Application of using fuzzy-neural network on PTZ camera
DOI: 10.1109/ICMLC.2010.5580868 Conference: International Conference on Machine Learning and Cybernetics, ICMLC 2010, Qingdao, China, July 11-14, 2010, Proceedings
Surveillance system is widely applied in various fields in recent years. The demand for monitoring quality is not only to capture the object image, but also to present sharp and recognizable image. Thus, PTZ camera, which has pan and zoom functions, has become the best equipment. How to zoom in object and move camera lens so that the object is placed at the center of image becomes the major issue. This paper proposes the method of using the widest camera viewing angle as the moving range, and employing the spatial adjustment method of camera to establish the relative position of the camera and space. However, once the targeted object is unclear, the zoom in function of the PTZ camera is used; if the targeted object is not within the center of the image, the targeted object will move out of the image frame during the zoom-in process. Hence, by using the fuzzy nerves to simulate nonlinear horizontal movement and vertical rotation of PTZ camera, the image can be moved to the center of the image. In this paper, PTZ camera can zoom in image of the targeted object and move camera lens so that the object is at the frame center. Without additional adjustment, the camera lens can be moved exactly to the target position.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.