A Comparison of Methods of Data Fusion for LandMine Detection

It has been suggested that fusion of multiple data sources may be required for the reliable detection of land mines at acceptable false alarm rates. This study validates this contention by showing that a fusion algorithm using images from two infrared wave bands (3-5 m and 8-12 m) yields signi cantly better false alarm rates than either by itself. The research was pursued with methodological rigour, both in experimental design and statistical assessment. The data processing involves orthographic registration, region of interest extraction, feature extraction, feature selection, classi cation.

[1]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[2]  Peter E. Hart,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[3]  N. Del Grande.  Temperature Evaluated Mine Position Survey (TEMPS) application of dual-band infrared methodology , 1992 .

[4]  J.E. Hernandez,et al.  Computer vision and sensor fusion for detecting buried objects , 1992, [1992] Conference Record of the Twenty-Sixth Asilomar Conference on Signals, Systems & Computers.

[5]  John C. Russ,et al.  The Image Processing Handbook , 2016, Microscopy and Microanalysis.

[6]  G. A. Clark,et al.  Detecting buried objects by fusing dual-band infrared images , 1993, Proceedings of 27th Asilomar Conference on Signals, Systems and Computers.

[7]  S. Pizer,et al.  The Image Processing Handbook , 1994 .

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

[9]  Douglas L. Smith.  Detection technologies for mines and minelike targets , 1995, Defense, Security, and Sensing.

[10]  J. Mullins.  ONE FALSE STEP , 1996 .