Abstract

Modern applications of stereo vision, such as advanced driver assistance systems and autonomous vehicles, require highest precision when determining the location and velocity of potential obstacles. Sub- pixel disparity accuracy in selected image regions is therefore essential. Evaluation benchmarks for stereo correspondence algorithms, such as the popular Middlebury and KITTI frameworks, provide important ref- erence values regarding dense matching performance, but do not suffi- ciently treat local sub-pixel matching accuracy. In this paper, we explore this important aspect in detail. We present a comprehensive statistical evaluation of selected state-of-the-art stereo matching approaches on an extensive dataset and establish reference values for the precision limits actually achievable in practice. For a carefully calibrated camera setup under real-world imaging conditions, a consistent error limit of 1/10 pixel is determined. We present guidelines on algorithmic choices derived from theory which turn out to be relevant to achieving this limit in practice.