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

A PROBABILISTIC APPROACH FOR PREDICTING ANOMALIES IN SOCIAL STREAMS

Basic presumption is that a new (emerging) topic is something people feel like discussing, commenting, or forwarding the information further to their friends. The proposed approach, spot the emergence of topics in a soci...

A Feature Learning and Object Recognition Framework for Underwater Fish Images with Segmentation

Live fish recognition is one of the most decisive elements of fisheries analysis where the massive amount of data is promptly assimilated .Diverse from wide-ranging scenarios, experiments to underwater image recognition...

WEAK INDIAN RUPEE – ISSUES AND CHALLENGES

Investors usually won’t spend much time on studying the currency movement. Many skipped the news of the Indian rupee hitting as low of against the dollar, even though it would hurt the econ...

DETECTION AND PREVENTION OF MALICIOUS FEEDBACK RATING IN WEB SERVICE RECOMMENDATION SYSTEMS

To facilitate a recommendation to users for selecting an appropriate or reputed web service from mass of services by avoiding dishonest recommendation. To prevent, avoid and de...

Effective Detection of Cervical Cancer During Pap Smear Screening Test

Mostly Woman is affected by cervical cancer in their different age groups. So, most of the Researchers, Pathologists prove more number of solutions to identify this cancer from the test images of pap smear screening test...

Download PDF file
  • EP ID EP365603
  • DOI -
  • Views 111
  • Downloads 0

How To Cite

Anuradha R. , RAVIMARAN S. (2016). ANALYSIS OF HUMAN ACTIVITY RECOGNITION USING ACTION RECOGNITION METHODS. Elysium Journal of Engineering Research and Management, 3(3), -. https://europub.co.uk/articles/-A-365603