A Study on the Effect of Multispectral LiDAR Data on Automated Semantic Segmentation of 3D-Point Clouds
Mobile mapping is an application field of ever-increasing relevance. Data of the surrounding environment is typically captured using combinations of LiDAR systems and cameras. The large amounts of measurement data are then processed and interpreted, which is often done automated using neural network...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/24/6349 |
| _version_ | 1797455423746342912 |
|---|---|
| author | Valentin Vierhub-Lorenz Maximilian Kellner Oliver Zipfel Alexander Reiterer |
| author_facet | Valentin Vierhub-Lorenz Maximilian Kellner Oliver Zipfel Alexander Reiterer |
| author_sort | Valentin Vierhub-Lorenz |
| collection | DOAJ |
| description | Mobile mapping is an application field of ever-increasing relevance. Data of the surrounding environment is typically captured using combinations of LiDAR systems and cameras. The large amounts of measurement data are then processed and interpreted, which is often done automated using neural networks. For the evaluation the data of the LiDAR and the cameras needs to be fused, which requires a reliable calibration of the sensors. Segmentation solemnly on the LiDAR data drastically decreases the amount of data and makes the complex data fusion process obsolete but on the other hand often performs poorly due to the lack of information about the surface remission properties. The work at hand evaluates the effect of a novel multispectral LiDAR system on automated semantic segmentation of 3D-point clouds to overcome this downside. Besides the presentation of the multispectral LiDAR system and its implementation on a mobile mapping vehicle, the point cloud processing and the training of the CNN are described in detail. The results show a significant increase in the mIoU when using the additional information from the multispectral channel compared to just 3D and intensity information. The impact on the IoU was found to be strongly dependent on the class. |
| first_indexed | 2024-03-09T15:53:16Z |
| format | Article |
| id | doaj.art-18213c82d956457a979aa5d62253597b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T15:53:16Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-18213c82d956457a979aa5d62253597b2023-11-24T17:48:15ZengMDPI AGRemote Sensing2072-42922022-12-011424634910.3390/rs14246349A Study on the Effect of Multispectral LiDAR Data on Automated Semantic Segmentation of 3D-Point CloudsValentin Vierhub-Lorenz0Maximilian Kellner1Oliver Zipfel2Alexander Reiterer3Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, GermanyFraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, GermanyMobile mapping is an application field of ever-increasing relevance. Data of the surrounding environment is typically captured using combinations of LiDAR systems and cameras. The large amounts of measurement data are then processed and interpreted, which is often done automated using neural networks. For the evaluation the data of the LiDAR and the cameras needs to be fused, which requires a reliable calibration of the sensors. Segmentation solemnly on the LiDAR data drastically decreases the amount of data and makes the complex data fusion process obsolete but on the other hand often performs poorly due to the lack of information about the surface remission properties. The work at hand evaluates the effect of a novel multispectral LiDAR system on automated semantic segmentation of 3D-point clouds to overcome this downside. Besides the presentation of the multispectral LiDAR system and its implementation on a mobile mapping vehicle, the point cloud processing and the training of the CNN are described in detail. The results show a significant increase in the mIoU when using the additional information from the multispectral channel compared to just 3D and intensity information. The impact on the IoU was found to be strongly dependent on the class.https://www.mdpi.com/2072-4292/14/24/6349mobile mappingmultispectral LiDARconvolutional neural network (CNN)deep learningsemantic segmentation |
| spellingShingle | Valentin Vierhub-Lorenz Maximilian Kellner Oliver Zipfel Alexander Reiterer A Study on the Effect of Multispectral LiDAR Data on Automated Semantic Segmentation of 3D-Point Clouds Remote Sensing mobile mapping multispectral LiDAR convolutional neural network (CNN) deep learning semantic segmentation |
| title | A Study on the Effect of Multispectral LiDAR Data on Automated Semantic Segmentation of 3D-Point Clouds |
| title_full | A Study on the Effect of Multispectral LiDAR Data on Automated Semantic Segmentation of 3D-Point Clouds |
| title_fullStr | A Study on the Effect of Multispectral LiDAR Data on Automated Semantic Segmentation of 3D-Point Clouds |
| title_full_unstemmed | A Study on the Effect of Multispectral LiDAR Data on Automated Semantic Segmentation of 3D-Point Clouds |
| title_short | A Study on the Effect of Multispectral LiDAR Data on Automated Semantic Segmentation of 3D-Point Clouds |
| title_sort | study on the effect of multispectral lidar data on automated semantic segmentation of 3d point clouds |
| topic | mobile mapping multispectral LiDAR convolutional neural network (CNN) deep learning semantic segmentation |
| url | https://www.mdpi.com/2072-4292/14/24/6349 |
| work_keys_str_mv | AT valentinvierhublorenz astudyontheeffectofmultispectrallidardataonautomatedsemanticsegmentationof3dpointclouds AT maximiliankellner astudyontheeffectofmultispectrallidardataonautomatedsemanticsegmentationof3dpointclouds AT oliverzipfel astudyontheeffectofmultispectrallidardataonautomatedsemanticsegmentationof3dpointclouds AT alexanderreiterer astudyontheeffectofmultispectrallidardataonautomatedsemanticsegmentationof3dpointclouds AT valentinvierhublorenz studyontheeffectofmultispectrallidardataonautomatedsemanticsegmentationof3dpointclouds AT maximiliankellner studyontheeffectofmultispectrallidardataonautomatedsemanticsegmentationof3dpointclouds AT oliverzipfel studyontheeffectofmultispectrallidardataonautomatedsemanticsegmentationof3dpointclouds AT alexanderreiterer studyontheeffectofmultispectrallidardataonautomatedsemanticsegmentationof3dpointclouds |