期刊名称：International Journal of Advances in Engineering and Management
电子版ISSN：2395-5252
出版年度：2021
卷号：3
期号：6
页码：2310-2316
DOI：10.35629/5252-030621772188
语种：English
出版社：IJAEM JOURNAL
摘要：Circuit Television Cameras (CCTV's) are widely used to control occurrence of crimes in the surroundings. Although CCTVs are deployed at various public and private areas to monitor the surroundings there is no improvement in the control of crimes. This is because CCTV requires human supervision which may lead to human prone errors like missing of some important crime events by human while monitoring so many screens recorded by CCTVs at same time. To overcome this issue, we came up with Crime Intension Detection System that detects crime in real time videos, images and alerts the human supervisor to take the necessary actions. To alert the supervisors or nearby police station about the occurrence of crime. This can be achieved by the Anomaly detection using Deep Learning using Autoencoders. An outlier (Anomaly) is an observation in a data set which appears to be inconsistent with the remainder of that set of data. An outlier is an observation which deviates so much from the other observations as to arouse suspicions that it was generated by a different mechanism. Anomalies are defined as events that deviate from the standard, happen rarely, and don‗t follow the rest of the ―pattern‖. Examples of anomalies include: Large dips and spikes in the stock market due to world events Defective items in a factory/on a conveyor belt Contaminated samples in a lab Depending on your exact use case and application, anomalies only typically occur 0.001-1% of the time — that‗s an incredibly small fraction of the time. The problem is only compounded by the fact that there is a massive imbalance in our class labels. By definition, anomalies will rarely occur, so the majority of our data points will be of valid events. To detect anomalies, machine learning researchers have created algorithms such as Isolation Forests, One-class SVMs, Elliptic Envelopes, and Local Outlier Factor to help detect such events; however, all of these methods are rooted in traditional machine learning.
