Image Feature Matching in Weak-Texture Areas Using Edge Cues
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current stereo matching technologies face errors in matching low-texture areas due to factors like illumination influence and occlusion, leading to misjudgments when color is the sole criterion for determining successful matching.
Innovation Solution
The method involves acquiring and transforming images, detecting weak texture areas using edge detection algorithms, extracting feature points with Harris corners, and matching these points by minimizing color differences and calculating position differences within preset thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If color-only matching is used for determining successful matching, then the matching process is simple, but misjudgment occurs in low-texture areas with same color
Solution Approach 1:
The patent segments the matching process into multiple stages: first performing color-based coarse matching, then applying texture analysis and edge detection to refine the matching results. This multi-stage segmentation allows the system to maintain simplicity while improving accuracy by addressing low-texture area errors in subsequent refinement steps
Solution Approach 2:
The patent transitions from one-dimensional color-only matching to multi-dimensional matching by incorporating texture features, edge information, and gradient analysis. This dimensional expansion enables the system to distinguish between different regions with similar colors, thereby resolving misjudgments in low-texture areas
2Device complexity
If traditional stereo matching is used, then the process is straightforward, but errors occur due to illumination influence and occlusion
Solution Approach 1:
The patent performs preliminary actions by pre-processing images with filtering operations before matching, and by pre-identifying potential matching regions using color segmentation. These preliminary steps prepare the data for more accurate disparity calculation while maintaining a straightforward overall process structure
Solution Approach 2:
The patent introduces intermediary elements such as gradient maps, texture descriptors, and confidence maps that mediate between the input images and the final disparity calculation. These intermediaries help mitigate the effects of illumination variations and occlusion by providing additional contextual information
Data Source
AI summary
An image feature matching method is provided by the present disclosure. The method includes determining a first weak texture area of a first image and a second weak texture area of a second image based on an edge detection algorithm. First feature points of the first weak texture area and second feature points of the second weak texture area are extracted. The first feature points and the second feature points are matched by determining a target point for each of the first feature points from the second feature points. Once a position difference value between each first feature point and the corresponding target point is determined, a matching point for each first feature point is determined according to the position difference value between the each first feature point and the corresponding target point.