STLAR: A localization and authenticity recognition method for specific targets based on land‐based hyperspectral images

Abstract

AbstractIn traditional two‐dimensional space object detection, it is believed that ‘objects with similar shapes belong to the same type’, making it difficult to distinguish true and false targets. In order to improve the efficiency of real object localization and detection, a specific target localization and authenticity recognition method (STLAR) based on joint spatial and spectral information is proposed. Firstly, the ground imaging spectrometer is utilized to obtain hyperspectral image data of the area to be measured. Then use a spatial object detection model to frame specific targets. Finally, compare the similarity between specific targets detected in space and prior spectral information. The experimental results successfully completed the task of target localization and recognition of authenticity. The proposed method can simultaneously solve the problems of spectral dimension detection or spatial dimension detection, providing new ideas for future rapid localization and recognition of specific targets.