Spectral Reconstruction Network From Multispectral Images to Hyperspectral Images: A Multitemporal Case

Hyperspectral (HS) satellite data have been widely applied in many fields due to its numerous bands. Along with the advantages of high spectral resolution, HS satellite data are still limited by some disadvantages of high acquisition cost, low revisiting capability, and low spatial resolution. Compared with HS satellites, multispectral (MS) satellites have a large number, large width, strong coverage, and high spatial resolution. Therefore, MS data can be used as the input to the spectral reconstruction (SR) to obtain HS data with high temporal resolution. Better HS data can be obtained by spectral reconstructing with these continuous multitemporal data than with single-temporal data. A multitemporal spectral reconstruction network (MTSRN) is proposed in this article, which is used to reconstruct HS images from multitemporal MS images. The proposed MTSRN comprises multiple single-temporal spectral reconstruction networks (STSRN) for extracting temporal features and a multitemporal fusion network (MTFN). The parallel component alternative (PA) post-processing method enhances the physical plausibility of reconstructed HS data. To demonstrate performance of the proposed method in aspects of multitemporal reconstruction, experiments are conducted on four multitemporal HS and MS satellite datasets. The experimental results prove that the proposed MTSRN obtains better SR results compared with the SR method based on single-temporal information.

Automated summary

In this article, a multitemporal spectral reconstruction network (MTSRN) is proposed to reconstruct hyperspectral (HS) images from multitemporal multispectral (MS) images. By extracting temporal features and utilizing a multitemporal fusion network, better HS data can be obtained.