期刊
ELECTRONICS LETTERS
卷 59, 期 10, 页码 -出版社
WILEY
DOI: 10.1049/ell2.12687
关键词
image processing; image recognition; image and vision processing and display technology; learning systems
To address the scale variation of crowd, a deformable channel non-local network (DCNLNet) is proposed for crowd counting, which can simultaneously learn global context information and adaptive local receptive field. The proposed DCNLNet consists of two modules: deformable channel non-local block (DCNL) and spatial attention feature fusion block (SAFF). The DCNL encodes long-range dependencies and adaptive local correlation, benefiting for improving the spatial discrimination of features. The SAFF aims to aggregate cross-level information and learn specific weights for feature maps with spatial attention. Experimental results demonstrate that the proposed DCNLNet achieves compelling performance compared to other counting models.
Both global dependency and local correlation are crucial for solving the scale variation of crowd. However, most of previous methods fail to take two factors into consideration simultaneously. Against the aforementioned issue, a deformable channel non-local network, abbreviated as DCNLNet for crowd counting, which can simultaneously learn global context information and adaptive local receptive field is proposed. Specifically, the proposed DCNLNet consists of two well-crafted designed modules: deformable channel non-local block (DCNL) and spatial attention feature fusion block (SAFF). The DCNL encodes long-range dependencies between pixels and the adaptive local correlation with channel non-local and deformable convolution, respectively, benefiting for improving the spatial discrimination of features. While the SAFF aims to aggregate the cross-level information, which interacts these features from different depths and learns specific weights for the feature maps with spatial attention. Extensive experiments are performed on three crowd counting benchmark datasets and experimental results indicate that the proposed DCNLNet achieves compelling performance compared to other representative counting models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据