Fuzzy Track Initialization with Combined Measurements for Heterogeneous Sensors

The Radar/IR integrated detector has become an important stream of combined precision guided technology. For track initialization caused by systematic error and different measurement spaces of 2D radar/IR sensors, a new fuzzy track initialization method based on measurement combination for heterogeneous sensors is proposed. In this proposed method, through extracting topology sequences of azimuth angle from each sensor in the same period, measurements of different dimension are classified with the topology sequence method and they are fused with the weighted average method. And a set of candidate targets’ measurements is built by cumulating combined measurements in several periods. Finally, a fuzzy Hough transform (FHT) method is utilized to detect targets’ tracks. In track detection, measurements’ sequence time information and targets’ kinematics information are utilized sufficiently. Furthermore, the influences of both measuring system uncertainties and fixing track rules on track initialization are considered. Experimental results illustrate that the proposed method can realize track initialization for heterogeneous sensors effectively. It achieves less computation load and higher accuracy of line tracks extraction than the traditional Hough transform (HT) method.