# Computer Vision-Based Corrosion Detection and Feature Extraction for Rock Bolts

## TL;DR

This paper presents a computer vision method to detect and analyze corrosion on rock bolts, using image processing and deep learning to assess corrosion over time.

## Contribution

The novel contribution is an integrated framework combining deep learning and fractal theory for automated corrosion detection and quantitative assessment.

## Key findings

- The model's multi-scale detection capability was significantly improved using a Feature Pyramid Network.
- Fractal dimension increased with corrosion time, providing a reliable indicator for corrosion assessment.
- Binary image analysis accurately quantified pitting density changes over time.

## Abstract

To address the challenges posed by rock bolt corrosion to engineering safety and service life, this study focuses on corrosion detection through integrated image processing, deep learning, and feature extraction methods. An automatic corrosion identification model was constructed based on computer-vision object-detection algorithms. By incorporating a Feature Pyramid Network, the model’s multi-scale object-detection capability was significantly enhanced. The corrosion features were extracted via image binarization and grayscale matrix analysis. The binary image method accurately quantified pitting density, revealing an initial increase followed by a decrease over time. The corrosion morphology was simulated using a Fractional Brownian Motion model, validating the accuracy of fractal feature calculations. The fractal dimension increased significantly with prolonged corrosion time, which not only characterize surface roughness evolution and corrosion rate, but also provide a reliable quantitative indicator for metal corrosion assessment. This research offers a technical framework integrating image processing, deep learning, and fractal theory for rock bolt corrosion monitoring and maintenance.