Slash or burn: Power line and vegetation classification for wildfire prevention

TL;DR

This paper presents a scalable method using transfer learning and feature engineering on Street View images to classify utility lines and vegetation overgrowth, aiding wildfire prevention efforts.

Contribution

It introduces a novel approach combining CNNs, HOG, and Hough transforms on Street View data for utility and vegetation classification, enabling prioritized vegetation management.

Findings

Achieved 80.15% accuracy with VGG11 model.

Ensemble model correctly classified 88.88% of risky vegetation images.

Demonstrated the feasibility of using Street View for utility asset mapping.

Abstract

Electric utilities are struggling to manage increasing wildfire risk in a hotter and drier climate. Utility transmission and distribution lines regularly ignite destructive fires when they make contact with surrounding vegetation. Trimming vegetation to maintain the separation from utility assets is as critical to safety as it is difficult. Each utility has tens of thousands of linear miles to manage, poor knowledge of where those assets are located, and no way to prioritize trimming. Feature-enhanced convolutional neural networks (CNNs) have proven effective in this problem space. Histograms of oriented gradients (HOG) and Hough transforms are used to increase the salience of the linear structures like power lines and poles. Data is frequently taken from drone or satellite footage, but Google Street View offers an even more scalable and lower cost solution. This paper uses $1,320$ images scraped from Street View, transfer learning on popular CNNs, and feature engineering to place images in one of three classes: (1) no utility systems, (2) utility systems with no overgrown vegetation, or (3) utility systems with overgrown vegetation. The CNN output thus yields a prioritized vegetation management system and creates a geotagged map of utility assets as a byproduct. Test set accuracy with reached $80.15\%$ using VGG11 with a trained first layer and classifier, and a model ensemble correctly classified $88.88\%$ of images with risky vegetation overgrowth.