Stand-off thermal IR minefield survey: system concept and experimental results

Cremer, Frank; Nguyễn, Thành Trung; Yang, Lei; Sahli, Hichem

doi:10.1117/12.626264

Cited by 14 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For landmine detection, landmines are thought of as a thermal barrier in the natural flow of the heat inside the soil, which produces a perturbation of the expected thermal pattern on the surface. The detection of these perturbations (anomalies) provides evidence of presence of potential landmine targets [8].…”

Section: Infrared Imaging Techniquesmentioning

confidence: 99%

A Geometrical Feature Based Sensor Fusion Model of GPR and IR for the Detection and Classification of Anti-Personnel Mines

Nath

Bhuiyan

2007

Seventh International Conference on Intelligent Systems Design and Applications (ISDA 2007)

View full text Add to dashboard Cite

The Ground penetrating radar (GPR) and Infrared (IR) imaging have become two established sensors for detecting buried anti-personnel mines (APM) which contain no or a little metal. The paper introduces the GPR and IR techniques briefly and compares the two sensors with respect to their strengths and weaknesses for target detection and emphasizes the necessity of fusion to harness the advantages of each of the methods. We propose a geometrical feature based sensor fusion framework, combining GPR and IR, as an effective technique for detection and classification of APM, which will reduce the false alarm rate significantly. We consider the basic geometrical shape descriptor features of an object and construct a feature vector for each of the objects. These feature vectors are used to train a Probabilistic Neural Network (PNN) for the classification of APMs. The method gives almost perfect detection accuracy.

show abstract

Section: Infrared Imaging Techniquesmentioning

confidence: 99%

A Geometrical Feature Based Sensor Fusion Model of GPR and IR for the Detection and Classification of Anti-Personnel Mines

Nath

Bhuiyan

2007

Seventh International Conference on Intelligent Systems Design and Applications (ISDA 2007)

View full text Add to dashboard Cite

show abstract

“…DN bias may be estimated by plotting the signal [DN] vs. the incident radiance and extrapolate down to a radiance = 0, which is shown in the figure below. The responses of individual pixels tend to be nonlinear [3] but the median, or mean, response of all pixels tends to be approximately linear in the measurement range [1]. For sensors in the VIS, NIR or SWIR range DN bias is obtained by registering the signal when the incident flux is blocked.…”

Section: Radiometric Calibrationmentioning

confidence: 99%

“…Even if extrapolation is performed down to an integration time = 0 there will still be a remaining offset contribution, which is denoted DN bias,0 in the following. The integration time is included in a model by Lucey et al [3] which is used for calibration of a NIR camera on the satellite Clementine …”

Section: Radiometric Calibrationmentioning

confidence: 99%

See 1 more Smart Citation

A study of the radiometric calibration of spectral bands in the mid-wave infrared (MWIR) spectral range 1.5-5 μm

2009

View full text Add to dashboard Cite

Radiometric calibrations of sensor data are routinely performed using one or more radiation sources at different radiance levels. Calibration of spectral bands in the thermal infrared region (> 2.0 μm) is needed due to the bias drift which is a characteristic of the detector technology (e.g. MCT, InSb). To maintain the accuracy during an extended measurement the calibration has to be frequently repeated. The complexity of the radiometric calibration increases even more when a) the number of spectral bands to calibrate increases, b) the spectral range of the sensors to calibrate increases, c) the radiation level of the scene or object under interest (like hot spots) increases. If the accuracy in the calibration is to be maintained, all these factors will both increase the time needed to perform the calibration and the number and/or complexity of the radiation sources needed. Either or both may be impractical to handle during a field trial. In this paper we have studied the radiometric calibration of spectral bands in the mid wave infrared region (MWIR, 1.5 -5.5 μm), with the focus on hot spots. The model and methodology proposed are however general and can be applied on an arbitrary set of sensor data collected in the 0.4 -12 μm spectral region. Data was obtained from a cooled multi-band sensor based on an MCT detector. The study also includes the development of a SWIR source practical for field trials.

show abstract

“…Many kinds of sensors are under investigation for landmine detection, e.g., multispectral sensor [4], hyperspectral sensor [5], infrared sensor [6], and ground penetrating radar (GPR) [7]. GPR is a promising technology which can detect both plastic and metal landmines.…”

Section: Introductionmentioning

confidence: 99%

Sparse Time-Frequency Representation Based Feature Extraction Method for Landmine Discrimination

Wang¹,

Song²,

Tian³

et al. 2013

PIER

View full text Add to dashboard Cite

Abstract-Low-frequency ultra-wideband synthetic aperture radar is a promising technology for landmine detection. According to the scattering characteristics of body-of-revolution (BOR) along with azimuth angles, a discriminator based on Bayesian decision rule is proposed, which uses sequential features, i.e., double-hump distance. First, the algorithm estimates the target scatterings in all azimuth angles based on regions of interest. Second, sequential aspect features are extracted by sparse time-frequency representation. Third, the distributions of features are obtained by training samples, and then the posterior probability of landmine class is computed as an input to the classifier adopting Mahalanobis distance. The experimental results indicate that the proposed algorithm is effective in BOR target discrimination.

show abstract

Stand-off thermal IR minefield survey: system concept and experimental results

Cited by 14 publications

References 8 publications

A Geometrical Feature Based Sensor Fusion Model of GPR and IR for the Detection and Classification of Anti-Personnel Mines

A Geometrical Feature Based Sensor Fusion Model of GPR and IR for the Detection and Classification of Anti-Personnel Mines

A study of the radiometric calibration of spectral bands in the mid-wave infrared (MWIR) spectral range 1.5-5 μm

Sparse Time-Frequency Representation Based Feature Extraction Method for Landmine Discrimination

Contact Info

Product

Resources

About