Activity Track: Live Human Activity Detection & Alert System

DOI

10.2991/978-94-6463-858-5_39How to use a DOI?

Keywords

Human Activity Recognition; CNN; OpenCV; Video Surveillance; Kinetics Dataset; Alert system

Abstract

Human Activity Recognition (HAR) employs machine learning to identify human activities and behaviors. Improvements in deep learning and kinetic models enable HAR systems to identify temporal and spatial features from images and videos to identify activities such as running, sitting, and eating. The applications of HAR are diverse, spanning healthcare, security, and labor monitoring, ultimately maximizing both safety and effectiveness across various industries. By utilizing datasets such as UCF-101, Kinetics, and Hollywood2, coupled with semi-supervised learning methods, HAR research applying CNNs and OpenCV achieves high precision and we got dependable recognition of human behaviors. Through constantly learning, refining their processes, and enhancing their reliability for real-world applications, these models will provide active real-time responses to alert authorities in cases of unusual and suspicious activities that might cause security breaches when accessed quickly. The rise of HAR opened up chances, such as fusing multi-modal input from wearable sensors and audio signals into the remainder of the input to improve recognition accuracy. With the continued advancements in technology, we might expect HAR systems to gain further sophistication and adaptability to become more familiar with and adaptable to new environments. Such innovations will foster intelligent, secure, and fully automated monitoring systems that guarantee greater safety and efficiency across various fields the experimental results demonstrate that our project improves HAR by achieving 84.6% in certain sectors.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - G. Anudeep Goud
AU  - R. Anusha
AU  - E. Indira
AU  - P. Saikumar
PY  - 2025
DA  - 2025/11/04
TI  - Activity Track: Live Human Activity Detection & Alert System
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 443
EP  - 455
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_39
DO  - 10.2991/978-94-6463-858-5_39
ID  - Goud2025
ER  -