Translator Disclaimer
Paper
18 December 2019 Using convolutional neural network for matching cost computation in stereo matching
Author Affiliations +
Proceedings Volume 11342, AOPC 2019: AI in Optics and Photonics; 113420P (2019) https://doi.org/10.1117/12.2548061
Event: Applied Optics and Photonics China (AOPC2019), 2019, Beijing, China
Abstract
Stereo matching is one of the most important computer vision tasks. Several methods can be used to compute a matching cost of two pictures. This paper proposes a method that uses convolutional neural networks to compute the matching cost. The network architecture is described as well as teaching process. The matching cost metric based on the result of neural network is applied to base method which uses support points grid (ELAS). The proposed method was tested on Middlebury benchmark images and showed an accuracy improvement compared to the base method.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Aleksei Denisov, Yan Wang, Andrey Zhdanov, and Sergei Bykovskii "Using convolutional neural network for matching cost computation in stereo matching", Proc. SPIE 11342, AOPC 2019: AI in Optics and Photonics, 113420P (18 December 2019); https://doi.org/10.1117/12.2548061
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

A joint mechanism algorithm for object detection
Proceedings of SPIE (May 06 2019)
Hybrid connection network for semantic segmentation
Proceedings of SPIE (August 09 2018)
Template generation for pattern classification
Proceedings of SPIE (June 01 1992)
Connectionist learning procedure for edge detector
Proceedings of SPIE (February 01 1992)

Back to Top