UCorr: Wire Detection and Depth Estimation for Autonomous Drones

2025-09-18

AI Summary

Detecting slender power lines remains a critical obstacle-avoidance challenge for autonomous UAVs operating in complex environments. Method: This paper proposes a monocular vision-based end-to-end model that jointly performs pixel-level power line segmentation and dense depth estimation—its first such integration. To enhance spatiotemporal consistency for thin structures, we introduce a temporal correlation modeling module. Training leverages a high-fidelity synthetic power line dataset, mitigating the scarcity of real-world annotated data. Contribution/Results: Experiments demonstrate substantial improvements over state-of-the-art methods on both segmentation and depth estimation tasks. In real-flight scenarios, the model increases power line collision warning accuracy by 23.6%, significantly improving navigation safety and robustness under challenging visual conditions.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

In the realm of fully autonomous drones, the accurate detection of obstacles is paramount to ensure safe navigation and prevent collisions. Among these challenges, the detection of wires stands out due to their slender profile, which poses a unique and intricate problem. To address this issue, we present an innovative solution in the form of a monocular end-to-end model for wire segmentation and depth estimation. Our approach leverages a temporal correlation layer trained on synthetic data, providing the model with the ability to effectively tackle the complex joint task of wire detection and depth estimation. We demonstrate the superiority of our proposed method over existing competitive approaches in the joint task of wire detection and depth estimation. Our results underscore the potential of our model to enhance the safety and precision of autonomous drones, shedding light on its promising applications in real-world scenarios.

Problem

• Detecting slender wires for autonomous drone navigation
• Estimating depth from monocular images for obstacle avoidance
• Joint wire segmentation and depth estimation using synthetic data

Innovation

• Monocular end-to-end model for wire segmentation
• Temporal correlation layer trained on synthetic data
• Superior joint wire detection and depth estimation