Enhancing wind power monitoring through motion deblurring with modified GoogleNet algorithm

Chillakuru, Prameeladevi; Madiajagan, M.; Prashanth, K. V. Mahendra; Ambala, Srinivas; Reddy, Pundru Chandra Shaker; Pavan, Jonnalagadda

doi:10.1007/s00500-023-08358-8

Cited by 40 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More specifically, researchers integrated the blur kernel extraction operation into the image-restoring process and proposed various hybrid models to restore a sharp image from the blurry input directly. Chillakuru et al [19] proposed an end-to-end motion deblurring model by modifying the GoogleNet algorithm, which was proven to surpass the traditional algorithms in terms of performance. Burdziakowski [20] applied generative adversarial networks (GAN) to eliminate unwanted blur in UAV images, based on which the geometric and interpretive quality of developed photogrammetric modes were improved.…”

Section: Introductionmentioning

confidence: 99%

Inspection of wind turbine blades using image deblurring and deep learning segmentation

Lu,

Gao,

Zhou

2024

Health Monitoring of Structural and Biological Systems XVIII

View full text Add to dashboard Cite

Remote and complex work sites of wind turbines limit the accessibility of the condition assessment. Wind turbine blades are subject to sustained wind load and harsh natural environmental conditions, which are vulnerable to various faults. Robotic-enabled sensing technology appears to be a promising solution for an efficient wind turbine blade inspection. Together with the recent advances in image processing and deep learning segmentation, automated inspection of wind turbine blades becomes possible. Nevertheless, it remains a challenging task to quantify the damage accurately due to the complex condition of images concerning motion blurs. To address this issue, an integrated framework, i.e., the combination of a Deblur Generative Adversarial Network v2 (DeblurGAN-v2) and You Only Look Once v8 (YOLO-v8) was proposed in this study. Specifically, the mapping between the motion-blurred images and those in high quality was adopted from the open-access pretrained DeblurGAN-v2, based on which the deblurring performance for wind turbine images with various motion blur scales was discussed concerning the image quality. Subsequently, the transfer learning method was implemented to fine-tune YOLO-v8. The well-trained YOLO v8 was then utilized for target defect segmentation on the deblurred images. Finally, various metrics were calculated to evaluate the segmentation accuracy and efficiency. Results prove a good generalization of DeblurGAN-v2 on wind turbine images and clearly illustrate the enhanced performance of the proposed methodology especially when the motion blur scale is within 35. The integrated framework could serve as a reference for dealing with other fuzzy image-related issues.

show abstract

Section: Introductionmentioning

confidence: 99%

Inspection of wind turbine blades using image deblurring and deep learning segmentation

Lu,

Gao,

Zhou

2024

Health Monitoring of Structural and Biological Systems XVIII

View full text Add to dashboard Cite

show abstract

A vehicular network based intelligent transport system for smart cities using machine learning algorithms

Prakash,

Murali,

Manikandan

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Smart cities and the Internet of Things have enabled the integration of communicating devices for efficient decision-making. Notably, traffic congestion is one major problem faced by daily commuters in urban cities. In developed countries, specialized sensors are deployed to gather traffic information to predict traffic patterns. Any traffic updates are shared with the commuters via the Internet. Such solutions become impracticable when physical infrastructure and Internet connectivity are either non-existent or very limited. In case of developing countries, no roadside units are available and Internet connectivity is still an issue in remote areas. Internet traffic analysis is a thriving field of study due to the myriad ways in which it may be put to practical use. In the intelligent Internet-of-Vehicles (IOVs), traffic congestion can be predicted and identified using cutting-edge technologies. Using tree-based decision-tree, random-forest, extra-tree, and XGBoost machine learning (ML) strategies, this research proposes an intelligent-transport-system for the IOVs-based vehicular network traffic in a smart city set-up. The suggested system uses ensemble learning and averages the selection of crucial features to give high detection accuracy at minimal computational costs, as demonstrated by the simulation results. For IOV-based vehicular network traffic, the tree-based ML approaches with feature-selection (FS) outperformed those without FS. When contrasted to the lowest KNN accuracy of 96.6% and the highest SVM accuracy of 98.01%, the Stacking approach demonstrates superior accuracy as 99.05%.

show abstract

Web application based Diabetes prediction using Machine Learning

Kumar,

Reddy,

et al. 2023

2023 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)

View full text Add to dashboard Cite

Enhancing wind power monitoring through motion deblurring with modified GoogleNet algorithm

Cited by 40 publications

References 13 publications

Inspection of wind turbine blades using image deblurring and deep learning segmentation

Inspection of wind turbine blades using image deblurring and deep learning segmentation

A vehicular network based intelligent transport system for smart cities using machine learning algorithms

Web application based Diabetes prediction using Machine Learning

Contact Info

Product

Resources

About