Study of the Effect of Exploiting 3D Semantic Segmentation in LiDAR Odometry
This paper presents a study of how the performance of LiDAR odometry is affected by the preprocessing of the point cloud through the use of 3D semantic segmentation. The study analyzed the estimated trajectories when the semantic information is exploited to filter the original raw data. Different fi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/16/5657 |
| _version_ | 1797558012817178624 |
|---|---|
| author | Francisco Miguel Moreno Carlos Guindel José María Armingol Fernando García |
| author_facet | Francisco Miguel Moreno Carlos Guindel José María Armingol Fernando García |
| author_sort | Francisco Miguel Moreno |
| collection | DOAJ |
| description | This paper presents a study of how the performance of LiDAR odometry is affected by the preprocessing of the point cloud through the use of 3D semantic segmentation. The study analyzed the estimated trajectories when the semantic information is exploited to filter the original raw data. Different filtering configurations were tested: raw (original point cloud), dynamic (dynamic obstacles are removed from the point cloud), dynamic vehicles (vehicles are removed), far (distant points are removed), ground (the points belonging to the ground are removed) and structure (only structures and objects are kept in the point cloud). The experiments were performed using the KITTI and SemanticKITTI datasets, which feature different scenarios that allowed identifying the implications and relevance of each element of the environment in LiDAR odometry algorithms. The conclusions obtained from this work are of special relevance for improving the efficiency of LiDAR odometry algorithms in all kinds of scenarios. |
| first_indexed | 2024-03-10T17:25:22Z |
| format | Article |
| id | doaj.art-74c3d3b1f6484d7eb21afe1b93726934 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T17:25:22Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-74c3d3b1f6484d7eb21afe1b937269342023-11-20T10:12:18ZengMDPI AGApplied Sciences2076-34172020-08-011016565710.3390/app10165657Study of the Effect of Exploiting 3D Semantic Segmentation in LiDAR OdometryFrancisco Miguel Moreno0Carlos Guindel1José María Armingol2Fernando García3Intelligent Systems Lab (LSI) Research Group, Universidad Carlos III de Madrid (UC3M), 28911 Leganés, Madrid, SpainIntelligent Systems Lab (LSI) Research Group, Universidad Carlos III de Madrid (UC3M), 28911 Leganés, Madrid, SpainIntelligent Systems Lab (LSI) Research Group, Universidad Carlos III de Madrid (UC3M), 28911 Leganés, Madrid, SpainIntelligent Systems Lab (LSI) Research Group, Universidad Carlos III de Madrid (UC3M), 28911 Leganés, Madrid, SpainThis paper presents a study of how the performance of LiDAR odometry is affected by the preprocessing of the point cloud through the use of 3D semantic segmentation. The study analyzed the estimated trajectories when the semantic information is exploited to filter the original raw data. Different filtering configurations were tested: raw (original point cloud), dynamic (dynamic obstacles are removed from the point cloud), dynamic vehicles (vehicles are removed), far (distant points are removed), ground (the points belonging to the ground are removed) and structure (only structures and objects are kept in the point cloud). The experiments were performed using the KITTI and SemanticKITTI datasets, which feature different scenarios that allowed identifying the implications and relevance of each element of the environment in LiDAR odometry algorithms. The conclusions obtained from this work are of special relevance for improving the efficiency of LiDAR odometry algorithms in all kinds of scenarios.https://www.mdpi.com/2076-3417/10/16/5657localizationintelligent vehiclesLiDAR |
| spellingShingle | Francisco Miguel Moreno Carlos Guindel José María Armingol Fernando García Study of the Effect of Exploiting 3D Semantic Segmentation in LiDAR Odometry Applied Sciences localization intelligent vehicles LiDAR |
| title | Study of the Effect of Exploiting 3D Semantic Segmentation in LiDAR Odometry |
| title_full | Study of the Effect of Exploiting 3D Semantic Segmentation in LiDAR Odometry |
| title_fullStr | Study of the Effect of Exploiting 3D Semantic Segmentation in LiDAR Odometry |
| title_full_unstemmed | Study of the Effect of Exploiting 3D Semantic Segmentation in LiDAR Odometry |
| title_short | Study of the Effect of Exploiting 3D Semantic Segmentation in LiDAR Odometry |
| title_sort | study of the effect of exploiting 3d semantic segmentation in lidar odometry |
| topic | localization intelligent vehicles LiDAR |
| url | https://www.mdpi.com/2076-3417/10/16/5657 |
| work_keys_str_mv | AT franciscomiguelmoreno studyoftheeffectofexploiting3dsemanticsegmentationinlidarodometry AT carlosguindel studyoftheeffectofexploiting3dsemanticsegmentationinlidarodometry AT josemariaarmingol studyoftheeffectofexploiting3dsemanticsegmentationinlidarodometry AT fernandogarcia studyoftheeffectofexploiting3dsemanticsegmentationinlidarodometry |