Automated 3D tree-ring detection and measurement from X-ray computed tomography

Martinez-Garcia, Jorge; Stelzner, Ingrid; Stelzner, Joerg; Gwerder, Damian; Schuetz, Philipp

doi:10.1016/j.dendro.2021.125877

Cited by 13 publications

(13 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is a powerful tool that can greatly cut down on the processing time to generate ring-width measurements while maintaining the benefits of image based measurements (Griffin et al, 2021; Maxwell & Larsson, 2021). Though trained only on Picea abies , the consistent structure of conifer wood means it should be easily deployable across other conifer species (Fabijańska et al, 2017; Martinez-Garcia et al, 2021; Resente et al, 2021). We consider this CNN to be a valuable tool for efficiently generating data that can reduce analysis time considerably, especially in large datasets or for potential reanalysis of old unmeasured datasets.Though our CNN performed well with 95% of its detections correct and correctly identifying 99% of true rings, these errors still prohibit an unsupervised use of the generated data and requires an experienced dendrochronologist to oversee crossdating (Holmes et al, 1986).…”

Section: Discussionmentioning

confidence: 99%

“…Increased use of imaged increment cores (Griffin et al, 2021;Larsson, 2003;Rademacher et al, 2021) provides an opportunity to automate detection and subsequent measurement of annual ring widths. Previous attempts at identifying ring boundaries have had variable and sometimes impressive AUTOMATED TREE-RING DETECTION AND MEASUREMENT success (Conner et al, 1998;Fabijańska et al, 2017;Fabijańska & Danek, 2018;Martinez-Garcia et al, 2021;Resente et al, 2021) but the only deployable method is limited to three-dimensional images (Martinez-Garcia et al, 2021). Here we present a new supervised Mask R-CNN and processing pipeline available as a Docker container.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automation of tree-ring detection and measurements using deep learning

Poláček

Arizpe

Hüther

et al. 2022

Preprint

View full text Add to dashboard Cite

We present an implementable neural network-based automated detection and measurement of tree-ring boundaries from coniferous species.We trained our Mask R-CNN extensively on over 8,000 manually annotated rings. We assessed the performance of the trained model from our core processing pipeline on real world data.The CNN performed well, recognizing over 99% of ring boundaries (precision) and a recall value of 95% when tested on real world data. Additionally, we have implemented automatic measurements based on minimum distance between rings. With minimal editing for missed ring detections, these measurements were a 99% match with human measurements of the same samples.Our CNN is readily deployable through a Docker container and requires only basic command line skills. Application outputs include editable annotations which facilitate the efficient generation of ring-width measurements from tree-ring samples, an important source of environmental data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automation of tree-ring detection and measurements using deep learning

Poláček

Arizpe

Hüther

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Известны попытки применения современных физических методов для пространственного картирования свойств дерева, в частности, методами рассеяния синхротронного излучения [7], 3D рентгеновской компьютерной [46][47][48][49] и магниторезонансной томографии [50]. Однако эти методы сложны в реализации, трудоемки и требуют дорогостоящего или уникального оборудования, поэтому они применяются редко.…”

Section: Introductionunclassified

Локальные Механические Свойства И Кольцевая Структура Древесины, Исследованные Методом Сканирующего Наноиндентирования

Головин¹,

Тюрин²,

Гусев³

et al. 2022

Журнал Технической Физики

View full text Add to dashboard Cite

The paper presents the results of scanning of mechanical properties of coniferous (common pine Pinus sylvestris) and deciduous (small-leaved lime Tilia cordata and common oak Quercus robur) trees wood using nanoindentation on crosscut face. Manifold increase in microhardness H and Young’s modulus E has been observed between early and late wood in every annual growth ring. Significant differences in intraring radial dependencies of H and E have been found among studied species. For all studied species the average values of E and H of early wood in each annual ring are found to be independent from ring width, while such dependence for late wood is weak at most. The ring widths measured by nanoindentation coincide with the ones measured by standard optical method within 2-3%. The developed technique and obtained results can be useful 1) to amend the understanding the origins of macromechanical properties of various wood species and their dependence upon microstructural characteristics and growth conditions, 2) to optimize the technologies of growing, reinforcement and subsequent usage of the wood, 3) to develop new independent high resolution methods in dendrochronology.

show abstract

“…Several attempts at applying modern physical methods (specifically, synchrotron scattering [7], 3D X-ray computer tomography [46][47][48][49], and magnetic resonance tomography [50]) to spatial mapping of the properties of wood have already been made. However, since these methods are complex, laborious, and require expensive or unique equipment, they are used only rarely.…”

Section: Introductionmentioning

confidence: 99%

Scanning naation as an instrument of studying local mechanical properties distribution in wood and a new technique for dendrochronology

Tyurin

Gusev

et al. 2022

Technical Physics

View full text Add to dashboard Cite

The paper presents the results of scanning of mechanical properties of coniferous (common pine Pinus sylvestris) and deciduous (small-leaved lime Tilia cordata and common oak Quercus robur) trees wood using naation on crosscut face. Manifold increase in microhardness H and Young's modulus E has been observed between early and late wood in every annual growth ring. Significant differences in intraring radial dependencies of H and E have been found among studied species. For all studied species the average values of E and H of early wood in each annual ring are found to be independent from ring width, while such dependence for late wood is weak at most. The ring widths measured by naation coincide with the ones measured by standard optical method within 2-3%. The developed technique and obtained results can be useful 1) to amend the understanding the origins of macromechanical properties of various wood species and their dependence upon microstructural characteristics and growth conditions, 2) to optimize the technologies of growing, reinforcement and subsequent usage of the wood, 3) to develop new independent high resolution methods in dendrochronology. Keywords: naation, nano-/microhardness and Young's modulus scanning, tree annual growth rings, dendrochronology.

show abstract

Automated 3D tree-ring detection and measurement from X-ray computed tomography

Cited by 13 publications

References 45 publications

Automation of tree-ring detection and measurements using deep learning

Automation of tree-ring detection and measurements using deep learning

Локальные Механические Свойства И Кольцевая Структура Древесины, Исследованные Методом Сканирующего Наноиндентирования

Scanning naation as an instrument of studying local mechanical properties distribution in wood and a new technique for dendrochronology

Contact Info

Product

Resources

About