Chromatic methodology for laser detection and ranging (LADAR) image description

Abstract

Chromatic methodology for information extraction has evolved from a number of origins, some based upon human perceptions and the others on scientific and analytical approaches. From the applications of this methodology, a new robust LADAR image descriptor is proposed. This descriptor is developed to has a high discrimination capability, robust to the effects that disturb LADAR images, and requires less storage space and computational time for recognition. The performance of the proposed LADAR descriptor is evaluated using simulated LADAR images. Experimental tests are also being undertaken on the new descriptor to validate its ability with processing real LADAR images. The results show high discrimination capability for the new descriptor over the traditional techniques such as Moments descriptor, which is used to benchmark the results. The results also show the robustness of the new descriptor in the presence of noise, view change, low resolution, translation, scaling, and rotation effects.