Processing tree point clouds using Gaussian Mixture Models

Belton, David; Moncrieff, Simon; Chapman, Jane

doi:10.5194/isprsannals-ii-5-w2-43-2013

Cited by 26 publications

(39 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Belton et al [47] successfully de-noised point clouds of evergreen trees automatically. Features are here extracted after performing a Principal Component Analysis (PCA) on neighbouring point coordinates.…”

Section: Methods In Computational Forestry Producing Qsms Of the Branmentioning

confidence: 99%

“…The method of Côté et al [42,44] was optimized for estimating the total leaf area and basal area instead of being trained on AGB predictions. The method of Belton et al [47] was validated on only one individual without reliable ground truth, while the methods of Dassot et al and Kankare et al [13,14] rely on significant manual interaction. This is to be avoided to ensure the methods are as general as possible.…”

Section: Relevance Of the Presented Work In The State Of The Artmentioning

confidence: 99%

See 1 more Smart Citation

SimpleTree —An Efficient Open Source Tool to Build Tree Models from TLS Clouds

Hackenberg

Spiecker

Calders

et al. 2015

Forests

281

260

View full text Add to dashboard Cite

An open source tool named SimpleTree, capable of modelling highly accurate cylindrical tree models from terrestrial laser scan point clouds, is presented and evaluated. All important functionalities, accessible in the software via buttons and dialogues, are described including the explanation of all necessary input parameters. The method is validated utilizing 101 point clouds of six different tree species, in the main evergreen and coniferous trees. All scanned trees have been destructively harvested to get accurate estimates of above ground biomass with which we assess the accuracy of the SimpleTree-reconstructed cylinder models. The trees were grouped into four data sets and for each one a Concordance Correlation Coefficient of at least 0. 92 (0.92, 0.97, 0.92, 0.94) and an total relative error at most ∼ 8 % (2.42%, 3.59%, -4.59%, 8.27%) was achieved in the comparison of the model results to the ground truth data. A global statistical improvement of derived cylinder radii is presented as well as an efficient optimization approach to Forests 2015, 6 4246 automatically improve user given input parameters. An additional check of the SimpleTree results is presented via comparison to the results of trees reconstructed using an alternative, published method.

show abstract

Section: Methods In Computational Forestry Producing Qsms Of the Branmentioning

confidence: 99%

Section: Relevance Of the Presented Work In The State Of The Artmentioning

confidence: 99%

SimpleTree —An Efficient Open Source Tool to Build Tree Models from TLS Clouds

Hackenberg

Spiecker

Calders

et al. 2015

Forests

281

260

View full text Add to dashboard Cite

show abstract

“…Belton et al [29] applied a volume calculation for trees under the leaf-on condition in three steps. After extracting the tree from the raw point cloud, they first applied a principal component analysis to each point's neighborhood.…”

Section: Related Workmentioning

confidence: 99%

“…The accuracy of the model must be validated by both ground truth measurements and by a quantification of the the goodness of fit of the model to the input data. This has not been performed at all or only to a lesser extent by other works [17][18][19]21,23,24,27,29,33] or has been performed in works showing improvable results [16,31]. Since the NLS-based method [8] provides a high accuracy, but a low level of robustness, we also implemented a second method that is less accurate, but more robust.…”

Section: Rationalementioning

confidence: 99%

Highly Accurate Tree Models Derived from Terrestrial Laser Scan Data: A Method Description

Hackenberg

Morhart

Sheppard

et al. 2014

Forests

158

181

View full text Add to dashboard Cite

This paper presents a method for fitting cylinders into a point cloud, derived from a terrestrial laser-scanned tree. Utilizing high scan quality data as the input, the resulting models describe the branching structure of the tree, capable of detecting branches with a diameter smaller than a centimeter. The cylinders are stored as a hierarchical tree-like data structure encapsulating parent-child neighbor relations and incorporating the tree's direction of growth. This structure enables the efficient extraction of tree components, such as the stem or a single branch. The method was validated both by applying a comparison of the resulting cylinder models with ground truth data and by an analysis between the input point clouds and the models. Tree models were accomplished representing more than 99% of the input point cloud, with an average distance from the cylinder model to the point cloud within sub-millimeter accuracy. After validation, the method was applied to build two allometric models based on 24 tree point clouds as an example of the application. Computation terminated successfully within less than 30 min. For the model predicting the total above ground volume, the coefficient of determination was 0.965, showing the high potential of terrestrial laser-scanning for forest inventories.

show abstract

“…QSMs allow for the analysis of volume distribution within a single tree (e.g., see Calders et al 2015). QSMs can also be produced from TLS point clouds obtained from trees under leaf-on conditions by applying appropriate de-noising procedures (Belton et al 2013, Hackenberg et al 2015b). However, QSMs using alternative geometrical methodology have been proposed, e.g., based on ellipses (Aiteanu & Klein 2014).…”

Section: Introductionmentioning

confidence: 99%

Terrestrial laser scanning as a tool for assessing tree growth

Sheppard¹,

Morhart²,

Hackenberg³

et al. 2017

iForest

View full text Add to dashboard Cite

(1) Terrestrial laser scanning (TLS) technology is a powerful tool for assessing tree growth based on time series analysis, as it allows a level of scrutiny not achievable using established destructive techniques. We applied TLS technology to 21 wild cherry trees grown in a research plot near Breisach (southern Germany) in order to build quantitative structure models (QSMs) for each tree. Scans were carried out over three subsequent years (2012-2014), so that three QSMs per each tree were constructed. Using the above approach, we were able to assess the annual growth of the individual wild cherry trees in terms of diameter and height, stem and branch volume, and the merchantable timber fraction. In addition, the growth of single branches of sample trees was detected and quantified. The availability of QSMs based on TLS-derived data allowed the accurate determination of crown length and width, as well as the volume reduction as the result of the tree pruning applied after the first scan (2012). The aboveground biomass (AGB) was assessed for each tree based on the QSM-derived volume and published wood density values for wild cherry, and then compared with AGB values estimated with standard allometric methods, obtaining a very high correlation (r 2 adj = 0.941). We concluded that the proposed approach is an effective non-destructive technique to accurately assess the increase of tree biomass, and discuss its future application in the forestry sector.

show abstract

Processing tree point clouds using Gaussian Mixture Models

Cited by 26 publications

References 15 publications

SimpleTree —An Efficient Open Source Tool to Build Tree Models from TLS Clouds

SimpleTree —An Efficient Open Source Tool to Build Tree Models from TLS Clouds

Highly Accurate Tree Models Derived from Terrestrial Laser Scan Data: A Method Description

Terrestrial laser scanning as a tool for assessing tree growth

Contact Info

Product

Resources

About