A Comparison of Segmentation Methods for Semantic OctoMap Generation

Semantic mapping plays a critical role in enabling autonomous vehicles to understand and navigate complex environments. Instead of computationally demanding 3D segmentation of point clouds, we propose efficient segmentation on RGB images and projection of the corresponding LIDAR measurements on the...

Full description

Saved in:
Bibliographic Details
Main Authors: Marcin Czajka, Maciej Krupka, Daria Kubacka, Michał Remigiusz Janiszewski, Dominik Belter
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/13/7285
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850118188798312448
author Marcin Czajka
Maciej Krupka
Daria Kubacka
Michał Remigiusz Janiszewski
Dominik Belter
author_facet Marcin Czajka
Maciej Krupka
Daria Kubacka
Michał Remigiusz Janiszewski
Dominik Belter
author_sort Marcin Czajka
collection DOAJ
description Semantic mapping plays a critical role in enabling autonomous vehicles to understand and navigate complex environments. Instead of computationally demanding 3D segmentation of point clouds, we propose efficient segmentation on RGB images and projection of the corresponding LIDAR measurements on the semantic OctoMap. This study presents a comparative evaluation of different semantic segmentation methods and examines the impact of input image resolution on the accuracy of 3D semantic environment reconstruction, inference time, and computational resource usage. The experiments were conducted using an ROS 2-based pipeline that combines RGB images and LiDAR point clouds. Semantic segmentation is performed using ONNX-exported deep neural networks, with class predictions projected onto corresponding 3D LiDAR data using calibrated extrinsic. The resulting semantically annotated point clouds are fused into a probabilistic 3D representation using an OctoMap, where each voxel stores both occupancy and semantic class information. Multiple encoder–decoder architectures with various backbone configurations are evaluated in terms of segmentation quality, latency, memory footprint, and GPU utilization. Furthermore, a comparison between high and low image resolutions is conducted to assess trade-offs between model accuracy and real-time applicability.
format Article
id doaj-art-d110b75809824d85be6f0a1d3aa17c2e
institution OA Journals
issn 2076-3417
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-d110b75809824d85be6f0a1d3aa17c2e2025-08-20T02:35:56ZengMDPI AGApplied Sciences2076-34172025-06-011513728510.3390/app15137285A Comparison of Segmentation Methods for Semantic OctoMap GenerationMarcin Czajka0Maciej Krupka1Daria Kubacka2Michał Remigiusz Janiszewski3Dominik Belter4Institute of Robotics and Machine Intelligence, Poznan University of Technology, pl. Marii Sklodowskiej-Curie 5, 60-965 Poznan, PolandInstitute of Robotics and Machine Intelligence, Poznan University of Technology, pl. Marii Sklodowskiej-Curie 5, 60-965 Poznan, PolandInstitute of Robotics and Machine Intelligence, Poznan University of Technology, pl. Marii Sklodowskiej-Curie 5, 60-965 Poznan, PolandInstitute of Robotics and Machine Intelligence, Poznan University of Technology, pl. Marii Sklodowskiej-Curie 5, 60-965 Poznan, PolandInstitute of Robotics and Machine Intelligence, Poznan University of Technology, pl. Marii Sklodowskiej-Curie 5, 60-965 Poznan, PolandSemantic mapping plays a critical role in enabling autonomous vehicles to understand and navigate complex environments. Instead of computationally demanding 3D segmentation of point clouds, we propose efficient segmentation on RGB images and projection of the corresponding LIDAR measurements on the semantic OctoMap. This study presents a comparative evaluation of different semantic segmentation methods and examines the impact of input image resolution on the accuracy of 3D semantic environment reconstruction, inference time, and computational resource usage. The experiments were conducted using an ROS 2-based pipeline that combines RGB images and LiDAR point clouds. Semantic segmentation is performed using ONNX-exported deep neural networks, with class predictions projected onto corresponding 3D LiDAR data using calibrated extrinsic. The resulting semantically annotated point clouds are fused into a probabilistic 3D representation using an OctoMap, where each voxel stores both occupancy and semantic class information. Multiple encoder–decoder architectures with various backbone configurations are evaluated in terms of segmentation quality, latency, memory footprint, and GPU utilization. Furthermore, a comparison between high and low image resolutions is conducted to assess trade-offs between model accuracy and real-time applicability.https://www.mdpi.com/2076-3417/15/13/7285semantic mappingsemantic segmentationautonomous vehicles
spellingShingle Marcin Czajka
Maciej Krupka
Daria Kubacka
Michał Remigiusz Janiszewski
Dominik Belter
A Comparison of Segmentation Methods for Semantic OctoMap Generation
Applied Sciences
semantic mapping
semantic segmentation
autonomous vehicles
title A Comparison of Segmentation Methods for Semantic OctoMap Generation
title_full A Comparison of Segmentation Methods for Semantic OctoMap Generation
title_fullStr A Comparison of Segmentation Methods for Semantic OctoMap Generation
title_full_unstemmed A Comparison of Segmentation Methods for Semantic OctoMap Generation
title_short A Comparison of Segmentation Methods for Semantic OctoMap Generation
title_sort comparison of segmentation methods for semantic octomap generation
topic semantic mapping
semantic segmentation
autonomous vehicles
url https://www.mdpi.com/2076-3417/15/13/7285
work_keys_str_mv AT marcinczajka acomparisonofsegmentationmethodsforsemanticoctomapgeneration
AT maciejkrupka acomparisonofsegmentationmethodsforsemanticoctomapgeneration
AT dariakubacka acomparisonofsegmentationmethodsforsemanticoctomapgeneration
AT michałremigiuszjaniszewski acomparisonofsegmentationmethodsforsemanticoctomapgeneration
AT dominikbelter acomparisonofsegmentationmethodsforsemanticoctomapgeneration
AT marcinczajka comparisonofsegmentationmethodsforsemanticoctomapgeneration
AT maciejkrupka comparisonofsegmentationmethodsforsemanticoctomapgeneration
AT dariakubacka comparisonofsegmentationmethodsforsemanticoctomapgeneration
AT michałremigiuszjaniszewski comparisonofsegmentationmethodsforsemanticoctomapgeneration
AT dominikbelter comparisonofsegmentationmethodsforsemanticoctomapgeneration