Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Apr 15, 2026

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1.3K

Data-driven spatio-temporal RGBD feature encoding for action recognition in operating rooms.

Andru P Twinanda1, Emre O Alkan, Afshin Gangi

  • 1ICube Laboratory, University of Strasbourg, CNRS, IHU Strasbourg, Strasbourg, France, twinanda@unistra.fr.

International Journal of Computer Assisted Radiology and Surgery
|April 8, 2015
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Surface-guided analysis of breast shape changes during postoperative radiotherapy by using a functional map framework.

Medical physics·2026
Same author

Profiling of desmoid tumors reveals frequent mutations in chromatin-remodeling genes and identifies an Immune-myogenic subtype.

European journal of cancer (Oxford, England : 1990)·2026
Same author

Surg-NAT+: negation-aware vision-language refinement for fine-grained surgical understanding.

International journal of computer assisted radiology and surgery·2026
Same author

GEN-Guard: correcting generalization failures for deployable federated surgical AI.

International journal of computer assisted radiology and surgery·2026
Same author

Endoshare: a publicly available, surgeons-friendly solution to de-identify and manage surgical videos.

Surgical endoscopy·2026
Same author

S4M: 4-points to segment anything.

International journal of computer assisted radiology and surgery·2026

This study introduces a novel non-rigid feature encoding method for surgical action recognition in operating rooms. The new approach improves classification accuracy using multi-view RGBD data, enhancing surgical workflow systems.

Area of Science:

  • Computer Vision
  • Medical Informatics
  • Surgical Workflow Analysis

Background:

  • Context-aware systems in operating rooms (OR) can enhance surgical workflow through applications like scheduling and automatic transcription.
  • Surgical action recognition is a key component for developing these context-aware OR systems.
  • Classifying surgical actions from video is crucial for improving OR efficiency and safety.

Purpose of the Study:

  • To classify surgical actions from video clips recorded in an operating room environment.
  • To develop and evaluate a novel feature encoding method for surgical action recognition.
  • To leverage multi-view RGBD data for enhanced surgical action classification.

Main Methods:

  • Acquired multi-view RGBD video recordings from a hybrid OR during X-ray-based procedures.

More Related Videos

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.6K

Related Experiment Videos

Last Updated: Apr 15, 2026

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

1.3K
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
05:12

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 2021

2.6K
  • Utilized a bag-of-words (BoW) classification pipeline for action recognition.
  • Proposed a novel non-rigid feature encoding method learning a data-driven layout from 4D spatio-temporal feature locations, contrasting with traditional rigid grid layouts.

    • Main Results:

    • A new dataset comprising 1734 video clips of 15 surgical actions (generic and procedure-specific) was created from 11-day recordings.
    • The proposed non-rigid feature encoding method outperformed the rigid encoding approach.
    • Classifier accuracy increased by over 4%, from 81.08% to 85.53%.

    Conclusions:

    • Combining intensity and depth information from RGBD data offers superior discriminative power for surgical action recognition compared to using either modality alone.
    • The novel non-rigid spatio-temporal feature encoding scheme yields more discriminative histogram representations than rigid methods.
    • This work represents the first reported action recognition results using multi-view RGBD data recorded in an OR setting.