基于YOLOv7-Tiny的密集行人检测模型

赵世礼; 莫红; 杨澳男; 欧阳玉琦

doi:10.11959/j.issn.2096-6652.202526

您当前的位置：

首页 >

文章列表页 >

基于YOLOv7-Tiny的密集行人检测模型

学术论文 | 更新时间：2025-11-18

- 基于YOLOv7-Tiny的密集行人检测模型
- Dense pedestrian detection model based on improved YOLOv7-Tiny
- 智能科学与技术学报 2025年7卷第3期页码：350-360
- 作者机构：
  
  长沙理工大学电气与信息工程学院，湖南长沙 410114
- 作者简介：
  
  [ "赵世礼（2000- ），男，长沙理工大学电气与信息工程学院硕士生，主要研究方向为数字图像与机器视觉。" ]
  [ "莫红（1972- ），女，长沙理工大学电气与信息工程学院教授，主要研究方向为智慧医疗、模糊AI和复杂系统管理与控制。" ]
  [ "杨澳男（2000- ），男，长沙理工大学电气与信息工程学院硕士生，主要研究方向为数字图像与机器视觉。" ]
  [ "欧阳玉琦（2000- ），男，长沙理工大学电气与信息工程学院硕士生，主要研究方向为数字图像与机器视觉。" ]
- 基金信息：
- DOI：10.11959/j.issn.2096-6652.202526
  中图分类号： TP391.4
- 收稿：2025-05-12，
  
  修回：2025-06-02，
  
  纸质出版：2025-09-15
- 稿件说明：
移动端阅览
赵世礼,莫红,杨澳男等.基于YOLOv7-Tiny的密集行人检测模型[J].智能科学与技术学报,2025,07(03):350-360.

ZHAO Shili,MO Hong,YANG Aonan,et al.Dense pedestrian detection model based on improved YOLOv7-Tiny[J].Chinese Journal of Intelligent Science and Technology,2025,07(03):350-360.
赵世礼,莫红,杨澳男等.基于YOLOv7-Tiny的密集行人检测模型[J].智能科学与技术学报,2025,07(03):350-360. DOI： 10.11959/j.issn.2096-6652.202526.

ZHAO Shili,MO Hong,YANG Aonan,et al.Dense pedestrian detection model based on improved YOLOv7-Tiny[J].Chinese Journal of Intelligent Science and Technology,2025,07(03):350-360. DOI： 10.11959/j.issn.2096-6652.202526.

摘要

针对现有密集行人检测模型的参数量大及精度低的问题，提出了一种基于YOLOv7-Tiny的跨级优化YOLOv7（you only look once version 7-tiny partial minimum cross，YOLOv7-TPMC）模型。首先，提出了结合部分卷积（partial convolution，PConv）与逐点卷积（pointwise convolution，PWConv）的部分点卷积高效层聚合网络（efficient layer aggregation networks-partial and pointwise，ELAN-PP）模块。其次，设计了一种跨级融合特征金字塔结构，通过浅层特征复用提升密集场景下行人检测的准确性。最后，为解决完整交并比（complete intersection over union，CIOU）损失函数在某些条件下定位不准确的问题，引入了最小焦点距交并比（minimum point distance and focaler-intersection over union，MF-IOU）损失函数。在WiderPerson和CrowdHuman数据集上进行实验，YOLOv7-TPMC相比于基准模型，参数量减少了20.5%，帧率（frame per second，FPS）提升了12.2%，mAP@0.5的值在WiderPerson数据集上增加了1.2%，在CrowdHuman数据集上增加了2.0%，能够较好地应用于密集行人检测。

Abstract

In response to the issues of large parameter quantity and low accuracy in the existing dense pedestrian detection models

YOLOv7-TPMC (you only look once version 7-tiny partial minimum cross) based on YOLOv7-Tiny was proposed. Firstly

the ELAN-PP (efficient layer aggregation networks-partial and pointwise) module combining PConv (partial convolution) and PWConv (pointwise convolution) was proposed. Secondly

a cross-level fusion feature pyramid structure was designed to improve the accuracy of pedestrian detection in dense scenes through shallow feature reuse. Finally

in order to solve the problem that the CIOU (complete intersection over union) loss function was not accurate in positioning under certain conditions

the MF-IOU (minimum point distance and focaler-intersection over union) loss function was introduced. Experiments were carried out on the WiderPerson and CrowdHuman datasets. Compared with the baseline model

YOLOv7-TPMC had the number of parameters reduced by 20.5%

FPS (frame per second) improved by 12.2%

and the value of mAP@0.5 increased by 1.2% on the WiderPerson dataset. It increased by 2.0% on the CrowdHuman dataset

which can be well applied to dense pedestrian detection.

关键词

Keywords

references

ZOU Z X, CHEN K Y, SHI Z W, et al. Object detection in 20 years: a survey[J]. Proceedings of the IEEE, 2023, 111(3): 257-276.

章博闻. 基于深度学习的有锚框行人检测方法综述[J]. 传感器世界, 2024, 30(1): 7-12.

ZHANG B W. A review of anchor-based pedestrian detection methods based on deep learning[J]. Sensor World, 2024, 30(1): 7-12.

HARRIS C, STEPHENS M. A combined corner and edge detector[C]//Proceedings of the Alvey Vision Conference 1988. Alvey Vision Club. United Kingdom: The Plessey Company, 1988: 147-152.

LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). Piscataway: IEEE Press, 2005: 886-893.

BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3): 346-359.

