Crowd Counting with Density Adaption Networks

2018/06/26 by Li Wang, Weiyuan Shao, Wang, Li +9
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #Evacuation and Crowd Dynamics #FOS: Computer and information sciences #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.1806.10040

openalex publication_date 2018/06/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Crowd counting is one of the core tasks in various surveillance applications. A practical system involves estimating accurate head counts in dynamic scenarios under different lightning, camera perspective and occlusion states. Previous approaches estimate head counts despite that they can vary dramatically in different density settings; the crowd is often unevenly distributed and the results are therefore unsatisfactory. In this paper, we propose a lightweight deep learning framework that can automatically estimate the crowd density level and adaptively choose between different counter networks that are explicitly trained for different density domains. Experiments on two recent crowd counting datasets, UCF_CC₅0 and ShanghaiTech, show that the proposed mechanism achieves promising improvements over state-of-the-art methods. Moreover, runtime speed is 20 FPS on a single GPU.

Citations

• Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting
• FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
• Switching Convolutional Neural Network for Crowd Counting

Related

• DecideNet: Counting Varying Density Crowds Through Attention Guided\n Detection and Density Estimation
• CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
• Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
• A-CCNN: adaptive ccnn for density estimation and crowd counting
• Recurrent Distillation based Crowd Counting