Crowd Counting from a Still Image Using Multi-scale Fully Convolutional Network with Adaptive Human-Shaped Kernel

Abstract

Crowd count estimation from a still crowd image with arbitrary perspective and density level is one of the challenges in crowd analysis. Techniques developed in the past performed poorly in highly congested scenes with several thousands of people. To resolve the problem, we propose a Multi-scale Fully Convolutional Network for robust crowd counting, that is achieved through estimating density map. Our approach consists of the following contributions: (1) an adaptive human-shaped kernel is proposed to generate the ground truth of the density map. (2) A deep, multi-scale, fully convolutional network is proposed to predict crowd counts. Per-scale loss is used to guarantee the effectiveness of multi-scale strategy. (3) Several attempts, e.g. de-convolutional and minimizing per-scale loss, are tried to improve the counting performance of the proposed approach. Our approach can adapt to not only sparse scenes, but also dense ones. In addition, it achieves the state-of-the-art counting performance in benchmarking datasets, including the World Expo’10, the UCF_CC_50, and the UCSD datasets.