Biswwas, RubelAurangzeb, Chowdhury FarsadShanchary, Israt JahanTasdid, Salman2015-01-312015-01-3120142014ID 11301019ID 10201022ID 08110072http://hdl.handle.net/10361/3970Cataloged from PDF version of thesis report.Includes bibliographical references (page 49 - 50).This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2014.We are presenting a new framework for smart threat detection with the help of video surveillance which captures live streaming from the camera and determine if any abandoned object has been set up. It then raises an alarm right after the carrier of the bag leaves the scene. The abandoned object is detected with the help of background subtraction and brought more accuracy on the object’s image with the help of morphology. Every individual person on the frame is being detected by their body with the help of Kalman filter and brought relation of the body with the bag, so that the alarm is raised only when the body of the abandoned object carrier leaves the frame.50 pagesenBRAC University thesis are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Computer science and engineeringVideo surveillanceThesis