Nick's Machine Perception Toolbox

Key Features

• FastSalience: An implementation of the "Fast Salience Using Natural-statistics" algorithm from Butko et al., 2008. If this code is used in your research, please cite both the paper and this NMPT package. FastSUN is an efficient implementation of Zhang et al.'s SUN algorithm (see Related Publications). • MIPOMDP: An implementation of the "Multinomial Infomax-POMDP" algorithm from Butko and Movellan, 2009. If this code is used in your research, please cite both the paper and this NMPT package. MIPOMDP is an extension of the IPOMDP Infomax Model of Eye-movment in Butko and Movellan, 2008; Najemnik and Geisler, 2005 (see Related Publications). • GentleBoostClassifier and GentleBoostCascadedClassifier: An implementation of a fast approach to object detection, described in Fasel 2006 (see Related Publications). GentleBoostClassifier is useful for two-way classification whole images (or image patches). GentleBoostCascadedClassifier is useful for learning very efficient object detectors that search for objects in video in real time. • InternalMotionModel: An implementation of the method described in Butko and Movellan, 2010 (see Related Publications) for allowing robots to learn how their eyes work.