An RGB-D video-based wire detection tool to aid robotic arms during machine alignment measurement
- 1 October 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Industrial equipment may require precise alignment of components in order to function properly. In this work, we consider the machine alignment of a beamline in a research facility where an autonomous measurement system is used to execute these machine alignment procedures. The system consists of two robotic arms equipped with laser sensors placed at their ends which with the help of fiducial markers, are used by a camera system to calculate the position of the machine with respect to a stretched wire installed on top of the machines. In this work we propose a wire detection tool that assists the measurement process by detecting the line automatically through RGB-D images. Although the system was implemented for the specific application of beam line component alignment in the LHC tunnel, the same principle can be used in various other applications requiring detection of fine lines at a close distance.Keywords
This publication has 13 references indexed in Scilit:
- Vision-based change detection for inspection of tunnel linersAutomation in Construction, 2018
- Analytical review on object segmentation and recognition2016
- An Edge-Less Approach to Horizon Line Detection2015
- Vision-based approach towards lane line detection and vehicle localizationMachine Vision and Applications, 2015
- Moving object detection: Review of recent research trends2015
- Straight line detection from remote sensing images by rule-based feature fusionGeo-spatial Information Science, 2012
- Forward-Backward Error: Automatic Detection of Tracking Failures2010
- Visual tracking with online Multiple Instance Learning2009
- Rapid object detection using a boosted cascade of simple features2005
- Support-vector networksMachine Learning, 1995