Context-Aware Crowd Counting

By Weizhe Liu, Mathieu Salzmann, Pascal Fua. Computer Vision and Pattern Recognition, 2018

688 citations recorded by the source corpus.

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over large image patches. Only then do they estimate local scale to compensate for perspective distortion. This is typically achieved by training an auxiliary classifier to select, for predefined image patches, the best kernel size among a limited set of choices. As such, these methods are not end-to-end trainable and restricted in the scope of context they can leverage. In this paper, we introduce an end-to-end trainable deep architecture that combines features obtained using multiple receptive field sizes and learns the importance of each such feature at each image location. In other words, our approach adaptively encodes the scale of the contextual information required to accurately predict crowd density. This yields an algorithm that outperforms state-of-the-art crowd counting methods, especially when perspective effects are strong.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1cb1bfd9af5bda1f712605695e47d37c03522652

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Distribution Matching for Crowd Counting (2020, background): “Almost all prior crowd density map estimation methods [56, 57, 60, 38, 20, 33, 35, 4, 28, 50, 27, 40, 29, 26] have followed this convention.”
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (2020, methodology): “Other techniques such as [64, 65, 66, 67, 68] leverage features from different layers of the network using different techniques like trellis style encoder decoder [64], explicitly considering perspective [65], context information [66], adaptive density map generation [68] and multiple views [67].”