Change Detection of Urban Trees in MLS Point Clouds Using Occupancy Grids

Hirt, Philipp-Roman; Xu, Yangsheng; Hoegner, L.; Stilla, Uwe

doi:10.1007/s41064-021-00179-4

Cited by 8 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3) Aligning the same trees with different geometries in the two years has been a nonstandard manual process so far, which can cause inconsistency in change detection and identification of parent cylinders. A possible alternative to detect these changes is comparing the occupancy grids ( Hirt et al., 2021 ).…”

Section: Discussionmentioning

confidence: 99%

Predicting resprouting of Platanus × hispanica following branch pruning by means of machine learning

Shu,

Yazdi,

Rötzer

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionResprouting is a crucial survival strategy following the loss of branches, being it by natural events or artificially by pruning. The resprouting prediction on a physiological basis is a highly complex approach. However, trained gardeners try to predict a tree’s resprouting after pruning purely based on their empirical knowledge. In this study, we explore how far such predictions can also be made by machine learning.MethodsTable-topped annually pruned Platanus × hispanica trees at a nursery were LiDAR-scanned for two consecutive years. Topological structures for these trees were abstracted by cylinder fitting. Then, new shoots and trimmed branches were labelled on corresponding cylinders. Binary and multiclass classification models were tested for predicting the location and number of new sprouts.ResultsThe accuracy for predicting whether having or not new shoots on each cylinder reaches 90.8% with the LGBMClassifier, the balanced accuracy is 80.3%. The accuracy for predicting the exact numbers of new shoots with the GaussianNB model is 82.1%, but its balanced accuracy is reduced to 42.9%.DiscussionThe results were validated with a separate dataset, proving the feasibility of resprouting prediction after pruning using this approach. Different tree species, tree forms, and other variables should be addressed in further research.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting resprouting of Platanus × hispanica following branch pruning by means of machine learning

Shu,

Yazdi,

Rötzer

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…3) Aligning the same trees with different geometries in the two years is a nonstandard manual process so far, which can cause inconsistence in change detection and identification of parent cylinders. A possible alternative to detect these changes is comparing the occupancy grids (Hirt et al, 2021).…”

Section: Discussionmentioning

confidence: 99%

Predicting resprouting ofPlatanus×hispanicafollowing branch pruning by means of machine learning

Shu,

Yazdi,

Rötzer

et al. 2023

Preprint

View full text Add to dashboard Cite

Resprouting is a crucial survival strategy following the loss of branches, being it by natural events or artificially by pruning. The prediction of resprouting patterns on a physiological basis is a highly complex approach. However, trained gardeners try to predict a tree's resprouting after pruning purely based on their empirical knowledge and a visual check of the tree's geometry. In this study, we explore in how far such predictions can also be made by algorithms, especially using machine learning. Table-topped annually pruned Platanus × hispanica trees at a nursery were documented with terrestrial LiDAR scanners in two consecutive years. Topological structures for these trees were abstracted from point clouds by cylinder fitting. Then, new shoots and trimmed branches were labelled on corresponding cylinders. Binary and multiclass classification models were tested for predicting the location and number of new sprouts. The accuracy for predicting whether having or not new shoots on each cylinder reaches 90.8% with the LGBMClassifier, the balanced accuracy is 80.3%. The accuracy for predicting the exact numbers of new shoots with GaussianNB model is 82.1% but its balanced accuracy is reduced to 42.9%. The results were validated with a separate evaluation dataset. It proves a feasibility in predicting resprouting patterns after pruning using this approach. Different tree species, tree forms, and other variables should be addressed in further research.

show abstract

“…Other works used region growing [53][54][55][56], clustering [54,57,58], or graph-based segmentation [59,60]. In [61], starting with an already filtered point cloud, lower tree points were outlined into individual trunks by graph-based segmentation. Then, the rest of the tree points were clustering to each closest trunk using a weighted distance combining spatial spacing and local point densities.…”

Section: Mls and Other Data Sourcesmentioning

confidence: 99%

Individual Tree Detection in Urban ALS Point Clouds with 3D Convolutional Networks

2022

View full text Add to dashboard Cite

Since trees are a vital part of urban green infrastructure, automatic mapping of individual urban trees is becoming increasingly important for city management and planning. Although deep-learning-based object detection networks are the state-of-the-art in computer vision, their adaptation to individual tree detection in urban areas has scarcely been studied. Some existing works have employed 2D object detection networks for this purpose. However, these have used three-dimensional information only in the form of projected feature maps. In contrast, we exploited the full 3D potential of airborne laser scanning (ALS) point clouds by using a 3D neural network for individual tree detection. Specifically, a sparse convolutional network was used for 3D feature extraction, feeding both semantic segmentation and circular object detection outputs, which were combined for further increased accuracy. We demonstrate the capability of our approach on an urban topographic ALS point cloud with 10,864 hand-labeled ground truth trees. Our method achieved an average precision of 83% regarding the common 0.5 intersection over union criterion. 85% percent of the stems were found correctly with a precision of 88%, while tree area was covered by the individual tree detections with an F1 accuracy of 92%. Thereby, we outperformed traditional delineation baselines and recent detection networks.

show abstract

Change Detection of Urban Trees in MLS Point Clouds Using Occupancy Grids

Cited by 8 publications

References 41 publications

Predicting resprouting of Platanus × hispanica following branch pruning by means of machine learning

Predicting resprouting of Platanus × hispanica following branch pruning by means of machine learning

Predicting resprouting ofPlatanus×hispanicafollowing branch pruning by means of machine learning

Individual Tree Detection in Urban ALS Point Clouds with 3D Convolutional Networks

Contact Info

Product

Resources

About