Advances in Aircraft Skin Defect Detection Using Computer Vision: A Survey and Comparison of YOLOv9 and RT-DETR Performance
Aircraft skin surface defect detection is critical for aviation safety but is currently mostly reliant on manual or visual inspections. Recent advancements in computer vision offer opportunities for automation. This paper reviews the current state of computer vision algorithms and their application...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/12/4/356 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849712267522736128 |
|---|---|
| author | Nutchanon Suvittawat Christian Kurniawan Jetanat Datephanyawat Jordan Tay Zhihao Liu De Wen Soh Nuno Antunes Ribeiro |
| author_facet | Nutchanon Suvittawat Christian Kurniawan Jetanat Datephanyawat Jordan Tay Zhihao Liu De Wen Soh Nuno Antunes Ribeiro |
| author_sort | Nutchanon Suvittawat |
| collection | DOAJ |
| description | Aircraft skin surface defect detection is critical for aviation safety but is currently mostly reliant on manual or visual inspections. Recent advancements in computer vision offer opportunities for automation. This paper reviews the current state of computer vision algorithms and their application in aircraft defect detection, synthesizing insights from academic research (21 publications) and industry projects (18 initiatives). Beyond a detailed review, we experimentally evaluate the accuracy and feasibility of existing low-cost, easily deployable hardware (drone) and software solutions (computer vision algorithms). Specifically, real-world data were collected from an abandoned aircraft with visible defects using a drone to capture video footage, which was then processed with state-of-the-art computer vision models—YOLOv9 and RT-DETR. Both models achieved mAP50 scores of 0.70–0.75, with YOLOv9 demonstrating slightly better accuracy and inference speed, while RT-DETR exhibited faster training convergence. Additionally, a comparison between YOLOv5 and YOLOv9 revealed a 10% improvement in mAP50, highlighting the rapid advancements in computer vision in recent years. Lastly, we identify and discuss various alternative hardware solutions for data collection—in addition to drones, these include robotic platforms, climbing robots, and smart hangars—and discuss key challenges for their deployment, such as regulatory constraints, human–robot integration, and weather resilience. The fundamental contribution of this paper is to underscore the potential of computer vision for aircraft skin defect detection while emphasizing that further research is still required to address existing limitations. |
| format | Article |
| id | doaj-art-0a5aad2fc9264dae95a1f82c72ec0284 |
| institution | DOAJ |
| issn | 2226-4310 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj-art-0a5aad2fc9264dae95a1f82c72ec02842025-08-20T03:14:20ZengMDPI AGAerospace2226-43102025-04-0112435610.3390/aerospace12040356Advances in Aircraft Skin Defect Detection Using Computer Vision: A Survey and Comparison of YOLOv9 and RT-DETR PerformanceNutchanon Suvittawat0Christian Kurniawan1Jetanat Datephanyawat2Jordan Tay3Zhihao Liu4De Wen Soh5Nuno Antunes Ribeiro6Information Systems Technology and Design, Singapore University of Technology and Design, Singapore 487372, SingaporeInformation Systems Technology and Design, Singapore University of Technology and Design, Singapore 487372, SingaporeEngineering Systems and Design, Singapore University of Technology and Design, Singapore 487372, SingaporeAviation Studies Institute, Singapore University of Technology and Design, Singapore 487372, SingaporeEngineering Systems and Design, Singapore University of Technology and Design, Singapore 487372, SingaporeInformation Systems Technology and Design, Singapore University of Technology and Design, Singapore 487372, SingaporeEngineering Systems and Design, Singapore University of Technology and Design, Singapore 487372, SingaporeAircraft skin surface defect detection is critical for aviation safety but is currently mostly reliant on manual or visual inspections. Recent advancements in computer vision offer opportunities for automation. This paper reviews the current state of computer vision algorithms and their application in aircraft defect detection, synthesizing insights from academic research (21 publications) and industry projects (18 initiatives). Beyond a detailed review, we experimentally evaluate the accuracy and feasibility of existing low-cost, easily deployable hardware (drone) and software solutions (computer vision algorithms). Specifically, real-world data were collected from an abandoned aircraft with visible defects using a drone to capture video footage, which was then processed with state-of-the-art computer vision models—YOLOv9 and RT-DETR. Both models achieved mAP50 scores of 0.70–0.75, with YOLOv9 demonstrating slightly better accuracy and inference speed, while RT-DETR exhibited faster training convergence. Additionally, a comparison between YOLOv5 and YOLOv9 revealed a 10% improvement in mAP50, highlighting the rapid advancements in computer vision in recent years. Lastly, we identify and discuss various alternative hardware solutions for data collection—in addition to drones, these include robotic platforms, climbing robots, and smart hangars—and discuss key challenges for their deployment, such as regulatory constraints, human–robot integration, and weather resilience. The fundamental contribution of this paper is to underscore the potential of computer vision for aircraft skin defect detection while emphasizing that further research is still required to address existing limitations.https://www.mdpi.com/2226-4310/12/4/356aircraft defect detectioncomputer visionmaintenance repair and overhaul (MRO)YOLORT-DETR |
| spellingShingle | Nutchanon Suvittawat Christian Kurniawan Jetanat Datephanyawat Jordan Tay Zhihao Liu De Wen Soh Nuno Antunes Ribeiro Advances in Aircraft Skin Defect Detection Using Computer Vision: A Survey and Comparison of YOLOv9 and RT-DETR Performance Aerospace aircraft defect detection computer vision maintenance repair and overhaul (MRO) YOLO RT-DETR |
| title | Advances in Aircraft Skin Defect Detection Using Computer Vision: A Survey and Comparison of YOLOv9 and RT-DETR Performance |
| title_full | Advances in Aircraft Skin Defect Detection Using Computer Vision: A Survey and Comparison of YOLOv9 and RT-DETR Performance |
| title_fullStr | Advances in Aircraft Skin Defect Detection Using Computer Vision: A Survey and Comparison of YOLOv9 and RT-DETR Performance |
| title_full_unstemmed | Advances in Aircraft Skin Defect Detection Using Computer Vision: A Survey and Comparison of YOLOv9 and RT-DETR Performance |
| title_short | Advances in Aircraft Skin Defect Detection Using Computer Vision: A Survey and Comparison of YOLOv9 and RT-DETR Performance |
| title_sort | advances in aircraft skin defect detection using computer vision a survey and comparison of yolov9 and rt detr performance |
| topic | aircraft defect detection computer vision maintenance repair and overhaul (MRO) YOLO RT-DETR |
| url | https://www.mdpi.com/2226-4310/12/4/356 |
| work_keys_str_mv | AT nutchanonsuvittawat advancesinaircraftskindefectdetectionusingcomputervisionasurveyandcomparisonofyolov9andrtdetrperformance AT christiankurniawan advancesinaircraftskindefectdetectionusingcomputervisionasurveyandcomparisonofyolov9andrtdetrperformance AT jetanatdatephanyawat advancesinaircraftskindefectdetectionusingcomputervisionasurveyandcomparisonofyolov9andrtdetrperformance AT jordantay advancesinaircraftskindefectdetectionusingcomputervisionasurveyandcomparisonofyolov9andrtdetrperformance AT zhihaoliu advancesinaircraftskindefectdetectionusingcomputervisionasurveyandcomparisonofyolov9andrtdetrperformance AT dewensoh advancesinaircraftskindefectdetectionusingcomputervisionasurveyandcomparisonofyolov9andrtdetrperformance AT nunoantunesribeiro advancesinaircraftskindefectdetectionusingcomputervisionasurveyandcomparisonofyolov9andrtdetrperformance |