Automatic Segmentation of Tree Structure From Point Cloud Data

Digumarti, Sundara Tejaswi; Nieto, Juan; Cadena, César; Siegwart, Roland; Beardsley, Paul

doi:10.1109/lra.2018.2849499

Cited by 21 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The numerous approaches for plant segmentation include the combination of colour information and 3D models [ADT11, MBW*18], adapted surface feature‐based techniques [PDMK13], model‐based approaches based on cylinder representations of stems and separate segmentation tailored to leaves [GDHB17], skeleton‐based stem and leaf point recognition approaches 2019, facet region growing approaches after an initial oversegmentation [LCT*18] as well as automated, data‐driven approaches for plant structure segmentation based on geometric features and Random Forests classifiers (e.g. [DNC*18]) or geometric features and clustering 2015.…”

Section: Related Workmentioning

confidence: 99%

Temporal Upsampling of Point Cloud Sequences by Optimal Transport for Plant Growth Visualization

Golla

Kneiphof

Kuhlmann

et al. 2020

Computer Graphics Forum

View full text Add to dashboard Cite

Plant growth visualization from a series of 3D scanner measurements is a challenging task. Time intervals between successive measurements are typically too large to allow a smooth animation of the growth process. Therefore, obtaining a smooth animation of the plant growth process requires a temporal upsampling of the point cloud sequence in order to obtain approximations of the intermediate states between successive measurements. Additionally, there are suddenly arising structural changes due to the occurrence of new plant parts such as new branches or leaves. We present a novel method that addresses these challenges via semantic segmentation and the generation of a segment hierarchy per scan, the matching of the hierarchical representations of successive scans and the segment‐wise computation of optimal transport. The transport problems' solutions yield the information required for a realistic temporal upsampling, which is generated in real time. Thereby, our method does not require shape templates, good correspondences or huge databases of examples. Newly grown and decayed parts of the plant are detected as unmatched segments and are handled by identifying corresponding bifurcation points and introducing virtual segments in the previous, respectively successive time step. Our method allows the generation of realistic upsampled growth animations with moderate computational effort.

show abstract

Section: Related Workmentioning

confidence: 99%

Temporal Upsampling of Point Cloud Sequences by Optimal Transport for Plant Growth Visualization

Golla

Kneiphof

Kuhlmann

et al. 2020

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…They include four broadleaved and two coniferous tree models with different structural features of woody organs (Figure 2). After removing the foliage parts in each tree model, we converted the woody parts into point cloud data (Digumarti, Nieto et al 2018). To reduce the computation cost during the skeleton extraction, each resampled point cloud data has 250, 000 points.…”

Section: The Validation Datasetsmentioning

confidence: 99%

“…Owing to the noise and missing parts inevitably exist in the in-situ collected data, we randomly added the Gaussian noise and outliers to the point cloud converted from the simulated tree models (Digumarti, Nieto et al 2018). Moreover, we randomly removed parts of point cloud data (Mei, Zhang et al 2016).…”

Section: The Validation Datasetsmentioning

confidence: 99%

“…The skeleton extraction requirements in this study are special to the above methods in the following aspects: (1) Obtaining the structural lossless skeleton of woody organs is necessary. It is the basis for assessing canopy phenotypic 7 characteristics ; (2) The points from twigs are almost part of the skeleton (Digumarti, Nieto et al 2018), while the data from thick branches and trunks need to be iteratively thinned. Moreover, the extracted skeleton should maintain connectivity, especially at the tree forks; (3) smoothing is not suitable for skeleton extraction from branches; 4The global setting parameters are not suitable to contract the tree point cloud data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

TreeSke: A Structural-Lossless Skeleton Extraction Method for Point Cloud Data of Canopy Woody Materials

