Optical Load Detection: Load Weighing for Construction Machines using Stereo Vision and Convolutional Neural Networks
dc.contributor.author | Stråhle, Daniel | |
dc.contributor.author | Wingård Olsson, Kevin | |
dc.contributor.department | Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper | sv |
dc.contributor.department | Chalmers University of Technology / Department of Mechanics and Maritime Sciences | en |
dc.contributor.examiner | Forsberg, Peter | |
dc.contributor.supervisor | Andreasson, Mathias | |
dc.date.accessioned | 2023-11-17T12:26:21Z | |
dc.date.available | 2023-11-17T12:26:21Z | |
dc.date.issued | 2022 | |
dc.date.submitted | 2023 | |
dc.description.abstract | Accurate excavation monitoring is important for the handling of materials within the construction industry. Modern construction machines provide built-in systems for weighing handled goods. In this thesis, an alternative optical weighing system is developed and implemented for an excavator and a wheel loader. The optical system detects and provides the volume and weight of the handled material through fill-factor estimation. The methodology is based on depth data and images captured by a stereo camera, mounted on the machines. By using a region-based convolutional neural network (CNN), localization of material and fill-factor estimation are managed jointly. Material classification is also proved to be possible using gathered images and a simple CNN. By combining the fill-factor and information about the material, weight is obtained. Evaluations reveal that the system measures fill-factor to mean absolute percentage errors (MAPE), relative to the maximum capacity of the excavator and the wheel loader, of 3.3 % and 3.0 % respectively. | |
dc.identifier.coursecode | MMSX30 | |
dc.identifier.uri | http://hdl.handle.net/20.500.12380/307383 | |
dc.language.iso | eng | |
dc.relation.ispartofseries | 2022:21 | |
dc.setspec.uppsok | Technology | |
dc.subject | Excavation Monitoring | |
dc.subject | CNN | |
dc.subject | Faster R-CNN | |
dc.subject | RPN | |
dc.subject | Range Sensor | |
dc.subject | Stereo Camera | |
dc.subject | Computer Vision | |
dc.subject | Material Classification | |
dc.title | Optical Load Detection: Load Weighing for Construction Machines using Stereo Vision and Convolutional Neural Networks | |
dc.type.degree | Examensarbete för masterexamen | sv |
dc.type.degree | Master's Thesis | en |
dc.type.uppsok | H | |
local.programme | Systems, control and mechatronics (MPSYS), MSc |
Ladda ner
Original bundle
1 - 1 av 1
Hämtar...
- Namn:
- 2022-21 Daniel Stråhle & Kevin Wingård Olsson.pdf
- Storlek:
- 20.85 MB
- Format:
- Adobe Portable Document Format
- Beskrivning:
License bundle
1 - 1 av 1
Hämtar...
- Namn:
- license.txt
- Storlek:
- 2.35 KB
- Format:
- Item-specific license agreed upon to submission
- Beskrivning: