Sensor feature fusion for detecting buried objects

Clark, G A; Sengupta, S K; Sherwood, R J; Hernandez, J E; Buhl, M R; Schaich, P C; Kane, R J; Barth, M J; DelGrande, N K

Title: Sensor feature fusion for detecting buried objects

Full Record
Other Related Research

Abstract

Given multiple registered images of the earth`s surface from dual-band sensors, our system fuses information from the sensors to reduce the effects of clutter and improve the ability to detect buried or surface target sites. The sensor suite currently includes two sensors (5 micron and 10 micron wavelengths) and one ground penetrating radar (GPR) of the wide-band pulsed synthetic aperture type. We use a supervised teaming pattern recognition approach to detect metal and plastic land mines buried in soil. The overall process consists of four main parts: Preprocessing, feature extraction, feature selection, and classification. These parts are used in a two step process to classify a subimage. Thee first step, referred to as feature selection, determines the features of sub-images which result in the greatest separability among the classes. The second step, image labeling, uses the selected features and the decisions from a pattern classifier to label the regions in the image which are likely to correspond to buried mines. We extract features from the images, and use feature selection algorithms to select only the most important features according to their contribution to correct detections. This allows us to save computational complexity and determine which of the sensors add valuemore »« less

Authors:: Clark, G A; Sengupta, S K; Sherwood, R J; Hernandez, J E; Buhl, M R; Schaich, P C; Kane, R J; Barth, M J; DelGrande, N K

Publication Date:: Thu Apr 01 00:00:00 EST 1993

Research Org.:: Lawrence Livermore National Lab., CA (United States)

Sponsoring Org.:: USDOE, Washington, DC (United States); Department of Defense, Washington, DC (United States)

OSTI Identifier:: 10180523

Report Number(s):: UCRL-JC-113727; CONF-930445-22
ON: DE93018666

DOE Contract Number:: W-7405-ENG-48

Resource Type:: Conference

Resource Relation:: Conference: Society of Photo-Optical Instrumentation Engineers (SPIE) OE/aerospace science and sensing meeting,Orlando, FL (United States),11-16 Apr 1993; Other Information: PBD: Apr 1993

Country of Publication:: United States

Language:: English

Subject:: 45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE; 47 OTHER INSTRUMENTATION; SYNTHETIC-APERTURE RADAR; TESTING; INFRARED THERMOGRAPHY; BOMBS; DETECTION; UNDERGROUND; PATTERN RECOGNITION; ARTIFICIAL INTELLIGENCE; ALGORITHMS; IMAGE PROCESSING; SYNERGISM; 450000; 440600; 440800; MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEFENSE; OPTICAL INSTRUMENTATION; MISCELLANEOUS INSTRUMENTATION

Citation Formats


                    Clark, G A, Sengupta, S K, Sherwood, R J, Hernandez, J E, Buhl, M R, Schaich, P C, Kane, R J, Barth, M J, and DelGrande, N K. Sensor feature fusion for detecting buried objects.  United States: N. p., 1993. 
        Web.

Copy to clipboard


                    Clark, G A, Sengupta, S K, Sherwood, R J, Hernandez, J E, Buhl, M R, Schaich, P C, Kane, R J, Barth, M J, & DelGrande, N K. Sensor feature fusion for detecting buried objects.  United States.

Copy to clipboard


                    Clark, G A, Sengupta, S K, Sherwood, R J, Hernandez, J E, Buhl, M R, Schaich, P C, Kane, R J, Barth, M J, and DelGrande, N K. 1993.  
        "Sensor feature fusion for detecting buried objects".  United States.  https://www.osti.gov/servlets/purl/10180523.

Copy to clipboard


                    
@article{osti_10180523,

  title        = {Sensor feature fusion for detecting buried objects},

  author       = {Clark, G A and Sengupta, S K and Sherwood, R J and Hernandez, J E and Buhl, M R and Schaich, P C and Kane, R J and Barth, M J and DelGrande, N K},

  abstractNote = {Given multiple registered images of the earth`s surface from dual-band sensors, our system fuses information from the sensors to reduce the effects of clutter and improve the ability to detect buried or surface target sites. The sensor suite currently includes two sensors (5 micron and 10 micron wavelengths) and one ground penetrating radar (GPR) of the wide-band pulsed synthetic aperture type. We use a supervised teaming pattern recognition approach to detect metal and plastic land mines buried in soil. The overall process consists of four main parts: Preprocessing, feature extraction, feature selection, and classification. These parts are used in a two step process to classify a subimage. Thee first step, referred to as feature selection, determines the features of sub-images which result in the greatest separability among the classes. The second step, image labeling, uses the selected features and the decisions from a pattern classifier to label the regions in the image which are likely to correspond to buried mines. We extract features from the images, and use feature selection algorithms to select only the most important features according to their contribution to correct detections. This allows us to save computational complexity and determine which of the sensors add value to the detection system. The most important features from the various sensors are fused using supervised teaming pattern classifiers (including neural networks). We present results of experiments to detect buried land mines from real data, and evaluate the usefulness of fusing feature information from multiple sensor types, including dual-band infrared and ground penetrating radar. The novelty of the work lies mostly in the combination of the algorithms and their application to the very important and currently unsolved operational problem of detecting buried land mines from an airborne standoff platform.},

  doi          = {},

  url          = {https://www.osti.gov/biblio/10180523},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {Thu Apr 01 00:00:00 EST 1993},

  month        = {Thu Apr 01 00:00:00 EST 1993}

}

Copy to clipboard

Conference:

View Conference (1.46 MB)

Other availability

Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Land mine detection using multispectral image fusion

Conference Clark, G; Sengupta, S; Aimonetti, W; ...

Our system fuses information contained in registered images from multiple sensors to reduce the effects of clutter and improve the ability to detect surface and buried land mines. The sensor suite currently consists of a camera that acquires images in six bands (400nm, 500nm, 600nm, 700nm, 800nm and 900nm). Past research has shown that it is extremely difficult to distinguish land mines from background clutter in images obtained from a single sensor. It is hypothesized, however, that information fused from a suite of various sensors is likely to provide better detection reliability, because the suite of sensors detects a varietymore »« less
Full Text Available
Multispectral image feature fusion for detecting land mines

Conference Clark, G; Fields, D; Sherwood, R

Our system fuses information contained in registered images from multiple sensors to reduce the effect of clutter and improve the the ability to detect surface and buried land mines. The sensor suite currently consists if a camera that acquires images in sixible wavelength bands, du, dual-band infrared (5 micron and 10 micron) and ground penetrating radar. Past research has shown that it is extremely difficult to distinguish land mines from background clutter in images obtained from a single sensor. It is hypothesized, however, that information fused from a suite of various sensors is likely to provide better detection reliability, becausemore »« less
Full Text Available
Computer vision and sensor fusion for detecting buried objects

Conference Clark, G; Hernandez, J; Sengupta, S; ...

Given multiple images of the surface of the earth from dual-band infrared sensors, our system fuses information from the sensors to reduce the effects of clutter and improve the ability to detect buried or surface target sites. Supervised learning pattern classifiers (including neural networks,) are used. We present results of experiments to detect buried land mines from real data, and evaluate the usefulness of fusing information from multiple sensor types. The novelty of the work lies mostly in the combination of the algorithms and their application to the very important and currently unsolved problem of detecting buried land mines frommore » an airborne standoff platform.« less
Full Text Available
Detection of buried objects by fusing dual-band infrared images

Conference Clark, G; Sengupta, S; Sherwood, R; ...

We have conducted experiments to demonstrate the enhanced detectability of buried land mines using sensor fusion techniques. Multiple sensors, including visible imagery, infrared imagery, and ground penetrating radar (GPR), have been used to acquire data on a number of buried mines and mine surrogates. Because the visible wavelength and GPR data are currently incomplete. This paper focuses on the fusion of two-band infrared images. We use feature-level fusion and supervised learning with the probabilistic neural network (PNN) to evaluate detection performance. The novelty of the work lies in the application of advanced target recognition algorithms, the fusion of dual-band infraredmore »« less
Full Text Available
Sensor fusion methodology for remote detection of buried land mines

Conference Del Grande, N

We are investigation a sensor fusion methodology for remote detection of buried land mines. Our primary approach is sensor intrafusion. Our dual-channel passive IR methodology decouples true (corrected) surface temperature variations of 0.2{degree}C from spatially dependent surface emissivity noise. It produces surface temperature maps showing patterns of conducted heat from buried objects which heat and cool differently from their surroundings. Our methodology exploits Planck's radiation law. It produces separate maps of surface emissivity variations which allow us to reduce false alarms. Our secondary approach is sensor interfusion using other methodologies. For example, an active IR CO{sub 2} laser reflectance channelmore »« less
Full Text Available

Similar Records