PaDNet: Pan-Density Crowd Counting
Authors:
- Yukun TianYTYukun Tian
- Yiming LeiYLYiming Lei
- Junping ZhangJZJunping Zhang
- James Z. WangJWJames Z. Wang
- 12 November 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29, 2714-2727
Abstract
Crowd counting is a highly challenging problem in computer vision and machine learning. Most previous methods have focused on consistent density crowds, i.e., either a sparse or a dense crowd, meaning they performed well in global estimation while neglecting local accuracy. To make crowd counting more useful in the real world, we propose a new perspective, named pan-density crowd counting, which aims to count people in varying density crowds. Specifically, we propose the Pan-Density Network (PaDNet) which is composed of the following critical components. First, the Density-Aware Network (DAN) contains multiple subnetworks pretrained on scenarios with different densities. This module is capable of capturing pandensity information. Second, the Feature Enhancement Layer (FEL) effectively captures the global and local contextual features and generates a weight for each density-specific feature. Third, the Feature Fusion Network (FFN) embeds spatial context and fuses these density-specific features. Further, the metrics Patch MAE (PMAE) and Patch RMSE (PRMSE) are proposed to better evaluate the performance on the global and local estimations. Extensive experiments on four crowd counting benchmark datasets, the ShanghaiTech, the UCF-CC-50, the UCSD, and the UCFQNRF, indicate that PaDNet achieves state-of-the-art recognition performance and high robustness in pan-density crowd counting.Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2018YFB1305104)
- National Natural Science Foundation of China (NSFC 61673118)
- Shanghai Municipal Science and Technology Major Project (2018SHZDZX01)
- ZJLab
- Pennsylvania State University
This publication has 43 references indexed in Scilit:
- Fast crowd density estimation with convolutional neural networksEngineering Applications of Artificial Intelligence, 2015
- Extremely Overlapping Vehicle Counting2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Multi-source Multi-scale Counting in Extremely Dense Crowd Images2013
- Feature Mining for Localised Crowd Counting2012
- Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part DetectorsInternational Journal of Computer Vision, 2007
- A MRF-based approach for real-time subway monitoring2005
- Histograms of Oriented Gradients for Human Detection2005
- Pedestrian Detection in Crowded Scenes2005