Predicting urban tree cover from incomplete point labels and limited background information
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Predicting urban tree cover from incomplete point labels and limited background information. / Zhang, Hui; Kariryaa, Ankit; Guthula, Venkanna Babu; Igel, Christian; Oehmcke, Stefan.
Urban-AI 2023 - Proceedings of the 1st ACM SIGSPATIAL International Workshop on Advances in Urban-AI. ed. / Olufemi A. Omitaomu; Ali Mostafavi; Yan Liu. Association for Computing Machinery, Inc., 2023. p. 52-60.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Predicting urban tree cover from incomplete point labels and limited background information
AU - Zhang, Hui
AU - Kariryaa, Ankit
AU - Guthula, Venkanna Babu
AU - Igel, Christian
AU - Oehmcke, Stefan
N1 - Publisher Copyright: © 2023 ACM.
PY - 2023
Y1 - 2023
N2 - Trees inside cities are important for the urban microclimate, contributing positively to the physical and mental health of the urban dwellers. Despite their importance, often only limited information about city trees is available. Therefore in this paper, we propose a method for mapping urban trees in high-resolution aerial imagery using limited datasets and deep learning. Deep learning has become best-practice for this task, however, existing approaches rely on large and accurately labelled training datasets, which can be difficult and expensive to obtain. However, often noisy and incomplete data may be available that can be combined and utilized to solve more difficult tasks than those datasets were intended for.This paper studies how to combine accurate point labels of urban trees along streets with crowd-sourced annotations from an open geographic database to delineate city trees in remote sensing images, a task which is challenging even for humans. To that end, we perform semantic segmentation of very high resolution aerial imagery using a fully convolutional neural network.The main challenge is that our segmentation maps are sparsely annotated and incomplete. Small areas around the point labels of the street trees coming from official and crowd-sourced data are marked as foreground class. Crowd-sourced annotations of streets, buildings, etc. define the background class. Since the tree data is incomplete, we introduce a masking to avoid class confusion.Our experiments in Hamburg, Germany, showed that the system is able to produce tree cover maps, not limited to trees along streets, without providing tree delineations. We evaluated the method on manually labelled trees and show that performance drastically deteriorates if the open geographic database is not used.
AB - Trees inside cities are important for the urban microclimate, contributing positively to the physical and mental health of the urban dwellers. Despite their importance, often only limited information about city trees is available. Therefore in this paper, we propose a method for mapping urban trees in high-resolution aerial imagery using limited datasets and deep learning. Deep learning has become best-practice for this task, however, existing approaches rely on large and accurately labelled training datasets, which can be difficult and expensive to obtain. However, often noisy and incomplete data may be available that can be combined and utilized to solve more difficult tasks than those datasets were intended for.This paper studies how to combine accurate point labels of urban trees along streets with crowd-sourced annotations from an open geographic database to delineate city trees in remote sensing images, a task which is challenging even for humans. To that end, we perform semantic segmentation of very high resolution aerial imagery using a fully convolutional neural network.The main challenge is that our segmentation maps are sparsely annotated and incomplete. Small areas around the point labels of the street trees coming from official and crowd-sourced data are marked as foreground class. Crowd-sourced annotations of streets, buildings, etc. define the background class. Since the tree data is incomplete, we introduce a masking to avoid class confusion.Our experiments in Hamburg, Germany, showed that the system is able to produce tree cover maps, not limited to trees along streets, without providing tree delineations. We evaluated the method on manually labelled trees and show that performance drastically deteriorates if the open geographic database is not used.
KW - CNN
KW - crowd-sourced datasets
KW - deep learning
KW - point labels
KW - sparse labels
KW - tree cover
KW - tree mapping
KW - urban environment
U2 - 10.1145/3615900.3628791
DO - 10.1145/3615900.3628791
M3 - Article in proceedings
AN - SCOPUS:85180406987
SP - 52
EP - 60
BT - Urban-AI 2023 - Proceedings of the 1st ACM SIGSPATIAL International Workshop on Advances in Urban-AI
A2 - Omitaomu, Olufemi A.
A2 - Mostafavi, Ali
A2 - Liu, Yan
PB - Association for Computing Machinery, Inc.
T2 - 1st ACM SIGSPATIAL International Workshop on Advances in Urban-AI, Urban-AI 2023
Y2 - 13 November 2023
ER -
ID: 378185580