| Chen Zhenyu (陈振宇)*,Yan Huaguang* ****,Du Jianguang*,Xue Meng**,Zhao Shuai***.[J].高技术通讯(英文),2026,32(1):11~20 |
|
| Enhanced sparse RCNN for transmission line bolt defect detection via text-to-image data augmentation and quality filterin |
| |
| DOI：10. 3772 / j. issn. 1006-6748. 2026. 01. 002 |
| 中文关键词: |
| 英文关键词: sparse region-based convolutional neural network, HyperNetwork, image quality assessment, text-to-image generation, data augmentation, bolt defect detection, transmission line inspection |
| 基金项目: |
| Author Name | Affiliation | | Chen Zhenyu (陈振宇)* | (* Information and Telecommunication Center, State Grid Corporation of China, Beijing 100031, P. R. China)
(** State Grid Information and Telecommunication Group Co. , Ltd. , Beijing 102211, P. R. China)
(*** Information and Communication Branch, State Grid Zhejiang Electric Power Co. , Ltd. , Hangzhou 310007, P. R. China)
(**** China Electric Power Research Institute, Beijing 100192, P. R. China) | | Yan Huaguang* **** | | | Du Jianguang* | | | Xue Meng** | | | Zhao Shuai*** | |
|
| Hits: 34 |
| Download times: 34 |
| 中文摘要: |
| |
| 英文摘要: |
| To address the issue of inconsistent image quality and data scarcity in bolt defect detection for transmission lines, this paper proposes an improved sparse region-based convolutional neural network (RCNN) based detection framework integrating image quality evaluation and text-to-image data augmentation. First, a HyperNetwork-based image quality assessment module is introduced to filter low-quality inspection images in terms of clarity and structural integrity, resulting in a high-quality training dataset. Second, a text-to-image diffusion model is utilized for sample augmentation. By designing text prompts that describe various bolt defect types under diverse lighting and viewing conditions, the model automatically generates realistic synthetic samples. The generated images are further filtered using a combination of quality and perceptual similarity metrics to ensure consistency with the real data distribution. Building upon the sparse RCNN baseline, a dynamic label assignment mechanism and a random decision path detection head are incorporated to enhance bounding box matching and prediction accuracy. Experimental results demonstrate that the proposed method significantly improves detection accuracy (mAP@ 0. 5) over the original sparse RCNN while maintaining low computational cost, enabling more efficient and intelligent inspection of transmission line components. |
|
View Full Text
View/Add Comment Download reader |
| Close |
|
|
|
