We propose a new method for segmentation-free joint estimation of orthogonal planes, their intersection lines, relationship graph and corners lying at the intersection of three orthogonal planes. Such unified scene exploration under orthogonality allows for multitudes of applications such as semantic plane detection or local and global scan alignment, which in turn can aid robot localization or grasping tasks. Our two-stage pipeline involves a rough yet joint estimation of orthogonal planes followed by a subsequent joint refinement of plane parameters respecting their orthogonality relations. We form a graph of these primitives, paving the way to the extraction of further reliable features: lines and corners. Our experiments demonstrate the validity of our approach in numerous scenarios from wall detection to 6D tracking, both on synthetic and real data.
- Pub Date:
- January 2020
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Robotics
- Accepted to IEEE Robotics and Automation Letters 2020 | Video: https://youtu.be/nHWJrA6RcB0 | Code: https://github.com/c-sommer/orthogonal-planes