A remote sensing detection method of the earth's surface anomalies based on multi-dimensional feature space

On-orbit processing is an important way in the real-time remote sensing detection of earth's surface anomalies (ESSA). However, the existing methods cannot comprehensively utilize multidimensional remote sensing characteristics to detect multi-type ESSA in a unified manner. Meanwhile, it is also difficult to realize the comprehensive utilization of multidimensional remote sensing characteristics under the condition of limited storage and computing resources on satellites. Therefore, this study proposed a remote sensing method for detecting multi-type ESSA on orbit based on multidimensional feature space. The proposed method first selected the remote sensing characteristics reflecting the basic earth's surface elements to construct a multidimensional feature space and generated two comprehensive remote sensing characteristics. Then, the optimized storage content of the two comprehensive remote sensing characteristics were used to build a prior knowledge base reflecting the normal conditions of the earth's surfaces. Finally, through comparing the prior knowledge base and the real-time acquired data, this study completed the ESSA detection. The validation results indicated that the proposed method can effectively detect multi-type ESSA with a accuracy of over 85%. Meanwhile, the proposed method simplified the large and complex ESSA remote sensing characteristic system, which would be conducive to greatly reducing the complexity of ESSA detection methods and increasing the possibility of on-orbit processing.