Exploring ALS and DIM data for semantic segmentation using CNNs

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

View graph of relations

Details

Original languageEnglish
Title of host publicationProceedings of Mid-term Symposium “Innovative Sensing – From Sensors to Methods and Applications”
Pages347-354
Number of pages8
Publication statusPublished - 2018
Event2018 ISPRS Technical Commission I Midterm Symposium on Innovative Sensing - From Sensors to Methods and Applications - Karlsruhe, Germany
Duration: 10 Oct 201812 Oct 2018

Publication series

NameInternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
PublisherInternational Society for Photogrammetry and Remote Sensing
VolumeXLII-1
ISSN (Print)1682-1750

Abstract

Over the past years, the algorithms for dense image matching (DIM) to obtain point clouds from aerial images improved significantly. Consequently, DIM point clouds are now a good alternative to the established Airborne Laser Scanning (ALS) point clouds for remote sensing applications. In order to derive high-level applications such as digital terrain models or city models, each point within a point cloud must be assigned a class label. Usually, ALS and DIM are labelled with different classifiers due to their varying characteristics. In this work, we explore both point cloud types in a fully convolutional encoder-decoder network, which learns to classify ALS as well as DIM point clouds. As input, we project the point clouds onto a 2D image raster plane and calculate the minimal, average and maximal height values for each raster cell. The network then differentiates between the classes ground, non-ground, building and no data. We test our network in six training setups using only one point cloud type, both point clouds as well as several transfer-learning approaches. We quantitatively and qualitatively compare all results and discuss the advantages and disadvantages of all setups. The best network achieves an overall accuracy of 96% in an ALS and 83% in a DIM test set.

Keywords

    Airborne Laser Scanning, CNN, Dense Image Matching, Encoder-decoder Network, Point cloud, Semantic segmentation

ASJC Scopus subject areas

Cite this

Exploring ALS and DIM data for semantic segmentation using CNNs. / Politz, Florian; Sester, Monika.
Proceedings of Mid-term Symposium “Innovative Sensing – From Sensors to Methods and Applications”. 2018. p. 347-354 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives; Vol. XLII-1).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Politz, F & Sester, M 2018, Exploring ALS and DIM data for semantic segmentation using CNNs. in Proceedings of Mid-term Symposium “Innovative Sensing – From Sensors to Methods and Applications”. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, vol. XLII-1, pp. 347-354, 2018 ISPRS Technical Commission I Midterm Symposium on Innovative Sensing - From Sensors to Methods and Applications, Karlsruhe, Germany, 10 Oct 2018. https://doi.org/10.5194/isprs-archives-XLII-1-347-2018, https://doi.org/10.15488/4067
Politz, F., & Sester, M. (2018). Exploring ALS and DIM data for semantic segmentation using CNNs. In Proceedings of Mid-term Symposium “Innovative Sensing – From Sensors to Methods and Applications” (pp. 347-354). (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives; Vol. XLII-1). https://doi.org/10.5194/isprs-archives-XLII-1-347-2018, https://doi.org/10.15488/4067
Politz F, Sester M. Exploring ALS and DIM data for semantic segmentation using CNNs. In Proceedings of Mid-term Symposium “Innovative Sensing – From Sensors to Methods and Applications”. 2018. p. 347-354. (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives). Epub 2018 Sept 26. doi: 10.5194/isprs-archives-XLII-1-347-2018, 10.15488/4067
Politz, Florian ; Sester, Monika. / Exploring ALS and DIM data for semantic segmentation using CNNs. Proceedings of Mid-term Symposium “Innovative Sensing – From Sensors to Methods and Applications”. 2018. pp. 347-354 (International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives).
Download
@inproceedings{64d0d99767884d638efc02cdc653203b,
title = "Exploring ALS and DIM data for semantic segmentation using CNNs",
abstract = "Over the past years, the algorithms for dense image matching (DIM) to obtain point clouds from aerial images improved significantly. Consequently, DIM point clouds are now a good alternative to the established Airborne Laser Scanning (ALS) point clouds for remote sensing applications. In order to derive high-level applications such as digital terrain models or city models, each point within a point cloud must be assigned a class label. Usually, ALS and DIM are labelled with different classifiers due to their varying characteristics. In this work, we explore both point cloud types in a fully convolutional encoder-decoder network, which learns to classify ALS as well as DIM point clouds. As input, we project the point clouds onto a 2D image raster plane and calculate the minimal, average and maximal height values for each raster cell. The network then differentiates between the classes ground, non-ground, building and no data. We test our network in six training setups using only one point cloud type, both point clouds as well as several transfer-learning approaches. We quantitatively and qualitatively compare all results and discuss the advantages and disadvantages of all setups. The best network achieves an overall accuracy of 96% in an ALS and 83% in a DIM test set.",
keywords = "Airborne Laser Scanning, CNN, Dense Image Matching, Encoder-decoder Network, Point cloud, Semantic segmentation",
author = "Florian Politz and Monika Sester",
year = "2018",
doi = "10.5194/isprs-archives-XLII-1-347-2018",
language = "English",
series = "International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives",
publisher = "International Society for Photogrammetry and Remote Sensing",
pages = "347--354",
booktitle = "Proceedings of Mid-term Symposium “Innovative Sensing – From Sensors to Methods and Applications”",
note = "2018 ISPRS Technical Commission I Midterm Symposium on Innovative Sensing - From Sensors to Methods and Applications ; Conference date: 10-10-2018 Through 12-10-2018",

