Year: 2023
Type: article
Abstract: In this paper, we propose an optical flow-based guide system that infers relative velocity by detecting movements of colonoscopy tips and colon muscles.The colonoscopy speed guide system detects the behavioral patterns of consecutive frame-based objects based on the Lucas-Kanade, farneback, and RLOF algorithms, which are sparse and dense optical flow algorithms.The sensed motion pattern expresses motion through the movement of points in the object area.This value is also converted into a numerical value, enabling inference of relative velocity values.Therefore, when it is determined that the endoscope operation is more than a certain speed based on the inferred relative speed value, it is known to the medical staff in
Institutions: Gachon University, Gachon University Gil Medical Center
Language: English
Topic: Advanced Vision and Imaging
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4367367947