Construction Deformation Tracking Across Misaligned Time-Series Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining the secular change in construction deformations, such as cracks in infrastructure, are inefficient due to misalignment issues in image capture conditions, requiring extensive processing time to align deformations across images captured at different times.
Innovation Solution
An information processing apparatus that selects important deformations based on predefined criteria, calculates matching degrees, and determines a reference deformation to efficiently assess the progress of these deformations, focusing on those with significant impact on construction soundness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all deformations are processed to obtain corresponding relationships while taking into account misalignment across images, then measurement precision is improved, but processing time increases significantly
Solution Approach 1:
The patent segments the set of all deformations into two categories: reference deformations (selected based on predetermined criteria such as deformation type, size, or location) and non-reference deformations. The image is divided into a reference deformation extraction target range that focuses only on regions containing reference deformations. This segmentation allows the system to process only critical deformations in detail while handling other deformations more efficiently, thus resolving the contradiction between measurement precision and processing time.
Solution Approach 2:
The patent extracts and isolates reference deformations from the complete set of deformations by applying predetermined selection criteria. By taking out only the most important deformations (those meeting the selection criteria) for detailed correspondence analysis, the system maintains high measurement precision for critical deformations while reducing the overall processing burden. This extraction approach directly addresses the contradiction by focusing computational resources on what matters most.
2Loss of time
If only a portion of deformations is selected for determination, then processing time is reduced, but measurement precision may be compromised
Solution Approach 1:
The patent applies local quality by differentiating the processing approach for different deformations based on their importance. Reference deformations (selected by predetermined criteria) receive detailed processing with full correspondence analysis and misalignment compensation, while non-reference deformations receive simplified processing. This local quality approach ensures that measurement precision is maintained for critical deformations while accepting reduced precision for less important ones, thereby resolving the contradiction between processing time and measurement precision.
Data Source
AI summary
This invention provides a processing apparatus for determining a state of secular change of a deformation of a construction, comprising a selection unit that selects, as a target for determination of secular change, at least a portion of deformations from among a plurality of deformations included in a first image at a first time period, on the basis of at least one of information relating to deformations, information relating to the construction, user selection, or a shape and a relative positional relationship of two or more deformations; a first determination unit that determines a deformation corresponding to a selected deformation among a plurality of deformations included in a second image at a second time period; and a second determination unit that determines a state of secular change between a selected deformation and a deformation determined by the first determination unit.