Open AccessAutomatic Detection of Anomalies in Video Surveillance using Artificial Intelligence
Author(s) -
Sreedevi R Krishnan,
P. Amudha,
S. Sivakumari
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1085/1/012020
Subject(s) - computer science , trace (psycholinguistics) , anomaly detection , task (project management) , event (particle physics) , identification (biology) , artificial intelligence , public security , anomaly (physics) , feature (linguistics) , machine learning , data mining , computer security , engineering , philosophy , linguistics , physics , botany , systems engineering , public administration , quantum mechanics , political science , biology , condensed matter physics
The significance of security in day to day life is increasing, and hence the use of a video surveillance system is becoming commonly accepted in almost every public places. Even though by placing surveillance system in public places will help to trace out the culprits of the anomalous situation, it is hard to trace it out. The knowledge of the incidence time is needed to identify the event, and also, it requires an enormous data handling task. To identify the anomalous situation in real-time will help the authorities to decrease the consequences and loss during the anomalous event. The paper proposes an in-depth study of various automatic anomaly detection techniques which helps to reduce the loss occurred of the anomalous situation. The advancements in Artificial Intelligence help in the quick and automatic identification of nominal and anomalous events. The sequential and incremental learning approach in feature extraction will help to generate a model that will provide much accurate classifications and predictions of anomalies.