Intelligent road detection based on local averaging classifier in real-time environments

The aim of this paper is to obtain real-time classification for robust road region detection in both highway and rural way environments. This approach uses a local averaging classifier relying on decision trees, and in case of altered or noisy road regions, a special intelligent detection procedure. The local averaging classifier based on the decision tree provides real-time road/nonroad classification. The main idea is that the neighbor feature vectors around the control point are analyzed, and the control point has conditioned feature vector by the decision tree. However, this algorithm performs poorly in case of noisy road regions. To overcome this problem, we use the intelligent detection method for missing road regions. Let us assume that there are two problematic situations in the highways: in the first one, a lane marking is missing. in the second one, both lane markings are missing. In the first case, we can predict where the other line marking is, and apple the ordinary K-means onto that region. In the second case, we split the image into six parts, and the ordinary K-means is applied onto the most left and right four regions. In the case of rural ways, we also split the image into six parts, and apply the ordinary K-means as in the second situation of the highways. The merits of the proposed method are that it provides efficient, accurate, and low cost classification in the real-time application.