Deep Neural Network Approachesfor Video Based Human Activity Recognition

Authors : Chaitanya Yeole; Hricha Singh; Hemal Waykole; Anagha Deshpande

Volume/Issue : Volume 6 - 2021, Issue 6 - June

Google Scholar :

Scribd :

- In this paper we explained, tried, and tested methods of Human Action recognition for the application of video surveillance. This paper provides a method for automatically recognizing human activities included in video sequences captured by a single large view camera in outdoor locations. The elaboration of the dataset which are videos are taken with the resolution of 720x480, precisely explained. The methods we implement are CNN-VGG16 model and the Single-frame CNN model. We demonstrated our techniques using real-world video data to automatically distinguish normal behaviors from suspicious ones in a playground setting, films of continuous performances of six different types of humanhuman interactions: handshakes, pointing, hugging, pushing, kicking, and punching. As per the observation, we concluded that the Single frame CNN model shows much better results as compared to CNN VGG16. The implementation was done in python. This paper consist of how theconvolution neural networks' simpleclassification method proved to be efficient for the prediction of the activity by using a single frame method. The working of this method is briefly mentions in the methodology. The difference and the drawback of these methods forhuman activity recognition can be clearly seen inthe output and results of the respective.

Keywords : Artificial Intelligence (AI) Models AreCreated to Perceive the Movement of Human from the Provided Dataset


Paper Submission Last Date
28 - February - 2023

Paper Review Notification
In 1-2 Days

Paper Publishing
In 2-3 Days

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.