In this paper, an algorithm for corner detection and localization is proposed based on local orientation distribution (LOD). The algorithm consists of two steps: The first is to detect corners by using the absolute corner energy and the relative corner energy; Then, the detected corners are re-located to sub-pixel accuracy by fitting the intersection of orientation lines of support pixels by the least squares technique. Experimental results show that the LOD-based algorithm can not only provide a higher localization accuracy than most popular detectors, but also has a better performance in resisting noises.