• MEGHA SHAH
• NITIN PANDYA

— Every moment counts in the recognition of the action a complete understanding of the human activity in the video requires labels according to the actions that occur, by placing several labels densely on a video sequence. Here are many issues related to the recognition of human action in videos, such as cluttered backgrounds, occlusions, variation in viewpoint, rate of execution, and camera movement. A large number of techniques in this search, the different datasets used are the KTH dataset, the Weizman dataset, the UCF Sport dataset, and so on. In this survey, we provide an overview of current methods based on the ability to solve these problems, as well as how these methods can be generalized and their ability to detect abnormal actions.

Action recognition, KNN (K-Nearest Neighbors),SVM, feature extraction.

"A SURVEY ON HUMAN ACTION RECOGNITION FROM VIDEO", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.359-364, February-2019, Available :http://www.jetir.org/papers/JETIR1902363.pdf

"A SURVEY ON HUMAN ACTION RECOGNITION FROM VIDEO", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp359-364, February-2019, Available at : http://www.jetir.org/papers/JETIR1902363.pdf