Crowd Counting With Deep Structured Scale Integration Network
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1774-1783
Abstract
Automatic estimation of the number of people in unconstrained crowded scenes is a challenging task and one major difficulty stems from the huge scale variation of people. In this paper, we propose a novel Deep Structured Scale Integration Network (DSSINet) for crowd counting, which addresses the scale variation of people by using structured feature representation learning and hierarchically structured loss function optimization. Unlike conventional methods which directly fuse multiple features with weighted average or concatenation, we first introduce a Structured Feature Enhancement Module based on conditional random fields (CRFs) to refine multiscale features mutually with a message passing mechanism. Specifically, each scale-specific feature is considered as a continuous random variable and passes complementary information to refine the features at other scales. Second, we utilize a Dilated Multiscale Structural Similarity loss to enforce our DSSINet to learn the local correlation of people's scales within regions of various size, thus yielding high-quality density maps. Extensive experiments on four challenging benchmarks well demonstrate the effectiveness of our method. In particular, our DSSINet achieves improvements of 9.5\% error reduction on Shanghaitech dataset and 24.9\% on UCF-QNRF dataset against the state-of-the-art methods.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Loss Functions for Image Restoration With Neural NetworksIEEE Transactions on Computational Imaging, 2016
- CrowdNet2016
- Learning to Count with CNN Boosting2016
- Towards Perspective-Free Object Counting with Deep Learning2016
- Deep Residual Learning for Image Recognition2016
- Single-Image Crowd Counting via Multi-Column Convolutional Neural Network2016
- Conditional Random Fields as Recurrent Neural Networks2015
- Cross-scene crowd counting via deep convolutional neural networks2015
- Multiscale structural similarity for image quality assessment2004
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004