Operating Room Depth Cameras for Object and Workflow Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing OR workflow management systems face challenges in accurately tracking personnel and objects while maintaining privacy, particularly under conditions of low lighting and with Personal Protective Equipment (PPE) usage, and existing solutions like RGB cameras are unreliable and costly.
Innovation Solution
Utilizing depth cameras to capture 3D geometric information for personnel detection and tracking, combined with machine learning to generate 3D body shapes and skeletons, and identifying target objects like patient beds and surgical tables, enabling privacy-protected OR workflow management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If RGB cameras are used to capture OR videos for workflow management, then visual feedback from OR events is obtained, but privacy concerns arise requiring de-identification processing that adds cost and complexity
Solution Approach 1:
The patent extracts only the essential geometric information (depth data, 3D body shapes, skeletal structures) from the visual scene while leaving out all personally identifiable visual features. This allows workflow monitoring to proceed using only structural and spatial data, eliminating the need for complex de-identification processing while maintaining privacy.
Solution Approach 2:
The patent creates a simplified 3D geometric copy of the OR scene that captures workflow-relevant information (object positions, personnel movements, body postures) without replicating visual identifiers. This geometric model serves as a privacy-protected representation that enables workflow analysis without exposing personal information.
2Reliability
If standard RGB cameras are used for personnel detection, then color images are captured, but detection reliability deteriorates under low lighting and with PPE coverage
Solution Approach 1:
The patent transitions from 2D color image analysis to 3D depth-based geometric analysis. By capturing depth information and reconstructing 3D body shapes and skeletal structures, the system achieves reliable personnel detection independent of lighting conditions and PPE coverage, as depth geometry remains detectable regardless of visual appearance changes.
3Measurement precision
If wireless electronic tags or trackers are attached to patients for tracking, then positional information is obtained with good accuracy, but workflow complexity increases and attachments must be removed during surgery preparation
Solution Approach 1:
The patent enables the environment to serve itself by using depth cameras and AI algorithms to automatically detect, track, and monitor personnel and objects without requiring any attachments or external tracking devices on patients or staff. The system passively captures geometric data and derives positional information, eliminating the need for active tracking hardware.
Solution Approach 2:
The patent replaces mechanical/electronic tracking devices (tags, transponders) with an optical sensing system based on depth cameras and computer vision algorithms. This substitution eliminates the need for physical attachments while achieving comparable or superior tracking accuracy through non-contact geometric measurement.
4Reliability
If depth cameras are used to capture 3D geometric information for tracking, then privacy protection is improved and lighting condition reliability is enhanced, but device complexity and cost increase
Solution Approach 1:
The patent makes the depth camera system multi-functional by using it for both personnel tracking and object tracking simultaneously. The same depth sensing infrastructure supports multiple workflow monitoring functions (staff detection, patient monitoring, equipment tracking), amortizing the complexity and cost across diverse applications rather than requiring separate specialized systems.
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 and efficient tracking of OR personnel and objects, enhancing OR efficiency by automating event detection and reducing privacy concerns through depth-image-based techniques.
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.
Data Source
AI summary
Embodiments described herein provide systems and techniques for tracking workflow inside an operating room (OR) by identifying and tracking target objects, such as a patient bed or a surgical table in the OR. In one aspect, a process for identifying and tracking a target object in an OR begins by receiving a depth image among a sequence of depth images captured by a depth camera installed in the OR. The process then generates a three-dimensional (3D) point cloud based on the depth image. Next, the process identifies a set of potential target points in the 3D point cloud that potentially belongs to the target object based on one or more target object criteria. The process next extracts one or more object clusters of from the set of potential target points using a data-point clustering technique. The process subsequently identifies the target object from the extracted one or more object clusters.