Aiming at the requirements of three-dimensional shape measurement of profiled surfaces with the deep hole feature, a method based on CAD (Computer Aided Design) digital model extraction information for self-adaptability measurement and a trajectory planning measurement method based on normal precision control are proposed. The simulation analysis of the displacement-time, speed-time and acceleration-time curves of a robot verifies the smoothness of the trajectory curve obtained by the high-order polynomial interpolation method. The positional deviation and angular deviation of TCP (Tool Centror Point) in the process of shape measurement are verified by the shape measurement experiment based on the normal precision control. The position deviation is within 0.092 mm and the angular deviation is within 0.19°, which proves the feasibility of the proposed method.

Aiming at the problem that the traditional feature representation ability is weak, we propose a polarization synthetic aperture radar image semantic segmentation method based on the multi-layer deep feature fusion. The pre-trained VGG-Net-16 model is used to extract multi-layer image features with strong representation ability, and then deep features of each layer are used to train the corresponding conditional random field model. The output results of multiple conditional random field models are finally merged to realize the final semantic segmentation of the images. The results show that compared with the methods based on classical features, the proposed method achieves the highest overall accuracy, indicating that the fusion features used by the proposed method have stronger representation ability than traditional features.