基于多尺度特征加权融合注意力的密集人群计数算法  

Dense Crowd Counting Algorithm Based on Multi-scale Feature Weighted Fusion Attention

作　　者：时东亮 葛艳[1] 徐慕君 SHI Dong-Liang;GE Yan;XU Mu-Jun(College of Information Science and Technology,Qingdao University of Science and Technology,Qingdao 266061,China)

机构地区：[1]青岛科技大学信息科学技术学院,青岛266061

出　　处：《计算机系统应用》2025年第3期210-219,共10页Computer Systems & Applications

摘　　要：针对人群计数面临的人头尺寸不统一、人群密度分布不均匀、背景复杂干扰等问题,提出一种解决多尺度变化加强关注人群区域的卷积神经网络模型(multi-scale feature weighted fusion attention convolutional neural network, MSFANet).该网络前端采用改进的VGG-16模型对输入人群图像做第1步的粗粒度特征提取,中间加入多尺度特征提取模块提取图像的多尺度特征信息.随后添加注意力模块对多尺度特征进行特征加权.后端利用锯齿状空洞卷积模块增大感受野,以提取图像的细节特征,生成高质量的人群密度图.对该模型在3个公开数据集上进行实验,结果显示,在Shanghai Tech Part B数据集上MAE (平均绝对误差)达到7.8, MSE (均方误差)达到12.5.在Shanghai Tech Part A数据集上MAE达到64.9, MSE达到108.4.在UCF_CC_50数据集上MAE达到185.1, MSE达到249.8.实验结果证实该模型有较好的准确度和鲁棒性.In response to challenges faced in crowd counting,such as non-uniform head sizes,uneven crowd density distribution,and complex background interference,a convolutional neural network(CNN)model(multi-scale feature weighted fusion attention convolutional neural network,MSFANet)that focuses on crowd regions and addresses multiscale changes is proposed.The front end of the network adopts an improved VGG-16 model to perform the first step of coarse-grained feature extraction on the input crowd image.A multi-scale feature extraction module is added in the middle to extract the multi-scale feature information of the image.Then,an attention module is added to weigh the multiscale features.At the back end,a sawtooth shaped dilated convolution module is adopted to increase the receptive field,extract the detailed features of the image,and generate high-quality crowd density maps.Experiments on this model are conducted on three public datasets.The results show that on the Shanghai Tech Part B dataset,the mean absolute error(MAE)is reduced to 7.8,and the mean squared error(MSE)decreases to 12.5.On the Shanghai Tech Part A dataset,the MAE is reduced to 64.9,and the MSE decreases to 108.4.On the UCF_CC_50 dataset,the MAE is reduced to 185.1,and the MSE decreases to 249.8.These experimental results affirm that the proposed model exhibits strong accuracy and robustness.

关 键 词：人群计数 深度学习 多尺度特征提取 注意力机制 密度图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]