Clustering based road detection method

Image based road detection is a vital task for many real-world applications such as autonomous driving and obstacle detection. In this paper, we propose a novel method for segmenting the road area based on estimation of horizon line and clustering technology. The key idea is to leverage normalized cross correlation (NCC) to search for the line separating road image. Additionally, we divide the lower part of road image into several identical parts horizontally and utilize Density-Peak clustering algorithm in terms of gray and HSV value of each pixel. Clustering results are further labelled as road and non-road based on the assumption that two adjacent horizontal parts share similar clustering size and average gray value. Experimental results on several complicated road images demonstrate the effectiveness and accuracy of our method.