An adaptive matching pursuit algorithm for linear frequency modulation signal compressive sampling

We focus on the problem of compressive sampling of Linear Frequency Modulation(LFM) signal via Matching Pursuit. We designed an adaptive matching pursuit algorithm through dynamic dictionary optimization. Results from the sparse property of LFM under Chirplet Basis, we use Chirplet atom to generate dictionary. Then by feeding the information of signal back into dictionary generating process, the grid error can be reduced significantly. It also allows us to get better parameter estimation results and lower signal sampling rate. We demonstrate computing performance on a LFM signal sampling example.