhiheng Zhang. Lightweight Trailer Chassis Based on Roll Punching Integrated Longitudinal Beam [J]. Automotive Engineering, 2023, 45(5): 865-872.
[12]	Yanyan Chen,Hai Wang,Yingfeng Cai,Long Chen,Yicheng Li. Efficient Automatic Driving Instance Segmentation Method Based on Detection [J]. Automotive Engineering, 2023, 45(4): 541-550.
[13]	Yizhe Chen,Hongde Fan,Yichun Wang,Hui Wang,Jun Li,Lin Hua. Research on Stamping Deformation of Automotive Fiber Metal Laminates [J]. Automotive Engineering, 2023, 45(3): 517-526.
[14]	Fengchong Lan,Jikai Chen,Jiqing Chen,Xinping Jiang,Zihan Li,Wei Pan. Research on Lithium Battery Remaining Useful Life Prediction Method Driven by Real Vehicle Data [J]. Automotive Engineering, 2023, 45(2): 175-182.
[15]	Libin Duan,Huajin Zhou,Zhanpeng Du,Yu Zhang,Wei Xu,Xing Liu,Haobin Jiang. Multi Workig Condition Crashworthiness Optimization Design of Body Frame Based on SHCA-T Algorithm [J]. Automotive Engineering, 2023, 45(2): 304-312.

Lightweight YOLOv7-R Algorithm for Road-Side View Target Detection

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 24

Related Articles 15

Metrics

Comments

Recommended 10