Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting
This work addresses crowd counting for surveillance or public safety applications, offering an incremental improvement over existing methods by enhancing robustness to appearance changes.
The paper tackles the problem of crowd counting under large appearance changes due to density and scale variations by proposing a method that uses multiple CNNs specialized to specific appearances and adaptively selects them for integration, resulting in lower counting error compared to a single CNN or fixed-weight CNN integration.
This paper proposes a crowd counting method. Crowd counting is difficult because of large appearance changes of a target which caused by density and scale changes. Conventional crowd counting methods generally utilize one predictor (e,g., regression and multi-class classifier). However, such only one predictor can not count targets with large appearance changes well. In this paper, we propose to predict the number of targets using multiple CNNs specialized to a specific appearance, and those CNNs are adaptively selected according to the appearance of a test image. By integrating the selected CNNs, the proposed method has the robustness to large appearance changes. In experiments, we confirm that the proposed method can count crowd with lower counting error than a CNN and integration of CNNs with fixed weights. Moreover, we confirm that each predictor automatically specialized to a specific appearance.