Adaptive Multi-Modality Processing for the Discrimination of Landmines

摘要

As in many application areas, performance of landmine detection algorithms is judged in terms of detection and false alarm rates. It is widely accepted that single sensors cannot simultaneously achieve both high detection rates and low false alarm rates, since every sensor has its advantages and disadvantages when dealing with a large variety of landmines, from large metal-cased mines to small plastic-cased mines. The recent development of high quality sensors in conjunction with statistical signal processing algorithms has shown that there are sensors that can not only discriminate targets from clutter, but can also identify subsurface or obscured targets. Here, we utilize this identification capability in addition to contextual information in a multi-modal adaptive algorithm where the identification capabilities of multiple sensors are utilized to modify the prior probability density functions associated with statistical models being utilized by other sensors. In general, every sensor modality is associated with a specific physics-based feature set that is extracted from the sensor data. Often, the statistics describing these features are assumed to follow a Gaussian mixture density, where in many cases the individual Gaussian distributions that make up the mixture result from different target types or target classes. We utilize identification information from one sensor to modify the weights associated with the probability density functions being utilized by algorithms associated with other sensor modalities. Using both simulated and real data, this approach is shown to be improve sensor performance by reducing the overall false alarm rate.