GLCrowd:基于全局-局部注意力的弱监督密集场景人群计数模型  

GLCrowd:a weakly supervised global-local attention model for congested crowd counting

作　　者：张红民 田钱前 颜鼎鼎 卜令宇 Zhang Hongmin;Tian Qianqian;Yan Dingding;Bu Lingyu(School of Electrical and Electronic Engineering,Chongqing University of Technology,Chongqing 400054,China)

机构地区：[1]重庆理工大学电气与电子工程学院,重庆400054

出　　处：《光电工程》2024年第10期75-86,共12页Opto-Electronic Engineering

基　　金：重庆市自然科学基金面上项目(cstc2021jcyj-msxmX0525,CSTB2022NSCQ-MSX0786,CSTB2023NSCQ-MSX0911);重庆市教委科学技术研究项目(KJQN202201109)。

摘　　要：针对人群计数在密集场景下存在背景复杂、尺度变化大等问题,提出了一种结合全局-局部注意力的弱监督密集场景人群计数模型——GLCrowd。首先,设计了一种结合深度卷积的局部注意力模块,通过上下文权重增强局部特征,同时结合特征权重共享获得高频局部信息。其次,利用Vision Transformer(ViT)的自注意力机制捕获低频全局信息。最后,将全局与局部注意力有效融合,并通过回归令牌来完成计数。在Shanghai Tech PartA、Shanghai Tech PartB、UCF-QNRF以及UCF_CC_50数据集上进行了模型测试,MAE分别达到了64.884、8.958、95.523、209.660,MSE分别达到了104.411、16.202、173.453、282.217。结果表明,提出的GLCrowd网络模型在密集场景下的人群计数中具有较好的性能。To address the challenges of crowd counting in dense scenes,such as complex backgrounds and scale variations,we propose a weakly supervised crowd counting model for dense scenes,named GLCrowd,which integrates global and local attention mechanisms.First,we design a local attention module combined with deep convolution to enhance local features through context weights while leveraging feature weight sharing to capture high-frequency local information.Second,the Vision Transformer(ViT)self-attention mechanism is used to capture low-frequency global information.Finally,the global and local attention mechanisms are effectively fused,and counting is accomplished through a regression token.The model was tested on the Shanghai Tech Part A,Shanghai Tech Part B,UCF-QNRF,and UCF_CC_50 datasets,achieving MAE values of 64.884,8.958,95.523,and 209.660,and MSE values of 104.411,16.202,173.453,and 282.217,respectively.The results demonstrate that the proposed GLCrowd model exhibits strong performance in crowd counting within dense scenes.

关 键 词：人群计数 Vision Transformer 全局-局部注意力 弱监督学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]