Illumination-Enhanced Crowd Counting Based on IC-Net in Low Lighting Conditions.

The low lighting in some extreme conditions always affect the accuracy of the crowd counting and other vision tasks. The existing methods mainly rely on the generalization ability of deep-learning model to count the crowd number. But in extremely low lighting conditions, these methods are not efficient. To alleviate this issue, this paper proposes a novel approach, named Illumination-aware Cascading Network (IC-Net). The IC-Net can handle the low lighting conditions and generate a high-quality crowd density map. It contains two submodules, i.e., the Illumination Fusion Module and the Feature Cascading Module. The Illumination Fusion Module can fuse the low-illumination feature and the illumination enhanced feature to highlight the missing feature in darkness. The Feature Cascading Module is a cascading model and used to further express the illumination feature. It can generate the high-quality density map. In addition, a new dataset is collected, named Low Light Scenes Crowd (LLSC) dataset, which all come from extremely low illumination conditions. Experimental results on LLSC and benchmark show that the proposed method outperforms the existing state-of-the art methods in such extreme conditions.