Active surveillance system with multiple cameras and camera calibration
碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 97 === Surveillance systems have been widely used in visitor control, traffic monitor and many other applications nowadays. Most of them provides functions such as data recording and simple information analyses. However, blurred images were usually captured and diffi...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2009
|
Online Access: | http://ndltd.ncl.edu.tw/handle/68508467634244292841 |
Summary: | 碩士 === 國立成功大學 === 資訊工程學系碩博士班 === 97 === Surveillance systems have been widely used in visitor control, traffic monitor and many other applications nowadays. Most of them provides functions such as data recording and simple information analyses. However, blurred images were usually captured and difficult to recognize due to a wide surveillance field. In order to resolve these problems, this thesis proposes an active surveillance which is system composed of a static camera and a PTZ (pan-tilt-zoom) camera with the corresponding cameras calibration methods. The system can monitor a wide field and obtain clear images of the objects.
The geometric relationship between static and PTZ cameras were first settled. Some significant points within the camera scene were chosen as the feature points. The information of these feature points were then used to calibrate both the static camera and PTZ camera. After cameras have been calibrated, the objects entering the surveillance scene will be detected and tracked. Then the system will steer the PTZ camera to get the clear image of the tracked object.
The image of the PTZ camera is then transformed into flesh probability image (FPI) for face detection. The image offset between the human face and the image center will be used to tune the PTZ camera to get the highest quality image of human face. Experimental result show that clear image of human face can be captured by the system even when the initial rotation of the PTZ camera is far away from the object.
|
---|