Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Counting

Crowd counting in still images is a challenging problem in practice due to huge crowd-density variations, large perspective changes, severe occlusion, and variable lighting conditions. The state-of-the-art patch rescaling module (PRM) based approaches prove to be very effective in improving the crowd counting performance. However, the PRM module requires an additional and compromising crowd-density classification process. To address these issues and challenges, the paper proposes a new multi-resolution fusion based end-to-end crowd counting network. It employs three deep-layers based columns/branches, each catering the respective crowd-density scale. These columns regularly fuse (share) the information with each other. The network is divided into three phases with each phase containing one or more columns. Three input priors are introduced to serve as an efficient and effective alternative to the PRM module, without requiring any additional classification operations. Along with the final crowd count regression head, the network also contains three auxiliary crowd estimation regression heads, which are strategically placed at each phase end to boost the overall performance. Comprehensive experiments on three benchmark datasets demonstrate that the proposed approach outperforms all the state-of-the-art models under the RMSE evaluation metric. The proposed approach also has better generalization capability with the best results during the cross-dataset experiments.

Automated summary

The paper proposes a new end-to-end crowd counting network based on multi-resolution fusion, with three deep-layered columns/branches catering to different crowd-density scales. It introduces three input priors as an alternative to the PRM module, and strategically places three auxiliary crowd estimation regression heads in the network to enhance overall performance. Comprehensive experiments show that the proposed approach outperforms state-of-the-art models in terms of RMSE evaluation metric and generalizes well in cross-dataset experiments.