Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Utility Pole Fire Risk Inspection from 2D Street-Side Images

Rajanie Prabha, Kopal Nihar

TL;DR

The paper tackles wildfire risk around aging California utility poles by combining three computer-vision pipelines that extract pole tilt and pole–vegetation proximity from Google Street View data and PG&E pole records. It presents a 2D detection+Hough approach for inclination, a monocular depth-estimation method (DepthAnything) for vegetation proximity, and a 3D SfM-based reconstruction with DBSCAN for robust scene understanding, plus evaluation metrics including mAP and depth-accuracy-based risk scoring. The work demonstrates that street-view–driven measurements can inform risk maps and decision-making for undergrounding and PSPS, albeit with noted limitations in accuracy and computation. It aims to enable data-driven resilience planning in the ACFM domain and to provide a foundation for heatmap visualization of pole-related wildfire risk. The framework emphasizes modularity and practicality, leveraging publicly accessible imagery to support utilities, policymakers, and researchers.

Abstract

In recent years, California's electrical grid has confronted mounting challenges stemming from aging infrastructure and a landscape increasingly susceptible to wildfires. This paper presents a comprehensive framework utilizing computer vision techniques to address wildfire risk within the state's electrical grid, with a particular focus on vulnerable utility poles. These poles are susceptible to fire outbreaks or structural failure during extreme weather events. The proposed pipeline harnesses readily available Google Street View imagery to identify utility poles and assess their proximity to surrounding vegetation, as well as to determine any inclination angles. The early detection of potential risks associated with utility poles is pivotal for forestalling wildfire ignitions and informing strategic investments, such as undergrounding vulnerable poles and powerlines. Moreover, this study underscores the significance of data-driven decision-making in bolstering grid resilience, particularly concerning Public Safety Power Shutoffs. By fostering collaboration among utilities, policymakers, and researchers, this pipeline aims to solidify the electric grid's resilience and safeguard communities against the escalating threat of wildfires.

Utility Pole Fire Risk Inspection from 2D Street-Side Images

TL;DR

The paper tackles wildfire risk around aging California utility poles by combining three computer-vision pipelines that extract pole tilt and pole–vegetation proximity from Google Street View data and PG&E pole records. It presents a 2D detection+Hough approach for inclination, a monocular depth-estimation method (DepthAnything) for vegetation proximity, and a 3D SfM-based reconstruction with DBSCAN for robust scene understanding, plus evaluation metrics including mAP and depth-accuracy-based risk scoring. The work demonstrates that street-view–driven measurements can inform risk maps and decision-making for undergrounding and PSPS, albeit with noted limitations in accuracy and computation. It aims to enable data-driven resilience planning in the ACFM domain and to provide a foundation for heatmap visualization of pole-related wildfire risk. The framework emphasizes modularity and practicality, leveraging publicly accessible imagery to support utilities, policymakers, and researchers.

Abstract

In recent years, California's electrical grid has confronted mounting challenges stemming from aging infrastructure and a landscape increasingly susceptible to wildfires. This paper presents a comprehensive framework utilizing computer vision techniques to address wildfire risk within the state's electrical grid, with a particular focus on vulnerable utility poles. These poles are susceptible to fire outbreaks or structural failure during extreme weather events. The proposed pipeline harnesses readily available Google Street View imagery to identify utility poles and assess their proximity to surrounding vegetation, as well as to determine any inclination angles. The early detection of potential risks associated with utility poles is pivotal for forestalling wildfire ignitions and informing strategic investments, such as undergrounding vulnerable poles and powerlines. Moreover, this study underscores the significance of data-driven decision-making in bolstering grid resilience, particularly concerning Public Safety Power Shutoffs. By fostering collaboration among utilities, policymakers, and researchers, this pipeline aims to solidify the electric grid's resilience and safeguard communities against the escalating threat of wildfires.
Paper Structure (19 sections, 7 equations, 12 figures)

This paper contains 19 sections, 7 equations, 12 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data
  4. Methodology
  5. Approach 1: Image Detection + Hough Transform
  6. Approach 2: Depth Estimation
  7. Approach 3: 3D Point Cloud Recontruction
  8. Evaluation Metrics
  9. Mean Average Precision
  10. Depth Anything Accuracy
  11. Impact Metric
  12. Cost Metric
  13. Results
  14. Image Detection + Hough Transform
  15. Depth Estimation
  16. ...and 4 more sections

Figures (12)

  • Figure 1: Locations of utility-caused ignitions in California
  • Figure 2: A Google Street View Image of a Utility Pole, showing two task objectives: distance from vegetation and pole inclination angle
  • Figure 3: Count of pole types by material
  • Figure 4: Distribution of vegetation (NVDI basemap), poles (blue), and ignitions (red) in SF
  • Figure 5: Methodology Pipeline for Image Detection + Hough Transform
  • ...and 7 more figures