{"title":"基于地面多同步摄像机捕获的风电叶片动态监测图像处理方法","authors":"Wenbo Wu, Yanbin Liu, Qiming Yang, Shuang Zhou, Yinggu Wu, Derui Gao, Shouxiao Ma","doi":"10.1002/cpe.70241","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>With the increase in the capacity of wind turbine units, the length of their blades has significantly grown. Existing machine vision-based image acquisition methods are unable to capture the full view of the blades, leading to the inability to accurately monitor the operational status of wind turbine blades dynamically. Therefore, this study proposes an image processing method for dynamic monitoring of wind turbine blade operation based on point and line features from images captured by ground multi-synchronous cameras. After image dehazing filtering and edge detection, the method utilizes line detection, so as to extract line features. Additionally, on the basis of improved Harris and Scale-Invariant Feature Transform (SIFT) registration, constraints such as line feature constraints, parallel constraints, and equidistant intercept constraints are incorporated for blade stitching. This process involves stitching fragmented images into a complete image, along with image enhancement, and assessing seam smoothness using root mean square error. Results indicate that this method can effectively capture and retain complete blade information, particularly blade edge information and blade damage information. The method proposed in this paper integrates machine vision, image recognition, and trajectory tracking technologies to construct a database of blade operating conditions and images. It is capable of operating in hazy environments, enabling accurate monitoring of blade operating conditions, supporting intelligent maintenance of wind farms, improving resource utilization, and reducing operating costs. Compared with existing methods, it has certain advantages. The research findings are expected to provide valuable data support for detecting potential defects or damages on the blades using machine vision-based methods.</p>\n </div>","PeriodicalId":55214,"journal":{"name":"Concurrency and Computation-Practice & Experience","volume":"37 21-22","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Image Processing Method for Dynamic Monitoring of Wind Turbine Blade Operation Based on Ground Multi-Synchronous Camera Capture\",\"authors\":\"Wenbo Wu, Yanbin Liu, Qiming Yang, Shuang Zhou, Yinggu Wu, Derui Gao, Shouxiao Ma\",\"doi\":\"10.1002/cpe.70241\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n <p>With the increase in the capacity of wind turbine units, the length of their blades has significantly grown. Existing machine vision-based image acquisition methods are unable to capture the full view of the blades, leading to the inability to accurately monitor the operational status of wind turbine blades dynamically. Therefore, this study proposes an image processing method for dynamic monitoring of wind turbine blade operation based on point and line features from images captured by ground multi-synchronous cameras. After image dehazing filtering and edge detection, the method utilizes line detection, so as to extract line features. Additionally, on the basis of improved Harris and Scale-Invariant Feature Transform (SIFT) registration, constraints such as line feature constraints, parallel constraints, and equidistant intercept constraints are incorporated for blade stitching. This process involves stitching fragmented images into a complete image, along with image enhancement, and assessing seam smoothness using root mean square error. Results indicate that this method can effectively capture and retain complete blade information, particularly blade edge information and blade damage information. The method proposed in this paper integrates machine vision, image recognition, and trajectory tracking technologies to construct a database of blade operating conditions and images. It is capable of operating in hazy environments, enabling accurate monitoring of blade operating conditions, supporting intelligent maintenance of wind farms, improving resource utilization, and reducing operating costs. Compared with existing methods, it has certain advantages. The research findings are expected to provide valuable data support for detecting potential defects or damages on the blades using machine vision-based methods.</p>\\n </div>\",\"PeriodicalId\":55214,\"journal\":{\"name\":\"Concurrency and Computation-Practice & Experience\",\"volume\":\"37 21-22\",\"pages\":\"\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2025-08-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Concurrency and Computation-Practice & Experience\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/cpe.70241\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Concurrency and Computation-Practice & Experience","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/cpe.70241","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
An Image Processing Method for Dynamic Monitoring of Wind Turbine Blade Operation Based on Ground Multi-Synchronous Camera Capture
With the increase in the capacity of wind turbine units, the length of their blades has significantly grown. Existing machine vision-based image acquisition methods are unable to capture the full view of the blades, leading to the inability to accurately monitor the operational status of wind turbine blades dynamically. Therefore, this study proposes an image processing method for dynamic monitoring of wind turbine blade operation based on point and line features from images captured by ground multi-synchronous cameras. After image dehazing filtering and edge detection, the method utilizes line detection, so as to extract line features. Additionally, on the basis of improved Harris and Scale-Invariant Feature Transform (SIFT) registration, constraints such as line feature constraints, parallel constraints, and equidistant intercept constraints are incorporated for blade stitching. This process involves stitching fragmented images into a complete image, along with image enhancement, and assessing seam smoothness using root mean square error. Results indicate that this method can effectively capture and retain complete blade information, particularly blade edge information and blade damage information. The method proposed in this paper integrates machine vision, image recognition, and trajectory tracking technologies to construct a database of blade operating conditions and images. It is capable of operating in hazy environments, enabling accurate monitoring of blade operating conditions, supporting intelligent maintenance of wind farms, improving resource utilization, and reducing operating costs. Compared with existing methods, it has certain advantages. The research findings are expected to provide valuable data support for detecting potential defects or damages on the blades using machine vision-based methods.
期刊介绍:
Concurrency and Computation: Practice and Experience (CCPE) publishes high-quality, original research papers, and authoritative research review papers, in the overlapping fields of:
Parallel and distributed computing;
High-performance computing;
Computational and data science;
Artificial intelligence and machine learning;
Big data applications, algorithms, and systems;
Network science;
Ontologies and semantics;
Security and privacy;
Cloud/edge/fog computing;
Green computing; and
Quantum computing.