A survey of landmine detection using hyperspectral imaging

Makki, Ihab; Younès, Rafic; Francis, Clovis; Bianchi, Tiziano; Zucchetti, Massimo

doi:10.1016/j.isprsjprs.2016.12.009

Cited by 135 publications

(48 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Particularly, spectral unmixing is a significant step of HSI data processing [3,4], and it correlates closely with realistic applications including land cover mapping [5], mine exploration [6], precision agriculture [7] and marine monitoring [8] and so on. The phenomenon of spectral mixture mainly results from limited spatial resolutions of imaging spectrometer (<30 m) and homogeneous mixture of distinct materials, and it refers to that the observed spectral reflectance at each pixel is physically a spectral mixture of several pure materials or called endmembers [9,10].…”

Section: Introductionmentioning

confidence: 89%

A Probabilistic Weighted Archetypal Analysis Method with Earth Mover’s Distance for Endmember Extraction from Hyperspectral Imagery

Sun

Zhang

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

Abstract:A Probabilistic Weighted Archetypal Analysis method with Earth Mover's Distance (PWAA-EMD) is proposed to extract endmembers from hyperspectral imagery (HSI). The PWAA-EMD first utilizes the EMD dissimilarity matrix to weight the coefficient matrix in the regular Archetypal Analysis (AA). The EMD metric considers manifold structures of spectral signatures in the HSI data and could better quantify the dissimilarity features among pairwise pixels. Second, the PWAA-EMD adopts the Bayesian framework and formulates the improved AA into a probabilistic inference problem by maximizing a joint posterior density. Third, the optimization problem is solved by the iterative multiplicative update scheme, with a careful initialization from the two-stage algorithm and the proper endmembers are finally obtained. The synthetic and real Cuprite Hyperspectral datasets are utilized to verify the performance of PWAA-EMD and five popular methods are implemented to make comparisons. The results show that PWAA-EMD surpasses all the five methods in the average results of spectral angle distance (SAD) and root-mean-square-error (RMSE). Especially, the PWAA-EMD obtains more accurate estimation than AA in almost all the classes of endmembers including two similar ones. Therefore, the PWAA-EMD could be an alternative choice for endmember extraction on the hyperspectral data.

show abstract

Section: Introductionmentioning

confidence: 89%

A Probabilistic Weighted Archetypal Analysis Method with Earth Mover’s Distance for Endmember Extraction from Hyperspectral Imagery

Sun

Zhang

et al. 2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Indicators of mine presence can be detected and isolated on digital images using some of the methods for processing digital images described in [47,48], or by methods of object-oriented identification of linear objects based on presuppositions regarding their geometric and radiometric features and use of various filters to emphasize them [49] or [50]. Isolating indicators of mine presence on hyperspectral images is done via their spectral characteristics, as shown in [51][52][53]. Table 1.…”

Section: Sensorsmentioning

confidence: 99%

The AIDSS Module for Data Acquisition in Crisis Situations and Environmental Protection

Krtalić

Bajić²,

Ivelja

et al. 2020

Sensors

View full text Add to dashboard Cite

The Toolbox implementation for removal of antipersonnel mines, submunitions and unexploded ordnance (TIRAMISU) Advanced Intelligence Decision Support System is an operational system proposed to Mine Action Centres worldwide for conducting non-technical surveys in humanitarian demining. The system consists of three modules, one of which is the module for data acquisition introduced and described in this study. The module has been designed, produced, improved, used and operationally tested and validated on several platforms (helicopters, remotely piloted aircraft systems (RPAS) and a blimp), with various sensors and acquisition units (Global Positioning System (GPS) and inertial measurement unit) in a variety of combinations for additional data acquisition from deep inside a suspected hazardous area. For the purposes of aerial data acquisition over a suspected hazardous area, the use of multiple sensors such as visible digital cameras and multi-spectral visible, near infrared (VNIR), hyperspectral VNIR and thermal infrared sensors are of benefit, because they display the scene in different ways. Off-the-shelf equipment and software were mostly used, but some specific equipment, such as sensor pods, was developed and also some software solutions for data acquisition and pre-processing (transforming hyperspectral line scanner data into hyperspectral images, and producing hyperspectral cubes). The technical stability and robustness of the module were confirmed by operationally testing and evaluating the systems on the aforementioned platforms and missions in several actual suspected hazardous areas in Croatia and Bosnia and Herzegovina, between 2001 and 2015.

show abstract

“…Hyperspectral image (HSI) consists of hundreds of narrow contiguous wavelength bands carrying a wealth of spectral information. Taking advantage of the rich spectral information, classification using hyperspectral data has been developed for a variety of applications, such as image segmentation, object recognition, land cover mapping and anomaly detection [1][2][3][4].…”

Section: Introductionmentioning

confidence: 99%

A New Dataset and Deep Residual Spectral Spatial Network for Hyperspectral Image Classification

Xue¹,

Zeng²,

Chen

et al. 2020

Symmetry

View full text Add to dashboard Cite

Due to the limited varieties and sizes of existing public hyperspectral image (HSI) datasets, the classification accuracies are higher than 99% with convolutional neural networks (CNNs). In this paper, we presented a new HSI dataset named Shandong Feicheng, whose size and pixel quantity are much larger. It also has a larger intra-class variance and a smaller inter-class variance. State-of-the-art methods were compared on it to verify its diversity. Otherwise, to reduce overfitting caused by the imbalance between high dimension and small quantity of labeled HSI data, existing CNNs for HSI classification are relatively shallow and suffer from low capacity of feature learning. To solve this problem, we proposed an HSI classification framework named deep residual spectral spatial setwork (DRSSN). By using shortcut connection structure, which is an asymmetry structure, DRSSN can be deeper to extract features with better discrimination. In addition, to alleviate insufficient training caused by unbalanced sample sizes between easily and hard classified samples, we proposed a novel training loss function named sample balanced loss, which allocated weights to the losses of samples according to their prediction confidence. Experimental results on two popular datasets and our proposed dataset showed that our proposed network could provide competitive results compared with state-of-the-art methods.

show abstract

A survey of landmine detection using hyperspectral imaging

Cited by 135 publications

References 69 publications

A Probabilistic Weighted Archetypal Analysis Method with Earth Mover’s Distance for Endmember Extraction from Hyperspectral Imagery

A Probabilistic Weighted Archetypal Analysis Method with Earth Mover’s Distance for Endmember Extraction from Hyperspectral Imagery

The AIDSS Module for Data Acquisition in Crisis Situations and Environmental Protection

A New Dataset and Deep Residual Spectral Spatial Network for Hyperspectral Image Classification

Contact Info

Product

Resources

About