Top-Down Feedback for Crowd Counting Convolutional Neural Network

Abstract

Counting people in dense crowds is a demanding task even for humans. This is primarily due to the large variability in appearance of people. Often people are only seen as a bunch of blobs. Occlusions, pose variations and background clutter further compound the difficulty. In this scenario, identifying a person requires larger spatial context and semantics of the scene. But the current state-of-the-art CNN regressors for crowd counting are feedforward and use only limited spatial context to detect people. They look for local crowd patterns to regress the crowd density map, resulting in false predictions. Hence, we propose top-down feedback to correct the initial prediction of the CNN. Our architecture consists of a bottom-up CNN along with a separate top-down CNN to generate feedback. The bottom-up network, which regresses the crowd density map, has two columns of CNN with different receptive fields. Features from various layers of the bottom-up CNN are fed to the top-down network. The feedback, thus generated, is applied on the lower layers of the bottom-up network in the form of multiplicative gating. This masking weighs activations of the bottom-up network at spatial as well as feature levels to correct the density prediction. We evaluate the performance of our model on all major crowd datasets and show the effectiveness of top-down feedback.

arXiv commentAAAI 2018

Cited by in corpus (21)

• Distribution Matching for Crowd Counting
• CNN-based Density Estimation and Crowd Counting: A Survey
• Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting
• Fast Video Crowd Counting with a Temporal Aware Network
• Feedback Network for Image Super-Resolution
• Fine-Grained Crowd Counting
• Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
• Gated Multiple Feedback Network for Image Super-Resolution
• Learning Spatial Awareness to Improve Crowd Counting
• Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
• Deep Density-aware Count Regressor
• Feature-aware Adaptation and Density Alignment for Crowd Counting in Video Surveillance
• Bayesian Multi-Scale Neural Network for Crowd Counting
• Crowd Scene Analysis by Output Encoding
• Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting
• Exploit the potential of Multi-column architecture for Crowd Counting
• A Real-Time Deep Network for Crowd Counting
• The Selectivity and Competition of the Mind's Eye in Visual Perception
• PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting
• Active Crowd Counting with Limited Supervision
• Multi-channel Deep Supervision for Crowd Counting