Date of Publication :23rd August 2019

Abstract: A key technology to fight against terrorism and crime for public safety, moving object detection and tracking has become very popular and one of the challenging research topic in various security areas of computer vision and video surveillance applications. Generally, an object is said to be abandoned if it is kept at a particular space in a video surveillance system & unattended for long time. An automatic abandoned object detection system typically uses a combination of background subtraction and object tracking to look for certain predefined patterns of activity that occur when an object is left behind by its owner. We propose a method to detect abandoned object from surveillance video using Image Processing. In first step, foreground objects are extracted using background subtraction methods. In second step, static objects are detected by using contour features of foreground objects of consecutive frames. In third step, detected static objects are classified into human and non-human objects by using edge based object recognition method. Nonhuman static object is analyzed to detect abandoned object. Experimental results show that proposed system is efficient and effective for real-time video surveillance.

Reference :