In order to meet the needs of digital in-situ detection of hole making quality for aerospace large components, a multi-view point cloud registration method based on feature locating plate was proposed, which realized the reconstruction and detection of 3D morphology of integral hole wall. Firstly, the requirements of multi-view detection of hole making were analyzed, and a method of multi-view point cloud registration assisted by feature locating plate was proposed. Then, the design of quadrilateral feature plate with unequal interior angles and the corresponding point cloud segmentation as well as recognition algorithm were introduced. Also, the method of multi-view point cloud registration and parameter extraction based on feature self-localization was described. Finally, combined the mechanical arm to build the experimental platform, the titanium, aluminum and composite materials commonly used in aerospace were tested, and the average error was 0.011 mm, 0.034 mm and 0.041 mm, respectively, which verified the reliability of the system. The robustness of this method was demonstrated by comparing the detection results of traditional single-view method with that of the proposed method.