A Spatio-Temporal Attentive Network for Video-Based Crowd Counting

TL;DR

This paper introduces a spatio-temporal attentive neural network that leverages temporal correlations in video sequences to improve pedestrian counting accuracy in surveillance videos, outperforming existing methods on standard benchmarks.

Contribution

It presents a novel neural network architecture that incorporates spatio-temporal attention for more accurate crowd counting in videos, addressing limitations of previous image-based approaches.

Findings

Reduced count error by 5% on FDST benchmark

Lowered localization error by 7.5%

Demonstrated effectiveness of temporal attention in crowd counting

Abstract

Automatic people counting from images has recently drawn attention for urban monitoring in modern Smart Cities due to the ubiquity of surveillance camera networks. Current computer vision techniques rely on deep learning-based algorithms that estimate pedestrian densities in still, individual images. Only a bunch of works take advantage of temporal consistency in video sequences. In this work, we propose a spatio-temporal attentive neural network to estimate the number of pedestrians from surveillance videos. By taking advantage of the temporal correlation between consecutive frames, we lowered state-of-the-art count error by 5% and localization error by 7.5% on the widely-used FDST benchmark.