Bi-window based stereo matching using combined Siamese convolutional neural network

José Rafael de Santana; Lucas F. S. Cambuim; Edna Barros

doi:10.1117/12.2599525

30 June 2021 Bi-window based stereo matching using combined Siamese convolutional neural network

José Rafael de Santana, Lucas F. S. Cambuim, Edna Barros

Proceedings Volume 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021); 118781Z (2021) https://doi.org/10.1117/12.2599525
Event: Thirteenth International Conference on Digital Image Processing, 2021, Singapore, Singapore

Abstract

Estimating a scene's depth from image pairs is a problem for many computer vision applications such as autonomous vehicles and 3D object reconstruction. However, traditional methods propose dissimilarity functions that do not solve ambiguity problems. We present a combined siamese convolutional neural network (CSCNN) approach to calculate the costs of disparities in stereo images using patches with different sizes. This approach can learn the patches context, improving the accuracy of the estimated costs. We apply the semi-global matching method and the median filter to increase further the robustness of matching costs. We trained and evaluated our approach using the Middlebury database, and, through the bad pixel evaluation, we demonstrate that our approach achieved an accuracy improvement of approximately 22%, compared to the results obtained by single-window CNN-based approaches.

Citation Download Citation

José Rafael de Santana, Lucas F. S. Cambuim, and Edna Barros "Bi-window based stereo matching using combined Siamese convolutional neural network", Proc. SPIE 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021), 118781Z (30 June 2021); https://doi.org/10.1117/12.2599525

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available