Robotic Mapping and Localization with Real-Time Dense Stereo on Reconfigurable Hardware
A reconfigurable architecture for dense stereo is presented as an observation framework for a real-time implementation of the simultaneous localization and mapping problem in robotics. The reconfigurable sensor detects point features from stereo image pairs to use at the measurement update stage of...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2010-01-01
|
| Series: | International Journal of Reconfigurable Computing |
| Online Access: | http://dx.doi.org/10.1155/2010/480208 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850212960094388224 |
|---|---|
| author | John Kalomiros John Lygouras |
| author_facet | John Kalomiros John Lygouras |
| author_sort | John Kalomiros |
| collection | DOAJ |
| description | A reconfigurable architecture for dense stereo is presented as an observation framework for a real-time implementation of the simultaneous localization and mapping problem in robotics. The reconfigurable sensor detects point features from stereo image pairs to use at the measurement update stage of the procedure. The main hardware blocks are a dense depth stereo accelerator, a left and right image corner detector, and a stage performing left-right consistency check. For the stereo-processor stage, we have implemented and tested a global-matching component based on a maximum-likelihood dynamic programming technique. The system includes a Nios II processor for data control and a USB 2.0 interface for host communication. Remote control is used to guide a vehicle equipped with a stereo head in an indoor environment. The FastSLAM Bayesian algorithm is applied in order to track and update observations and the robot path in real time. The system is assessed using real scene depth detection and public reference data sets. The paper also reports resource usage and a comparison of mapping and localization results with ground truth. |
| format | Article |
| id | doaj-art-8b9e706539b947ac8b167b99826bc737 |
| institution | OA Journals |
| issn | 1687-7195 1687-7209 |
| language | English |
| publishDate | 2010-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Reconfigurable Computing |
| spelling | doaj-art-8b9e706539b947ac8b167b99826bc7372025-08-20T02:09:13ZengWileyInternational Journal of Reconfigurable Computing1687-71951687-72092010-01-01201010.1155/2010/480208480208Robotic Mapping and Localization with Real-Time Dense Stereo on Reconfigurable HardwareJohn Kalomiros0John Lygouras1Department of Informatics and Communications, Technological Educational Institute of Serres, Terma Magnisias, 62124 Serres, GreeceSection of Electronics and Information Systems Technology, Department of Electrical Engineering & Computer Engineering, School of Engineering, Democritus University of Thrace, 67100 Xanthi, GreeceA reconfigurable architecture for dense stereo is presented as an observation framework for a real-time implementation of the simultaneous localization and mapping problem in robotics. The reconfigurable sensor detects point features from stereo image pairs to use at the measurement update stage of the procedure. The main hardware blocks are a dense depth stereo accelerator, a left and right image corner detector, and a stage performing left-right consistency check. For the stereo-processor stage, we have implemented and tested a global-matching component based on a maximum-likelihood dynamic programming technique. The system includes a Nios II processor for data control and a USB 2.0 interface for host communication. Remote control is used to guide a vehicle equipped with a stereo head in an indoor environment. The FastSLAM Bayesian algorithm is applied in order to track and update observations and the robot path in real time. The system is assessed using real scene depth detection and public reference data sets. The paper also reports resource usage and a comparison of mapping and localization results with ground truth.http://dx.doi.org/10.1155/2010/480208 |
| spellingShingle | John Kalomiros John Lygouras Robotic Mapping and Localization with Real-Time Dense Stereo on Reconfigurable Hardware International Journal of Reconfigurable Computing |
| title | Robotic Mapping and Localization with Real-Time Dense Stereo on Reconfigurable Hardware |
| title_full | Robotic Mapping and Localization with Real-Time Dense Stereo on Reconfigurable Hardware |
| title_fullStr | Robotic Mapping and Localization with Real-Time Dense Stereo on Reconfigurable Hardware |
| title_full_unstemmed | Robotic Mapping and Localization with Real-Time Dense Stereo on Reconfigurable Hardware |
| title_short | Robotic Mapping and Localization with Real-Time Dense Stereo on Reconfigurable Hardware |
| title_sort | robotic mapping and localization with real time dense stereo on reconfigurable hardware |
| url | http://dx.doi.org/10.1155/2010/480208 |
| work_keys_str_mv | AT johnkalomiros roboticmappingandlocalizationwithrealtimedensestereoonreconfigurablehardware AT johnlygouras roboticmappingandlocalizationwithrealtimedensestereoonreconfigurablehardware |