Feature Hourglass Network for Skeleton Detection

Nan Jiang, Yifei Zhang, Dezhao Luo, Chang Liu, Yu Zhou, Zhenjun Han

CVPRW 2019 pp. 1172-1176

doi:10.1109/CVPRW.2019.00154 /cvprw/2019/jiang2019cvprw-feature/

Abstract

Geometric shape understanding provides an intuitive representation of object shapes. Skeleton is typical geometrical information. Lots of traditional approaches are developed for skeleton extraction and pruning, while it is still a new area to investigate deep learning for geometric shape understanding. In this paper, we build a fully convolutional network named Feature Hourglass Network (FHN) for skeleton detection. FHN uses rich features of a fully convolutional network by hierarchically integrating side-outputs with a deep-to-shallow manner to decrease the residual between the prediction result and the ground-truth. Experiment data shows that FHN achieves better performance compared with baseline on both Pixel SkelNetOn and Point SkelNetOn datasets.

CVPRW Semantic Scholar

Cite

Text

Jiang et al. "Feature Hourglass Network for Skeleton Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00154

Markdown

[Jiang et al. "Feature Hourglass Network for Skeleton Detection." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/jiang2019cvprw-feature/) doi:10.1109/CVPRW.2019.00154

BibTeX

@inproceedings{jiang2019cvprw-feature,
  title     = {{Feature Hourglass Network for Skeleton Detection}},
  author    = {Jiang, Nan and Zhang, Yifei and Luo, Dezhao and Liu, Chang and Zhou, Yu and Han, Zhenjun},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {1172-1176},
  doi       = {10.1109/CVPRW.2019.00154},
  url       = {https://mlanthology.org/cvprw/2019/jiang2019cvprw-feature/}
}