Scale-aware and Anti-interference Convolutional Network for Crowd Counting

Crowd counting is a challenging vision task which aims to estimate the count and distribution of the crowd in a single image accurately. To this end, we propose a novel end - to-end trainable architecture called Scale-aware and Anti-interference Convolutional Network (SACN) to learn a mapping from the input image to the corresponding crowd density map, which concentrates on dealing with the scale variation and background interference of input images for the crowd counting problem. In specific, aiming to cope with the scale variation, we propose Scale-aware Feature Extraction Module (SFEM) to extract multiscale feature maps and learn corresponding pixel-level weight maps for assigning appropriate weights to features of different scales to generate scale-aware features. Futhermore, Regression and Classification Double-head Module (RCDM) is placed at the end of the network to resist the background interference, where the regression head is designed to perform the density map regression and the classification head provides the density map regression task with attention masks related to the foreground and background. In addition, we supervise the intermediate information to help optimize the network and alleviate the gradient vanishing phenomenon. Extensive experiments on three challenging datasets including ShanghaiTech, UCF-QNRF and JHU-CROWD++ were conducted to demonstrate the superiority of the proposed approach compared with the state-of-the-art.