A Robust Edge-Preserving Stereo Matching Method for Laparoscopic Images

Stereo matching has become an active area of research in the field of computer vision. In minimally invasive surgery, stereo matching provides depth information to surgeons, with the potential to increase the safety of surgical procedures, particularly those performed laparoscopically. Many stereo m...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2022-07, Vol.41 (7), p.1651-1664
Main Authors: Xia, Wenyao, Chen, Elvis C. S., Pautler, Stephen, Peters, Terry M.
Format: Article
Language:English
Subjects:
Computer vision
Costs
depth information
Equalization
Feature extraction
Illumination
Image acquisition
Image edge detection
Laparoscopes
Laparoscopy
Lighting
Matching
Minimally invasive surgery
Optimization
Robustness
stereo matching
Texture
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Stereo matching has become an active area of research in the field of computer vision. In minimally invasive surgery, stereo matching provides depth information to surgeons, with the potential to increase the safety of surgical procedures, particularly those performed laparoscopically. Many stereo matching methods have been reported to perform well for natural images, but for images acquired during a laparoscopic procedure, they are limited by image characteristics including illumination differences, weak texture content, specular highlights, and occlusions. To overcome these limitations, we propose a robust edge-preserving stereo matching method for laparoscopic images, comprising an efficient sparse-dense feature matching step, left and right image illumination equalization, and refined disparity optimization. We validated the proposed method using both benchmark biological phantoms and surgical stereoscopic data. Experimental results illustrated that, in the presence of heavy illumination differences between image pairs, texture and textureless surfaces, specular highlights and occlusions, our proposed approach consistently obtains a more accurate estimate of the disparity map than state-of-the-art stereo matching methods in terms of robustness and boundary preservation.
ISSN:0278-0062
1558-254X
DOI:10.1109/TMI.2022.3147414