Human Action Recognition using a Hybrid NTLD Classifier

This work proposes a hybrid classifier to recognize humanactions in different contexts. In particular, the proposedhybrid classifier (a neural tree with linear discriminantnodes NTLD), is a neural tree whose nodes can be eithersimple preceptrons or recursive fisher linear discriminant(RFLD) classifiers. A novel technique to substitute badtrained perceptron with more performant linear discriminatorsis introduced. For a given frame, geometrical featuresare extracted from the skeleton of the human blob (silhouette).These geometrical features are collected for a fixednumber of consecutive frames to recognize the correspondingactivity. The resulting feature vector is adopted as inputto the NTLD classifier. The performance of the proposedclassifier has been evaluated on two available databases.