There has been significant research into the development of visual feature detectors and descriptors that are robust to a number of image deformations. Some of these methods have emphasized the need to improve on computational speed and compact representations so that they can enable a range of real-time applications with reduced computational requirements. In this paper we present modified detectors and descriptors based on the recently introduced CenSurE, and show experimental results that aim to highlight the computational savings that can be made with limited reduction in performance. The developed methods are based on exploiting the concept of sparse sampling which may be of interest to a range of other existing approaches.
|Translated title of the contribution||SUSurE: Speeded Up Surround Extrema Feature Detector and Descriptor for Realtime Applications|
|Title of host publication||"Workshop on Feature Detectors and Descriptors: The State Of The Art and Beyond" as part of IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2009|
|Publication status||Published - 2009|
Bibliographical noteOther page information: -
Conference Proceedings/Title of Journal: "Workshop on Feature Detectors and Descriptors: The State Of The Art and Beyond" as part of IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2009
Other identifier: 2001018