Efficient feature detection using OBAloG: optimized box approximation of Laplacian of Gaussian
Year: 2010
Type: dissertation
Abstract: This thesis presents a novel approach for detecting robust and scale invariant interest points in images.The detector accurately and efficiently approximates the Laplacian of Gaussian using an optimal set of weighted box filters that take advantage of integral images to reduce computations.When combined with state-of-the art descriptors for matching, the algorithm performs better than leading feature tracking algorithms including SIFT and SURF in terms of speed and accuracy.
Author: Vinayak Reddy Jakkula
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W33143622