Using genetic algorithms and neural networks for surface land mine detection

Knowledge-based techniques have been used to automatically detect surface l and mines present in thermal and multispectral images. Polarization-sensiti ve infrared sensing is used to highlight the polarization signature of man- made targets such as land mines over natural features in the image. Process ing the thermal polarization images using a background-discrimination algor ithm, we were able to successfully identify eight of the nine man-made targ ets, three of which were mines, with only three false targets. A digital ca mera is used to collect a number of multispectral bands of the test mine ar ea containing three surface land mines with natural and man-made clutter. U sing a supervised and unsupervised neural network technique on the textural and spectral characteristics of selected multispectral bands (using a gene tic algorithm tool), we successfully identified the three surface mines but obtained numerous false targets with varying degrees of accuracy. Finally, to further improve our detection of land mines, we use a fuzzy rule-based fusion technique on the processed polarization resolved image together with the output results of the two best classifies. Fuzzy rule-based fusion ide ntified the locations of all three land mines and reduced the number of fal se alarms from seven (as obtained by the polarization resolved image) to tw o. Additional experiments on several other images have also produced favora ble results at this early stage in testing the algorithm and comparing it w ith an existing commercial system.