This paper proposes the Top-View Transformation Model for image coordinate\r\ntransformation, which involves transforming a perspective projection image into its\r\ncorresponding bird�s eye vision. A fitting parameters searching algorithm estimates the\r\nparameters that are used to transform the coordinates from the source image. Using this\r\napproach, it is not necessary to provide any interior and exterior orientation parameters of\r\nthe camera. The designed car parking assistant system can be installed at the rear end of\r\nthe car, providing the driver with a clearer image of the area behind the car. The processing\r\ntime can be reduced by storing and using the transformation matrix estimated from the first\r\nimage frame for a sequence of video images. The transformation matrix can be stored as\r\nthe Matrix Mapping Table, and loaded into the embedded platform to perform the\r\ntransformation. Experimental results show that the proposed approaches can provide a\r\nclearer and more accurate bird�s eye view to the vehicle driver.
Loading....