Direct Measure Matching for Crowd Counting
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Crowd CountingSimilar Papers 제목 키워드 기반
Crowd Counting and Individual Localization Using Pseudo Square Label
Recent work in crowd counting focuses on counting over detected individuals rather than estimating the number of people in the image. However, existing crowd localization methods directly detect the head point or region …
Crowd CountingDistribution Matching for Crowd Counting
In crowd counting, each training image contains multiple people, where each person is annotated by a dot. Existing crowd counting methods need to use a Gaussian to smooth each annotated dot or to estimate the likelihood …
Crowd CountingWSCF-MVCC: Weakly-supervised Calibration-free Multi-view Crowd Counting
Multi-view crowd counting can effectively mitigate occlusion issues that commonly arise in single-image crowd counting. Existing deep-learning multi-view crowd counting methods project different camera view images onto a…
Crowd CountingImproving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance
Crowd counting and localization have become increasingly important in computer vision due to their wide-ranging applications. While point-based strategies have been widely used in crowd counting methods, they face a sign…
Crowd CountingFusionCounting: Robust visible-infrared image fusion guided by crowd counting via multi-task learning
Visible and infrared image fusion (VIF) is an important multimedia task in computer vision. Most VIF methods focus primarily on optimizing fused image quality. Recent studies have begun incorporating downstream tasks, su…
Semantic SegmentationMulti-Task LearningObject DetectionCrowd Counting