A morphological approach to automatic mine detection problems

Banerji, A.; Goutsias, John

doi:10.1109/7.722683

Cited by 22 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Morphology has become a popular tool in many image processing applications such as noise removal, image enhancement and image segmentation [11]. Also, this technique can be used for reducing the effect of clutter and enhancing the presence of targets in landmine detection [12].…”

Section: Morphology Based Detection Techniquementioning

confidence: 99%

Efficient Detection of Landmines From Acoustic Images

Kasban¹,

Zahran²,

El-Kordy³

et al. 2009

PIER C

View full text Add to dashboard Cite

Abstract-The Laser Doppler Vibrometer (LDV)-based Acoustic toSeismic (A/S) landmine detection system is one of the reliable and powerful landmine detection systems. The interpretation of the LDVbased A/S data is performed off-line, manually, depending heavily on the skills, experience, alertness and consistency of a trained operator. This takes a long time. The manually obtained results suffer from errors, particularly when dealing with large volumes of data. This paper proposes some techniques for the automatic detection of objects from the acoustic images which are obtained from the LDV-based A/S landmine detection system. These techniques are based on Corresponding author: F. E. Abd El-Samie (fathi sayed@yahoo.com). 80Kasban et al.color image transformations, morphological image processing and the wavelet transform. The proposed techniques are compared considering the probability of detection, the false alarm rate, the accuracy and the processing speed.

show abstract

Section: Morphology Based Detection Techniquementioning

confidence: 99%

Efficient Detection of Landmines From Acoustic Images

Kasban¹,

Zahran²,

El-Kordy³

et al. 2009

PIER C

View full text Add to dashboard Cite

show abstract

“…A unique approach was explored by Banerji and Goutsias [85], who used mathematical morphology to detect mines in individual bands followed by fusion of the band information. Correlation among the bands was addressed by using a i-naximumu noise fraction transform to generate independent bands.…”

Section: Prior Workmentioning

confidence: 99%

Physics-Based Radiometric Signature Modeling and Detection Algorithms of Landmines Using Electro-Optical Sensors

Liao¹

2005

View full text Add to dashboard Cite

“…. • , Qk} are then fused using a majority voting method, following M1k=l{O}, (2) where 1 is a number from 1 to p (in our experiments, 1 is picked as p/2 rounded to the nearest integer). Observe that, only pixels that are present in at least 1 of the p multispectral bands can survive majority voting.…”

Section: Morphological Detectionmentioning

confidence: 99%

Iterative morphological algorithms for automated detection of land mines

Batman

Goutsias

2000

SPIE Proceedings

View full text Add to dashboard Cite

A new hybrid algorithm, based on combining the decorrelating and packing qualities of Principal Component (PC) analysis and the shape extracting and filtering properties of Mathematical Morphology, is investigated in the framework of land mine detection. The new method is similar in spirit to the MM-MNF algorithm, which is based on a linear pre-filter (the Maximum Noise Fraction (MNF) transform), followed by a morphological multispectral detection component (MM). The new filter (PC-MM), has a similar concatenated structure, and addresses some of the weaknesses inherent in the linear component of the MM-MNF algorithm; namely, the susceptibility of the MNF transform to clutter inhomogeneity, as well as to variations in clutter covariance estimation. The PC-MM algorithm addresses the stationarity problem by solely operating on image peaks extracted by a morphological top-hat transform. Therefore, the algorithm is much less susceptible to the presence of different textural regions. Subsequently, the peaks in the extracted multispectral top-hat image are projected into uncorrelated bands using the principal component (PC) transform. Due to the packing property of the PC transform, the target markers are typically found in the first and second bands in the PC transformed image (as opposed to any one or two of the 6 possible bands for the MNF transform) . The targets are then detected using a variant of the morphological detection scheme ( MM) . The new method provides a fast and satisfactory first-pass detection result, for images of different clutter homogeneities and target types. The extracted targets, from the first pass, are then used to improve the detection result in a subsequent iteration, by updating covariance estimates of relevant filter variables.

show abstract

A morphological approach to automatic mine detection problems

Cited by 22 publications

References 27 publications

Efficient Detection of Landmines From Acoustic Images

Efficient Detection of Landmines From Acoustic Images

Physics-Based Radiometric Signature Modeling and Detection Algorithms of Landmines Using Electro-Optical Sensors

Iterative morphological algorithms for automated detection of land mines

Contact Info

Product

Resources

About