Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 29, Issue -, Pages 323-335Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2019.2928634
Keywords
Training; Task analysis; Adaptation models; Supervised learning; Semantics; Decoding; Image segmentation; Crowd counting; weakly supervised learning; crowd analytics
Funding
- US Office of Naval Research (ONR) [YIP N00014-16-1-3134]
Ask authors/readers for more resources
Single image-based crowd counting has recently witnessed increased focus, but many leading methods are far from optimal, especially in highly congested scenes. In this paper, we present the Hierarchical Attention-based Crowd Counting Network (HA-CCN) that employs attention mechanisms at various levels to selectively enhance the features of the network. The proposed method, which is based on the VGG16 network, consists of a spatial attention module (SAM) and a set of global attention modules (GAM). SAM enhances low-level features in the network by infusing spatial segmentation information, whereas the GAM focuses on enhancing channel-wise information in the higher level layers. The proposed method is a single-step training framework, simple to implement and achieves the state-of-the-art results on different datasets. Furthermore, we extend the proposed counting network by introducing a novel set-up to adapt the network to different scenes and datasets via weak supervision using image-level labels. This new set up reduces the burden of acquiring labor intensive point-wise annotations for new datasets while improving the cross-dataset performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available