VGF-Net: Visual-Geometric Fusion Learning for Simultaneous Drone Navigation and Height Mapping

04/07/2021
by   Yilin Liu, et al.
0

The drone navigation requires the comprehensive understanding of both visual and geometric information in the 3D world. In this paper, we present a Visual-Geometric Fusion Network(VGF-Net), a deep network for the fusion analysis of visual/geometric data and the construction of 2.5D height maps for simultaneous drone navigation in novel environments. Given an initial rough height map and a sequence of RGB images, our VGF-Net extracts the visual information of the scene, along with a sparse set of 3D keypoints that capture the geometric relationship between objects in the scene. Driven by the data, VGF-Net adaptively fuses visual and geometric information, forming a unified Visual-Geometric Representation. This representation is fed to a new Directional Attention Model(DAM), which helps enhance the visual-geometric object relationship and propagates the informative data to dynamically refine the height map and the corresponding keypoints. An entire end-to-end information fusion and mapping system is formed, demonstrating remarkable robustness and high accuracy on the autonomous drone navigation across complex indoor and large-scale outdoor scenes. The dataset can be found in http://vcc.szu.edu.cn/research/2021/VGFNet.

READ FULL TEXT

page 1

page 6

page 9

page 10

research
07/19/2023

A3D: Adaptive, Accurate, and Autonomous Navigation for Edge-Assisted Drones

Accurate navigation is of paramount importance to ensure flight safety a...
research
01/09/2020

A Deep Neural Networks Approach for Pixel-Level Runway Pavement Crack Segmentation Using Drone-Captured Images

Pavement conditions are a critical aspect of asset management and direct...
research
09/14/2023

VAPOR: Legged Robot Navigation in Outdoor Vegetation Using Offline Reinforcement Learning

We present VAPOR, a novel method for autonomous legged robot navigation ...
research
11/18/2019

Simultaneous Mapping and Target Driven Navigation

This work presents a modular architecture for simultaneous mapping and t...
research
06/17/2021

Towards bio-inspired unsupervised representation learning for indoor aerial navigation

Aerial navigation in GPS-denied, indoor environments, is still an open c...
research
08/30/2023

Drone-NeRF: Efficient NeRF Based 3D Scene Reconstruction for Large-Scale Drone Survey

Neural rendering has garnered substantial attention owing to its capacit...
research
07/18/2022

PlaneSDF-based Change Detection for Long-term Dense Mapping

The ability to process environment maps across multiple sessions is crit...

Please sign up or login with your details

Forgot password? Click here to reset