Ortho-Fuse: Orthomosaic Generation for Sparse High-Resolution Crop Health Maps Through Intermediate Optical Flow Estimation

2025-10-11

AI Summary

Traditional photogrammetry requires 70–80% image overlap to ensure geometric registration accuracy, yet such high overlap is often infeasible in resource-constrained aerial monitoring, degrading orthomosaic quality and reducing the reliability of crop health maps. To address this, we propose a deep optical flow–based framework for intermediate-frame synthesis and feature-enhanced fusion: optical flow estimation predicts transitional frames between sparse input images, thereby augmenting valid feature correspondences and relaxing reliance on high overlap. This work presents the first high-fidelity geometric reconstruction from sparse aerial imagery. Experiments demonstrate that the minimum required overlap is reduced to 50–60%, representing a 20% decrease; orthomosaic geometric consistency and spatial usability of crop health maps are significantly improved. Our approach establishes a novel paradigm for autonomous agricultural monitoring under low-overlap conditions.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Distributed Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

AI-driven crop health mapping systems offer substantial advantages over conventional monitoring approaches through accelerated data acquisition and cost reduction. However, widespread farmer adoption remains constrained by technical limitations in orthomosaic generation from sparse aerial imagery datasets. Traditional photogrammetric reconstruction requires 70-80% inter-image overlap to establish sufficient feature correspondences for accurate geometric registration. AI-driven systems operating under resource-constrained conditions cannot consistently achieve these overlap thresholds, resulting in degraded reconstruction quality that undermines user confidence in autonomous monitoring technologies. In this paper, we present Ortho-Fuse, an optical flow-based framework that enables the generation of a reliable orthomosaic with reduced overlap requirements. Our approach employs intermediate flow estimation to synthesize transitional imagery between consecutive aerial frames, artificially augmenting feature correspondences for improved geometric reconstruction. Experimental validation demonstrates a 20% reduction in minimum overlap requirements. We further analyze adoption barriers in precision agriculture to identify pathways for enhanced integration of AI-driven monitoring systems.

Problem

• Generating orthomosaics from sparse aerial crop imagery
• Reducing high overlap requirements for geometric registration
• Improving reconstruction quality in resource-constrained agricultural monitoring

Innovation

• Uses optical flow to synthesize transitional imagery
• Reduces overlap requirements for orthomosaic generation
• Artificially augments feature correspondences for reconstruction