基于多尺度感知的密集人群计数网络  

Dense Crowd Counting Network Based on Multi-scale Perception

作　　者：李恒超[1,2] 刘香莲 刘鹏[1] 冯斌[3] LI Hengchao;LIU Xianglian;LIU Peng;FENG Bin(School of Information Science and Technology,Southwest Jiaotong University,Chengdu 611756,China;National Engineering Laboratory of Integrated Transportation Big Data Application Technology,Southwest Jiaotong University,Chengdu 611756,China;School of Sports,Southwest Jiaotong University,Chengdu 611756,China)

机构地区：[1]西南交通大学信息科学与技术学院,四川成都611756 [2]西南交通大学综合交通大数据应用技术国家工程实验室,四川成都611756 [3]西南交通大学体育学院,四川成都611756

出　　处：《西南交通大学学报》2024年第5期1176-1183,1214,共9页Journal of Southwest Jiaotong University

基　　金：国家自然科学基金项目(62271418);四川省自然科学基金项目(23NSFSC0058)。

摘　　要：针对密集人群场景存在的目标尺度多样、人群大尺度变化等问题,提出一种基于多尺度感知的密集人群计数网络.首先,考虑到小尺度目标在图像中占比较大,以VGG-16 (visual geometry group 2016)网络为基础,引入空洞卷积模块,以挖掘图像细节信息;其次,为充分利用目标多尺度信息,构建新的上下文感知模块,以提取不同尺度之间的对比特征;最后,考虑到目标尺度连续变化的特点,设计多尺度特征聚合模块,提高密集尺度采样范围与多尺度信息交互,从而提升网络性能.实验结果显示:在ShangHai Tech (Part_A/Part_B)和UCF_CC_50数据集上,本文方法的平均绝对误差(mean absolute error,MAE)分别为62.5、6.9、156.5,均方根误差(root mean square error,RMSE)分别为95.7、11.0、223.3;相较于最优对比方法,在UCF_QNRF数据集上的MAE和RMSE分别降低1.1%和4.3%,在NWPU数据集上分别降低8.7%和13.9%.A dense crowd counting network based on multi-scale perception was proposed to solve the problems of diverse target scales and large-scale changes of crowds in dense crowd scenes.Firstly,since the small-scale targets account for a relatively large proportion of the images,a dilated convolution module was introduced based on the visual geometry group 2016(VGG-16) network to mine the detailed information in the images.Then,by utilizing the multi-scale information of the target,a novel context-aware module was designed to extract the contrast features between different scales.Finally,In view of the continuous change of target scales,the multiscale feature aggregation module was designed to improve the sampling range of dense scales,enhance the interaction of multi-scale information,and thus improve the model performance.The experimental results show that mean absolute errors(MAEs) of the proposed method are 62.5,6.9,and 156.5,and the root mean square errors(RMSEs) are 95.7,11.0,and 223.3 on ShangHai Tech(Part_A/Part_B) and UCF_CC_50 datasets,respectively.Compared with the optimal method of comparison model,the MAE and RMSE are reduced by 1.1%and 4.3% on the UCF_QNRF dataset and by 8.7% and 13.9% on the NWPU dataset.

关 键 词：人群密度估计 多尺度聚合 空洞卷积 密度图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]