Crowd Counting via Scale-Adaptive Convolutional Neural Network

Abstract : The task of crowd counting is to automatically estimate the pedestrian number in crowd images. To cope with the scale and perspective changes that commonly exist in crowd images, state-of-the-art approaches employ multi-column CNN architectures to regress density maps of crowd images. Multiple columns have different receptive fields corresponding to pedestrians (heads) of different scales. We instead propose a scale-adaptive CNN (SaCNN) architecture with a backbone of fixed small receptive fields. We extract feature maps from multiple layers and adapt them to have the same output size; we combine them to produce the final density map. The number of people is computed by integrating the density map. We also introduce a relative count loss along with the density map loss to improve the network generalization on crowd scenes with few pedestrians , where most representative approaches perform poorly on. We conduct extensive experiments on the ShanghaiTech, UCF_CC_50 and WorldExpo'10 datasets as well as a new dataset SmartCity that we collect for crowd scenes with few people. The results demonstrate significant improvements of SaCNN over the state-of-the-art.
Type de document :
Communication dans un congrès
WACV 2018 - IEEE Winter Conference on Applications of Computer Vision, Mar 2018, Lake Tahoe, United States. IEEE, pp.1-9, 〈10.1109/WACV.2018.00127〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01830946
Contributeur : Miaojing Shi <>
Soumis le : jeudi 5 juillet 2018 - 15:45:20
Dernière modification le : jeudi 15 novembre 2018 - 11:59:01
Document(s) archivé(s) le : lundi 1 octobre 2018 - 18:12:50

Fichier

wacv2018shi.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Lu Zhang, Miaojing Shi, Qiaobo Chen. Crowd Counting via Scale-Adaptive Convolutional Neural Network. WACV 2018 - IEEE Winter Conference on Applications of Computer Vision, Mar 2018, Lake Tahoe, United States. IEEE, pp.1-9, 〈10.1109/WACV.2018.00127〉. 〈hal-01830946〉

Partager

Métriques

Consultations de la notice

456

Téléchargements de fichiers

51