Recursive estimation of the scatter matrix of ECD: the Riemannian Information Gradient method⁎we thank the support from the ANR MAR- GARITA under Grant ANR-17-ASTR-0015 for our works. Issue 9 (2021)

• Record Type: Journal Article
• Authors: Jialun, Zhou; Said, Salem; Berthoumieu, Yannick
• Is Part Of: IFAC-PapersOnLine. Volume 54:Issue 9(2021)
• Page Start: 713
• Page End: 718
• Publication Date: 2021
• Subjects: elliptically-contoured distribution -- online estimation -- maximum-likelihood -- Fisher information metric; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2021.06.134
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: ECD (elliptically-contoured distribution) models have been found remarkably successful in representing natural signals. At present, the estimation of these models is at the heart of numerous signal processing applications. Unfortunately, state-of-the-art methods for estimating the parameters of an ECD, especially its scatter matrix, may turn out to have excessive computational complexity. To remedy this problem, the present work introduces the Riemannian information gradient method, for recursive (i.e. online) estimation of the scatter matrix. It is shown that this method holds a significant advantage in terms of computational complexity, while still achieving the same performance as state-of-the-art methods.