FDCNet: Frontend-Backend Fusion Dilated Network Through Channel-Attention Mechanism

Crowd counting has attracted much attention in computer vision owing to its fundamental contribution in public security. But due to occlusions, perspective distortions, scale variations, and background interference it faces a great challenge. In this paper we propose a novel model to count crowds, named FDCNet: frontend-backend fusion dilated network through channel-attention mechanism. It merges the frontend feature map with the backend feature map, achieving a fusion of various scale features without additional branches or extra subtasks. The fusion is fed into the channel-attention block to optimize the procedure and to conduct feature recalibration to use global and spatial information. Furthermore, we utilize dilated layers to obtain a high-quality density map, and the SSIM-based loss function is added to compare the local correlation between the estimated density map and the ground truth. Our FDCNet is verified in four common datasets and gets a brilliant estimation.