Abstract
Advancements in security have provided ways of recording anomalies of daily life through video surveillance. For the present investigation, a semi-supervised generative adversarial network model to detect and classify different types of crimes on videos. Additionally, we intend to tackle one of the most recurring difficulties of anomaly detection: illumination. For this, we propose a light augmentation algorithm based on gamma correction to help the semi-supervised generative adversarial networks on its classification task. The proposed process performs slightly better than other proposed models.
Highlights
The role of anomaly detection is identifying certain events, observations or data characteristics that diverge from a supposed norm [1]
An anomaly detection system aims to prompt a signal for a certain activity that diverges from a pattern that is considered normal
Anomaly detection can subtract the anomalies from the video and categorize them according to a certain classification list [3]
Summary
The role of anomaly detection is identifying certain events, observations or data characteristics that diverge from a supposed norm [1] The video anomalies such as anomalous activities and anomalous entities are defined as the abnormal or irregular patterns present in the video that does not follow the normal trained patterns [2]. Waqas et all.[3] proposed a deep Multiple Instance Learning (MIL) ranking loss This method of anomaly detection treated the classification of the video as a regression problem. − To extensively evaluate the proposed framework on the largest publicly available video anomaly detection data set: The UCF crime detection dataset. − Use a light-based data augmentation process to give allow the model to perform a better feature extraction for high and low light videos
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
