Font Size: a A A

Based On The Sequence Of Images Of The Head Positioning

Posted on:2005-10-16Degree:MasterType:Thesis
Country:ChinaCandidate:Y Q ShaoFull Text:PDF
GTID:2208360125953809Subject:Pattern Recognition and Intelligent Systems
Abstract/Summary:PDF Full Text Request
Human head location based on image sequence is brought forward by the automatic surveillance and alarm system that is applied in the halls of banks or import indoor places. It aims at endowing the video surveillance system with intelligence. The video surveillance system, as a visible surveillance approach, is widely employed in the public security field. In this paper, the system continuously captures the images of the monitored scene by a camera, perceives the invasion of irregular people with a mask on its face, a respirator on its mouth or a cap on its head and so on by the detection and recognition of the computer as early as possible and automatically alarms the remote control center according to the setting of the system.In this paper, we research the human head location based on image sequence according to the dynamic information of moving objects in a image sequence and the fact that some of organs on the face are perhaps not present when the face is covered.First, this paper investigates the background generation and update technology, systematically analyzes and contrasts the algorithms of the technology, then presents a new group-update background generation algorithm and an improved multiple Gaussian model background generation algorithm. Second, we propose a contour detection method by which we can detect moving objects in the current image according to the three latest images. Then we apply the Shen Jun Operator and the smooth criteria of lines to eliminate interference from the detected target. Third, This paper introduces a head location approach according to the characteristic points at people's neck and presents a new cirque-based Hough transform for locating human head. Finally, the experimental results and analysis are presented.
Keywords/Search Tags:Image Sequence, Human Head Location, Moving Object Detection, Image Difference, Background Generation and Updating
PDF Full Text Request
Related items