Distributed Camera Subsystem for Obstacle Detection
This work focuses on improving a camera system for sensing a workspace in which dynamic obstacles need to be detected. The currently available state-of-the-art solution (MoveIt!) processes data in a centralized manner from cameras that have to be registered before the system starts. Our solution ena...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/12/4588 |
| _version_ | 1797482315324063744 |
|---|---|
| author | Petr Oščádal Tomáš Spurný Tomáš Kot Stefan Grushko Jiří Suder Dominik Heczko Petr Novák Zdenko Bobovský |
| author_facet | Petr Oščádal Tomáš Spurný Tomáš Kot Stefan Grushko Jiří Suder Dominik Heczko Petr Novák Zdenko Bobovský |
| author_sort | Petr Oščádal |
| collection | DOAJ |
| description | This work focuses on improving a camera system for sensing a workspace in which dynamic obstacles need to be detected. The currently available state-of-the-art solution (MoveIt!) processes data in a centralized manner from cameras that have to be registered before the system starts. Our solution enables distributed data processing and dynamic change in the number of sensors at runtime. The distributed camera data processing is implemented using a dedicated control unit on which the filtering is performed by comparing the real and expected depth images. Measurements of the processing speed of all sensor data into a global voxel map were compared between the centralized system (MoveIt!) and the new distributed system as part of a performance benchmark. The distributed system is more flexible in terms of sensitivity to a number of cameras, better framerate stability and the possibility of changing the camera number on the go. The effects of voxel grid size and camera resolution were also compared during the benchmark, where the distributed system showed better results. Finally, the overhead of data transmission in the network was discussed where the distributed system is considerably more efficient. The decentralized system proves to be faster by 38.7% with one camera and 71.5% with four cameras. |
| first_indexed | 2024-03-09T22:31:30Z |
| format | Article |
| id | doaj.art-066e00dccb294c4dac4ef1ff06608ab6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T22:31:30Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-066e00dccb294c4dac4ef1ff06608ab62023-11-23T18:55:56ZengMDPI AGSensors1424-82202022-06-012212458810.3390/s22124588Distributed Camera Subsystem for Obstacle DetectionPetr Oščádal0Tomáš Spurný1Tomáš Kot2Stefan Grushko3Jiří Suder4Dominik Heczko5Petr Novák6Zdenko Bobovský7Department of Robotics, Faculty of Mechanical Engineering, VSB-TU Ostrava, 70800 Ostrava, Czech RepublicDepartment of Robotics, Faculty of Mechanical Engineering, VSB-TU Ostrava, 70800 Ostrava, Czech RepublicDepartment of Robotics, Faculty of Mechanical Engineering, VSB-TU Ostrava, 70800 Ostrava, Czech RepublicDepartment of Robotics, Faculty of Mechanical Engineering, VSB-TU Ostrava, 70800 Ostrava, Czech RepublicDepartment of Robotics, Faculty of Mechanical Engineering, VSB-TU Ostrava, 70800 Ostrava, Czech RepublicDepartment of Robotics, Faculty of Mechanical Engineering, VSB-TU Ostrava, 70800 Ostrava, Czech RepublicDepartment of Robotics, Faculty of Mechanical Engineering, VSB-TU Ostrava, 70800 Ostrava, Czech RepublicDepartment of Robotics, Faculty of Mechanical Engineering, VSB-TU Ostrava, 70800 Ostrava, Czech RepublicThis work focuses on improving a camera system for sensing a workspace in which dynamic obstacles need to be detected. The currently available state-of-the-art solution (MoveIt!) processes data in a centralized manner from cameras that have to be registered before the system starts. Our solution enables distributed data processing and dynamic change in the number of sensors at runtime. The distributed camera data processing is implemented using a dedicated control unit on which the filtering is performed by comparing the real and expected depth images. Measurements of the processing speed of all sensor data into a global voxel map were compared between the centralized system (MoveIt!) and the new distributed system as part of a performance benchmark. The distributed system is more flexible in terms of sensitivity to a number of cameras, better framerate stability and the possibility of changing the camera number on the go. The effects of voxel grid size and camera resolution were also compared during the benchmark, where the distributed system showed better results. Finally, the overhead of data transmission in the network was discussed where the distributed system is considerably more efficient. The decentralized system proves to be faster by 38.7% with one camera and 71.5% with four cameras.https://www.mdpi.com/1424-8220/22/12/4588human–robot interactioncollaborationworkspace monitoringdistributed processingsensors networkobstacles detection |
| spellingShingle | Petr Oščádal Tomáš Spurný Tomáš Kot Stefan Grushko Jiří Suder Dominik Heczko Petr Novák Zdenko Bobovský Distributed Camera Subsystem for Obstacle Detection Sensors human–robot interaction collaboration workspace monitoring distributed processing sensors network obstacles detection |
| title | Distributed Camera Subsystem for Obstacle Detection |
| title_full | Distributed Camera Subsystem for Obstacle Detection |
| title_fullStr | Distributed Camera Subsystem for Obstacle Detection |
| title_full_unstemmed | Distributed Camera Subsystem for Obstacle Detection |
| title_short | Distributed Camera Subsystem for Obstacle Detection |
| title_sort | distributed camera subsystem for obstacle detection |
| topic | human–robot interaction collaboration workspace monitoring distributed processing sensors network obstacles detection |
| url | https://www.mdpi.com/1424-8220/22/12/4588 |
| work_keys_str_mv | AT petroscadal distributedcamerasubsystemforobstacledetection AT tomasspurny distributedcamerasubsystemforobstacledetection AT tomaskot distributedcamerasubsystemforobstacledetection AT stefangrushko distributedcamerasubsystemforobstacledetection AT jirisuder distributedcamerasubsystemforobstacledetection AT dominikheczko distributedcamerasubsystemforobstacledetection AT petrnovak distributedcamerasubsystemforobstacledetection AT zdenkobobovsky distributedcamerasubsystemforobstacledetection |