| Summary: | 碩士 === 國立中正大學 === 電機工程研究所 === 92 === Motion blur is a result of finite acquisition time of practical
cameras and the relative motion between the camera and the oject.Traditionally, the image degradations caused by motion blur are treated as undesirable artifacts and usually have to be removed before further processing.Most research on this type of image degradation is focused on motion blur removal. In this work, we propose a novel approach for vehicle speed detection
based on motion blurred images as opposed to the most commonly used RADAR and LIDAR devices for traffic law enforcement. The blur parameters are estimated from a single motion blurred image
and then used to calculate the speed of the moving vehicle in a scene. First, the motion direction of the vehicle is estimated using image gradient information and the orientation of the motion blur is simplified to a one-dimensional case with image rotation and rectification. The number of motion blurred pixels and the vehicle location in the image are then estimated according to the intensity gradient changes along the
horizontal direction in the image. Finally, the speed of the moving vehicle is computed according to the imaging geometry and the camera parameters. The image is taken with the ehicle's license plate for both the assistance of image restoration using sharp edges and the identification of the moving vehicle for traffic violation enforcement. We have established a link between the motion blur information of a 2D image and the speed information of a moving object. Experimental results are presented for indoor environment, local and highway traffic.
|
|---|
