Interest-point matching refers to the process of matching two sets of features and finding similarities between them. It is a key technique for image registration. It is widely used for 3D shape reconstruction, change detection, medical image processing, computerized visioning systems, and pattern recognition. Although numerous algorithms have been developed for different applications, processing local distortion inherent in images that are captured from different viewpoints remains problematic.
High-resolution satellite images are normally acquired at widely spaced intervals and typically contain local distortion due to ground relief variation. Interest point matching algorithms can be grouped into two broad categories: area-based and feature-based. Although each type has its own particular advantages in specific applications, they all face the common problem of dealing with ambiguity in smooth (low texture) areas, such as grass, water, highway surfaces, building roofs, etc.
This invention is a new algorithm for interest point matching of high-resolution satellite images. The conceptual basis of this algorithm is the detection of ‘super points’, points which have the greatest interest strength and the subsequent construction of a control network using the super points. Sufficient spatial information is then available to reduce the ambiguity and avoid false matches. It is simple, fast, and accurate.
The novel features of the algorithm are:
A prototype has been developed and successfully tested on a small scale (lab testing).
This technology is available for licensing.
Office of Research Services, Industry-Government Services
University of New Brunswick
Phone: (506) 453-4674
partner@unb.ca