Object movement identification via sparse representation

Abstract

Object Movement Identification from videos is very challenging, and has got numerous applications in sports evaluation, video surveillance, elder/child care, etc. In thisresearch, a model using sparse representation is presented for the human activity detection from the video data. This is done using a linear combination of atoms from a dictionary and a sparse coefficient matrix. The dictionary is created using a Spatio Temporal Interest Points (STIP) algorithm. The Spatio temporal features are extracted for the training video data as well as the testing video data. The K-Singular Value Decomposition (KSVD)algorithm is used for learning dictionaries for the trainingvideo dataset. Finally, human action is classified using aminimum threshold residual value of the corresponding actionclass in the testing video dataset. Experiments are conducted onthe KTH dataset which contains a number of actions. Thecurrent approach performed well in classifying activities with asuccess rate of 90%.