A sub-pixel center extraction algorithm based on hierarchical processing was proposed for the implementation of laser stripe processing in the large aerospace parts measurement with high speed and precision. Firstly, the high-resolution image was compressed into low-resolution image with structural invariance. Then, the normal vector of the center of laser stripe was calculated by using quadratic curve fitting in the low-resolution image. The normal vector in the low-resolution image was reproduced to the high-resolution image based on the theory of normal regression. The judgment of gray center on normal direction was established to determine calculated pixels. The sub-pixel center of calculated pixels on the normal direction was accurately calculated by the gray weighted centroid method. Finally, the presented method was utilized to measure a composite material standard part and complex aviation parts in the laboratory and assembly testing machine, respectively. Experimental results show that the precision of the reconstruction of a single stripe on the surface of object is 0.269 mm and the precision of three-dimension surface measurement is 0.268 mm. It indicates that the proposed method can improve the speed and precision of the engineering measurement of large part. Moreover, the method can satisfy the requirements of the in-site measurement of large aerial parts.