Scene disparity estimation with convolutional neural networks
- Submitting institution
-
University of Central Lancashire
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 30080
- Type
- E - Conference contribution
- DOI
-
10.1117/12.2527628
- Title of conference / published proceedings
- SPIE Proceedings Multimodal Sensing: Technologies and Applications
- First page
- 110590T
- Volume
- 11059
- Issue
- -
- ISSN
- 0277-786X
- Open access status
- Not compliant
- Month of publication
- June
- Year of publication
- 2019
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Strong requirements have been emerging for disparity estimation with a specific focus on the real-time processing, which is critical for applications in robotics and autonomous navigation. In this paper, we reported our work on effective detection of object occlusion regions in images. It is achieved through disparity estimation in both, forward and backward correspondence model with two matching deep subnetworks. Our method, namely, using a single deep learning structure for bi-direction training largely improves the efficiency for disparity estimation and has great potential for real world applications.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -