Institute Homepage
Institute Homepage DE Sign In

Back

Perceiving Systems Conference Paper 2016

Occlusion boundary detection via deep exploration of context

Thumb ticker sm thumb chaohui
Perceiving Systems
Chaohui Wang
Thumb ticker sm headshot2021
Perceiving Systems
Michael Black
Director
Futeaser

Occlusion boundaries contain rich perceptual information about the underlying scene structure. They also provide important cues in many visual perception tasks such as scene understanding, object recognition, and segmentation. In this paper, we improve occlusion boundary detection via enhanced exploration of contextual information (e.g., local structural boundary patterns, observations from surrounding regions, and temporal context), and in doing so develop a novel approach based on convolutional neural networks (CNNs) and conditional random fields (CRFs). Experimental results demonstrate that our detector significantly outperforms the state-of-the-art (e.g., improving the F-measure from 0.62 to 0.71 on the commonly used CMU benchmark). Last but not least, we empirically assess the roles of several important components of the proposed detector, so as to validate the rationale behind this approach.

Author(s): Huang Fu and Chaohui Wang and Dacheng Tao and Michael J. Black
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Pages: 241-250
Year: 2016
Month: June
Bibtex Type: Conference Paper (inproceedings)
Event Name: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2016
Electronic Archiving: grant_archive
Links:

BibTex 

@inproceedings{Fu:CVPR:2016,
  title = {Occlusion boundary detection via deep exploration of context},
  booktitle = { IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)},
  abstract = {Occlusion boundaries contain rich perceptual information about the underlying scene structure. They also provide important cues in many visual perception tasks such as scene understanding, object recognition, and segmentation.  In this paper, we improve occlusion boundary detection via enhanced exploration of contextual information (e.g., local structural boundary patterns, observations from surrounding regions, and temporal context), and in doing so develop a novel approach based on convolutional neural networks (CNNs) and conditional random fields (CRFs). Experimental results demonstrate that our detector significantly outperforms the state-of-the-art (e.g., improving the F-measure from 0.62 to 0.71 on the commonly used CMU benchmark). Last but not least, we empirically assess the roles of several important components of the proposed detector, so as to validate the rationale behind this approach.},
  pages = {241-250},
  month = jun,
  year = {2016},
  slug = {fu-cvpr-2016},
  author = {Fu, Huang and Wang, Chaohui and Tao, Dacheng and Black, Michael J.},
  month_numeric = {6}
}