Many conventional distinction methods of road surface condition using car-mounted cameras have been already proposed. However, most of these methods are only effective for daytime and bright conditions. Therefore, we need to expand these methods for impractical night-time that is much more dangerous environment. In this paper, we propose a new distinction method for road surface conditions at night-time, such as dry, wet and snow. This method uses only video information acquired by an inexpensive car-mounted video camera and uses the difference in road surface features for each condition. The image features of the road surface are depending on the illuminant conditions such as street lamps, signal lights, reflections and other lighting sources. Therefore, we analyze the image features based on color information and the presence of other light sources. As a result, the distinction of road surface conditions was achieved with high accuracy, including the areas illuminated by street lamps and other light sources.

No abstract

No abstract

No abstract

The necessity of distinguishing the road surface condition at night time is increasing because most of the previously proposed methods correspond only to daytime. In this paper, we propose a method of distinguishing road surface condition using only video information acquired from a visible surveillance video camera. The feature of this method is that it simply uses automobile headlights as the light source. Thus it becomes possible to distinguish between road surface conditions, such as dry and wet, with high accuracy using this method. C⃝ 2014 Wiley Periodicals, Inc. Electron Comm Jpn, 97(6): 51-57, 2014; Published online in Wiley Online Library (wileyonlinelibrary.com).

No abstract

We proposed a progressive display method of images by using a image segmentation algorithm.Progressive image display makes us take vague view of the image on early stage, so that it is useful to retrieve an image from the image data base and to transmit images coded at variable bit-rates. In the past several progressive methods have been proposed; they are based on image refinement getting higher spatialor frequency-resolution. But they don't use any characteristics of the image. It is important at very high compression ratios to preserve the sharp object edges. In this sense we adopt the segmented-image algorithm which has been proposed by M.J. Biggar et al.In this method the regions in a segmented image is represented by assigning to them the mean intensity of the original image within the region boundary. We use the segmentation algorithm that merges repeatedly two neighborhood regions that minimize the sum squared error and that makes regions grow bigger. At one stage of the merging process two kinds of information are lost, they are mean intensity values of two merged regions and the region boundary. So we code them at each stage till the region number is one.On the other hand, at the decoding process while region being splited the image is reconstracted progressively.From the standpoint of taking vague view of the image on the early display, we compared our method with a following method. The method is based on quad-tree search but has the display priority in the image refinement. According to this priority the image is splited into non-uniform blocks. As the result of the experiment judging the subjective quarity of the resulting images we verified the advantage of our method.

The danger of causing serious traffic accidents at night-time is much higher than in the daytime. In this paper, we propose a distinction method of estimating road surface conditions by using only video information from a visible video camera. Compared to the conventional method, our innovative method provides the added benefit of the principal component analysis (PCA) of texture features and the reliability of the Mahalanobis distance. By using this method, it was possible to distinguish road surface conditions at night with high accuracy.