Direct Measure Matching for Crowd Counting

Direct Measure Matching for Crowd Counting

Hui Lin, Xiaopeng Hong, Zhiheng Ma, Xing Wei, Yunfeng Qiu, Yaowei Wang, Yihong Gong

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 837-844. https://doi.org/10.24963/ijcai.2021/116

Traditional crowd counting approaches usually use Gaussian assumption to generate pseudo density ground truth, which suffers from problems like inaccurate estimation of the Gaussian kernel sizes. In this paper, we propose a new measure-based counting approach to regress the predicted density maps to the scattered point-annotated ground truth directly. First, crowd counting is formulated as a measure matching problem. Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching. Third, we propose a self-supervised mechanism by devising a Sinkhorn scale consistency loss to resist scale changes. Finally, an efficient optimization method is provided to minimize the overall loss function. Extensive experiments on four challenging crowd counting datasets namely ShanghaiTech, UCF-QNRF, JHU++ and NWPU have validated the proposed method.
Keywords:
Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation
Data Mining: Class Imbalance and Unequal Cost
Constraints and SAT: Constraint Optimization