Novel Stereo Matching Method on Multi-scale Harris Corner Points

A feature point detection algorithm is presented based on the scale-space theory. The algorithm overcome the drawback that a typical single-scale Harris detector usually leads to either missing significant corner points or detecting false corner points due to noise and position displacement. Original matching is solved by similarity of the image gradient module and argument, and the crude matching is optimized result to get exact matching sets. The suggested stereo matching method is independent of detecting feature points and adapt to various feature points to match. The means make better harmony between running speed and matching effect.