Human Suspicious Activity Detection Using Ensemble Machine Learning Techniques

Public safety is a concern, especially with our growing population. An increasing population also calls for effective crowd management and it is not possible to manually monitor a huge crowd. A lot of approaches to this problem are being analyzed, and with this paper, we have implemented the problem with ensemble learning techniques which will detect suspicious activities. An automated alert system is also set up to detect, record and report suspicious activities to the concerned authorities. Therefore, the anomalous activity detection system will provide a basic surveillance system with an alarm which will help for safety of the public along with lesser costs and more security.