The Dempster-Shafer method, fuzzy reasoning and backpropagation neural networks were applied to data fusion for automatic target recognition of airborne targets using three knowledge sources: a continuous wave (CW) coherent (X band) radar, which provides high resolution Doppler signature measurements, together with a surveillance radar, which provides positional information of airborne targets, and a priori information of flight times of targets flying regular flight paths, obtained from Adelaide Airport (Australia) flight time tables. The target classification was restricted to jet or propeller-driven aircrafts. A comparison is made between the three data-fusion techniques, on the trial data obtained. The method using neural networks were better then the other two methods. The neural networks need less computation time because of parallel processing and they obtain the uncertainty of the knowledge source indirectly without a priori knowledge or calculation.
Data fusion using sensor data and a priori information
Flugzeugerkennung und Flugzielerkennung aus zwei unterschiedlichen Radarmessungen
Control Engineering Practice ; 4 , 1 ; 43-53
1996
11 Seiten, 7 Bilder, 9 Tabellen, 11 Quellen
Article (Journal)
English
Perception and autonomous navigation using a priori data
Automotive engineering | 2006
|Perception and Autonomous Navigation Using a Priori Data
SAE Technical Papers | 2006
|Dynamic Origin-Destination Matrix Estimation Using Probe Vehicle Data as A Priori Information
British Library Conference Proceedings | 2010
|Dynamic Origin–Destination Matrix Estimation Using Probe Vehicle Data as A Priori Information
Springer Verlag | 2010
|