INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
. The proposed IHAR system includes principal component analysis (PCA)-based features extraction, closed-circuit television (CCTV) camera-based image acquisition, multiple filtering-based picture improvement, and a variety of machine learning methods for performance comparison. 35,530 photos make up our dataset of 10 actions, including walking, sitting down, and standing up. The dataset was separated into training and testing portions (90%, 10%), 80%, 20%, and 70%, respectively, and three classifiers—KNN, RF, and Decision Tree—were assessed (DT). The experimental results demonstrate that KNN, RF, and DT, respectively, have accuracy levels of 95%, 97%, and 90%.
Keywords:
Human Activity Recognition, CCTV, Principal ,Component Analysis, Random Forest, Decision Tree
Cite Article:
"Efficient Detection of Human Misbehaviour in a CCTV RealTime Footage", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 4, page no.870 - 874, April-2023, Available :http://www.ijsdr.org/papers/IJSDR2304149.pdf
Downloads:
000336256
Publication Details:
Published Paper ID: IJSDR2304149
Registration ID:204877
Published In: Volume 8 Issue 4, April-2023
DOI (Digital Object Identifier):
Page No: 870 - 874
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn