Multi-sensor Data Fusion Based on Belief Functions and Possibility Theory: Close Range Antipersonnel Mine Detection and Remote Sensing Mined Area Reduction

Two main humanitarian mine action types may benefit from multi-sensor data fusion techniques: 1) close range antipersonnel (AP) mine detection and 2) mined area reduction. Data fusion for these two applications is presented here. Close range detection consists of detection of (sub-)surface anomalies that may be related to the presence of mines (e.g., detection of metals using a metal detector, or detection of temperature differences using an infrared camera) and/or detection of explosive materials. Area reduction consists in identifying the mine-free areas out of the mine-suspected areas. For both close range detection and area reduction, efficient modeling and fusion of extracted features can improve the reliability and quality of single-sensor based processing (Acheroy, 2003). However, due to a huge variety of scenarios and conditions within a minefield (specific moisture, depth, burial angles) and between different minefields (types of mines, types of soil, minefield structure), a satisfactory performance of humanitarian mine action tools can only be obtained using multi-sensor and data fusion approaches (Keller et al., 2002; Milisavljevic & Bloch, 2005). Furthermore, as the sensors used are typically detectors of different anomalies, combinations of these complementary pieces of information may improve the detection and classification results. Finally, in order to take into account the interand intra-minefield variability, uncertainty, ambiguity and partial knowledge, fuzzy set or possibility theory (Dubois & Prade, 1980) as well as belief functions (Smets, 1990b) within the framework of the Dempster-Shafer theory (Shafer, 1976) prove to be useful. In case of close range detection, a detailed analysis of modeling and fusion of extracted features is presented and two fusion methods are discussed, one based on the belief functions and the other based on the possibility theory. They are illustrated using real data coming from three complementary sensors (metal detector, ground-penetrating radar and infrared camera), gathered within the Dutch project HOM-2000 (de Yong et al., 1999). These

[1]  R. W. G. Dennis,et al.  Mushrooms, Russia and History , 1957 .

[2]  Roger Heim,et al.  Les Champignons Hallucinogenes du Mexique, etudes ethnologiques, taxinomiques, biologiques, physiologiques et chimiques , 1958 .

[3]  Aboul-Enein Hy,et al.  Psilocybin: a pharmacological profile. , 1974, American journal of pharmacy and the sciences supporting public health.

[4]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[5]  Didier Dubois,et al.  Fuzzy sets and systems ' . Theory and applications , 2007 .

[6]  Didier Dubois,et al.  A review of fuzzy set aggregation connectives , 1985, Inf. Sci..

[7]  Henri Prade,et al.  Representation and combination of uncertainty with belief functions and possibility measures , 1988, Comput. Intell..

[8]  Philippe Smets,et al.  Constructing the Pignistic Probability Function in a Context of Uncertainty , 1989, UAI.

[9]  Philippe Smets,et al.  The Combination of Evidence in the Transferable Belief Model , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Paul Suetens,et al.  Road extraction from multi-temporal satellite images by an evidential reasoning approach , 1991, Pattern Recognit. Lett..

[11]  Philippe Smets,et al.  What is Dempster-Shafer's model? , 1994 .

[12]  Thierry Denoeux,et al.  A k-nearest neighbor classification rule based on Dempster-Shafer theory , 1995, IEEE Trans. Syst. Man Cybern..

[13]  Isabelle Bloch.  Information combination operators for data fusion: a comparative review with classification , 1996, IEEE Trans. Syst. Man Cybern. Part A.

[14]  Isabelle Bloch,et al.  Application of Dempster-Shafer evidence theory to unsupervised classification in multisource remote sensing , 1997, IEEE Trans. Geosci. Remote. Sens..

[15]  Isabelle Bloch,et al.  Fusion of Image Information under Imprecision , 1998 .

[16]  Isabelle Bloch,et al.  Introduction of neighborhood information in evidence theory and application to data fusion of radar and optical images with partial cloud cover , 1998, Pattern Recognit..

[17]  Isabelle Bloch,et al.  A first step toward automatic interpretation of SAR images using evidential fusion of several structure detectors , 1999, IEEE Trans. Geosci. Remote. Sens..

[18]  Henk A. Lensen,et al.  Sophisticated test facility to detect land mines , 1999, Defense, Security, and Sensing.

[19]  Aleksandra Pizurica,et al.  A new restoration method and its application to speckle images , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[20]  Stéphane Perrin.  Contribution à l'algorithmique multicapteur pour la détection de mines antipersonnel , 2001 .

[21]  Klamer Schutte,et al.  A comparison of decision-level sensor-fusion methods for anti-personnel landmine detection , 2001, Inf. Fusion.

[22]  Mark L. Yee.  Multisensor probabilistic fusion for mine detection , 2001, SPIE Defense + Commercial Sensing.

[23]  Michel Grabisch,et al.  Using the transferable belief model and a qualitative possibility theory approach on an illustrative example: The assessment of the value of a candidate * , 2001, Int. J. Intell. Syst..

[24]  Nada Milisavljevic,et al.  Reduction of mine suspected areas by multisensor airborne measurements: first results , 2002, SPIE Defense + Commercial Sensing.

[25]  Paul D. Gader,et al.  Feature and decision level sensor fusion of electromagnetic induction and ground penetrating radar sensors for landmine detection with hand-held units , 2002, Inf. Fusion.

[26]  Paul D. Gader,et al.  Generalized Choquet fuzzy integral fusion , 2002, Inf. Fusion.

[27]  Isabelle Bloch,et al.  Improving mine recognition through processing and Dempster-Shafer fusion of ground-penetrating radar data , 2003, Pattern Recognit..

[28]  Isabelle Bloch,et al.  Sensor fusion in anti-personnel mine detection using a two-level belief function model , 2003, IEEE Trans. Syst. Man Cybern. Part C.

[29]  M. Acheroy.  Mine Action Technologies: Problems and Recommendations , 2003 .

[30]  Didier Dubois,et al.  Possibilistic logic : a retrospective and prospective view , 2003 .

[31]  Isabelle Bloch,et al.  Improving Mine Recognition through Processing and Dempster–Shafer Fusion of Multisensor Data , 2005 .

[32]  Mahamadou Idrissa,et al.  PARADIS: GIS Tools for Humanitarian Demining , 2005 .

[33]  Y. Yvinec.  A validated method to help area reduction in mine action with remote sensing data , 2005, ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005..

[34]  Aleksandra Pizurica,et al.  Supervised feature-based classification of multi-channel SAR images , 2006, Pattern Recognit. Lett..

[35]  John K. Waters.  Out of Print. , 2007 .

[36]  Isabelle Bloch,et al.  Multisensor Data Fusion for Spaceborne and Airborne Reduction of Mine Suspected Areas , 2007 .

[37]  A Method for Managing Evidential Reasoning in a Hierarchical Hypothesis Space , 2008, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[38]  Philippe Smets,et al.  The Transferable Belief Model , 1991, Artif. Intell..