An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation

The recent surge in diverse 3D datasets spanning various scales and applications marks a significant advancement in the field. However, the comprehensive process of data acquisition, refinement, and annotation at a large scale poses a formidable challenge, particularly for individual researchers and...

Full description

Saved in:
Bibliographic Details
Main Authors: Meida Chen, Kangle Han, Zifan Yu, Andrew Feng, Yu Hou, Suya You, Lucio Soibelman
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4240
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152574549360640
author Meida Chen
Kangle Han
Zifan Yu
Andrew Feng
Yu Hou
Suya You
Lucio Soibelman
author_facet Meida Chen
Kangle Han
Zifan Yu
Andrew Feng
Yu Hou
Suya You
Lucio Soibelman
author_sort Meida Chen
collection DOAJ
description The recent surge in diverse 3D datasets spanning various scales and applications marks a significant advancement in the field. However, the comprehensive process of data acquisition, refinement, and annotation at a large scale poses a formidable challenge, particularly for individual researchers and small teams. To this end, we present a novel synthetic 3D point cloud generation framework that can produce detailed outdoor aerial photogrammetric 3D datasets with accurate ground truth annotations without the labor-intensive and time-consuming data collection/annotation processes. Our pipeline procedurally generates synthetic environments, mirroring real-world data collection and 3D reconstruction processes. A key feature of our framework is its ability to replicate consistent quality, noise patterns, and diversity similar to real-world datasets. This is achieved by adopting UAV flight patterns that resemble those used in real-world data collection processes (e.g., the cross-hatch flight pattern) across various synthetic terrains that are procedurally generated, thereby ensuring data consistency akin to real-world scenarios. Moreover, the generated datasets are enriched with precise semantic and instance annotations, eliminating the need for manual labeling. Our approach has led to the development and release of the Semantic Terrain Points Labeling—Synthetic 3D (STPLS3D) benchmark, an extensive outdoor 3D dataset encompassing over 16 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>km</mi><mn>2</mn></msup></semantics></math></inline-formula>, featuring up to 19 semantic labels. We also collected, reconstructed, and annotated four real-world datasets for validation purposes. Extensive experiments on these datasets demonstrate our synthetic datasets’ effectiveness, superior quality, and their value as a benchmark dataset for further point cloud research.
format Article
id doaj-art-6d431cb8572e4f4e824f0d7c5f0fb111
institution Kabale University
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-6d431cb8572e4f4e824f0d7c5f0fb1112024-11-26T18:20:08ZengMDPI AGRemote Sensing2072-42922024-11-011622424010.3390/rs16224240An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style TranslationMeida Chen0Kangle Han1Zifan Yu2Andrew Feng3Yu Hou4Suya You5Lucio Soibelman6Institute for Creative Technologies, University of Southern California, Los Angeles, CA 90094, USAAstani Department of Civil and Environmental Engineering, USC Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90007, USADepartment of Computer Science, Arizona State University, Tempe, AZ 85281, USAInstitute for Creative Technologies, University of Southern California, Los Angeles, CA 90094, USAThe Department of Construction Management, Western New England University, Springfield, MA 01119, USADEVCOM Army Research Laboratory, Los Angeles, CA 90089, USAAstani Department of Civil and Environmental Engineering, USC Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90007, USAThe recent surge in diverse 3D datasets spanning various scales and applications marks a significant advancement in the field. However, the comprehensive process of data acquisition, refinement, and annotation at a large scale poses a formidable challenge, particularly for individual researchers and small teams. To this end, we present a novel synthetic 3D point cloud generation framework that can produce detailed outdoor aerial photogrammetric 3D datasets with accurate ground truth annotations without the labor-intensive and time-consuming data collection/annotation processes. Our pipeline procedurally generates synthetic environments, mirroring real-world data collection and 3D reconstruction processes. A key feature of our framework is its ability to replicate consistent quality, noise patterns, and diversity similar to real-world datasets. This is achieved by adopting UAV flight patterns that resemble those used in real-world data collection processes (e.g., the cross-hatch flight pattern) across various synthetic terrains that are procedurally generated, thereby ensuring data consistency akin to real-world scenarios. Moreover, the generated datasets are enriched with precise semantic and instance annotations, eliminating the need for manual labeling. Our approach has led to the development and release of the Semantic Terrain Points Labeling—Synthetic 3D (STPLS3D) benchmark, an extensive outdoor 3D dataset encompassing over 16 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>km</mi><mn>2</mn></msup></semantics></math></inline-formula>, featuring up to 19 semantic labels. We also collected, reconstructed, and annotated four real-world datasets for validation purposes. Extensive experiments on these datasets demonstrate our synthetic datasets’ effectiveness, superior quality, and their value as a benchmark dataset for further point cloud research.https://www.mdpi.com/2072-4292/16/22/4240synthetic point cloud datasetaerial photogrammetrysemantic and instance segmentation
spellingShingle Meida Chen
Kangle Han
Zifan Yu
Andrew Feng
Yu Hou
Suya You
Lucio Soibelman
An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation
Remote Sensing
synthetic point cloud dataset
aerial photogrammetry
semantic and instance segmentation
title An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation
title_full An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation
title_fullStr An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation
title_full_unstemmed An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation
title_short An Aerial Photogrammetry Benchmark Dataset for Point Cloud Segmentation and Style Translation
title_sort aerial photogrammetry benchmark dataset for point cloud segmentation and style translation
topic synthetic point cloud dataset
aerial photogrammetry
semantic and instance segmentation
url https://www.mdpi.com/2072-4292/16/22/4240
work_keys_str_mv AT meidachen anaerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT kanglehan anaerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT zifanyu anaerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT andrewfeng anaerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT yuhou anaerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT suyayou anaerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT luciosoibelman anaerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT meidachen aerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT kanglehan aerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT zifanyu aerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT andrewfeng aerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT yuhou aerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT suyayou aerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation
AT luciosoibelman aerialphotogrammetrybenchmarkdatasetforpointcloudsegmentationandstyletranslation