Loading...
Please wait, while we are loading the content...
Similar Documents
Quasi-random scale space approach to robust keypoint extraction in high-noise environments (2010)
| Content Provider | CiteSeerX |
|---|---|
| Author | Wong, Er Mishra, Akshaya Clausi, David A. Fieguth, Paul |
| Description | A novel multi-scale approach is presented for the pur-pose of robust keypoint extraction in high-noise environ-ments. A multi-scale representation of the noisy scene is computed using quasi-random scale space theory. A gra-dient second-order moment analysis is employed at each quasi-random scale to identify initial keypoint candidates. Final keypoints and their characteristic scales are selected based on the local Hessian trace extrema over all quasi-random scales. The proposed keypoint extraction method is designed to reduce noise sensitivity by taking advantage of the structural localization and noise robustness gained through the use of quasi-random scale space theory. Exper-imental results using scenes under different high noise con-ditions, as well as real synthetic aperture sonar imagery, show the effectiveness of the proposed method for noise ro-bust keypoint extraction when compared to existing keypoint extraction techniques. 1 |
| File Format | |
| Language | English |
| Publisher Date | 2010-01-01 |
| Publisher Institution | In Proceedings of the Canadian Conference on Computer and Robot Vision (CRV |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
