Structure Aware SLAM using Quadrics and Planes

TL;DR

This paper introduces a SLAM method that integrates quadrics and planes to create semantically rich maps, improving localization accuracy by combining geometric and semantic scene understanding.

Contribution

It presents a novel approach to incorporate object detections as quadrics and planar structures into SLAM, enhancing map semantics and localization.

Findings

Improved camera localization accuracy.

Generated maps with semantic information.

Effective integration of objects and planes in SLAM.

Abstract

Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art object detection methods provide rich information about entities present in the scene from a single image. This work marries the two and proposes a method for representing generic objects as quadrics which allows object detections to be seamlessly integrated in a SLAM framework. For scene coverage, additional dominant planar structures are modeled as infinite planes. Experiments show that the proposed points-planes-quadrics representation can easily incorporate Manhattan and object affordance constraints, greatly improving camera localization and leading to semantically meaningful maps. The performance of our SLAM system is demonstrated in https://youtu.be/dR-rB9keF8M .