YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images
Object detection from aerial and satellite remote sensing images has been an active research topic over the past decade. Thanks to the increase in computational resources and data availability, deep learning-based object detection methods have achieved numerous successes in computer vision, and more...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/15/2501 |
| _version_ | 1797560347166507008 |
|---|---|
| author | Minh-Tan Pham Luc Courtrai Chloé Friguet Sébastien Lefèvre Alexandre Baussard |
| author_facet | Minh-Tan Pham Luc Courtrai Chloé Friguet Sébastien Lefèvre Alexandre Baussard |
| author_sort | Minh-Tan Pham |
| collection | DOAJ |
| description | Object detection from aerial and satellite remote sensing images has been an active research topic over the past decade. Thanks to the increase in computational resources and data availability, deep learning-based object detection methods have achieved numerous successes in computer vision, and more recently in remote sensing. However, the ability of current detectors to deal with (very) small objects still remains limited. In particular, the fast detection of small objects from a large observed scene is still an open question. In this work, we address this challenge and introduce an enhanced one-stage deep learning-based detection model, called You Only Look Once (YOLO)-fine, which is based on the structure of YOLOv3. Our detector is designed to be capable of detecting small objects with high accuracy and high speed, allowing further real-time applications within operational contexts. We also investigate its robustness to the appearance of new backgrounds in the validation set, thus tackling the issue of domain adaptation that is critical in remote sensing. Experimental studies that were conducted on both aerial and satellite benchmark datasets show some significant improvement of YOLO-fine as compared to other state-of-the art object detectors. |
| first_indexed | 2024-03-10T17:58:23Z |
| format | Article |
| id | doaj.art-c4cf81378e274e659a0285d3a5b35fa1 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T17:58:23Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c4cf81378e274e659a0285d3a5b35fa12023-11-20T09:04:39ZengMDPI AGRemote Sensing2072-42922020-08-011215250110.3390/rs12152501YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing ImagesMinh-Tan Pham0Luc Courtrai1Chloé Friguet2Sébastien Lefèvre3Alexandre Baussard4IRISA, Université Bretagne Sud, 56000 Vannes, FranceIRISA, Université Bretagne Sud, 56000 Vannes, FranceIRISA, Université Bretagne Sud, 56000 Vannes, FranceIRISA, Université Bretagne Sud, 56000 Vannes, FranceInstitut Charles Delaunay, Université de Technologie de Troyes, 10000 Troyes, FranceObject detection from aerial and satellite remote sensing images has been an active research topic over the past decade. Thanks to the increase in computational resources and data availability, deep learning-based object detection methods have achieved numerous successes in computer vision, and more recently in remote sensing. However, the ability of current detectors to deal with (very) small objects still remains limited. In particular, the fast detection of small objects from a large observed scene is still an open question. In this work, we address this challenge and introduce an enhanced one-stage deep learning-based detection model, called You Only Look Once (YOLO)-fine, which is based on the structure of YOLOv3. Our detector is designed to be capable of detecting small objects with high accuracy and high speed, allowing further real-time applications within operational contexts. We also investigate its robustness to the appearance of new backgrounds in the validation set, thus tackling the issue of domain adaptation that is critical in remote sensing. Experimental studies that were conducted on both aerial and satellite benchmark datasets show some significant improvement of YOLO-fine as compared to other state-of-the art object detectors.https://www.mdpi.com/2072-4292/12/15/2501small object detectionremote sensingbackground variabilitydeep learningone-stage detector |
| spellingShingle | Minh-Tan Pham Luc Courtrai Chloé Friguet Sébastien Lefèvre Alexandre Baussard YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images Remote Sensing small object detection remote sensing background variability deep learning one-stage detector |
| title | YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images |
| title_full | YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images |
| title_fullStr | YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images |
| title_full_unstemmed | YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images |
| title_short | YOLO-Fine: One-Stage Detector of Small Objects Under Various Backgrounds in Remote Sensing Images |
| title_sort | yolo fine one stage detector of small objects under various backgrounds in remote sensing images |
| topic | small object detection remote sensing background variability deep learning one-stage detector |
| url | https://www.mdpi.com/2072-4292/12/15/2501 |
| work_keys_str_mv | AT minhtanpham yolofineonestagedetectorofsmallobjectsundervariousbackgroundsinremotesensingimages AT luccourtrai yolofineonestagedetectorofsmallobjectsundervariousbackgroundsinremotesensingimages AT chloefriguet yolofineonestagedetectorofsmallobjectsundervariousbackgroundsinremotesensingimages AT sebastienlefevre yolofineonestagedetectorofsmallobjectsundervariousbackgroundsinremotesensingimages AT alexandrebaussard yolofineonestagedetectorofsmallobjectsundervariousbackgroundsinremotesensingimages |