Open AccessDETECTING ANOMALOUS ACTIVITIES IN SPATIO-TEMPORAL REGION
Author(s) -
H Manoj T Gadiyar,
Kanchana Goudar,
G S Thyagaraju,
K Harshitha,
Megha Jeevan Kurdekar,
K Manjushree
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v06i01.070
Subject(s) - anomaly detection , computer science , anomaly (physics) , frame (networking) , event (particle physics) , artificial intelligence , computer vision , tracking (education) , pattern recognition (psychology) , data mining , psychology , telecommunications , pedagogy , physics , quantum mechanics , condensed matter physics
Anomaly detection system using MachineLearning helps to detect the anomalies like accidentsetc. Detecting anomalies in videos is important but it isan unsolved problem. This system will automaticallydetect the anomaly by image analysis from thesurveillance videos. This system is capable of trackingabnormal event in each frame and generates anotification of such event. The proposed K-meansalgorithm performs existing anomaly detectiontechniques, while being comparatively time efficient.The system just requires a dataset of video frames andis fed as input to the anomaly detecting module