ElectricSight: 3D Hazard Monitoring for Power Lines Using Low-Cost Sensors

TL;DR

Power transmission lines are vulnerable to nearby hazards such as cranes, and depth-aware monitoring is necessary for effective safety. ElectricSight combines offline environmental point clouds with real-time monocular images to perform 3D distance measurements through a three-stage pipeline: 2D hazard detection, 3D-2D registration, and monocular depth estimation with geometric depth constraints. The approach leverages depth priors from point clouds, apex/ground-point key-parts extraction, and a ray-ground intersection framework to compute minimum distances to lines, achieving an average error of about 1.08 m and 92% early-warning accuracy in real-world tests. This framework offers a scalable, low-cost alternative to full 3D sensing for power-grid hazard monitoring with strong robustness across object types, distances, and environments.

Abstract

Protecting power transmission lines from potential hazards involves critical tasks, one of which is the accurate measurement of distances between power lines and potential threats, such as large cranes. The challenge with this task is that the current sensor-based methods face challenges in balancing accuracy and cost in distance measurement. A common practice is to install cameras on transmission towers, which, however, struggle to measure true 3D distances due to the lack of depth information. Although 3D lasers can provide accurate depth data, their high cost makes large-scale deployment impractical. To address this challenge, we present ElectricSight, a system designed for 3D distance measurement and monitoring of potential hazards to power transmission lines. This work's key innovations lie in both the overall system framework and a monocular depth estimation method. Specifically, the system framework combines real-time images with environmental point cloud priors, enabling cost-effective and precise 3D distance measurements. As a core component of the system, the monocular depth estimation method enhances the performance by integrating 3D point cloud data into image-based estimates, improving both the accuracy and reliability of the system. To assess ElectricSight's performance, we conducted tests with data from a real-world power transmission scenario. The experimental results demonstrate that ElectricSight achieves an average accuracy of 1.08 m for distance measurements and an early warning accuracy of 92%.

Figures (6)

• Figure 1: Our distance measurement system: the UAV (sensor1) collects environmental point cloud data, while the fixed camera (sensor2) provides image information. The two work together to accurately measure the distance between hazardous objects (e.g., cranes) and power lines to detect potential risks.
• Figure 2: Overview of our Electricsight: The method consists of three main stages: (1) 2D Detection: Detect hazardous objects (e.g., cranes) in 2D images and extract key points. (2) 3D-2D Registration: Perform initial estimation and optimization of the extrinsic parameters between point clouds and images using a neighbor rendering-based approach. (3) 3D Measurement: Construct depth constraints to accurately calculate the distance between hazardous objects and power lines, ensuring reliable safety assessment.
• Figure 3: Key steps of the 3D measurement stage, including ray construction, ground normal vector generation, depth constrain point creation, and final distance calculation.
• Figure 4: The visualization of distance measurement and warning. Crane: Distance = 6.08m (below 10m threshold), warning triggered. Aerial lift: Distance = 10.48m (above 10m threshold), no warning.
• Figure 5: 3D Measure results of different target types in 20-140m range: (a)Lifts-like targets, (b)Crane-like targets.