Salient Point Detector

The core spatiotemporal salient point detector is based on the method developed by Oikonomopoulos et al. (SMC-B’2006). It finds spatio-temporal salient points in an image sequence, and therefore takes a directory with an image sequence in png format as input. Some time/scale parameters need to be specified too.

In this updated version of the detector, a set of HOG/HOF descriptors is also extracted around each detected salient point. Each HOG/HOF descriptor is a 1×48 vector (4 blocks along the spatial dimension, 1 block along the temporal dimension, 12 bins per each block histogram), giving rise to a 102-dimensional descriptor around each detected point (also counting the 6-dimensional vector containing information over the spatiotemporal location of the detected point (3d), its spatiotemporal scale (2d) and its saliency value (1d)).

Read the included README.txt for more information. The package consists of a binary compiled from Matlab code. It is intended to run with the Matlab Component Runtime, so the user does not need to have a Matlab license.

• url: http://ibug.doc.ic.ac.uk/resources/salient-point-detector-2010/
• platform: Windows XP/vista only