摘要
密集人群计数是计算机视觉领域的一个经典问题,仍然受制于尺度不均匀、噪声和遮挡等因素的影响。该文提出一种基于新型多尺度注意力机制的密集人群计数方法。深度网络包括主干网络、特征提取网络和特征融合网络。其中,特征提取网络包括特征支路和注意力支路,采用由并行卷积核函数组成的新型多尺度模块,能够更好地获取不同尺度下的人群特征,以适应密集人群分布的尺度不均匀特性;特征融合网络利用注意力融合模块对特征提取网络的输出特征进行增强,实现了注意力特征与图像特征的有效融合,提高了计数精度。在ShanghaiTech,UCF_CC_50,Mall和UCSD等公开数据集的实验表明,提出的方法在MAE和MSE两项指标上均优于现有方法。
Dense crowd counting is a classic problem in the field of computer vision,and it is still subject to the influence of factors such as uneven scale,noise and occlusion.This paper proposes a dense crowd counting method based on a new multi-scale attention mechanism.Deep network includes backbone network,feature extraction network and feature fusion network.Among them,the feature extraction network includes feature branch and attention branch.It adopts a new multi-scale module composed of parallel convolution kernel functions,which can better obtain the characteristics of people at different scales to adapt to the uneven scale of dense population distribution features;The feature fusion network uses the attention fusion module to enhance the output features of the feature extraction network,realizes the effective fusion of attention features and image features,and improves counting accuracy.Experiments on public data sets such as ShanghaiTech,UCF_CC_50,Mall and UCSD show that the proposed method outperforms existing methods in both MAE and MSE indicators.
作者
万洪林
王晓敏
彭振伟
白智全
杨星海
孙建德
WAN Honglin;WANG Xiaomin;PENG Zhenwei;BAI Zhiquan;YANG Xinghai;SUN Jiande(School of Physics and Electronic Science,Shandong Normal University,Jinan 250358,China;School of Information Science and Engineering,Shandong Normal University,Jinan 250358,China;School of Information Science and Engineering,Shandong University,Qingdao 266237,China;School of Information Science and Technology,Qingdao University of Science and Technology,Qingdao 266061,China)
出处
《电子与信息学报》
EI
CSCD
北大核心
2022年第3期1129-1136,共8页
Journal of Electronics & Information Technology
基金
国家自然科学基金(61971271)
山东省重点研发计划(2018GGX106008)。
关键词
人群计数
新型多尺度注意力
卷积神经网络
人工智能
Crowd counting
New multi-scale attention
Convolutional neural network
Artificial intelligence
