Table 2.

Computer Vision Technologies for Depth Sensing and Capsule Endoscope Localization

Study	suggested algorithm	Purpose	outcome
Karargyris et al. [14]	Shape-from-shading	Depth sensing	Create three dimensional-surfaced CE videos
Fan et al. [15]	SIFT, epipolar geometry	Depth sensing	Three-dimensional reconstruction of the GI tract’s inner surfaces from CE images
Park et al. [16]	Stereo-type capsule endoscope, direct attenuation model	Depth sensing	Create three-dimensional depth map, size estimation for lesions observed in stereo-type CE images
Turan et al. [24]	Vision-based SLAM, Shape-from-shading	Capsule localization	Improved RMSE for the three-dimensional reconstruction of stomach model and capsule trajectory length

CE, capsule endoscopy; GI, gastrointestinal; RMSE, root mean square error; SIFT, scale invariant feature transform; SLAM, simultaneous localization and mapping.