OR Video De-Identification With Depth-Based Personnel Tracking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing OR personnel detection and tracking systems face challenges under low lighting conditions and PPE coverage, and RGB cameras are unreliable for de-identification due to privacy concerns and PII, leading to inefficient OR resource management.

Innovation Solution

Utilizing depth cameras to generate 3D point clouds for OR personnel detection and tracking, leveraging machine-learning to identify 3D body shapes and joints, and projecting these onto RGB images for de-identification, while also tracking target objects like patient beds and surgical tables.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If RGB cameras are used to capture OR personnel, then visual feedback and workflow analysis are improved, but privacy protection deteriorates due to PII capture

Engineering Contradiction:

Improveworkflow informationVSAvoidprivacy violation

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The system extracts only the necessary geometric information (3D body shapes, joints, positions) from depth images while completely removing personally identifiable information (faces, names, identifiers) before workflow analysis. This allows workflow information to be captured without capturing harmful PII.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Depth images serve as an intermediary that provides geometric information about OR personnel without capturing visible PII. The depth data acts as a mediator between the need for workflow monitoring and the requirement for privacy protection, enabling analysis while maintaining anonymity.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Device complexity

If standard RGB cameras are used for personnel detection, then system complexity is reduced, but detection reliability deteriorates under PPE coverage and low lighting

Engineering Contradiction:

Improvecamera system complexityVSAvoidpersonnel detection reliability

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system changes the measurement parameter from optical intensity (RGB) to spatial distance (depth). Depth measurements are unaffected by lighting conditions or PPE coverage, providing reliable detection when RGB cameras fail while adding only moderate system complexity.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If wireless electronic tags are attached to patients for tracking, then tracking accuracy is improved, but workflow complexity increases due to attachment and removal requirements

Engineering Contradiction:

Improvepositional tracking accuracyVSAvoidworkflow protocol complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The depth camera system automatically detects and tracks personnel without requiring any attachments to patients or staff. The system serves itself by using the natural reflection of depth camera light off bodies, eliminating the need for wireless tags and their associated workflow complexities.

Inventive Principle:

Principle #25Self-service

4Use of energy by moving object

If RGB cameras operate in OR under surgical lights, then energy consumption is reduced, but image quality deteriorates due to low lighting conditions

Engineering Contradiction:

Improvecamera energy consumptionVSAvoidimage brightness

Core Design Contradiction:

Use of energy by moving objectVSIllumination intensity

Solution Approach 1:

The system replaces optical intensity-based imaging (RGB) with time-of-flight or phase-shift based depth imaging. This substitution allows operation in low-light conditions without additional illumination, as depth cameras can use infrared or other non-visible wavelengths that do not interfere with surgical lighting energy constraints.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Provides reliable personnel detection and tracking under PPE and low lighting, ensures high privacy protection, and enhances OR efficiency by automating event notifications.

Implementation Method 1

Depth sensors or depth cameras are imaging devices that produce two-dimensional (2D) images by casting lights (typically in infrared wavelengths) and measuring distances of points in a scene based on the travel time or intensity of the reflected light.

Methodology Applied

Scientific EffectTime of Flight: Time of Flight

Data Source

PatentUS20250308211A1Automatic de-identification of operating room (OR) videos based on depth images

Publication Date: 2025.10.02 AURIS HEALTH INC

AI summary

Embodiments described herein provide systems and techniques for tracking and de-identifying a person in a captured operating room (OR) video. In one aspect, a computer-implemented method may include detecting, from a three-dimensional (3D) point cloud generated based on a depth image, a 3D body corresponding to a person, wherein detecting the 3D body includes estimating a set of human-body keypoints for the person from a 3D-point cluster in the 3D point cloud; projecting the 3D body into a two-dimensional (2D) body outline in a color image to represent the person in the color image; and de-identifying the person in the color image based on the 2D body outline. Other aspects are also described and claimed.