Crowd density analysis using co-occurrence texture features

Abstract

Crowd density analysis is crucial for crowd monitoring and management. This paper proposes a novel method for crowd density analysis. According to the framework, input images are firstly divided into patches, and each patch is associated with a density label based on its texture features. Finally, local information is synthesized for global density estimation. Local image content is described by features based on co-occurrence textures and visual words processing chain. Experiments show that the system is highly robust to scene changes and background noise yet remain discriminative for crowd detection.