Paper-10 | Reg. No.:20151210|DOI:V4I3P10
Abandoned Object Detection in Crowded Places
Tejas Raut, Dhanashree Poojary, Aparna Rane,Prof. Saroja T.V.
Security is becoming a primary concern of the society. Having a security system is therefore becoming a requirement. Video surveillance plays an important role in security systems. Consider a fixed camera for monitoring a motion restricted area.The system works on a real- time video, from the camera, which is accessed frame to frame.A mathematical morphology is used in our proposed system.
The system is implemented using EmguCV package in OpenCV integrated along with .Net C#. The system uses absolute differencing for object detection. For noise removal, image filtering is done to each video frame. For handling illumination changes contour extraction and blob detection are used. Appropriate threshold is selected for respective area to be surveillance, to avoid fictitious movements.Once object is detected, alert is generated continuously until the alert is not de-activated. After the object is detected, the object is compared with master image in live video. Even after the process is stopped,it’s movements are saved and respective frames are stored on hard disk drive.