Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade Images
The processing of aerial images taken by drones is a challenging task due to their high resolution and the presence of small objects. The scale of the objects varies diversely depending on the position of the drone, which can result in loss of information or increased difficulty in detecting small o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/11/10/953 |
| _version_ | 1797573154042806272 |
|---|---|
| author | Imad Gohar Abderrahim Halimi John See Weng Kean Yew Cong Yang |
| author_facet | Imad Gohar Abderrahim Halimi John See Weng Kean Yew Cong Yang |
| author_sort | Imad Gohar |
| collection | DOAJ |
| description | The processing of aerial images taken by drones is a challenging task due to their high resolution and the presence of small objects. The scale of the objects varies diversely depending on the position of the drone, which can result in loss of information or increased difficulty in detecting small objects. To address this issue, images are either randomly cropped or divided into small patches before training and inference. This paper proposes a defect detection framework that harnesses the advantages of slice-aided inference for small and medium-size damage on the surface of wind turbine blades. This framework enables the comparison of different slicing strategies, including a conventional patch division strategy and a more recent slice-aided hyper-inference, on several state-of-the-art deep neural network baselines for the detection of surface defects in wind turbine blade images. Our experiments provide extensive empirical results, highlighting the benefits of using the slice-aided strategy and the significant improvements made by these networks on an ultra high-resolution drone image dataset. |
| first_indexed | 2024-03-10T21:06:49Z |
| format | Article |
| id | doaj.art-54952526b7d34e29bbd9360156471dff |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-10T21:06:49Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-54952526b7d34e29bbd9360156471dff2023-11-19T17:08:34ZengMDPI AGMachines2075-17022023-10-01111095310.3390/machines11100953Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade ImagesImad Gohar0Abderrahim Halimi1John See2Weng Kean Yew3Cong Yang4School of Engineering and Physical Sciences, Heriot-Watt University, Putrajaya 62200, MalaysiaSchool of Engineering and Physical Sciences, Heriot-Watt University, Edinburgh EH14 4AS, UKSchool of Mathematical and Computer Sciences, Heriot-Watt University, Putrajaya 62200, MalaysiaSchool of Engineering and Physical Sciences, Heriot-Watt University, Putrajaya 62200, MalaysiaSchool of Future Science and Engineering, Soochow University, Suzhou 215006, ChinaThe processing of aerial images taken by drones is a challenging task due to their high resolution and the presence of small objects. The scale of the objects varies diversely depending on the position of the drone, which can result in loss of information or increased difficulty in detecting small objects. To address this issue, images are either randomly cropped or divided into small patches before training and inference. This paper proposes a defect detection framework that harnesses the advantages of slice-aided inference for small and medium-size damage on the surface of wind turbine blades. This framework enables the comparison of different slicing strategies, including a conventional patch division strategy and a more recent slice-aided hyper-inference, on several state-of-the-art deep neural network baselines for the detection of surface defects in wind turbine blade images. Our experiments provide extensive empirical results, highlighting the benefits of using the slice-aided strategy and the significant improvements made by these networks on an ultra high-resolution drone image dataset.https://www.mdpi.com/2075-1702/11/10/953surface defect detectionwind turbine bladesultra high-resolution imagesdrone imagessmall object detectiondeep neural networks |
| spellingShingle | Imad Gohar Abderrahim Halimi John See Weng Kean Yew Cong Yang Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade Images Machines surface defect detection wind turbine blades ultra high-resolution images drone images small object detection deep neural networks |
| title | Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade Images |
| title_full | Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade Images |
| title_fullStr | Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade Images |
| title_full_unstemmed | Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade Images |
| title_short | Slice-Aided Defect Detection in Ultra High-Resolution Wind Turbine Blade Images |
| title_sort | slice aided defect detection in ultra high resolution wind turbine blade images |
| topic | surface defect detection wind turbine blades ultra high-resolution images drone images small object detection deep neural networks |
| url | https://www.mdpi.com/2075-1702/11/10/953 |
| work_keys_str_mv | AT imadgohar sliceaideddefectdetectioninultrahighresolutionwindturbinebladeimages AT abderrahimhalimi sliceaideddefectdetectioninultrahighresolutionwindturbinebladeimages AT johnsee sliceaideddefectdetectioninultrahighresolutionwindturbinebladeimages AT wengkeanyew sliceaideddefectdetectioninultrahighresolutionwindturbinebladeimages AT congyang sliceaideddefectdetectioninultrahighresolutionwindturbinebladeimages |