AKYON F C, ONUR ALTINUC S, TEMIZEL A. Slicing aided hyper inference and fine-tuning for small object detection[C]//Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP). Piscataway: IEEE Press, 2022: 966-970.

李欣健, 张大胜, 孙利雷, 等. 复杂场景下基于CNN的轻量火焰检测方法[J]. 模式识别与人工智能, 2021, 34(5): 415-422.

LI X J, ZHANG D S, SUN L L, et al. CNN-based lightweight flame detection method in complex scenes[J]. Pattern Recognition and Artificial Intelligence, 2021, 34(5): 415-422.

LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Computer Vision-ECCV 2016: Proceedings of the 14th European Conference on Computer Vision. Berlin: Springer, 2016: 21-37.

苑朝, 赵亚冬, 张耀, 等. 基于YOLO轻量化的多模态行人检测算法[J]. 图学学报, 2024, 45(1): 35-46.

YUAN C, ZHAO Y D, ZHANG Y, et al. Lightweight multi-modal pedestrian detection algorithm based on YOLO[J]. Journal of Graphics, 2024, 45(1): 35-46.

HAN K, WANG Y H, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 1577-1586.

MA N N, ZHANG X Y, ZHENG H T, et al. ShuffleNet V2: practical guidelines for efficient CNN architecture design[C]//Proceedings of the European Conference on Computer Vision. Berlin: Springer, 2018: 122-138.

史健婷, 张贵强, 陶金, 等. 改进的YOLOv4红外图像行人检测算法[J]. 智能计算机与应用, 2021, 11(8): 31-34, 41.

SHI J T, ZHANG G Q, TAO J, et al. Pedestrian detection algorithm in infrared image based on improved YOLOv4[J]. Intelligent Computer and Applications, 2021, 11(8): 31-34, 41.

高正中, 于明沆, 孟晗, 等. 基于改进YOLOv5算法的红外图像行人目标检测[J]. 中国科技论文, 2024, 19(2): 209-214.

GAO Z Z, YU M H, MENG H, et al. Improved YOLOv5-based infrared pedestrian target detection[J]. China Sciencepaper, 2024, 19(2): 209-214.

ZHU X K, LYU S C, WANG X, et al. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Piscataway: IEEE Press, 2021: 2778-2788.

WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2023: 7464-7475.

杨慧聪, 陈慈发, 张上. 基于通道剪枝的YOLOv8n印刷电路板缺陷检测[J]. 无线电工程, 2025, 55(2): 271-280.

YANG H C, CHEN C F, ZHANG S. PCB defect detection using YOLOv8n based on channel pruning[J]. Radio Engineering, 2025, 55(2): 271-280.

涂智荣, 凌海英, 李帼, 等. 基于改进YOLOv7-Tiny的轻量化百香果检测方法[J]. 广西师范大学学报(自然科学版), 2024, 42(5): 79-90.

TU Z R, LING H Y, LI G, et al. Lightweight passion fruit detection method based on improved YOLOv7-tiny[J]. Journal of Guangxi Normal University (Natural Science Edition), 2024, 42(5): 79-90.

MA L, ZHAO L Y, WANG Z X, et al. Detection and counting of small target apples under complicated environments by using improved YOLOv7-tiny[J]. Agronomy, 2023, 13(5): 1419.

CHEN J R, KAO S H, HE H, et al. Run, don't walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2023: 12021-12031.

LIU S, QI L, QIN H F, et al. Path aggregation network for instance segmentation[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2018: 8759-8768.

TAN M X, PANG R M, LE Q V. EfficientDet: scalable and efficient object detection[C]//Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 10781-10790.

YANG G Y, LEI J, ZHU Z K, et al. AFPN: asymptotic feature pyramid network for object detection[C]//Proceedings of the 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Piscataway: IEEE Press, 2023: 2184-2189.

WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the 15th European Conference on Computer Vision (ECCV). Berlin: Springer, 2018: 3-19.

方祯祺, 李雪, 莫红. 基于改进EfficientNet的乳腺肿瘤诊断[J]. 智能科学与技术学报, 2023, 5(4): 505-514.

FANG Z Q, LI X, MO H. Diagnostic of breast tumors based on improved EfficientNet[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(4): 505-514.

XU S B, ZHANG M H, SONG W, et al. A systematic review and analysis of deep learning-based underwater object detection[J]. Neurocomputing, 2023, 527: 204-232.

OU J Y, SHEN Y J. Underwater target detection based on improved YOLOv7 algorithm with BiFusion neck structure and MPDIoU loss function[J]. IEEE Access, 2024, 12: 105165-105177.

ZHANG H, ZHANG S J. Focaler-IoU: more focused intersection over union loss[EB]. arXiv preprint, 2024, arXiv: 2401.10525.

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, 2020, 22(2): 380-393.

HE H Y, LIN W Y, ZHANG Y A, et al. Toward accurate and robust pedestrian detection via variational inference[J]. International Journal of Computer Vision, 2025, 133(2): 867-889.

ZHANG L J, QIU Y, FAN J W, et al. Underwater fish detection and counting using image segmentation[J]. Aquaculture International, 2024, 32(4): 4799-4817. ]

LI D Y, WANG G F, ZHANG Y, et al. Coal gangue detection and recognition algorithm based on deformable convolution YOLOv3[J]. IET Image Processing, 2022, 16(1): 134-144.

HE Z Y, TONG M J. LT-YOLO: a lightweight network for detecting tomato leaf diseases[J]. Computers, Materials & Continua, 2025, 82(3): 4301-4317.

浏览量

111

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Cerberus：基于深度学习的跨站社交网络机器人检测系统