Search results
30 mar 2022 · We tackle the problem of online surgical phase recognition in laparoscopic procedures, which is key in developing context-aware supporting systems. We propose a novel approach to take temporal context in surgical videos into account by precise modeling of temporal neighborhoods.
26 sty 2010 · Using one of these so-called camera matrices, you can "project" a 3D point M on the scene to the 2D image of the camera on to pixel coordinate m (as in the tutorial). We will use this to triangulate the real 3D point from 2D points found in your video.
The surgical process is modeled as a spatial-temporal graph. Elements (e.g. individual operative notions) in surgery are modeled as graph nodes (color points). The interactions of the elements are modeled as graph hyperedges (black squares) and inferred via message passing during video analysis.
27 wrz 2023 · Illustration of surgical Dynamic Scene Graph (DSG) creation: a) Video recorded from the microscopic view of cataract surgery b) semantic segmentation maps indicating anatomical structures and tools c) static scene graphs constructed for each frame highlighting
25 wrz 2023 · In this work, we exploit scene graphs as a more holistic, semantically meaningful and human-readable way to represent surgical videos while encoding all anatomical structures, tools, and their interactions.
21 wrz 2022 · Understand how to calculate distance between two points / objects in an image or video; Convert pixel distance to real world measurements; Conceptualize how estimating distance can be applied to other use cases; Components of Computer Vision for Measuring Distance
We demonstrate results in surgical video data for tasks such as verification of the critical view of safety, estimation of the Parkland grading scale as well as recognizing instrument-action-tissue triplets.
