ing at the problems of complex structures and difficult debugging in the current design based on prism-grating combination, we established a mathematical model of dispersion based on prism-grating combination and proposed an optimization method of only changing the relative positions of the prism and grating to increase the spectral dispersion linearity. As a result, we obtained the parameters of the prism-grating combination structure with good linearity. Furthermore, we used optical standard elements to simulate and experimentally verify the correctness of the model, and the results showed that our system had the advantages of 15 cm length, good spectral linearity, and simple structure in the band of 400-1000 nm. Finally, the experiments demonstrated that the overall resolution was better than 2 nm in the band of 420-780 nm, which further proved the effectiveness of the proposed method. In a word, this paper provides a flexible and simple structural design method based on prism-grating combination.
.ing at the problems in the semantic segmentation of remote sensing images, such as missed detection of multi-scale targets and rough segmentation boundary, we propose a method of building change detection for aerial images based on an attention pyramid network. The method adopts an encoding-decoding configuration. In the encoding phase, we utilize ResNet101 as the basic network to extract the features and apply dilated convolutions to improve the receptive field in partial residual modules. Meanwhile, the pyramid pooling structure is selected as the last layer of the encoding network to extract multi-scale features of the images. In the decoding phase, the attention mechanism is employed in lateral connection to highlight significant features, and the procedure of top-down dense connection is used to calculate the feature pyramid and then to fuse the features with different resolutions at different phases. Furthermore, the verification experiments are performed on the dataset of building change detection, and the results indicate that our method has good adaptability to different-size-building change detection and has certain advantages in comparison with the classical semantic segmentation networks.
.