Visual Information Retrieval in Endoscopic Video Archives

TL;DR

This paper presents a demo application for retrieving specific video segments from endoscopic archives using visual features and late fusion, aiding surgeons in accessing relevant surgical footage on demand.

Contribution

It introduces a novel video retrieval system tailored for endoscopic videos, combining visual features with late fusion techniques for accurate shot re-identification.

Findings

Effective retrieval of endoscopic video shots demonstrated

System improves access to surgical documentation

Potential to enhance surgical review processes

Abstract

In endoscopic procedures, surgeons work with live video streams from the inside of their subjects. A main source for documentation of procedures are still frames from the video, identified and taken during the surgery. However, with growing demands and technical means, the streams are saved to storage servers and the surgeons need to retrieve parts of the videos on demand. In this submission we present a demo application allowing for video retrieval based on visual features and late fusion, which allows surgeons to re-find shots taken during the procedure.