Narrow Baseline Disparity Reconstruction Method Based on Multiscale Superpixels and Phase Correlation
A phase correlation, superpixel technology, applied in the field of computer vision, can solve problems such as obesity, inability to reconstruct correctly, and less matching information
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0052] Such as figure 1 Shown is a schematic flow chart of the overall method of the present invention, which mainly includes three parts: image registration (Image coregistration), pixel-level disparity estimation (Pixel-level disparity estimation) and sub-pixel parallax refinement (Subpixel refinement), in the In one step, a global similarity transformation model between two input images (Left image and Right image) is obtained by using the sub-pixel precision Fourier-Melin Transform (Fourier-Media Transform), and then, through the multi-scale superpixel way to iteratively estimate pixel-level disparity. In each iteration, a simple linear iterative clustering (SLIC) method is employed to segment the input image into a different number of superpixels. Pixel-level phase correlation is performed using a window size and position determined from superpixels. Also implement reliability checks to ensure robustness in low texture areas. Subsequently, pixels with the same superpix...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com