QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM
Abstract
In this paper, we use 2D object detections from multiple views to simultaneously estimate a 3D quadric surface for each object and localize the camera position. We derive a SLAM formulation that uses dual quadrics as 3D landmark representations, exploiting their ability to compactly represent the size, position and orientation of an object, and show how 2D object detections can directly constrain the quadric parameters via a novel geometric error formulation. We develop a sensor model for object detectors that addresses the challenge of partially visible objects, and demonstrate how to jointly estimate the camera pose and constrained dual quadric parameters in factor graph based SLAM with a general perspective camera.
Cite
@article{arxiv.1804.04011,
title = {QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in Object-oriented SLAM},
author = {Lachlan Nicholson and Michael Milford and Niko Sünderhauf},
journal= {arXiv preprint arXiv:1804.04011},
year = {2018}
}
Comments
Accepted at IEEE Robotics and Automation Letters (RA-L). arXiv admin note: text overlap with arXiv:1708.00965