A Novel Solution for Drone Photogrammetry with Low-overlap Aerial Images using Monocular Depth Estimation

2025-03-06

AI Summary

Traditional photogrammetry suffers from incomplete and inaccurate 3D reconstruction under low-overlap UAV aerial imagery (e.g., only 20 images) due to insufficient feature matching. To address this, we propose a novel pipeline integrating monocular depth estimation with aerial triangulation (AT). Sparse tie points derived from AT establish a geometric mapping between monocular depth maps and true metric depth, enabling unsupervised, non-parametric depth map metric calibration. This calibrated depth is subsequently used to generate a high-completeness digital surface model (DSM). To our knowledge, this is the first work to incorporate monocular depth estimation into low-overlap photogrammetry. The method significantly improves reconstruction coverage—especially in single-view regions—achieving meter-level depth accuracy and substantially outperforming conventional structure-from-motion (SfM) and multi-view stereo (MVS) approaches in terms of geometric completeness.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Low-overlap aerial imagery poses significant challenges to traditional photogrammetric methods, which rely heavily on high image overlap to produce accurate and complete mapping products. In this study, we propose a novel workflow based on monocular depth estimation to address the limitations of conventional techniques. Our method leverages tie points obtained from aerial triangulation to establish a relationship between monocular depth and metric depth, thus transforming the original depth map into a metric depth map, enabling the generation of dense depth information and the comprehensive reconstruction of the scene. For the experiments, a high-overlap drone dataset containing 296 images is processed using Metashape to generate depth maps and DSMs as ground truth. Subsequently, we create a low-overlap dataset by selecting 20 images for experimental evaluation. Results demonstrate that while the recovered depth maps and resulting DSMs achieve meter-level accuracy, they provide significantly better completeness compared to traditional methods, particularly in regions covered by single images. This study showcases the potential of monocular depth estimation in low-overlap aerial photogrammetry.

Problem

• Addresses challenges in low-overlap aerial photogrammetry.
• Proposes monocular depth estimation for accurate scene reconstruction.
• Improves completeness of depth maps in single-image regions.

Innovation

• Monocular depth estimation for low-overlap drone imagery
• Transforms depth maps into metric depth maps
• Enhances scene reconstruction completeness and accuracy