Sequence #11
Sequence #15
Sequence #44
Sequence #74
Figure 1: Results for the non-occluded ground truth of the four KITTI training image sequences which include illumination changes. For each sequence, first image: flow field with flow color-code, second: flow error and third image: histogram representation of the bad pixel (in %).
Robust bladder image registration by redefining data-term in variational approach
Submitted by Anonymous (not verified) on Mon, 11/03/2014 - 17:45
Cystoscopy is the standard procedure for bladder cancer diagnosis. Bladder tumors are often multifocal and spread over large areas. Localization and follow-up of these tumors and their nearby sites is necessary. But, due to the small field of view (FOV) of the cystoscopic video images clinicians cannot easily interpret the scene. 2-D bladder mosaicing using image registration facilitates this interpretation through the visualization of entire lesions with respect to anatomical landmarks.
Tags: