Camera Field Occlusion Mapping Around Target Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In robotics and automation, camera data used for object recognition can be affected by noise and inaccuracies due to occlusion, leading to errors in robot interaction with objects, particularly in environments like warehouses and manufacturing plants.
Innovation Solution
A computing system and method that determines occlusion within a camera field of view by identifying a target feature, determining a 2D and 3D region, calculating the size of an occluding region, and adjusting object recognition confidence parameters to improve interaction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If camera data is used for object recognition in cluttered environments, then robot interaction capability is enabled, but measurement precision deteriorates due to occlusion and noise
Solution Approach 1:
The system performs preliminary occlusion analysis by determining a 3D region from the camera field of view and identifying occluding regions before object recognition. This preliminary action allows the system to assess potential occlusion issues and adjust processing accordingly, improving measurement precision while maintaining robot interaction capability in cluttered environments
Solution Approach 2:
The patent introduces an intermediary occlusion assessment mechanism that acts between the camera data and object recognition process. By determining occluding regions and their impact on target features, this intermediary layer filters and adjusts the camera data, resolving the contradiction between enabling robot interaction and maintaining recognition accuracy
2Measurement precision
If occlusion assessment is performed to improve object recognition accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system segments the camera field of view into a 3D region and further identifies specific occluding regions within that space. This segmentation approach allows precise occlusion assessment only where needed, improving object recognition accuracy while avoiding the complexity of analyzing the entire scene
Solution Approach 2:
The patent applies local quality by focusing occlusion analysis specifically on regions affecting target features rather than the entire camera field of view. By determining occluding regions locally around relevant objects and features, the system achieves high measurement precision without proportionally increasing device complexity
Data Source
AI summary
A system and method for determining occlusion are presented. The system receives camera data generated by at least one camera, which includes a first camera having a first camera field of view. The camera data is generated when a stack having a plurality of objects is in the first camera field of view, and describes a stack structure formed from at least an object structure for a first object of the plurality of objects. The system identifies a target feature of or disposed on the object structure, and determines a 2D region that is co-planar with and surrounds the target feature. The system determines a 3D region defined by connecting a location of the first camera and the 2D region. The system determines, based on the camera data and the 3D region, a size of an occluding region, and determines a value of an object recognition confidence parameter.