Aggregation Pedestrian Detection Model Based on Improved YOLOv8

doi:10.19678/j.issn.1000-3428.0069026

Abstract

Abstract:

Pedestrian detection in crowded scenes is a key technology in intelligent monitoring of public space. It enables the intelligent monitoring of crowds, using object detection methods to detect the positions and number of pedestrians in videos. This paper presents Crowd-YOLOv8, an improved version of the YOLOv8 detection model, to address the issue of pedestrians being easily missed owing to occlusion and small target size in densely populated areas. First, nostride-Conv-SPD is introduced into the backbone network to enhance its capability of extracting fine-grained information, such as small object features in images. Second, small object detection heads and the CARAFE upsampling operator are introduced into the neck part of the YOLOv8 network to fuse features at different scales and improve the detection performance in the case of small targets. Experimental results demonstrate that the proposed method achieves an mAP@0.5 of 84.3% and an mAP@0.5∶0.95 of 58.2% on a CrowdedHuman dataset, which is an improvement of 3.7 and 5.2 percentage points, respectively, compared to those of the original YOLOv8n. On the WiderPerson dataset, the proposed method achieves an mAP@0.5 of 88.4% and an mAP@0.5∶0.95 of 67.4%, which is an improvement of 1.1 and 1.5 percentage points compared to those of the original YOLOv8n.

Key words: aggregation pedestrian detection, YOLOv8 network, nostride-Conv-SPD module, CARAFE operator, small object detection head

摘要：

密集行人检测是公共智能监控的关键技术, 其采用目标检测方法对视频中的行人位置和数量进行检测, 进而实现对视频中人群的智能监控。在人员密集场景下因遮挡和行人的目标太小造成漏检。为此, 提出一种改进YOLOv8检测模型Crowd-YOLOv8。首先, 在主干网络使用nostride-Conv-SPD模块, 增强对图像小目标特征等细粒度信息的提取能力; 其次, 在YOLOv8网络的颈部引入小目标检测头和CARAFE上采样算子对各尺度特征进行融合, 以提高在小目标情况下的检测效果。实验结果表明, 所提模型在CrowdHuman数据集上mAP@0.5和mAP@0.5∶0.95分别取得了84.3%和58.2%的检测效果, 与原YOLOv8n相比分别提高了3.7和5.2百分点; 在WiderPerson数据集上取得了88.4%和67.4%, 与原YOLOv8n相比提高了1.1和1.5百分点。

关键词: 密集行人检测, YOLOv8网络, nostride-Conv-SPD模块, CARAFE算子, 小目标检测头

HUANG Kun, QI Zhaojian, WANG Juanmin, HU Qian, HU Weichao, PI Jianyong. Aggregation Pedestrian Detection Model Based on Improved YOLOv8[J]. Computer Engineering, 2025, 51(5): 133-142.

黄昆, 齐肇建, 王娟敏, 胡倩, 胡伟超, 皮建勇. 基于改进YOLOv8的密集行人检测模型[J]. 计算机工程, 2025, 51(5): 133-142.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069026

https://www.ecice06.com/EN/Y2025/V51/I5/133

Figures/Tables 13

Fig.1 Structure of YOLOv8n network

Fig.2 The structure of nostride-Conv-SPD module

Fig.3 The structure of small object detection head

Fig.4 The structure of CARAFE

Fig.5 The CrowdHuman dataset

Fig.6 The WiderPerson dataset

Fig.7 Comparison of detection performance of each model on CrowdHuman dataset

Fig.8 Comparison of detection performance of each model on WiderPerson dataset

Fig.9 Comparison of detection performance between original YOLOv8n and Crowd-YOLOv8

