To get information about generation of synthetic data, please visit Virtaul Capsule Endoscopy repository. The experimental procedure of ex-vivo part of the dataset is demonstrated at YouTube. Sample trajectories from each organ is publicly available in Mendeley. Some of the sub-datasets include the same trajectories in two versions, e.g with and without polyps so that effect of having polyps as distinguishable features in the organ environment can be analysed, as well.We also provide images and pose values for two types of wireless endoscopes, which differ from each other in certain aspects like camera resolution, frame rate, and diagnostic results for detecting Z-line, duodenal papillae and bleeding. Images from different cameras with various resolutions for same organs and depth for each related organs are further unique features of the proposed dataset. Two different capsules and conventional endoscope cameras, with high and low resolution were used, so as to generate variety in camera specifications and lighting conditions.To the best of authors' knowledge, this is the very first dataset published to be used in capsule endoscopy SLAM tasks, with timed 6 DoF pose data and high precision 3D map ground truth.Specifically, 18, 5 and 12 sub-datasets exist for colon, small intestine and stomach respectively. The dataset is divided into 35 sub-datasets. The ex-vivo part of the dataset includes standard as well as capsule endoscopy recordings. We introduce an endoscopic SLAM dataset which consists of both ex-vivo and synthetically generated data. EndoSLAM Dataset and an Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos
0 kommentar(er)
