| Object recognition is one of the important parts of computer vision, and has been widely applied to many fields like military affairs and automatization. The recognition of airplane is one of the applications of object recognition. There are many methods for the recognition of the friend-or-foe airplane, but it is only in the groping stage that airplane mode can be recognized. Rapid and efficient recognition is playing important role in information processing in the late period of commanding automatization system as well as in civil aviation filed.In this paper, we study the method of recognizing airplane in its 2-D image. Because of the far distance of the object's image, we must find a proper method to recognize the object accurately and effectively. It is the core of the paper. In this case, the double vision is used to get the object's images. Then we analyze the inner and outer parameters of the double vision so as to compensate and modify the error and the aberration occurred during taking the images. On the basis of comparing with several edge detector used frequently, we propose a new method of edge detection which uses grads operator to construct corresponding threshold to confirm step-edge points in a quantitative way. And then on the basis of edge detection and image segmentation , we find the corresponding points of the double airplane edge images through epipolar constraint. At the same time, we extracted corner points' character of the airplane's figure during character extraction. In the phase of recognition, we adopted the recognition method that is based on the model. We constructed the 3-D airplane's models through 3-D construction technique. Then the revolving vector in 3-D coordinates was obtained according to the double vision measure depth theory and character points acquired above. We revolved the models by using the revolving vector, in this way the object can be recognized. Finally we testified the validity of the method proposed in this paper. |
PDF Full Text Request