ACTION RECOGNITION BASED ON SPARSE MOTION TRAJECTORIES
Refereed Conference Meeting Proceeding
We present a method that extracts effective features in videos for hu- man action recognition. The proposed method analyses the 3D vol- umes along the sparse motion trajectories of a set of interest points from the video scene. To represent human actions, we generate a Bag-of-Features (BoF) model based on extracted features, and fi- nally a support vector machine is used to classify human activities. Evaluation shows that the proposed features are discriminative and computationally efficient. Our method achieves state-of-the-art per- formance with the standard human action recognition benchmarks, namely KTH and Weizmann datasets.
IEEE International Conference on Image Processing
Digital Object Identifer (DOI):
Dublin City University (DCU)
Open access repository: