Switching Convolutional Neural Network for Crowd Counting

TL;DR

This paper introduces a switching CNN model for crowd counting that adaptively assigns image patches to specialized regressors based on crowd density, resulting in improved accuracy and interpretability over existing methods.

Contribution

The paper presents a novel switching CNN architecture that dynamically selects the best regressor for each scene patch based on crowd density, enhancing counting precision.

Findings

Outperforms current state-of-the-art crowd counting methods

Provides interpretable space partitioning based on crowd density

Demonstrates robustness across multiple datasets

Abstract

We propose a novel crowd counting model that maps a given crowd scene to its density. Crowd analysis is compounded by myriad of factors like inter-occlusion between people due to extreme crowding, high similarity of appearance between people and background elements, and large variability of camera view-points. Current state-of-the art approaches tackle these factors by using multi-scale CNN architectures, recurrent networks and late fusion of features from multi-column CNN with different receptive fields. We propose switching convolutional neural network that leverages variation of crowd density within an image to improve the accuracy and localization of the predicted crowd count. Patches from a grid within a crowd scene are relayed to independent CNN regressors based on crowd count prediction quality of the CNN established during training. The independent CNN regressors are designed to have different receptive fields and a switch classifier is trained to relay the crowd scene patch to the best CNN regressor. We perform extensive experiments on all major crowd counting datasets and evidence better performance compared to current state-of-the-art methods. We provide interpretable representations of the multichotomy of space of crowd scene patches inferred from the switch. It is observed that the switch relays an image patch to a particular CNN column based on density of crowd.