On-board selection of relevant images: an application to linear feature recognition

We propose an on-board selection scheme for aerial and space images, based on linear feature detection in a feature hyperspace. The detection task is performed by means of the Radon transform (RT) and the wavelet transform; a fast algorithm for the RT computation is described, and counteractions against the discretization errors are proposed. A new, wavelet-based algorithm is introduced, which performs a fine analysis of the waveforms of the RT peaks, yielding a possibly error-free detection in images corrupted by a high level of noise. A technique, based on the feature hyperspace, is proposed, able to significantly exploit all the available pieces of information on these peaks. Results of the tests on synthetic and real images are reported, which show that this method achieves satisfactory results, making the detection task highly reliable in the presence of both noise and clutter.