Co-Communication Graph Convolutional Network for Multi-View Crowd Counting
- 17 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 5813-5825
Abstract
We study and address the multi-view crowd counting (MVCC) problem which poses more realistic challenges than single-view crowd counting for better facilitating crowd management / public safety systems. Its major challenge lies in how to fully distill and aggregate useful, complementary information among multiple camera views to create powerful ground-plane representations for wide-area crowd analysis. In this paper, we present a graph-based, multi-view learning model called Co-Communication Graph Convolutional Network (CoCo-GCN) to jointly investigate intra-view contextual dependencies and inter-view complementary relations. More specifically, CoCo-GCN builds a view-agnostic graph interaction space for each camera view to conduct efficient contextual reasoning, and extends the intra-view reasoning by using a novel Graph Communication Layer (GCL) to also take between-graph (cross-view), complementary information into account. Moreover, CoCo-GCN uses a new Co-Memory Layer (CoML) to jointly coarsen the graphs and close the ‘representational gap’ among them for further exploiting the compositional nature of graphs and learning more consistent representations. Finally, these jointly learned features of multiple views can be easily fused to create ground-plane representations for wide-area crowd counting. Experiments show that the proposed CoCo-GCN achieves state-of-the-art results on three MVCC datasets, i.e., PETS2009, DukeMTMC, and City Street, significantly improving the scene-level accuracy over previous models.Keywords
Funding Information
- National Natural Science Foundation of China (U1964203)
- National Key R&D Program Project of China (2017YFB0102603)
This publication has 75 references indexed in Scilit:
- Cross-scene crowd counting via deep convolutional neural networks2015
- Cross-Camera Knowledge Transfer for Multiview People CountingIEEE Transactions on Image Processing, 2014
- Scene invariant multi camera crowd countingPattern Recognition Letters, 2014
- People counting by learning their appearance in a multi-view camera environmentPattern Recognition Letters, 2014
- A Reliable People Counting System via Multiple CamerasACM Transactions on Intelligent Systems and Technology, 2012
- Feature Mining for Localised Crowd Counting2012
- Video sensor network for real-time traffic monitoring and surveillanceIET Intelligent Transport Systems, 2010
- Histograms of Oriented Gradients for Human Detection2005
- Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns2000
- Object recognition from local scale-invariant features1999