AAE-Dpeak-SC: A novel unsupervised clustering method for space target ISAR images based on adversarial autoencoder and density peak-spectral clustering. Issue 5 (1st September 2022)

• Record Type: Journal Article
• Authors: Yang, Hong; Ding, Wenzhe; Yin, Canbin
• Is Part Of: Advances in space research. Volume 70:Issue 5(2022)
• Page Start: 1472
• Page End: 1495
• Publication Date: 2022-09-01
• Subjects: Space target -- unlabeled ISAR image -- Unsupervised clustering -- Adversarial autoencoder -- Density peak clustering -- Spectral clustering; Space sciences -- Periodicals; Astronautics -- Periodicals; Geophysics -- Periodicals; 500.505
• DOI: 10.1016/j.asr.2022.05.068
• Languages: English
• ISSNs: 0273-1177

Abstract

Abstract: Aiming at the problem of unlabeled ISAR image clustering of space targets, the paper proposes a new unsupervised clustering method based on adversarial autoencoder (AAE) and density peak-spectral clustering (Dpeak-SC). This method introduces the AAE into the unsupervised clustering problem of radar images for the first time and realizes the automatic extraction of the features of unlabeled space target ISAR image data. And on this basis, by combining the density peak algorithm with the spectral clustering algorithm, the ISAR image data is classified into multiple clusters with good clustering accuracy, clustering coincidence, and clustering similarity without providing any prior information. This method first implements the self-supervised training of the AAE model through the adversarial and reconstruction process. Then, it uses the trained encoder to extract the latent features of the ISAR image of the space target in the low-dimensional space. Next, a decision graph is constructed by calculating the local density and relative distance of the proposed features to determine the number of clusters in the hidden feature vector set. Finally, the spectral clustering algorithm is used to transform the problem into the graph's optimal partition problem. The clustering is realized by constructing and segmenting the undirected weight graph of the hidden feature vector set. The simulation test on the unlabeled space target ISAR image data verifies the method's effectiveness in this paper.