Simultaneous Localization and 3D-Semi Dense Mapping for Micro Drones Using Monocular Camera and Inertial Sensors

2025-11-18

AI Summary

To address key challenges in monocular visual-inertial SLAM for micro aerial vehicles—including insufficient geometric information in sparse mapping, high computational cost of dense approaches, and scale ambiguity—this paper proposes a lightweight semi-dense visual-inertial SLAM system. Methodologically, it integrates sparse keypoint-based pose estimation with edge-guided dense geometric reconstruction, introduces an edge-aware geometric consistency optimization framework, and achieves loop-closure-free scale recovery by jointly leveraging deep learning–predicted depth and edge maps. Tightly coupled visual-inertial fusion is realized via an extended Kalman filter. The system runs in real time on the DJI Tello platform, enabling autonomous corridor navigation and obstacle avoidance indoors. Evaluated on the TUM RGB-D dataset, it achieves high accuracy (mean absolute trajectory error < 0.035 m) and strong robustness. The core contributions are an edge-driven lightweight semi-dense mapping strategy and a loop-closure-free scale self-calibration framework.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Monocular simultaneous localization and mapping (SLAM) algorithms estimate drone poses and build a 3D map using a single camera. Current algorithms include sparse methods that lack detailed geometry, while learning-driven approaches produce dense maps but are computationally intensive. Monocular SLAM also faces scale ambiguities, which affect its accuracy. To address these challenges, we propose an edge-aware lightweight monocular SLAM system combining sparse keypoint-based pose estimation with dense edge reconstruction. Our method employs deep learning-based depth prediction and edge detection, followed by optimization to refine keypoints and edges for geometric consistency, without relying on global loop closure or heavy neural computations. We fuse inertial data with vision by using an extended Kalman filter to resolve scale ambiguity and improve accuracy. The system operates in real time on low-power platforms, as demonstrated on a DJI Tello drone with a monocular camera and inertial sensors. In addition, we demonstrate robust autonomous navigation and obstacle avoidance in indoor corridors and on the TUM RGBD dataset. Our approach offers an effective, practical solution to real-time mapping and navigation in resource-constrained environments.

Problem

• Resolving scale ambiguity in monocular SLAM using sensor fusion
• Achieving real-time dense mapping on resource-constrained drone platforms
• Combining geometric and learning methods for lightweight 3D reconstruction

Innovation

• Edge-aware lightweight monocular SLAM system
• Deep learning depth prediction with edge optimization
• Fusing inertial data via extended Kalman filter