References 32

1	齐鹏宇, 王洪元, 张继, 等. 基于改进FCOS的拥挤行人检测算法. 智能系统学报, 2021, 16 (4): 811- 818.
	QI P Y , WANG H Y , ZHANG J , et al. Crowded pedestrian detection algorithm based on improved FCOS. Journal of Intelligent Systems, 2021, 16 (4): 811- 818.
2	罗艳, 张重阳, 田永鸿, 等. 深度学习行人检测方法综述. 中国图象图形学报, 2022, 27 (7): 2094- 2111.
	LUO Y , ZHANG C Y , TIAN Y H , et al. An overview of deep learning based pedestrian detection algorithms. Journal of Image and Graphics, 2022, 27 (7): 2094- 2111.
3	陈宁, 李梦璐, 袁皓, 等. 遮挡情形下的行人检测方法综述. 计算机工程与应用, 2020, 56 (16): 13- 20.
	CHEN N , LI M L , YUAN H , et al. Review of pedestrian detection with occlusion. Journal of Computer Engineering and Applications, 2020, 56 (16): 13- 20.
4	DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2005: 886-893.
5	田仙仙, 鲍泓, 徐成. 一种改进HOG特征的行人检测算法. 计算机科学, 2014, 41 (9): 320- 324.
	TIAN X X , BAO H , XU C . Improved HOG algorithm of pedestrian detection. Computer Science, 2014, 41 (9): 320- 324.
6	REN S Q , HE K M , GIRSHICK R , et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
7	DANELLJAN M, ROBINSON A, KHAN F S, et al. Beyond correlation filters: learning continuous convolution operators for visual tracking[C]//Proceedings of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 472-488.
8	HE K M, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 2961-2969.
9	郑华伟, 王飞, 高建邦. DES-YOLO: 一种更精确的目标检测方法. 光电工程, 2024, 51 (11): 240212.
	ZHENG H W , WANG F , GAO J B . DES-YOLO: a more accurate object detection method. Opto-Electronic Engineering, 2024, 51 (11): 240212.
10	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2017: 2081-2086.
11	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[EB/OL]. [2023-11-08]. https://link.springer.com/content/pdf/10.1007/978-3-319-46448-0_2.pdf.
12	邓杰, 万旺根. 基于改进YOLOv3的密集行人检测. 电子测量技术, 2021, 44 (11): 99- 95.
	DENG J , WANG W G . Dense pedestrian detection based on improved YOLOv3. Electronic Measurement Technology, 2021, 44 (11): 99- 95.
13	TERVEN J, CORDOVA-ESPARZA D. A comprehensive review of YOLO: from YOLOv1 to YOLOv8 and beyond[EB/OL]. [2023-11-08]. https://arXiv preprint arXiv: 2304.00501, 2023.
14	JOCHER G, CHAURASIA A, QIU J. YOLO by ultralytics[EB/OL]. [2023-11-08]. https://github.com/ultralytics/ultralytics.
15	娄翔飞, 吕文涛, 叶冬, 等. 基于计算机视觉的行人检测方法研究进展. 浙江理工大学学报(自然科学), 2023, 49 (3): 318- 330.
	LOU X F , LU W T , YE D , et al. Research progress on pedestrian detection methods based on computer vision. Journal of Zhejiang Sci-Tech University (Natural Science), 2023, 49 (3): 318- 330.
16	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. Washington D. C., USA: IEEE Press, 2016: 779-788.
17	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2023-11-08]. https://arxiv.org/pdf/1804.02767.
18	JOCHER G, STOKEN A, BOROVEC J, et al. ultralytics/yolov5: v3.1-bug fixes and performance improvements[EB/OL]. [2023-11-08]. https://www.semanticscholar.org/paper/ultralytics-yolov5%3A-v3.1-Bug-Fixes-and-Performance-Jocher-Stoken/c12d7dcd6d13f0187dc7922b4ce97d31e4d00f60.
19	WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 7464-7475.
20	SUNKARA R, LUO T. No more strided convolutions or pooling: a new CNN building block for low-resolution images and small objects[C]//Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin, Germany: Springer, 2022: 443-459.
21	WANG J Q, CHEN K, XU R, et al. CARAFE: content-aware reassembly of features[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2019: 3007-3016.
22	SHAO S, ZHAO Z J, LI B X, et al. CrowdHuman: a benchmark for detecting human in a crowd[EB/OL]. [2023-11-08]. https://arxiv.org/pdf/1805.00123.
23	ZHANG S , XIE Y , WAN J , et al. WiderPerson: a diverse dataset for dense pedestrian detection in the wild. IEEE Transactions on Multimedia, 2020, 22 (2): 380- 393. URL
24	YANG G, LEI J, ZHU Z, et al. AFPN: asymptotic feature pyramid network for object detection[C]//Proceedings of IEEE International Conference on Systems, Man, and Cybernetics. Washington D. C., USA: IEEE Press, 2023: 2184-2189.
25	LI J, WEN Y, HE L. SCConv: spatial and channel reconstruction convolution for feature redundancy[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 6153-6162.
26	ZHU X Z, HU H, LIN S, et al. Deformable ConvNetsV2: more deformable, better results[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2019: 9308-9316.
27	HUANG H, ZHOU X, CAO J, et al. Vision Transformer with super token sampling[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 22690-22699.
28	HOWARD A, SANDLER M, CHEN B, et al. Searching for MobileNetV3[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2019: 1314-1324.
29	MEHTA S, RASTEGARI M. MobileViT: light-weight, general-purpose, and mobile-friendly vision Transformer[EB/OL]. [2023-11-08]. https://arxiv.org/abs/2110.02178?context=cs.
30	ZHOU D Q, HOU Q B, CHEN Y P, et al. Rethinking bottleneck structure for efficient mobile network design[C]//Proceedings of the 16th European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 680-697.
31	DAI J F, QI H Z, XIONG Y W, et al. Deformable convolutional networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 764-773.
32	ZHANG X, SONG Y, SONG T, et al. AKConv: convolutional kernel with arbitrary sampled shapes and arbitrary number of parameters[EB/OL]. [2023-11-08]. http://arXiv preprint arXiv: 2311.11587.

[1]	ZHAO Nannan, GAO Feichen. Improved YOLOv8-based Algorithm for Instance Segmentation in Traffic Scenes [J]. Computer Engineering, 2025, 51(1): 198-207.
[2]	YANG Yudi, GE Haibo, XIN Shiao, XUE Zihan, YUAN Hao. Lightweight Small-Object Detection for Remote Sensing Images Integrating Super-Resolution and Feature Enhancement [J]. Computer Engineering, 2024, 50(11): 284-296.

Please choose a citation manager

Content to export