Human Activity Recognition

Read full text Summarise with VIRAT
Authors: Akhilesh Nishad
Cited by: 0
References: 5

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This project presents a dual-mode system that integrates Human Activity Recognition (HAR) with Hand and Eye Gesture Control using Python. The system is designed to ensure mutual exclusivity: when HAR is active, gesture control pauses, and when gesture control is active, HAR pauses. This approach eliminates conflicts between simultaneous recognition tasks and provides a seamless user experience. The gesture control module leverages OpenCV and Mediapipe to detect hand movements (scroll, zoom, cursor control) and eye gestures (blink, gaze navigation). The activity recognition module classifies human activities such as Sitting, Standing, Walking, Talking, and Laughing using machine learning techniques. An integration layer manages switching between modules, ensuring real-time responsiveness and reliability. The proposed system enhances humancomputer interaction by offering natural, intuitive control mechanisms. It is lightweight, cost-effective, and scalable, making it suitable for applicationsin desktop control, multimedia navigation, accessibility tools, and healthcare monitoring.

Fields of Study & Subjects

Hand Gesture Recognition Systems Context-Aware Activity Recognition Systems Gaze Tracking and Assistive Technology

Publication details

Journal / source
International Journal for Research in Applied Science and Engineering Technology
Volume
14
Issue
3
Pages
3329–3335
Publication date
26 March 2026
Language
EN