A comparison of decision-level sensor-fusion methods for anti-personnel landmine detection

We present the sensor-fusion results obtained from measurements within the European research project ground explosive ordinance detection (GEODE) system that strives for the realisation of a vehicle-mounted, multi-sensor, anti-personnel landmine-detection system for humanitarian de-mining. The system has three sensor types: a metal detector (MD), an infrared camera (IR), and a ground penetrating radar (GPR). The output of the sensors is processed to produce confidence levels on a grid covering the test-bed. A confidence level expresses a confidence or belief in a landmine detection on a certain position. The grid with confidence levels is the input for the decision-level sensor-fusion and provides a co-registration of the sensors. The applied fusion methods are naive Bayes' approaches, Dempster-Shafer theory, fuzzy probabilities, a rule-based method, and voting techniques. To compare fusion methods and to analyse the capacity of a method to separate landmines from the background on the basis of the output of different sensors, we provide an analysis of the different methods by viewing them as discriminant functions in the sensor confidence space. The results of experiments on real sensor data are evaluated with the leave-one-out method. © 2001 Elsevier Science B.V.

[1]  Gregory A. Clark,et al.  Sensor feature fusion for detecting buried objects , 1993, Defense, Security, and Sensing.

[2]  D. W. McMichael,et al.  Data fusion for vehicle-borne mine detection , 1996 .

[3]  S. L. Earp,et al.  Ultra-wideband ground-penetrating radar for the detection of buried metallic mines , 1996, Proceedings of the 1996 IEEE National Radar Conference.

[4]  Karl-Heinz Bers,et al.  Model-based sensor fusion for minefield detection , 1995, Defense, Security, and Sensing.

[5]  Thomas J. Gorman.  IGMMDT: multisensor approach to mine detection , 1996, Defense, Security, and Sensing.

[6]  Klaus Scheerer.  Airborne multisensor system for the autonomous detection of land mines , 1997, Defense, Security, and Sensing.

[7]  Brian A. Baertlein,et al.  Improving detection of buried land mines through sensor fusion , 1998, Defense, Security, and Sensing.

[8]  John Lester Miller,et al.  Multisensor system for mine detection , 1998, Optics & Photonics.

[9]  Neil A. Macmillan,et al.  Detection Theory: A User's Guide , 1991 .

[10]  Colin King,et al.  Jane's Mines and Mine Clearance , 1998 .

[11]  L. Klein.  A Boolean algebra approach to multiple sensor voting fusion , 1993 .

[12]  Sailes K. Sengupta,et al.  Land mine detection using multispectral image fusion , 1995 .

[13]  Mahesan Niranjan,et al.  Realisable Classifiers: Improving Operating Performance on Variable Cost Problems , 1998, BMVC.

[14]  L. Zadeh.  Fuzzy sets as a basis for a theory of possibility , 1999 .

[15]  Nancy DelGrande,et al.  Computer vision for locating buried objects , 1991, [1991] Conference Record of the Twenty-Fifth Asilomar Conference on Signals, Systems & Computers.

[16]  Claudio Bruschini,et al.  A Survey of Current Sensor Technology Research for the Detection of Landmines , 1997 .

[17]  A. Gunatilaka,et al.  Comparison of predetection and postdetection fusion for mine detection , 1999, Defense, Security, and Sensing.

[18]  Robert A. Kowalski,et al.  Logic for problem solving , 1982, The computer science library : Artificial intelligence series.

[19]  Piet B. W. Schwering,et al.  Sensor fusion algorithms for the detection of land mines , 1999, Defense, Security, and Sensing.

[20]  Gregory A. Clark,et al.  Data fusion for the detection of buried land mines , 1994, Other Conferences.

[21]  K. D. Sherbondy.  Status of vehicular mounted mine detection (VMMD) program , 1998 .

[22]  Mahmood R. Azimi-Sadjadi,et al.  Detection of mines and minelike targets using principal component and neural-network methods , 1998, IEEE Trans. Neural Networks.

[23]  B. Brusmark,et al.  Combination of GPR and metal detector for mine detection , 1998 .

[24]  James E. Baker.  Adaptive multisensor integration for mine detection , 1997, Defense, Security, and Sensing.

[25]  C. A. Amazeen,et al.  Developmental status of the U.S. Army's new handheld standoff mine detection system (HSTAMIDS) , 1998 .

[26]  Otto Löhlein,et al.  Sensor Fusion for the Detection of Landmines , 2000 .

[27]  Kelly D. Sherbondy,et al.  Multisensor system for mine detection , 1996, Defense, Security, and Sensing.

[28]  I. A. Burch,et al.  Countermine: hand held and vehicle mounted mine detection , 1998 .

[29]  N. K. Del Grande.  Sensor fusion methodology for remote detection of buried land mines , 1990 .

[30]  Klamer Schutte,et al.  Sensor fusion for antipersonnel landmine detection: a case study , 1999, Defense, Security, and Sensing.

[31]  R. Voles.  Confidence in the assessment and use of mine detection systems , 1998 .

[32]  Sholom M. Weiss,et al.  Computer Systems That Learn , 1990 .

[33]  D. L. Hall,et al.  Mathematical Techniques in Multisensor Data Fusion , 1992 .

[34]  Terilee Hanshaw.  Multisensor application for mines and minelike target detection in the operational environment , 1996, Defense, Security, and Sensing.

[35]  Belur V. Dasarathy,et al.  Decision fusion benefits assessment in a three-sensor suite framework , 1998 .

[36]  Anthony N. S. Freeling.  Fuzzy Sets and Decision Analysis , 1980, IEEE Transactions on Systems, Man, and Cybernetics.

[37]  Terilee Hanshaw.  Multisensor fusion for the detection of mines and minelike targets , 1995, Defense, Security, and Sensing.

[38]  Klamer Schutte,et al.  Detection of anti-personnel land-mines using sensor-fusion techniques , 1999 .