Features from Accelerated Segment Test ( FAST )

FAST is an algorithm proposed originally by Rosten and Drummond [1] for identifying interest points in an image. An interest point in an image is a pixel which has a well-defined position and can be robustly detected. Interest points have high local information content and they should be ideally repeatable between different images [2]. Interest point detection has applications in image matching, object recognition, tracking etc.

[1]  Tom Drummond,et al.  Fusing points and lines for high performance tracking , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[2]  Ioannis Patras,et al.  The fast-3D spatio-temporal interest region detector , 2009, 2009 10th Workshop on Image Analysis for Multimedia Interactive Services.

[3]  Tom Drummond,et al.  Faster and Better: A Machine Learning Approach to Corner Detection , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Tom Drummond,et al.  Machine Learning for High-Speed Corner Detection , 2006, ECCV.