Borehole Image Feature Alignment via Global Solution Pruning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual post-processing of borehole images from wireline and downhole imaging tools is time-consuming and expensive due to misalignment of sub-images, which requires manual adjustment of features to create an accurate, aligned image of the borehole.
Innovation Solution
A method using a processing system to align borehole sub-images by estimating missing information, locating reference feature points, matching candidate feature points through local and global feature matching, and applying global solution pruning to automate the image alignment process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual post-processing is used to align sub-images, then alignment accuracy is improved, but time consumption and cost increase significantly
Solution Approach 1:
The system performs self-alignment by automatically detecting features in sub-images, computing transformation parameters, and adjusting the sub-images without human intervention. The computer implementation autonomously completes the alignment task that previously required manual interpretation engineer work, thereby reducing time consumption while maintaining alignment accuracy.
Solution Approach 2:
The manual mechanical process of visually inspecting and manually adjusting sub-images is replaced with a computer-based automated system. The computer implementation uses algorithmic feature detection and mathematical transformation computations to substitute the manual alignment process, achieving both time efficiency and precision.
2Area of stationary object
If multiple sub-images are collected from different pads and locations, then complete borehole coverage is improved, but alignment difficulty increases
Solution Approach 1:
The borehole imaging task is divided into multiple sub-images captured by different pads at different locations. Each pad independently captures a portion of the borehole, and the computer implementation subsequently integrates these segmented sub-images through automated feature matching and transformation, making the complex multi-pad integration manageable and systematic.
Solution Approach 2:
The computer implementation acts as an intermediary that bridges multiple sub-images from different pads and locations. It detects features in each sub-image, computes transformation parameters, and integrates them into a unified aligned image, thereby simplifying the complexity of combining multiple data sources.
3Manufacturing precision
If features are manually adjusted to align sub-images, then alignment precision is improved, but productivity decreases
Solution Approach 1:
The system performs self-alignment by automatically detecting features in sub-images, computing transformation parameters, and adjusting the sub-images without human intervention. The computer implementation autonomously completes the alignment task that previously required manual interpretation engineer work, thereby reducing time consumption while maintaining alignment accuracy.
Solution Approach 2:
The computer implementation changes the approach from manual parameter adjustment to automated parameter computation. It uses algorithmic feature detection and mathematical transformation computations to determine alignment parameters, achieving both precision and improved productivity through automated parameter optimization.
Data Source
AI summary
Image feature alignment is provided. In some implementations, a computer-readable tangible medium includes instructions that direct a processor to access a reference feature point associated with a high contrast region in a first sub-image that is associated with a first section of a borehole. Instructions are also present that direct the processor to identify several candidate feature points in a second sub-image associated with a second section of the borehole adjacent to the first section of the borehole, with each of the candidate feature points being believed to possibly be associated with the high contrast region. Additional instructions are present that direct the processor to prune the candidate feature points using global solution pruning to arrive at a matching candidate feature point in the second sub-image.