Study on guide hole detection method for precise assembly based on binocular stereo vision

摘要

The guide holes are widely used in aircraft components machining and assembly but it is difficult to perform the visual inspection methods because of their various structural forms and inconsistent positions. To solve this problem, the paper proposes a guide holes detection method for plane parts based on binocular vision. Firstly, Harris angular points detection is used to identify the feature points of the captured images of the left and right cameras. Secondly, Scale-invariant feature transform (SIFT) algorithm is used to match the feature points, and the spatial position of the feature points is determined according to the binocular stereo vision principle. Then the space plane where the guide hole is located is found by the least squares method. Finally, the position of the camera is adjusted with the multi-axis numerical control mechanism so that the perspective projection distortion can be reduced and the detection efficiency and accuracy may be improved.