Multi‐scale supervised network for crowd counting. Issue 17 (24th February 2021)

• Record Type: Journal Article
• Authors: Wang, Yongjie; Zhang, Wei; Huang, Dongxiao; Liu, Yanyan; Zhu, Jianghua
• Is Part Of: IET image processing. Volume 14:Issue 17(2020)
• Page Start: 4701
• Page End: 4707
• Publication Date: 2021-02-24
• Subjects: image resolution -- feature extraction -- convolutional neural nets -- supervised learning -- image sampling; density map size -- counting accuracy -- multiscale supervised network -- crowd counting -- safety problems -- VGG16 model -- multiscale dilated convolution module -- backbone network -- attention map -- feature map -- high‐quality density map -- feature extraction -- upsampling operation; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.0897
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Crowd counting is getting more and more attention in our daily life, because it can effectively prevent some safety problems. However, due to scale variations and background noise in the image, such as buildings and trees, getting the accurate number from image is a hard work. In order to address these problems, this work introduces a new multi‐scale supervised network. The proposed model uses part of vgg16 model as the backbone to extract feature. In the training process, a multi‐scale dilated convolution module is added at the end of each stage of the backbone network to generate attention map with different resolutions to help the model focus on the head area in feature map. In addition, the dilated convolution adopts three dilation ratios to fit different sizes of head in the image. Finally, in order to get the high‐quality density map with high‐resolution, the authors employ the upsampling operation to restore the density map size to the quarter size of original image. A large number of experiments on these four datasets show that the proposed network has greatly improved the counting accuracy of many existing methods.