Relevant Region Prediction for Crowd Counting
This work addresses crowd counting for computer vision applications, offering an incremental improvement by refining density map methods with region relation modeling.
The paper tackles the problem of crowd counting in congested scenes by proposing Relevant Region Prediction (RRP), which includes a count map to focus on counting rather than localization and a Region Relation-Aware Module (RRAM) using Graph Convolutional Networks to capture region dependencies, resulting in state-of-the-art performance on three datasets.
Crowd counting is a concerned and challenging task in computer vision. Existing density map based methods excessively focus on the individuals' localization which harms the crowd counting performance in highly congested scenes. In addition, the dependency between the regions of different density is also ignored. In this paper, we propose Relevant Region Prediction (RRP) for crowd counting, which consists of the Count Map and the Region Relation-Aware Module (RRAM). Each pixel in the count map represents the number of heads falling into the corresponding local area in the input image, which discards the detailed spatial information and forces the network pay more attention to counting rather than localizing individuals. Based on the Graph Convolutional Network (GCN), Region Relation-Aware Module is proposed to capture and exploit the important region dependency. The module builds a fully connected directed graph between the regions of different density where each node (region) is represented by weighted global pooled feature, and GCN is learned to map this region graph to a set of relation-aware regions representations. Experimental results on three datasets show that our method obviously outperforms other existing state-of-the-art methods.