An Enhanced Data Processing Framework for Mapping Tree Root Systems Using Ground Penetrating Radar

Lantini, Livia; Tosti, Fabio; Giannakis, Iraklis; Zou, Lu; Benedetto, Andrea; Alani, Amir M.

doi:10.3390/rs12203417

Cited by 21 publications

(15 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The survey was carried out as part of a wider research campaign 13 in Gunnersbury Park, Ealing, London (United Kingdom) (Fig. 1).…”

Section: Methodology 21 Test Site and Equipmentmentioning

confidence: 99%

“…GPR is gaining popularity in forestry applications because of its effectiveness and the ability to get accurate information on the subsoil, moisture level, and root systems in an entirely non-intrusive manner 10,11 . Research to date has focused on the development of automated methods for root mapping in a three-dimensional environment 12,13 and the assessment of root mass density 14 . A recent experimental investigation examined the viability of a novel tree root assessment method based on the analysis of GPR data in the time and frequency domains 15,16 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Assessing the root system of urban trees by geostatistical analysis of GPR data

Lantini

Trevisani²,

Tosti³

et al. 2022

Earth Resources and Environmental Remote Sensing/Gis Applications XIII

View full text Add to dashboard Cite

“…The survey was carried out as part of a wider research campaign 13 in Gunnersbury Park, Ealing, London (United Kingdom) (Fig. 1).…”

Section: Methodology 21 Test Site and Equipmentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Assessing the root system of urban trees by geostatistical analysis of GPR data

Lantini

Trevisani²,

Tosti³

et al. 2022

Earth Resources and Environmental Remote Sensing/Gis Applications XIII

View full text Add to dashboard Cite

“…The GPR survey was carried out in Gunnersbury Park, Ealing, London (United Kingdom), as part of a major investigation [6]. A set of 36 semi-circular scans were performed around the investigated tree.…”

Section: A Gpr Test Site and Equipmentmentioning

confidence: 99%

“…Hence, GPR is gaining popularity as a nondestructive tool for estimating root patterns. Recent research has focused on methods for automatic root mapping in threedimensional settings [6]. Additionally, recent studies have proposed a new signal processing approach and demonstrated the feasibility of a combined time-frequency analysis of the GPR signal [7].…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Approach for Tree Root Detection using GPR Spectrogram Imagery

Lantini

Massimi

Tosti

et al. 2022

2022 45th International Conference on Telecommunications and Signal Processing (TSP)

Self Cite

View full text Add to dashboard Cite

Monitoring and conservation of natural resources such as trees have become necessary as the impact of new diseases attacking the integrity of trees has created major concerns for environmentalists and communities in recent years. Within this context, tree roots are one of the plants' most important and vulnerable organs as well as one of the most challenging ones to inspect. Tree roots naturally are developed under the ground, hence difficult to be seen and access. To that effect, the non-destructive testing (NDT) methods have become one of the preferred methods of tree roots assessment and monitoring as opposed to other conventional and destructive techniques. The applications of the ground penetrating radar (GPR) have proven to be an accurate approach and methodology for the investigation and mapping of tree roots. However, a major challenge for GPR detection of tree roots architecture and pattern accurately is the soil inhomogeneity, including the presence of various natural and artificial features within the soil. This study aims to mitigate the uncertainty in root detection by proposing a deep learning method based on the analysis of GPR spectrograms (i.e., a graphic representation of a signal's frequency spectrum with respect to time). In this study, the GPR signal is first processed in both the time and frequency domains to filter the existing noise-related information and hence, to produce spectrograms. Subsequently, an image-based deep learning framework is implemented, and the effectiveness in detecting tree roots is analysed in comparison with conventional feature-based machine learning classifiers. The preliminary results of this research demonstrate the potential of the proposed approach and pave the way for the implementation of new methodologies in assessing tree root systems.

show abstract

“…Several processing techniques on tree roots detection have been proposed [22,23], these are referred to as conventional frameworks. These frameworks consider the soil's relative permittivity as a constant (same medium velocity) throughout the survey site and use the measured or estimated permittivity at a specific location to map the entire underground environment.…”

Section: Introductionmentioning

confidence: 99%

Tree Roots Reconstruction Framework for Accurate Positioning in Heterogeneous Soil

Luo

Lee

Sun

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Ground-penetrating radar (GPR) has recently found wide application in the underground imaging of tree roots. However, Ignoring the random and complex nature of the heterogeneous soil and assuming the soil's relative permittivity constant throughout the survey region may yield an inaccurate tree root positioning. Meanwhile, the incompatible relative soil permittivity results in low image quality of the roots reconstruction. Furthermore, the soil's spatial heterogeneity introduces unwanted environmental clutter in the mapping of the tree root. A data processing framework is proposed to address these issues for retrieving the tree roots in heterogeneous soil environments. The proposed framework combines four techniques to be applied consecutively: 1) A hyperbola extraction method based on a column-connection clustering algorithm is used to extract individual hyperbolae in B-scans, eliminate mutual influence in the process, and suppress noise. 2) An improved Hough transform technique is adopted to estimate the equivalent permittivity of each root's surrounding soil environment for each extracted hyperbola. 3) Individual root restoration is done by transferring each hyperbola to a spot using its corresponding soil equivalent permittivity. 4) Finally, individually restored features are combined in the final image. The images obtained via the proposed framework show a well reconstructed 2D tree roots scenario. The applicability and the effectiveness of the proposed framework have been demonstrated through numerical simulations and field measurements.

show abstract

An Enhanced Data Processing Framework for Mapping Tree Root Systems Using Ground Penetrating Radar

Cited by 21 publications

References 46 publications

Assessing the root system of urban trees by geostatistical analysis of GPR data

Assessing the root system of urban trees by geostatistical analysis of GPR data

A Deep Learning Approach for Tree Root Detection using GPR Spectrogram Imagery

Tree Roots Reconstruction Framework for Accurate Positioning in Heterogeneous Soil

Contact Info

Product

Resources

About