BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data
Common Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an e...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/6/2144 |
| _version_ | 1797540787534168064 |
|---|---|
| author | Stefan Reitmann Lorenzo Neumann Bernhard Jung |
| author_facet | Stefan Reitmann Lorenzo Neumann Bernhard Jung |
| author_sort | Stefan Reitmann |
| collection | DOAJ |
| description | Common Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an even more time-consuming task. To simplify the training data generation process for a wide range of domains, we have developed the <i>BLAINDER</i> add-on package for the open-source 3D modeling software Blender, which enables a largely automated generation of semantically annotated point-cloud data in virtual 3D environments. In this paper, we focus on classical depth-sensing techniques Light Detection and Ranging (LiDAR) and Sound Navigation and Ranging (Sonar). Within the <i>BLAINDER</i> add-on, different depth sensors can be loaded from presets, customized sensors can be implemented and different environmental conditions (e.g., influence of rain, dust) can be simulated. The semantically labeled data can be exported to various 2D and 3D formats and are thus optimized for different ML applications and visualizations. In addition, semantically labeled images can be exported using the rendering functionalities of Blender. |
| first_indexed | 2024-03-10T13:05:52Z |
| format | Article |
| id | doaj.art-7273a84969c54648ab01bb903558aaf4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T13:05:52Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7273a84969c54648ab01bb903558aaf42023-11-21T11:06:17ZengMDPI AGSensors1424-82202021-03-01216214410.3390/s21062144BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing DataStefan Reitmann0Lorenzo Neumann1Bernhard Jung2Virtual Reality and Multimedia Group, Institute of Computer Science, Freiberg University of Mining and Technology, 09599 Freiberg, GermanyOperating Systems and Communication Technologies Group, Institute of Computer Science, Freiberg University of Mining and Technology, 09599 Freiberg, GermanyVirtual Reality and Multimedia Group, Institute of Computer Science, Freiberg University of Mining and Technology, 09599 Freiberg, GermanyCommon Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an even more time-consuming task. To simplify the training data generation process for a wide range of domains, we have developed the <i>BLAINDER</i> add-on package for the open-source 3D modeling software Blender, which enables a largely automated generation of semantically annotated point-cloud data in virtual 3D environments. In this paper, we focus on classical depth-sensing techniques Light Detection and Ranging (LiDAR) and Sound Navigation and Ranging (Sonar). Within the <i>BLAINDER</i> add-on, different depth sensors can be loaded from presets, customized sensors can be implemented and different environmental conditions (e.g., influence of rain, dust) can be simulated. The semantically labeled data can be exported to various 2D and 3D formats and are thus optimized for different ML applications and visualizations. In addition, semantically labeled images can be exported using the rendering functionalities of Blender.https://www.mdpi.com/1424-8220/21/6/2144machine learningdepth-sensingLiDARSonarvirtual sensorslabeling |
| spellingShingle | Stefan Reitmann Lorenzo Neumann Bernhard Jung BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data Sensors machine learning depth-sensing LiDAR Sonar virtual sensors labeling |
| title | BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data |
| title_full | BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data |
| title_fullStr | BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data |
| title_full_unstemmed | BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data |
| title_short | BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data |
| title_sort | blainder a blender ai add on for generation of semantically labeled depth sensing data |
| topic | machine learning depth-sensing LiDAR Sonar virtual sensors labeling |
| url | https://www.mdpi.com/1424-8220/21/6/2144 |
| work_keys_str_mv | AT stefanreitmann blainderablenderaiaddonforgenerationofsemanticallylabeleddepthsensingdata AT lorenzoneumann blainderablenderaiaddonforgenerationofsemanticallylabeleddepthsensingdata AT bernhardjung blainderablenderaiaddonforgenerationofsemanticallylabeleddepthsensingdata |