基于 Yolov5 的密集场所人数估计方法

吉林大学学报(信息科学版) ›› 2021, Vol. 39 ›› Issue (6): 682-687.

基于 Yolov5 的密集场所人数估计方法

王婧媛, 方健

吉林工程技术师范学院电气工程学院, 长春 130052

收稿日期:2021-10-11 出版日期:2021-12-01 发布日期:2021-12-02
通讯作者: 方健(1974— ), 男, 长春人, 吉林工程技术师范学院教授, 主要从事人工智能和机器人研究, (Tel)86-13644408497(E-mail)757314739@ qq. com。
作者简介:王婧媛( 1988— ), 女, 长春人, 吉林工程技术师范学院助教, 博士研究生, 主要从事模式识别研究, ( Tel) 86- 15844017079(E-mail)wjingyuancc@ 163. com。
基金资助:
吉林工程技术师范学院校级基金资助项目(XYBK202009)

Method for Estimating Number of People in Dense Place Based on Yolov5

WANG Jingyuan, FANG Jian

School of Electrical Engineering, Jilin Engineering Normal University, Changchun 130052, China

Received:2021-10-11 Online:2021-12-01 Published:2021-12-02

摘要/Abstract

摘要： 为解决目前对高密度人群计数问题, 提出了一种基于 Yolov5 的人群计数方法。其中输入层主要进行 Mosaic数据增强, 即自适应锚框和自适应的图片缩放技术; Backbone 中 Yolov5 主要采用 Focus 和 CSP(Cross Stage Partial)结构; Neck 层采用 SPP(Spatial Pyramid Pooling)模块和 FPN(Feature Pyramid Networks) +PAN(Pixel Aggregation Network)结构; 输出端主要针对 Bounding Box 损失函数采用了 CIOU_Loss 作为损失函数和 DIOU_ loss 作为 NMS(Non Maximum Suppression)的平均指标; 最终输出训练结果。实验结果表明, 该方法能有效提高人群计数的精度。

关键词: 人群计数 , Mosaic 数据增强 , Yolov5 算法 , Focus 和 CSP 结构

Abstract: In view of the current limitations of counting high-density population, a population counting method based on Yolov5 is proposed. The input layer is mainly used for Mosaic data enhancement, adaptive anchor frame and adaptive picture zooming technology. Backbone Yolov5 mainly adopts Focus and CSP( Cross Stage Partial) structure. The Neck layer mainly adopts SPP ( Spatial Pyramid Pooling) module and FPN ( Feature Pyramid Networks)+PAN(Pixel Aggregation Network) structure. The output end adopts CIOU_Loss as the loss function mainly for Bounding Box Loss function and DIOU_Loss as average indicator of the NMS(Non Maximum Suppression). Finally the training results are output. Experimental results show that this method can effectively improve the accuracy of crowd counting.

Key words: people counting, Mosaic data enhancement, Yolov5 algorithm, Focus and cross stage partial (CSP) structure

中图分类号:

TP305

王婧媛, 方健. 基于 Yolov5 的密集场所人数估计方法[J]. 吉林大学学报(信息科学版), 2021, 39(6): 682-687.

WANG Jingyuan, FANG Jian. Method for Estimating Number of People in Dense Place Based on Yolov5[J]. Journal of Jilin University (Information Science Edition), 2021, 39(6): 682-687.