Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Frontiers of Information Technology & Electronic Engineering >> 2020, Volume 21, Issue 8 doi: 10.1631/FITEE.1900282

A novel convolutional neural network method for crowd counting

哈尔滨工业大学控制与仿真中心,中国哈尔滨市,150080

Received: 2019-06-05 Accepted: 2020-08-10 Available online: 2020-08-10

Next Previous

Abstract

Crowd , in general, is a challenging task due to the large variation of head sizes in the crowds. Existing methods always use a multi-column convolutional neural network (MCNN) to adapt to this variation, which results in an average effect in areas with different densities and brings a lot of noise to the density map. To address this problem, we propose a new method called the segmentation-aware prior network (SAPNet), which generates a high-quality density map without noise based on a coarse head-segmentation map. SAPNet is composed of two networks, i.e., a foreground-segmentation convolutional neural network (FS-CNN) as the front end and a crowd-regression convolutional neural network (CR-CNN) as the back end. With only the single dot annotation, we generate the ground truth of segmentation masks in heads. Then, based on the ground truth, FS-CNN outputs a coarse head-segmentation map, which helps eliminate the noise in regions without people in the density map. By inputting the head-segmentation map generated by the front end, CR-CNN performs accurate estimation and generates a high-quality density map. We demonstrate SAPNet on four datasets (i.e., ShanghaiTech, UCF-CC-50, WorldExpo’10, and UCSD), and show the state-of-the-art performances on ShanghaiTech part and UCF-CC-50 datasets.

Related Research