A fuzzy shell clustering approach to recognize hyperbolic signatures in subsurface radar images

Delbo, S.; Gamba, Paolo; Roccato, D.

doi:10.1109/36.843039

Cited by 64 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Capineri et al used the Hough transform for straight line to remove the inclined clutter noise [34]. Other noise reduction method such as wavelet method [43], deconvolution method [44] and K distribution method [45] may also increase the signal-noise ratio of the GPR data and improve the performance of recognition. In addition, an algorithm to recover missing traces is also helpful to improve the completeness of reflection signals when some traces were missed in radargrams [46].…”

Section: Development Of Noise Reduction Methods For Heterogeneous Soimentioning

confidence: 99%

Tree Root Automatic Recognition in Ground Penetrating Radar Profiles Based on Randomized Hough Transform

Cui

Guo

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

Abstract:As a nondestructive geophysical tool, Ground penetrating radar (GPR) has been applied in tree root study in recent years. With increasing amounts of GPR data collected for roots, it is imperative to develop an efficient automatic recognition of roots in GPR images. However, few works have been completed on this topic because of the complexity in root recognition problem. Based on GPR datasets from both controlled and in situ experiments, the randomized Hough transform (RHT) algorithm was evaluated in root object recognition for different center frequencies (400 MHz, 900 MHz, and 2000 MHz) in this paper. Reasonable accuracy was obtained (both a high recognition rate and a low false alarm rate) in these datasets, which shows it is feasible to apply the RHT algorithm for root recognition. Furthermore, we evaluated the influence of root and soil factors on the recognition. We found that the performance of RHT algorithm is mainly affected by root interval length, root orientation, and clutter noise of soil. The recognition results by RHT could be applied for large scale root system distribution study in belowground ecology. Further studies should be conducted to reduce clutter noise and improve the recognition of the complex root reflections.

show abstract

Section: Development Of Noise Reduction Methods For Heterogeneous Soimentioning

confidence: 99%

Tree Root Automatic Recognition in Ground Penetrating Radar Profiles Based on Randomized Hough Transform

Cui

Guo

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…1,3,8 The characteristics of landmine responses in GPR data as a sensor passes over it can be seen in Figure 2. The hyperbola-like shape is caused by the reflection pulse from the soil/landmine interface as the sensor moves over the landmine.…”

Section: Introductionmentioning

confidence: 99%

“…1,8,9 One of the problems with performing landmine detection using these methods in GPR data is limiting processing to only image regions that contain energy reflections caused by a buried landmine. Due to the variation in soil types, it is not possible to know exactly where the landmine response is located in the GPR data, even when the burial depth is known.…”

Section: Introductionmentioning

confidence: 99%

Application of image categorization methods for buried threat detection in GPR data

et al. 2013

View full text Add to dashboard Cite

Utilizing methods from the image processing and computer vision fields has led to advances in high resolution Ground Penetrating Radar (GPR) based threat detection. By analyzing 2-D slices of GPR data and applying various image processing algorithms, it is possible to discriminate between threat and non-threat objects. In initial attempts to utilize such approaches, object instance-matching algorithms were applied to GPR images, but only limited success was obtained when utilizing feature point methods to identify patches of data that displayed landmine-like characteristics. While the approach worked well under some conditions, the instance-matching method of classification was not designed to identify a type of class, only reproductions of a specific instance. In contrast, our current approach is focused on identifying methods that can account for within-class variations that result from changing target types and varying operating conditions that a GPR system regularly encounters. Image category recognition is an area of research that attempts to account for within class variation of objects within visual images. Instead of finding a reproduction of a particular known object within an image, algorithms for image categorization are designed to learn the qualities of images that contain an instance belonging to a known class. The results illustrate how image category recognition algorithms can be successfully applied to threat identification in GPR data.

show abstract

“…Related studies mainly contribute to the automated analyses of data acquired by Ground Penetrating Radars (GPRs) showing linear and hyperbolic returns (Capineri et al, 1998;Delbo et al, 2000;Gamba and Lossani, 2000;Al-Nuaimy et al, 2001;Pasolli et al, 2009). Few attempts have been reported in the literature to address the automated detection of subsurface linear features from Martian radar sounding data.…”

Section: Introductionmentioning

confidence: 99%

Automated reconstruction of subsurface interfaces in Promethei Lingula near the Martian south pole by using SHARAD data

Xiong

Müller

2019

Planetary and Space Science

View full text Add to dashboard Cite

A B S T R A C TSubsurface layers are preserved in polar regions on Mars, which are considered to be a record of past climate changes on Mars. Orbital radar instruments like the SHAllow RADar (SHARAD) on board Mars Reconnaissance Orbiter (MRO) transmit radar signals to Mars and receive a set of signals returned from interfaces having a contrast in dielectric properties in the probed subsurface regions. These subsurface layers which are preserved in the upper % 1 km of the Martian Polar Layered Deposits (PLDs) can be observed in SHARAD radargrams. Extraction of these layering features is the preliminary work before interpreting and understanding their origins. In this study, we use a new method based on log-Gabor filtering and Continuous Wavelet Transform (CWT)-based peak detection to extract subsurface radar reflections and a workflow to remove clutter reflections in order to reconstruct 3-D subsurface layers. These methods and workflow are then tested on the SHARAD data in the Promethei Lingula region near the Martian south pole. The results show that following this workflow, the ground surface and six subsurface interfaces can be reconstructed, which aids in the interpretation of the depositional and erosional history of this region.

show abstract

A fuzzy shell clustering approach to recognize hyperbolic signatures in subsurface radar images

Cited by 64 publications

References 15 publications

Tree Root Automatic Recognition in Ground Penetrating Radar Profiles Based on Randomized Hough Transform

Tree Root Automatic Recognition in Ground Penetrating Radar Profiles Based on Randomized Hough Transform

Application of image categorization methods for buried threat detection in GPR data

Automated reconstruction of subsurface interfaces in Promethei Lingula near the Martian south pole by using SHARAD data

Contact Info

Product

Resources

About