CSFNet: A novel counting network based on context features and multi-scale information

The goal of crowd-counting techniques is to estimate the number of people in an image or video in real-time and accurately. In recent years, with the development of deep learning, the accuracy of the crowd-counting task has improved. However, the accuracy of the crowd-counting task in crowded scenes with large-scale variations still needs improvement. To address this situation, this paper proposes a novel crowd-counting network: Context-Scaled Fusion Network (CSFNet). The details include: (1) the design of the Multi-Scale Receptive Field Fusion Module (MRFF Module), which employs multiple dilated convolutional layers with different dilation rates and uses a fusion mechanism to obtain multi-scale hybrid information to generate higher quality feature maps; (2) the proposal of the Contextual Space Attention Module (CSA Module), which can obtain pixel-level contextual information and combine it with the attention map to enable the model to autonomously learn and focus on important regions, thereby achieving a reduction in counting error. In this paper, the model is trained and evaluated on five datasets: ShanghaiTech, UCF_CC_50, WorldExpo'10, BEIJING-BRT, and Mall. The experimental results show that CSFNet outperforms many state-of-the-art (SOTA) methods on these datasets, demonstrating its superior counting ability and robustness.