}

Download

TY - GEN

T1 - Exploring ALS and DIM data for semantic segmentation using CNNs

AU - Politz, Florian

AU - Sester, Monika

PY - 2018

Y1 - 2018

N2 - Over the past years, the algorithms for dense image matching (DIM) to obtain point clouds from aerial images improved significantly. Consequently, DIM point clouds are now a good alternative to the established Airborne Laser Scanning (ALS) point clouds for remote sensing applications. In order to derive high-level applications such as digital terrain models or city models, each point within a point cloud must be assigned a class label. Usually, ALS and DIM are labelled with different classifiers due to their varying characteristics. In this work, we explore both point cloud types in a fully convolutional encoder-decoder network, which learns to classify ALS as well as DIM point clouds. As input, we project the point clouds onto a 2D image raster plane and calculate the minimal, average and maximal height values for each raster cell. The network then differentiates between the classes ground, non-ground, building and no data. We test our network in six training setups using only one point cloud type, both point clouds as well as several transfer-learning approaches. We quantitatively and qualitatively compare all results and discuss the advantages and disadvantages of all setups. The best network achieves an overall accuracy of 96% in an ALS and 83% in a DIM test set.

AB - Over the past years, the algorithms for dense image matching (DIM) to obtain point clouds from aerial images improved significantly. Consequently, DIM point clouds are now a good alternative to the established Airborne Laser Scanning (ALS) point clouds for remote sensing applications. In order to derive high-level applications such as digital terrain models or city models, each point within a point cloud must be assigned a class label. Usually, ALS and DIM are labelled with different classifiers due to their varying characteristics. In this work, we explore both point cloud types in a fully convolutional encoder-decoder network, which learns to classify ALS as well as DIM point clouds. As input, we project the point clouds onto a 2D image raster plane and calculate the minimal, average and maximal height values for each raster cell. The network then differentiates between the classes ground, non-ground, building and no data. We test our network in six training setups using only one point cloud type, both point clouds as well as several transfer-learning approaches. We quantitatively and qualitatively compare all results and discuss the advantages and disadvantages of all setups. The best network achieves an overall accuracy of 96% in an ALS and 83% in a DIM test set.

KW - Airborne Laser Scanning

KW - CNN

KW - Dense Image Matching

KW - Encoder-decoder Network

KW - Point cloud

KW - Semantic segmentation

UR - http://www.scopus.com/inward/record.url?scp=85056153771&partnerID=8YFLogxK

U2 - 10.5194/isprs-archives-XLII-1-347-2018

DO - 10.5194/isprs-archives-XLII-1-347-2018

M3 - Conference contribution

AN - SCOPUS:85056153771

T3 - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives

SP - 347

EP - 354

BT - Proceedings of Mid-term Symposium “Innovative Sensing – From Sensors to Methods and Applications”

T2 - 2018 ISPRS Technical Commission I Midterm Symposium on Innovative Sensing - From Sensors to Methods and Applications

Y2 - 10 October 2018 through 12 October 2018

ER -

By the same author(s)