Zheng

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Skeletons extracted from point clouds of woody materials present canopy structural features (e.g., the inclination angle of branches) for simulating canopy interception and understory solar radiation distribution. However, existing methods cannot easily capture structure-lossless skeletons of woody organs from tree point-cloud data. To fulfill this goal, we proposed a distance-weighted method, named the TreeSke method, to iteratively contract the point cloud of canopy woody materials to their median-axis skeleton. After heuristically searching the local point set, we pointwise-extracted the tightened weights to obtain the coarse skeleton. Then, we thinned the skeleton of woody organs and optimized it by a noise filtering and re-centering process. Results: The proposed method was verified on six simulated tree models that have reference skeletons and two field-collected datasets at the plot level. The results show that the TreeSke-extracted skeletons were with higher location accuracy than using the other two tested methods. The mean offset distance, the RMSE of the offset distance, and the Hausdorff distance between the extracted and reference skeletons were less than 0.04 m, less than 0.06 m, and less than 0.11 m, respectively. Conclusions: The extracted skeletons by the TreeSke method could nearly integrally depict the structural features of woody materials. The proposed method showed robust for noisy points and outliers, while missing data would reduce the skeleton integrity and cause deformation errors. From the extracted skeletons, users can extract the inclination-angle features of canopy woody materials, which are useful for simulating most eco-hydrological processes.

show abstract

“…In the case of this paper, we are focused on separating parts of a forest into terrain, vegetation, coarse woody debris, and stem categories from a point cloud. There have been many different approaches to the segmentation of forest point clouds [20][21][22][23][24][25][26][27][28][29][30][31][32][33][34] so far. Some approaches use heuristics [20,22,25,28,29] or morphological operations [27], while others use supervised [23,26,[30][31][32][33] or unsupervised [21,34] machine learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Sensor Agnostic Semantic Segmentation of Structurally Diverse and Complex Forest Point Clouds Using Deep Learning

et al. 2021

View full text Add to dashboard Cite

Forest inventories play an important role in enabling informed decisions to be made for the management and conservation of forest resources; however, the process of collecting inventory information is laborious. Despite advancements in mapping technologies allowing forests to be digitized in finer granularity than ever before, it is still common for forest measurements to be collected using simple tools such as calipers, measuring tapes, and hypsometers. Dense understory vegetation and complex forest structures can present substantial challenges to point cloud processing tools, often leading to erroneous measurements, and making them of less utility in complex forests. To address this challenge, this research demonstrates an effective deep learning approach for semantically segmenting high-resolution forest point clouds from multiple different sensing systems in diverse forest conditions. Seven diverse point cloud datasets were manually segmented to train and evaluate this model, resulting in per-class segmentation accuracies of Terrain: 95.92%, Vegetation: 96.02%, Coarse Woody Debris: 54.98%, and Stem: 96.09%. By exploiting the segmented point cloud, we also present a method of extracting a Digital Terrain Model (DTM) from such segmented point clouds. This approach was applied to a set of six point clouds that were made publicly available as part of a benchmarking study to evaluate the DTM performance. The mean DTM error was 0.04 m relative to the reference with 99.9% completeness. These approaches serve as useful steps toward a fully automated and reliable measurement extraction tool, agnostic to the sensing technology used or the complexity of the forest, provided that the point cloud has sufficient coverage and accuracy. Ongoing work will see these models incorporated into a fully automated forest measurement tool for the extraction of structural metrics for applications in forestry, conservation, and research.

show abstract

Automatic Segmentation of Tree Structure From Point Cloud Data

Cited by 21 publications

References 30 publications

Temporal Upsampling of Point Cloud Sequences by Optimal Transport for Plant Growth Visualization

Temporal Upsampling of Point Cloud Sequences by Optimal Transport for Plant Growth Visualization

TreeSke: A Structural-Lossless Skeleton Extraction Method for Point Cloud Data of Canopy Woody Materials

Sensor Agnostic Semantic Segmentation of Structurally Diverse and Complex Forest Point Clouds Using Deep Learning

Contact Info

Product

Resources

About