PROJECT TITLE :
Human action recognition and analysis algorithm for fixed and moving cameras
A replacement algorithm for human action recognition is presented. The employment of each front and side views of the optical flow (OF) in multiple layers representing completely different angles is proposed. The facet read of the OF, created from the frontal read, is introduced as a replacement feature. It improves recognition accuracy and provides a lot of information about the action such as the number of repetitions. Two-dimensional (2D) discrete Fourier rework is applied to the obtained OF features that makes the algorithm not sensitive to translation and alignment. 2D principal element analysis is employed to extract features from the eigenspace maintaining the spatial relation between pixels and increases the popularity accuracy. Results of experiments performed on four diverse datasets, Weizmann, IXMAS, KTH, and UCF sports, representing fixed and moving cameras, ensure these glorious properties compared with recent reported strategies.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here