Optical Marker Localization Using Diverse Camera Channels
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vision systems using fiducial markers do not meet safety standards for machine safety or functional safety, and 3D cameras do not inherently provide safety levels, leading to potential errors in pose determination and localization.
Innovation Solution
A camera device with at least two diverse camera channels, each processing image data differently, compares poses determined from first and second image data to ensure reliability and safety, using a control and evaluation unit to output safeguarding signals when poses differ beyond tolerances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional vision systems with fiducial markers are used, then the localization process is simplified and robustness is improved, but safety standards for machine safety and functional safety are not met
Solution Approach 1:
The camera device is divided into at least two diverse camera channels, where each channel independently processes image data to determine pose. This segmentation allows the system to meet safety standards through redundant evaluation while maintaining manageable complexity in each individual channel.
Solution Approach 2:
Each camera channel is configured with different local qualities - using diverse image processing methods, different evaluation algorithms, or different sensor types (e.g., 2D vs. 3D cameras). This local differentiation ensures that no single point of failure compromises the entire system's safety level.
2Reliability
If a single camera channel is used for marker localization, then the device complexity is reduced, but the reliability and safety level are insufficient
Solution Approach 1:
The control unit compares pose determinations from multiple camera channels and uses this feedback to validate results. When the pose determinations agree within tolerances, the system confirms accurate localization; when they differ, the system can trigger safety responses or request re-evaluation.
3Reliability
If diverse camera channels with different processing methods are used, then functional safety and integrity levels are ensured, but the processing complexity and computational load increase
Solution Approach 1:
The system performs preliminary pose determination in each camera channel independently before comparison. This preliminary action allows parallel processing of image data through different methods, reducing the computational burden on any single processor while ensuring comprehensive safety evaluation.
Data Source
AI summary
A camera device for localizing an optical marker is provided that has at least one image sensor and a control and evaluation unit. A first camera channel for recording first image data having the optical marker is formed from the image sensor and the control and evaluation unit. The control and evaluation unit is configured to locate the optical marker in the first image data and to determine a first pose of the optical marker relative to the camera device. A second camera channel for recording second image data having the optical marker is formed from the image sensor and the control and evaluation unit. The control and evaluation unit is configured to locate the optical marker in the second image data, to determine a second pose of the optical marker relative to the camera device, and to compare the first pose and the second pose with one another.