This work with Mosalam Ebrahimi looks at ways to sample images and data for making computer vision algorithms more efficient. The question is not whether things can be faster but what data should an algorithm work with. The results can be algorithms that are faster and have very close performance to an algorithm that uses the entire image. Sampling can be extended to other parts of a visual pipeline and work is under way.
- Mosalam Ebrahimi, Walterio Mayol-Cuevas, SUSurE: Speeded Up Surround Extrema Feature Detector and Descriptor for Realtime Applications. "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. June 2009. PDF.
- Mosalam Ebrahimi, Walterio Mayol-Cuevas, Adaptive Sampling for Feature Detection, Tracking and Recognition on Mobile Platforms. IEEE Transactions on Circuits and Systems for Video Technology, . ISSN 1051-8215. September 2011. PDF.