Open AccessEarly Action Prediction using 3DCNN with LSTM and Bidirectional LSTM
Author(s) -
Seetha M Mrs. Manju D
Publication year - 2021
Publication title -
türk bilgisayar ve matematik eğitimi dergisi
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.218
H-Index - 3
ISSN - 1309-4653
DOI - 10.17762/turcomat.v12i6.4833
Subject(s) - computer science , artificial intelligence , focus (optics) , convolutional neural network , action (physics) , action recognition , motion (physics) , variety (cybernetics) , long short term memory , machine learning , deep learning , recurrent neural network , artificial neural network , pattern recognition (psychology) , computer vision , physics , quantum mechanics , optics , class (philosophy)
Predicting and identifying suspicious activities before hand is highly beneficial because it results in increased protection in video surveillance cameras’. Detecting and predicting human's action before it is carried out has a variety of uses like autonomous robots, surveillance, and health care. The main focus of the paper is on automated recognition of human actions in surveillance videos. 3DCNN (3 Dimensional Convolutional Neural Network) is based on 3D convolutions, there by capturing the motion information encoded in multiple adjacent frames. The 3DCNN is combined with Long short team memory (LSTM) and Bidirectional LSTM for prediction of abnormal events from past observations of events in video stream. It is observed that 3DCNN with LSTM resulted in increased accuracy compared to 3DCNN with Bidirectional LSTM. The experiments were carried out on UCF crime Dataset.