Hide/Show Apps

Target classification under multi sensor environment

Atıcı, Bengü
Radar systems have important roles in both military and civilian applications. As the capabilities increase in terms of range, sensitivity and the number of tracks to be handled, the requirement for Automatic Target Recognition (ATR) increases. ATR systems are used as decision support systems to classify the potential targets in military applications. These systems are composed of four phases, which are selection of sensors, preprocessing of radar data, feature extraction and selection, and processing of features to classify potential targets. In this study, we focus on the classification phase of an ATR system having heterogeneous sensors and develop a novel multiple criteria classification method based on modified Dempster-Shafer theory. Ensemble of classifiers is used as the first step probabilistic classification algorithm. It is treated as the state of the art technology for classification in which each single classifier is trained separately, and then the results of them are combined through several fusion algorithms. Artificial Neural Network and Support Vector Machine are employed in ensemble. Each non-imaginary dataset coming from multiple heterogeneous sensors is classified by both classifiers in the ensemble, and the classification result that has higher accuracy ratio is chosen for each of the sensor. After getting probabilistic classification of targets by different sensors, modified Dempster-Shafer data fusion algorithm is used to combine the sensors’ results to reach the final classification of targets.