Data fusion and evidence accumulation for landmine detection

“In this thesis, an architecture for multi-sensor data fusion and evidence accumulation for landmine detection and discrimination is presented. Evidential and discriminatory information about the buried object such as shape, size, depth, and material, chemical or electromagnetic properties is obtained from different sensors and sensor algorithms. Each sensor may provide one or more of this information. Type data channel provides any relevant discriminatory characteristics of the buried object, which may include shape, chemical content, material property etc. A supervised feed-forward neural network is used to learn the causality between the cluster information and the evidence of a given class of the buried object. Size, depth and phenomenology input are used as control gating input for the neural network mapping. The feedback accommodates both autonomous (adaptive) and human assisted learning. Dempster- Shafer evidential reasoning is used to accumulate different evidence from sensor channels. The supervisory feedback is provided by the output of the global sensor fusion system. Performance of fusion architecture and Dempster-Shafer reasoning is studied using simulated data. For the simulated data noisy images of regular and irregular shapes of different objects are produced. Fourier descriptor, moment invariant and Matlab shape features are used to define the shape information of the objects. Each of these algorithms was considered as different sensor channel providing dissimilar information about the buried object. Evidence accumulation is done using shape and size information from each of the algorithms. Dempster-Shafer evidential theory is compared with a Bayesian Statistics, as applied to sensor fusion”--Abstract, page iii