A New Hyperspectral Image Identification Method Based on LSDA and OSELM

Abstract

To solve the problems of information loss and nonlinear transformation of hyperspectral image dimensionality reduction methods and the problem that recognition methods are sensitive to noise and cannot be trained online, a new hyperspectral image identification method based on locality sensitive discriminant analysis (LSDA) and online sequential extreme learning machine (OSELM) is proposed. Firstly, LSDA is used to reduce the redundant information and data noise, and the local structure and discriminant information of the hyperspectral image are extracted on the basis of reducing the data dimension. Then, a real-time recognition model based on OSELM is constructed to identify various terrain targets in hyperspectral images through online real-time updates of data. According to the experimental results of the Pavia University dataset and Salinas dataset, the proposed LSDA-OSELM not only achieved the maximum overall accuracy (OA) of 97.56 and 97.88 but also obtained the maximum kappa coefficient of 0.9726 and 0.9774. Compared with several new dimensionality reduction methods and identification methods, the proposed LSDA-OSELM has achieved a leading position in both OA and kappa indicators. The proposed method improves the generalization ability and accuracy of hyperspectral image target recognition models. In the future, its computational complexity and parameter robustness are expected to be further improved and applied in practical application scenarios.