# Monocular Absolute Depth Estimation from Motion for Small Unmanned Aerial Vehicles by Geometry-Based Scale Recovery

## TL;DR

This paper introduces a new method for estimating absolute depth from a single camera on small drones using geometry-based scale recovery, enabling better navigation and scene understanding.

## Contribution

A novel geometry-based scale recovery method for absolute depth estimation in UAVs using monocular vision.

## Key findings

- The proposed method successfully generates absolute depth maps from relative depth estimates using pose data and feature correspondences.
- Experiments on the Mid-Air dataset and custom data show the method's effectiveness and robustness to sensor noise.
- The approach requires only a monocular camera and standard navigation sensors, making it practical for UAVs.

## Abstract

In recent years, there has been extensive research and application of unsupervised monocular depth estimation methods for intelligent vehicles. However, a major limitation of most existing approaches is their inability to predict absolute depth values in physical units, as they generally suffer from the scale problem. Furthermore, most research efforts have focused on ground vehicles, neglecting the potential application of these methods to unmanned aerial vehicles (UAVs). To address these gaps, this paper proposes a novel absolute depth estimation method specifically designed for flight scenes using a monocular vision sensor, in which a geometry-based scale recovery algorithm serves as a post-processing stage of relative depth estimation results with scale consistency. By exploiting the feature correspondence between successive images and using the pose data provided by equipped navigation sensors, the scale factor between relative and absolute scales is calculated according to a multi-view geometry model, and then absolute depth maps are generated by pixel-wise multiplication of relative depth maps with the scale factor. As a result, the unsupervised monocular depth estimation technology is extended from relative depth estimation in semi-structured scenes to absolute depth estimation in unstructured scenes. Experiments on the publicly available Mid-Air dataset and customized data demonstrate the effectiveness of our method in different cases and settings, as well as its robustness to navigation sensor noise. The proposed method only requires UAVs to be equipped with monocular camera and common navigation sensors, and the obtained absolute depth information can be directly used for downstream tasks, which is significant for this kind of vehicle that has rarely been explored in previous depth estimation studies.