A Segmentation-driven Editing Method for Bolt Defect Augmentation and Detection

TL;DR

This paper introduces a segmentation-driven editing method to augment bolt defect datasets, improving detection accuracy by generating high-quality defect images through attribute editing and scene integration.

Contribution

The proposed SBDE method combines advanced segmentation, attribute editing, and scene recovery to effectively augment bolt defect datasets for improved detection performance.

Findings

Generated defect images outperform state-of-the-art editing models.

Augmented datasets significantly improve bolt defect detection accuracy.

Method demonstrates strong application potential in transmission line safety.

Abstract

Bolt defect detection is critical to ensure the safety of transmission lines. However, the scarcity of defect images and imbalanced data distributions significantly limit detection performance. To address this problem, we propose a segmentationdriven bolt defect editing method (SBDE) to augment the dataset. First, a bolt attribute segmentation model (Bolt-SAM) is proposed, which enhances the segmentation of complex bolt attributes through the CLAHE-FFT Adapter (CFA) and Multipart- Aware Mask Decoder (MAMD), generating high-quality masks for subsequent editing tasks. Second, a mask optimization module (MOD) is designed and integrated with the image inpainting model (LaMa) to construct the bolt defect attribute editing model (MOD-LaMa), which converts normal bolts into defective ones through attribute editing. Finally, an editing recovery augmentation (ERA) strategy is proposed to recover and put the edited defect bolts back into the original inspection scenes and expand the defect detection dataset. We constructed multiple bolt datasets and conducted extensive experiments. Experimental results demonstrate that the bolt defect images generated by SBDE significantly outperform state-of-the-art image editing models, and effectively improve the performance of bolt defect detection, which fully verifies the effectiveness and application potential of the proposed method. The code of the project is available at https://github.com/Jay-xyj/SBDE.