After briefly discussing the different statistical models (Gaussian and non-Gaussian) used to describe the radar data, different optimum and suboptimum detection methods will be introduced. Then, to deal with real applications, adaptive detection procedures will be presented with a particular focus on the clutter covariance matrix estimation, which is strongly related to the final detection performance. Finally, results on real data will be shown according to the presented detection schemes and some conclusions and perspectives will be drawn.