Low-resolution vehicle image recognition technology by frame-composition of moving images

Developing on-board automotive driver assistance systems aiming to alert drivers about driving environments, and possible collision with other vehicles has attracted a lot of attention lately. Especially, many researchers have suggested the forward vehicle recognition technology by a camera on vehicle. In the forward vehicle recognition, however, it is difficult to detect the features of vehicle from a distant vehicle image by conventional methods because the image is too low-resolution (LR). This paper presents vehicle image recognition technology for detecting of the features of a distant vehicle by frame-composition of moving images. To detect the vehicle features of a distant LR vehicle image, we use the moving images obtained from the camera on the vehicle, and utilize super-resolution (SR) image reconstruction. SR image reconstruction is to use signal processing techniques to obtain a high-resolution (or sequence) image from observed multiple LR images. Use of this technique on real road image, we show the effectiveness of the proposed techniques.