Context-Aware Crowd Counting

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.

Publié dans:
Conference on Computer Vision and Pattern Recognition (CVPR)
Présenté à:
Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, June 16-20, 2019
Jun 20 2019

 Notice créée le 2019-05-24, modifiée le 2019-12-05

Télécharger le document

Évaluer ce document:

Rate this document:
(Pas encore évalué)