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

Li, Wentao; Cui, Xihong; Guo, Li; Chen, Jin; Chen, Xuehong; Cao, Xin

doi:10.3390/rs8050430

Cited by 68 publications

(49 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides that, cave sediments can have very heterogeneous mineral composition and their extent can be of various size and shape. In order to provide possible automation of the proposed procedure (e.g., [49]), additional mineralogical-geochemical analyses should be done in the future and the electrical resistivity tomography (ERT) as a complementary method can be conducted in the further research. However, due to the locally rough karst terrain and the time-consuming nature of ERT, we decided to apply only the GPR method for the purpose of this study.…”

Section: Integration Of Resultsmentioning

confidence: 99%

Application of Ground Penetrating Radar Supported by Mineralogical-Geochemical Methods for Mapping Unroofed Cave Sediments

2018

View full text Add to dashboard Cite

Ground penetrating radar (GPR) using a special unshielded 50 MHz Rough Terrain Antenna (RTA) in combination with a shielded 250 MHz antenna was used to study the capability of this geophysical method for detecting cave sediments. Allochthonous cave sediments found in the study area of Lanski vrh (W Slovenia) are now exposed on the karst surface in the so-called "unroofed caves" due to a general lowering of the surface (denudation of carbonate rocks) and can provide valuable evidence of the karst development. In the first phase, GPR profiles were measured at three test locations, where cave sediments are clearly evident on the surface and appear with flowstone. It turned out that cave sediments are clearly visible on GPR radargrams as areas of strong signal attenuation. Based on this finding, GPR profiling was used in several other places where direct indicators of unroofed caves or other indicators for speleogenesis are not present due to strong surface reshaping. The influence of various field conditions, especially water content, on GPR measurements was also analysed by comparing radargrams measured in various field conditions. Further mineralogical-geochemical analyses were conducted to better understand the factors that influence the attenuation in the area of cave sediments. Samples of cave sediments and soils on carbonate rocks (rendzina) were taken for X-ray diffraction (XRD) and X-ray fluorescence (XRF) analyses to compare the mineral and geochemical compositions of both sediments. Results show that cave sediments contain higher amounts of clay minerals and iron/aluminium oxides/hydroxides which, in addition to the thickness of cave sediments, can play an important role in the depth of penetration. Differences in the mineral composition also lead to water retention in cave sediments even through dry periods which additionally contribute to increased attenuation with respect to surrounding soils. The GPR method has proven to be reliable for locating areas of cave sediments at the surface and to determine their spatial extent, which is very important in delineating the geometry of unroofed cave systems. GPR thus proved to be a very valuable method in supporting geological and geomorphological mapping for a more comprehensive recognition of unroofed cave systems. These are important for understanding karstification and speleogenetic processes that influenced the formation of former underground caves and can help us reconstruct the direction of former underground water flows.

show abstract

Section: Integration Of Resultsmentioning

confidence: 99%

Application of Ground Penetrating Radar Supported by Mineralogical-Geochemical Methods for Mapping Unroofed Cave Sediments

2018

View full text Add to dashboard Cite

show abstract

“…To date, there have been various approaches aiming to automatize the object detection procedure. Wavelet transform, Hough transform, and Radon transform are popular techniques among electrical engineering scholars.…”

Section: Introductionmentioning

confidence: 99%

Real‐time object detection using power spectral density of ground‐penetrating radar data

Saghafi

Jazayeri

Esmaeili

et al. 2019

Struct Control Health Monit

View full text Add to dashboard Cite

A statistical analytical monitoring scheme is developed that utilizes maximum energy of ground-penetrating radar signals to detect hidden buried objects and estimate their location and depth automatically. The maximum energy is calculated for locations by Welch's power spectral density estimation. Using the proposed analytic, the maximum energy is tightly monitored for a significant change from reference signals generated using target-free locations.A warning message is triggered when monitoring process detects a site with potential buried objects, on average, 90 cm (2.95 ft) away from the object for 800-MHz antenna. Continuing the ground-penetrating radar scan in the same direction and monitoring the signals, the procedure uses a sophisticated hyperbola-mapping method to estimate the location and depth of buried objects with high accuracy. The analytics could successfully pinpoint the location and depth of hidden objects, respectively, with mean absolute error of 0.38 and 2.03 cm in synthetic noisy environments. Reliable performance of the proposed analytics in real cases that run in real-time for multiple object detection even in noisy media proves its efficiency for real-life exploration.

show abstract

“…One of the most popular and classical approaches is the Hough transform (HT) method. In [1,2], the generalized HT and the randomized HT were employed to find the hyperbola parameters which are recorded within the Hough accumulator space. However, This work is supported by the Région Bretagne grant.…”

Section: Introductionmentioning

confidence: 99%

Buried Object Detection from B-Scan Ground Penetrating Radar Data Using Faster-RCNN

Pham

Lefèvre

2018

IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium

116

View full text Add to dashboard Cite

In this paper, we adapt the Faster-RCNN framework for the detection of underground buried objects (i.e. hyperbola reflections) in B-scan ground penetrating radar (GPR) images. Due to the lack of real data for training, we propose to incorporate more simulated radargrams generated from different configurations using the gprMax toolbox. Our designed CNN is first pre-trained on the grayscale Cifar-10 database. Then, the Faster-RCNN framework based on the pre-trained CNN is trained and fine-tuned on both real and simulated GPR data. Preliminary detection results show that the proposed technique can provide significant improvements compared to classical computer vision methods and hence becomes quite promising to deal with this kind of specific GPR data even with few training samples.

show abstract

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

Cited by 68 publications

References 41 publications

Application of Ground Penetrating Radar Supported by Mineralogical-Geochemical Methods for Mapping Unroofed Cave Sediments

Application of Ground Penetrating Radar Supported by Mineralogical-Geochemical Methods for Mapping Unroofed Cave Sediments

Real‐time object detection using power spectral density of ground‐penetrating radar data

Buried Object Detection from B-Scan Ground Penetrating Radar Data Using Faster-RCNN

Contact Info

Product

Resources

About