Crowd Counting using Deep Recurrent Spatial-Aware Network

Abstract

Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera's perspective that causes huge appearance variations in people's scales and rotations. Conventional methods address such challenges by resorting to fixed multi-scale architectures that are often unable to cover the largely varied scales while ignoring the rotation variations. In this paper, we propose a unified neural network framework, named Deep Recurrent Spatial-Aware Network, which adaptively addresses the two issues in a learnable spatial transform module with a region-wise refinement process. Specifically, our framework incorporates a Recurrent Spatial-Aware Refinement (RSAR) module iteratively conducting two components: i) a Spatial Transformer Network that dynamically locates an attentional region from the crowd density map and transforms it to the suitable scale and rotation for optimal crowd estimation; ii) a Local Refinement Network that refines the density map of the attended region with residual learning. Extensive experiments on four challenging benchmarks show the effectiveness of our approach. Specifically, comparing with the existing best-performing methods, we achieve an improvement of 12% on the largest dataset WorldExpo'10 and 22.8% on the most challenging dataset UCF_CC_50.

Accepted to IJCAI 2018

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
• Switching Convolutional Neural Network for Crowd Counting
• Multi-label Image Recognition by Recurrently Discovering Attentional Regions
• Recurrent Attentional Networks for Saliency Detection
• FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras
• Recurrent Attentional Reinforcement Learning for Multi-label Image Recognition

Cited by in corpus (13)

• Learning from Synthetic Data for Crowd Counting in the Wild
• Fast Video Crowd Counting with a Temporal Aware Network
• Perspective-Guided Convolution Networks for Crowd Counting
• Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey
• Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition
• Locality-constrained Spatial Transformer Network for Video Crowd Counting
• Content-aware Density Map for Crowd Counting and Density Estimation
• Crowd Counting on Images with Scale Variation and Isolated Clusters
• Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning
• Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
• Coarse- and Fine-grained Attention Network with Background-aware Loss for Crowd Density Map Estimation
• Efficient Crowd Counting via Structured Knowledge Transfer
• Pixel-wise Crowd Understanding via Synthetic Data