Elliptically symmetric distributions are widely used in portfolio modeling, as well as in signal processing applications for modeling impulsive background noises. Of particular interest are algorithms for covariance estimation and subspace detection in such backgrounds. This article tackles the issue of correctly estimating the covariance matrix associated to such models and detecting additional signal superimposed on such distributions. A particular attention is given to the proper accounting of the circular symmetry for the subclass of complex elliptical distributions in the case of complex signals. In particular Tyler's estimator is shown to be a maximum likelihood estimate over all elliptical models, and its extension to the complex case is shown to be a maximum likelihood estimate for the subclass of complex elliptical models (CES); other M-estimators are also shown to be maximum likelihood estimates over some restricted classes of elliptical models. The extension of Tyler's and other M-estimators to constrained covariance estimation is also discussed, in particular for toeplitz constrains. Finally likelihood ratio signal detection tests associated to the various estimators introduced in this article are also discussed.