Image Data Segmentation Using Multi-Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Scanners struggle to effectively segment and separate multiple objects of different types, including two-dimensional and three-dimensional objects, from one another and from backgrounds, due to limitations in processing and optimizing image data based on object classification or type.
Innovation Solution
A computing system employs a sensor cluster that captures image data comprising color pixel data, IR data, and depth data, which is segmented into a list of objects based on computed features, with object types determined and refined using algorithms such as edge detection, texture analysis, and object classification, resulting in a refined output list of segmented objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple objects are scanned simultaneously, then productivity is improved, but measurement precision deteriorates due to inability to segment objects from one another and from background
Solution Approach 1:
The patent applies segmentation by dividing the scanned image data into multiple distinct object regions using edge detection algorithms and texture analysis. The system segments objects from each other and from the background by identifying boundaries based on computed features such as edges, textures, and depth information, enabling precise separation of multiple objects scanned simultaneously.
Solution Approach 2:
The patent incorporates depth data as an additional dimension to differentiate objects. By utilizing depth information from the sensor cluster alongside color and IR data, the system can distinguish between objects at different depths and segment them effectively, resolving the contradiction between scanning multiple objects and maintaining segmentation accuracy.
2Measurement precision
If object classification algorithms are applied, then measurement precision is improved, but device complexity increases due to multiple processing steps
Solution Approach 1:
The patent merges multiple processing functions into a unified object classification system. The sensor cluster simultaneously captures color pixel data, IR data, and depth data, which are then processed together through integrated algorithms that perform edge detection, texture analysis, and object classification in a coordinated manner, reducing overall system complexity while maintaining high measurement precision.
Solution Approach 2:
The patent implements multi-functional processing algorithms that can handle various object types and classification requirements using the same core processing framework. The system uses universal feature extraction and classification methods that adapt to different object characteristics, eliminating the need for separate specialized processing chains for each object type.
Data Source
AI summary
According to one example for segmenting image data, image data comprising color pixel data, IR data, and depth data is received from a sensor. The image data is segmented into a first list of objects based on at least one computed feature of the image data. At least one object type is determined for at least one object in the first list of objects. The segmentation of the first list of objects is refined into a second list of objects based on the at least one object type. In an example, the second list of objects is output.