2results about How to "Achieve super-resolution" patented technology

The invention provides a radar range profile super-resolution intelligent imaging method, which comprises the following steps of: firstly, converting a radar echo into a high-dimensional space to represent and capture difference characteristics of a deeper layer; then, a plurality of iteration stages composed of a measurement consistency module and a prior filtering module are provided, so that noise is suppressed and target features are enhanced in a high-dimensional space; and finally, weighting and combining the extracted high-dimensional features through a data dimension reduction module to realize HRPP super-resolution. Therefore, the HRPP super-resolution is realized in a model guiding and data driving mode, the robustness of the result can be ensured through the model, and the algorithm performance is improved through data driving; in addition, the distance high-dimensional feature extraction capability and discrimination capability can be improved through adaptive high-dimensional hyper-parameter learning, and the overall architecture learning capability is improved through a true value fuzzy technology.

The invention relates to the field of spectrum reconstruction, in particular to a spectrum reconstruction method for a broadband filtering modulation spectrum detection system, which comprises the following steps of: converting a hyperspectral data set into a training data set according to parameters of the broadband filtering modulation spectrum detection system; building a spectrum reconstruction network model based on deep learning and carrying out training; and pixel splitting point-by-point scanning reconstruction is carried out on a reconstruction target, a hyperspectral image is constructed according to original arrangement, space-spectrum joint optimization is carried out, and finally high-precision spectral image reconstruction is realized. According to the method, the demand of a spectrum reconstruction process on a data set scale is reduced through a pixel splitting point-by-point scanning reconstruction strategy, a Transform architecture is introduced into a reconstruction network, the feature information extraction capability of the network is improved, the strong nonlinear characterization capability of a KAN architecture is combined, the spectrum curve reconstruction precision is improved, and spatial spectrum combined processing is combined, so that the spectrum reconstruction efficiency is improved. The error is further reduced, and high-quality reconstruction of the spectral image is realized.