3D Model Image Mapping for More Accurate Automated Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated classification techniques for photo-realistic images are inaccurate and imprecise, often producing indefinite classifications with confidence scores, necessitating a need for improved accuracy.
Innovation Solution
The classification of a photo-realistic image is adjusted based on the classifications produced by a machine learning engine for other images that correspond to the same portion of a 3D model generated from the photo-realistic images, using techniques such as Bayes' formula and model-centric segmentation to aggregate and refine classifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated classification using machine learning engine is used, then productivity is improved, but measurement precision deteriorates
Solution Approach 1:
The patent combines multiple image classifications from different images that map to the same 3D model portion to produce a single refined classification. This merging approach leverages the consistency across multiple images to improve classification accuracy while maintaining automated processing efficiency.
Solution Approach 2:
The system uses feedback from multiple image classifications to iteratively refine the classification of a target image. By analyzing classifications from other images that correspond to the same 3D model portion, the system adjusts and improves the accuracy of the target classification, creating a self-correcting automated classification process.
2Measurement precision
If manual tagging is used, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The system enables automated classification to self-correct and improve its own accuracy by leveraging consistency across multiple images. Instead of requiring manual review, the automated system uses the relationships between images and their shared 3D model portions to independently refine classifications, maintaining both speed and accuracy.
3Device complexity
If classification is based on single image analysis, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent transitions from analyzing a single image in isolation to analyzing multiple images within the context of their relationships to a shared 3D model. This dimensional expansion from single-image to multi-image analysis enables improved accuracy without requiring complex manual intervention, as the system leverages the additional dimension of cross-image consistency.
Data Source
AI summary
Techniques are provided for increasing the accuracy of automated classifications produced by a machine learning engine. Specifically, the classification produced by a machine learning engine for one photo-realistic image is adjusted based on the classifications produced by the machine learning engine for other photo-realistic images that correspond to the same portion of a 3D model that has been generated based on the photo-realistic images. Techniques are also provided for using the classifications of the photo-realistic images that were used to create a 3D model to automatically classify portions of the 3D model. The classifications assigned to the various portions of the 3D model in this manner may also be used as a factor for automatically segmenting the 3D model.