Bayesian Dense Inverse Searching Algorithm for Real-Time Stereo Matching in Minimally Invasive Surgery

Song, J; Zhu, Q; Lin, J; Ghaffari, M

Bayesian Dense Inverse Searching Algorithm for Real-Time Stereo Matching in Minimally Invasive Surgery

Song, J Zhu, Q Lin, J Ghaffari, M

Permalink

Publisher:: Springer Nature
Publication Type:: Conference Proceeding
Citation:: Medical Image Computing and Computer Assisted Intervention – MICCAI 2022, 2022, 13437, pp. 333-344
Issue Date:: 2022

Closed Access

	Filename	Description	Size
	978-3-031-16449-1_32.pdf	Published version	3.58 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Song, J
dc.contributor.author	Zhu, Q
dc.contributor.author	Lin, J
dc.contributor.author	Ghaffari, M
dc.date	2022-09-18
dc.date.accessioned	2023-06-30T23:39:19Z
dc.date.available	2023-06-30T23:39:19Z
dc.date.issued	2022
dc.identifier.citation	Medical Image Computing and Computer Assisted Intervention – MICCAI 2022, 2022, 13437, pp. 333-344
dc.identifier.isbn	978-3-031-16448-4
dc.identifier.issn	1611-3349
dc.identifier.issn	1611-3349
dc.identifier.uri	http://hdl.handle.net/10453/171060
dc.description.abstract	This paper reports a CPU-level real-time stereo matching method for surgical images (10 Hz on 640×480 image with a single core of i5-9400). The proposed method is built on the fast LK algorithm, which estimates the disparity of the stereo images patch-wisely and in a coarse-to-fine manner. We propose a Bayesian framework to evaluate the probability of the optimized patch disparity at different scales. Moreover, we introduce a spatial Gaussian mixed probability distribution to address the pixel-wise probability within the patch. In-vivo and synthetic experiments show that our method can handle ambiguities resulted from the textureless surfaces and the photometric inconsistency caused by the non-Lambertian reflectance. Our Bayesian method correctly balances the probability of the patch for stereo images at different scales. Experiments indicate that the estimated depth has similar accuracy and fewer outliers than the baseline methods in the surgical scenario with real-time performance. The code and data set are available at https://github.com/JingweiSong/BDIS.git.
dc.language	en
dc.publisher	Springer Nature
dc.relation.ispartof	Medical Image Computing and Computer Assisted Intervention – MICCAI 2022
dc.relation.ispartof	International Conference on Medical Image Computing and Computer Assisted Intervention
dc.relation.ispartofseries	Lecture Notes in Computer Science
dc.relation.isbasedon	10.1007/978-3-031-16449-1_32
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	Bayesian Dense Inverse Searching Algorithm for Real-Time Stereo Matching in Minimally Invasive Surgery
dc.type	Conference Proceeding
utslib.citation.volume	13437
utslib.location.activity	Singapore
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-06-30T23:39:16Z
pubs.finish-date	2022-09-22
pubs.publication-status	Published
pubs.start-date	2022-09-18
pubs.volume	13437

Abstract:

This paper reports a CPU-level real-time stereo matching method for surgical images (10 Hz on 640×480 image with a single core of i5-9400). The proposed method is built on the fast LK algorithm, which estimates the disparity of the stereo images patch-wisely and in a coarse-to-fine manner. We propose a Bayesian framework to evaluate the probability of the optimized patch disparity at different scales. Moreover, we introduce a spatial Gaussian mixed probability distribution to address the pixel-wise probability within the patch. In-vivo and synthetic experiments show that our method can handle ambiguities resulted from the textureless surfaces and the photometric inconsistency caused by the non-Lambertian reflectance. Our Bayesian method correctly balances the probability of the patch for stereo images at different scales. Experiments indicate that the estimated depth has similar accuracy and fewer outliers than the baseline methods in the surgical scenario with real-time performance. The code and data set are available at https://github.com/JingweiSong/BDIS.git.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/171060