Tiny Videos-based Cascade Boosting (TCB) Classifier on Human Action Recognition

  • R. Amsaveni, Dr. (Mrs). M.Punithavalli


Computer Vision is picking up significance with broad applications in video observation, video recovery and investigation, and human - computer communication. Discovery and recognition of human action from the video databases is extremely a troublesome and demanding job. The tiny video has been engaged to accomplish high video compression rates and it is concurrently holding the video's entire visual look since it modifies after some time. The tiny video representation is feasible to recognize the human actions. Further, the HVF feature descriptor extracts the motion feature from the video and helps to understand the actions faster. Therefore, human action detection and recognition is focused by utilizing Tiny Videos Based Cascade Boosting (TCB) classifier. At this point, the video is given as input, and it has an additional transient measurement in examination with pictures. The proposed TCB classifier accelerates both detector speed and accuracy with respect to a predictor that complies with the sequential decision-making structure of the cascade architecture. The investigational outcome demonstrates that the projected Tiny Video based Cascade Boosting (TCB) classifier achieved elevated performance than other human action recognition plans.

How to Cite
R. Amsaveni, Dr. (Mrs). M.Punithavalli. (2020). Tiny Videos-based Cascade Boosting (TCB) Classifier on Human Action Recognition. International Journal of Advanced Science and Technology, 29(6s), 427 - 433. Retrieved from http://sersc.org/journals/index.php/IJAST/article/view/8778