Many researchers have proposed methods of recognizing front vehicles by onboard cameras. However, with these recognition methods, it is difficult to detect features of a distant vehicle from an image by conventional methods because the image is too low-resolution (LR). This paper presents a vehicle image recognition method for detecting features of a distant vehicle by frame-merging based on multi resolution analysis (MRA). To detect vehicle features in an LR image, image sequences obtained from the camera are used, and super-resolution image reconstruction and MRA are applied. The effectiveness of the proposed method is shown through experiments in real road images.
Abstract