Human Action Recognition Using Transfer Learning with Spatio-Temporal Templates

فاقد چكيده

A gait energy image (GEI) is a spatial template that collapses regions of motion into a single image in which more moving pixels are brighter than others. The discrete wavelet transform template (DWT-TEMP) is a temporal template that represents the time changes of motion. The static and dynamic information of every video is compressed utilizing these templates. In the proposed method, every video is parted into N groups of successive frames, and the GEI and DWT-TEMP are made for every group, resulting spatial and temporal templates. Transfer learning method has been utilized for classifying. It gives the recognition accuracies of 92.40%, 95.30% and 87.06% for UCF Sport, UCF-11 and Olympic Sport action datasets, respectively.