Mono-hydra: Real-time 3D scene graph construction from monocular camera input with IMU

TL;DR

Mono-Hydra is a real-time system that constructs 3D scene graphs from monocular camera input combined with IMU data, enabling efficient indoor navigation and environment understanding for robots.

Contribution

It introduces a novel real-time 3D scene graph construction method using monocular vision and IMU, with deep learning and visual-inertial odometry, adaptable to indoor and outdoor scenarios.

Findings

Achieves sub-20 cm accuracy at 15 fps in real-time

Uses deep learning for depth and semantic extraction

Provides publicly available code for reproducibility

Abstract

The ability of robots to autonomously navigate through 3D environments depends on their comprehension of spatial concepts, ranging from low-level geometry to high-level semantics, such as objects, places, and buildings. To enable such comprehension, 3D scene graphs have emerged as a robust tool for representing the environment as a layered graph of concepts and their relationships. However, building these representations using monocular vision systems in real-time remains a difficult task that has not been explored in depth. This paper puts forth a real-time spatial perception system Mono-Hydra, combining a monocular camera and an IMU sensor setup, focusing on indoor scenarios. However, the proposed approach is adaptable to outdoor applications, offering flexibility in its potential uses. The system employs a suite of deep learning algorithms to derive depth and semantics. It uses a robocentric visual-inertial odometry (VIO) algorithm based on square-root information, thereby ensuring consistent visual odometry with an IMU and a monocular camera. This system achieves sub-20 cm error in real-time processing at 15 fps, enabling real-time 3D scene graph construction using a laptop GPU (NVIDIA 3080). This enhances decision-making efficiency and effectiveness in simple camera setups, augmenting robotic system agility. We make Mono-Hydra publicly available at: https://github.com/UAV-Centre-ITC/Mono_Hydra