Crowd Counting with Deep Structured Scale Integration Network

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. In this module, 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. Specifically, 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.

arXiv commentAccepted to ICCV 2019

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Conditional Random Fields as Recurrent Neural Networks
• Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid
• Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds
• CRF-CNN: Modeling Structured Information in Human Pose Estimation
• ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding
• Context-Aware Crowd Counting
• PCC Net: Perspective Crowd Counting via Spatial Convolutional Network

Cited by in corpus (5)

• Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions
• Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
• SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting
• Efficient Crowd Counting via Structured Knowledge Transfer
• Recurrent Distillation based Crowd Counting