Landmine Detection Using MWIR Images

Traditional landmine detection techniques are both dangerous and time consuming. Landmines can be square, round, cylindrical, or bar shaped. The casing can be metal, plastic, or wood. These characteristics make landmine detection challenging. We have developed new methods that improve the performance of both surface and buried mine detection. Our system starts with the image segmentation based on a wavelet thresholding algorithm. In this method, we estimate the thresholding value in the wavelet domain and obtain the corresponding thresholding value in the image domain via inverse discrete wavelet transform. The thresholded image retains the pixels associated with mines together with background clutter. To determine which pixels represent the mines, we apply an adaptive self-organizing maps algorithm to cluster the thresholded image. Our surface mine classifiers are based on Fourier Descriptor and Moment Invariant to explore the geometric features of surface mines shown in the MWIR images. Our buried mine classifier utilizes the cluster intensity variations. To do this, we first cluster the target chip using a 3D unsupervised clustering algorithm. We then perform horizontal scanning to build a cluster intensity variation profile which is statistically compared with the signature profiles via Kolmogorov-Smirnov hypothesis test.