An Improved YOLOv5-based Method for Dense Pedestrian Detection Under Complex Road Conditions

doi:10.3969/j.issn.1006-2475.2024.05.015

Abstract

Abstract: Abstract： Aiming at the problem of low pedestrian detection accuracy in complex street scene environment， a new network YOLO-BEN is proposed based on the improvement of YOLOv5 network. The network uses a residual connection module Res2Net with hierarchical system to integrate with C3 module，enhancing fine-grained multi-scale feature representation. The paper adopts the Bi-level routing attention module to construct and prune a region level directed graph， and applies fine-grained attention in the union of routing regions， enabling the network to have dynamic query aware sparsity and improving the feature extraction ability of fuzzy images. We incorporate the EVC module to preserve local corner area information and compensate for the problem of information loss caused by occluded pedestrians. In this paper， NWD metric and original IoU metric are used to form a joint loss function， and a small target detection head is added to improve the effect of long-distance pedestrian detection. In the experiment， the method has achieved good results on self-made data sets and some WiderPerson data sets. Compared with the original network， the accuracy， recall and average accuracy of the improved network are increased by 2.8， 4.3 and 3.9 percentage points respectively.

Key words: Key words： pedestrian detection, multi scale features, double layer routing attention mechanism, angular areal feature, small target detection

CLC Number:

TP391.4

SUN Ruiqi1, DOU Xiuchao2, LI Zhihua1, JIANG Xuemei2, SUN Yuhao1. An Improved YOLOv5-based Method for Dense Pedestrian Detection Under Complex Road Conditions[J]. Computer and Modernization, 2024, 0(05): 85-91.

References

［1］ LI R. Application of deep learning in computer vision［J］. Computer and Network， 2021，47（15）：27-29.
［2］ AHMED Z， INIYAVAN R， MADHAN M P. Enhanced vulnerable pedestrain detection using deep learning［C］// 2019 International Conference on Communication and Signal Processing. IEEE， 2019：971-974.
［3］李晓艳，符惠桐，牛文涛，等. 基于深度学习的多模态行人检测算法［J］. 西安交通大学学报， 2022，56（10）：61-70.
［4］ XU J L ， RAMOS S， VAZQUEZ D， et al. Hierarchical adaptive structural SVM for domain adaptation［J］. International Journal of Computer Vision， 2014，119（2）：159-178.
［5］ WASALA M， KRYJAK T. Real-time HOG+SVM based object detection using SoC FPGA for a UHD video stream［C］// 2022 11th Mediterranean Conference on Embedded Computing. IEEE， 2022. DOI：10.1109/MECO55406.2022.
9797113.
［6］ GE W H， PAN C Y， WU A C， et al. Cross-camera feature prediction for intra-camera supervised person re-identification across distant scenes［C］// Proceedings of the 29th ACM International Conference on Multimedia. ACM，2021. 10.48550/arXiv.2107.13904.
［7］ GHARI B， TOURANI A， SHAHBAHRAMI A. A robust pedestrian detection approach for autonomous vehicles［J］. arXiv preprint arXiv：2210.10489， 2022.
［8］ NGUYEN Q K， NGUYEN T T H， NGUYEN V T K，et al. G-CAME： Gaussian-class activation mapping explainer for object detectors［J］. arXiv preprint arXiv：2306.03400， 2023.
［9］苏松志，李绍滋，陈淑媛，等. 行人检测技术综述［J］. 电子学报， 2012，40（4）：814-820.
［10］ UIJLINGS J R R， VAN DE SANDE K E A， GEVERS T， et al. Selective search for object recognition［J］. International Journal of Computer Vision， 2013，104（2）：154-171.
［11］ GIRSHICK R， DONAHUE J， DARRELL T， et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］// 2014 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2014：580-587.
［12］ GIRSHICK R. Fast R-CNN［C］// 2015 IEEE International Conference on Computer Vision. IEEE， 2015：1440-1448.
［13］ REN S Q， HE K M， GIRSHICK R. Faster R-CNN： Towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017，39（6）：1440-1448.
［14］ REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： Unified， real-time object detection［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2015：779-788.
［15］ REDMON J， FARHADI A. YOLOv3： An incremental improvement［J］. arXiv preprint arXiv：1804.02767， 2018.
［16］ VAN ETTEN A. You only look twice： Rapid multi-scale object detection in satellite imagery［J］. arXiv preprint arXiv：1805.09512， 2018.
［17］曾凯，李响，陈宏君，等. 引入注意力机制的改进型YOLOv5网络研究［J］. 软件工程， 2023，26（1）：55-58.
［18］杨文涛，张维光. 基于改进YOLOv5m的弱小目标识别方法［J］. 计算机测量与控制， 2022，30（12）：218-223.
［19］俞军，贾银山. 改进YOLOv5的小目标检测算法［J］. 计算机工程与应用， 2023，59（12）：201-207.
［20］ ZHAO J Q， ZHANG X H， YAN J W， et al. A wheat spike detection method in UAV images based on improved YOLOv5［J］. Remote Sensing， 2021，13（16）：3095-4001.
［21］ HE K M， ZHANG X Y， REN S Q. Deep residual learning for image recognition［C］// 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2016：770-778.
［22］ GAO S H， CHENG M M， ZHAO K. Res2Net： A new multi-scale backbone architecture［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2019，43（2）：652-662.
［23］毛琳，任凤至，杨大伟，等. 基于卷积神经网络的全景分割Transformer模型［J］. 软件学报， 2023，34（7）：3408-3421.
［24］ ZHU L， WANG X J， KE Z H. BiFormer： Vision transformer with bi-level routing attention［C］// 2023 IEEE Conference on Computer Vision and Pattern Recognition. IEEE， 2023：10323-10333.
［25］ QUAN Y， ZHANG D， ZHANG L Y. Centralized feature pyramid for object detection［J］. arXiv preprint arXiv：2210.02093.
［26］ XU C， WANG J W， YANG W， et al. Detecting tiny objects in aerial images： A normalized Wasserstein distance and a new benchmark［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2022，190（8）：79-93.
［27］ ZHANG S F， XIE Y L， WAN J， et al. WiderPerson： A diverse dataset for dense pedestrian detection in the wild［J］. IEEE Transactions on Multimedia， 2019，22（2）：380-393.