Local Adaptive Histogram Equalization for Image Region Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Image alignment techniques face challenges in accurately matching regions across images captured by asymmetric sensors, which leads to errors in stereoscopic depth maps due to varying intensity values, especially in spatially varying illumination conditions.
Innovation Solution
The implementation of local intensity equalization techniques, which segment images into regions, perform local histogram matching, and apply bilinear interpolation, ensures equalized intensity variation across images, thereby improving region matching accuracy by adapting to local changes in intensity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If global histogram equalization is used to equalize intensity across images, then overall intensity uniformity is improved, but local intensity variations and spatially varying illumination effects are not adequately addressed, leading to matching errors in specific regions
Solution Approach 1:
The patent divides the image into multiple local regions or blocks, and performs histogram equalization independently on each region. This segmentation allows the method to adapt to local intensity variations while maintaining overall intensity uniformity, resolving the contradiction between global uniformity and local adaptability.
Solution Approach 2:
The patent applies different intensity equalization parameters to different local regions of the image. By making the equalization process local rather than global, the method can adapt to spatially varying illumination conditions and preserve local intensity relationships, thereby improving region matching accuracy in diverse lighting conditions.
2Device complexity
If asymmetric sensors are used to capture different views in stereoscopic imaging, then device complexity and cost are reduced, but intensity variations between corresponding features in different images occur, degrading matching precision
Solution Approach 1:
The patent modifies the intensity parameters of one or more images through histogram equalization to match the intensity distribution of corresponding features. By changing the intensity parameters locally in different regions, the method compensates for sensor asymmetries and achieves precise intensity matching without requiring symmetric sensors.
3Measurement precision
If local histogram matching is performed on each block, then local intensity equalization is improved, but computational complexity increases compared to global histogram equalization
Solution Approach 1:
The patent segments the image into multiple blocks and performs histogram equalization on each block independently. While this increases localization accuracy, the segmentation itself provides a structured approach that can be efficiently implemented through parallel processing, mitigating the computational complexity increase.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Certain aspects relate to systems and techniques for performing local intensity equalization on images in a set of images exhibiting local intensity variations. For example, the local intensity equalization can be used to perform accurate region matching and alignment of the images. The images can be partitioned into regions of pixel blocks, for instance based on location, shape, and size of identified keypoints in the images. Regions depicting the same feature in the images can be equalized with respect to intensity. Region matching based on the keypoints in the intensity-equalized regions can be performed with accuracy even in images captured by asymmetric sensors or exhibiting spatially varying intensity.