DUDMap: 3D RGB-D mapping for dense, unstructured, and dynamic environment. (4th June 2021)
- Record Type:
- Journal Article
- Title:
- DUDMap: 3D RGB-D mapping for dense, unstructured, and dynamic environment. (4th June 2021)
- Main Title:
- DUDMap: 3D RGB-D mapping for dense, unstructured, and dynamic environment
- Authors:
- Hastürk, Özgür
Erkmen, Aydan M - Abstract:
- Simultaneous localization and mapping (SLAM) problem has been extensively studied by researchers in the field of robotics, however, conventional approaches in mapping assume a static environment. The static assumption is valid only in a small region, and it limits the application of visual SLAM in dynamic environments. The recently proposed state-of-the-art SLAM solutions for dynamic environments use different semantic segmentation methods such as mask R-CNN and SegNet; however, these frameworks are based on a sparse mapping framework (ORBSLAM). In addition, segmentation process increases the computational power, which makes these SLAM algorithms unsuitable for real-time mapping. Therefore, there is no effective dense RGB-D SLAM method for real-world unstructured and dynamic environments. In this study, we propose a novel real-time dense SLAM method for dynamic environments, where 3D reconstruction error is manipulated for identification of static and dynamic classes having generalized Gaussian distribution. Our proposed approach requires neither explicit object tracking nor object classifier, which makes it robust to any type of moving object and suitable for real-time mapping. Our method eliminates the repeated views and uses consistent data that enhance the performance of volumetric fusion. For completeness, we compare our proposed method using different types of high dynamic dataset, which are publicly available, to demonstrate the versatility and robustness of ourSimultaneous localization and mapping (SLAM) problem has been extensively studied by researchers in the field of robotics, however, conventional approaches in mapping assume a static environment. The static assumption is valid only in a small region, and it limits the application of visual SLAM in dynamic environments. The recently proposed state-of-the-art SLAM solutions for dynamic environments use different semantic segmentation methods such as mask R-CNN and SegNet; however, these frameworks are based on a sparse mapping framework (ORBSLAM). In addition, segmentation process increases the computational power, which makes these SLAM algorithms unsuitable for real-time mapping. Therefore, there is no effective dense RGB-D SLAM method for real-world unstructured and dynamic environments. In this study, we propose a novel real-time dense SLAM method for dynamic environments, where 3D reconstruction error is manipulated for identification of static and dynamic classes having generalized Gaussian distribution. Our proposed approach requires neither explicit object tracking nor object classifier, which makes it robust to any type of moving object and suitable for real-time mapping. Our method eliminates the repeated views and uses consistent data that enhance the performance of volumetric fusion. For completeness, we compare our proposed method using different types of high dynamic dataset, which are publicly available, to demonstrate the versatility and robustness of our approach. Experiments show that its tracking performance is better than other dense and dynamic SLAM approaches. … (more)
- Is Part Of:
- International journal of advanced robotic systems. Volume 18:Number 3(2021)
- Journal:
- International journal of advanced robotic systems
- Issue:
- Volume 18:Number 3(2021)
- Issue Display:
- Volume 18, Issue 3 (2021)
- Year:
- 2021
- Volume:
- 18
- Issue:
- 3
- Issue Sort Value:
- 2021-0018-0003-0000
- Page Start:
- Page End:
- Publication Date:
- 2021-06-04
- Subjects:
- Dynamic mapping -- visual SLAM -- localization -- 3D reconstruction
Robotics -- Periodicals
Robotics
Periodicals
629.892 - Journal URLs:
- http://arx.sagepub.com/ ↗
http://search.epnet.com/direct.asp?db=bch&jid=13CR&scope=site ↗
http://www.intechweb.org/journal.php?id=3 ↗
http://www.uk.sagepub.com/home.nav ↗ - DOI:
- 10.1177/17298814211016178 ↗
- Languages:
- English
- ISSNs:
- 1729-8806
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 15990.xml