ANALYSIS OF HUMAN ACTIVITY RECOGNITION USING ACTION RECOGNITION METHODS
Journal Title: Elysium Journal of Engineering Research and Management - Year 2016, Vol 3, Issue 3
Abstract
The labelling of image sequences with action labels is termed as human action recognition and the main goal of this process is the series observations on actions. Human activity recognition aims to make better representation using deep and shallow learning techniques. For humans moving in the scene, we use techniques for tracking, body pose estimation, or space-time shape templates and categorize activities based on the video’s over- all pattern of appearance and motion using spatio - temporal interest operators and local descriptors to build the representation. It can be support for different fields of studies such as human computer interaction, or sociology, medicine and other applications. The system uses Binary Motion Image (BMI) to perform human activity recognition after preprocessing and used as input for Convolutional neural network (CNN) algorithm to recognize the human activity. The CNN combined with support vector machine (SVM) algorithm can be used as the classifiers to recognize the human action. The algorithm has three kind of inputs test samples, train samples, train labels. This project proposes a joint learning framework to identify the performance of Deep and Shallow Classifiers in training videos.
Authors and Affiliations
Anuradha R. , RAVIMARAN S.
Keywords
Related Articles
- EP ID EP365603
- DOI -
- Views 107
- Downloads 0
A Model for Trusted Cloud Computing with Remote Attestation
Enforcing an interactive pattern in any association will force it to behave in the predictable way thorough which it can be secured against any unauthorized access leading to a trusted atmosphere. Security declaration in...
BASED ON GREEN COMPUTING WORLD, THE HYBRID MALWARE DETECT MEMORY MAPPER IN KERNEL CENTRIC VIRTUAL MACHINE
Kernel malwares can provide user level-malware characteristics with additional probabilities of hiding their malicious activities by altering the legitimate kernel behavior of an operating system. Many researc...
SELECTION OF OPTIMAL MINING ALGORITHM FOR OUTLIER DETECTION - AN EFFICIENT METHOD TO PREDICT/DETECT MONEY LAUNDERING CRIME IN FINANCE INDUSTRY
Today, Money Laundering (ML) poses a serious threat and unique challenge to financial institutions. Most of the financial institutions internationally have been implementing Anti-Money Laundering solutions (AML) to fight...
An Efficient Ant Colony Optimization (ACO) for Dynamic Optimal Power Flow in Active Distribution Networks
Renewable Distributed Generations (DG) with high penetration becomes the requirement for Active Distribution Networks (ADN). In the proposed work, the Dynamic Optimal Power Flow output can be improved with the help of An...
GEO-DISTRIBUTED MAP REDUCE FRAMEWORK FOR COST EFFICIENT BIG DATA ANALYSIS
Big data analysis is one of the major challenges of current era. The limits to what can be done are often times due to how much data can be processed in a given time-frame Implementation of map reduce framework in Hadoop...