Abstract: In order to reduce the scale invariant feature transform (SIFT) algorithm's complexity, improve the real-time performance of the algorithm and ensure that the feature points are corners, a new Harris-SIFT algorithm is proposed. The feature points of images are detected by using Harris operator, the main orientation for each feature point is calculated, and lastly, the feature point descriptors are generated after rotating the coordinates of the descriptors relative to the feature points' main orientations. Experimental results of image matching in binocular stereo vision demonstrate the effectiveness of the proposed algorithm.