18395090. POLARIZED SEMI-GLOBAL MATCHING simplified abstract (Intrinsic Innovation LLC)
Contents
POLARIZED SEMI-GLOBAL MATCHING
Organization Name
Inventor(s)
Achuta Kadambi of Los Angeles CA (US)
Agastya Kalra of Palo Alto CA (US)
Kerim Doruk Karinca of Mountain View CA (US)
Tomas Gerlich of Palo Alto CA (US)
Vage Taamazyan of Balashikha (RU)
POLARIZED SEMI-GLOBAL MATCHING - A simplified explanation of the abstract
This abstract first appeared for US patent application 18395090 titled 'POLARIZED SEMI-GLOBAL MATCHING
The patent application describes methods, systems, and apparatus for detecting pixel correspondences in stereo imaging using polarization data.
- Obtaining a first image and a second image from different viewpoints of a stereo pair.
- Obtaining an angle of linear polarization (AOLP) map and a degree of linear polarization (DOLP) map overlapping the first and second images.
- Computing a surface normal map based on the AOLP and DOLP maps.
- Detecting corresponding pixels between the first and second images by computing a disparity map that minimizes an energy function.
Potential Applications: - 3D imaging and mapping - Augmented reality - Robotics and autonomous navigation
Problems Solved: - Accurate pixel correspondence in stereo imaging - Improved depth perception and object recognition
Benefits: - Enhanced image quality and accuracy - Increased efficiency in stereo imaging applications
Commercial Applications: - Medical imaging systems - Surveillance and security systems - Virtual reality and gaming technology
Questions about the technology: 1. How does this technology improve the accuracy of pixel correspondences in stereo imaging? 2. What are the potential limitations of using polarization data for detecting pixel correspondences in stereo imaging?
Frequently Updated Research: - Ongoing research in the field of computer vision and image processing may lead to advancements in stereo imaging techniques using polarization data.
Original Abstract Submitted
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detection of pixel correspondences in stereo imaging through the use of polarization data. One of the methods include: obtaining a first image from a first viewpoint of a stereo pair and a second image from a second viewpoint of the stereo pair; obtaining an angle of linear polarization (AOLP) map and a degree of linear polarization (DOLP) map having a field of view overlapping the first image and the second image; computing a surface normal map based on the AOLP map and the DOLP map; and detecting corresponding pixels between the first image and the second image by computing a disparity map that minimizes an energy function comprising a pixel matching cost term and a polarized smoothness regularization term computed based on pixels in a local neighborhood and based on the surface normal map.
