LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation
Abstract The low‐light environment is integral to everyday activities but poses significant challenges in object detection. Due to the low brightness, noise, and insufficient illumination of the acquired image, the model's object detection performance is reduced. Opposing recent studies mainly...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-04-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.13017 |
| _version_ | 1797216887201857536 |
|---|---|
| author | Yun Xiao Hai Liao |
| author_facet | Yun Xiao Hai Liao |
| author_sort | Yun Xiao |
| collection | DOAJ |
| description | Abstract The low‐light environment is integral to everyday activities but poses significant challenges in object detection. Due to the low brightness, noise, and insufficient illumination of the acquired image, the model's object detection performance is reduced. Opposing recent studies mainly developing using supervised learning models, this paper suggests LIDA‐YOLO, an approach for unsupervised adaptation of low‐illumination object detectors. The model improves the YOLOv3 by using normal illumination images as the source domain and low‐illumination images as the target domain and achieves object detection in low‐illumination images through an unsupervised learning strategy. Specifically, a multi‐scale local feature alignment and global feature alignment module are proposed to align the overall attributes of the image and feature biases such as background, scene, and target layout are thus reduced. The experimental results of LIDA‐YOLO on the ExDark dataset achieved the highest performance mAP score of 56.65% compared to several current state‐of‐the‐art unsupervised domain adaptation object detection methods. Compared to I3Net, the performance improvement is 4.04%, and compared to OSHOT, the performance improvement is 6.5%. LIDA‐YOLO achieves a performance improvement of 2.7% compared to the supervised baseline method YOLOv3. Overall, the suggested LIDA‐YOLO model requires fewer samples and presents a stronger generalization ability than previous works. |
| first_indexed | 2024-04-24T11:53:06Z |
| format | Article |
| id | doaj.art-3cff910e8e2e4765899a004a958b4951 |
| institution | Directory Open Access Journal |
| issn | 1751-9659 1751-9667 |
| language | English |
| last_indexed | 2024-04-24T11:53:06Z |
| publishDate | 2024-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj.art-3cff910e8e2e4765899a004a958b49512024-04-09T06:07:10ZengWileyIET Image Processing1751-96591751-96672024-04-011851178118810.1049/ipr2.13017LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptationYun Xiao0Hai Liao1School of Software Sichuan Vocational College of Information Technology Guangyuan ChinaSchool of Software Sichuan Vocational College of Information Technology Guangyuan ChinaAbstract The low‐light environment is integral to everyday activities but poses significant challenges in object detection. Due to the low brightness, noise, and insufficient illumination of the acquired image, the model's object detection performance is reduced. Opposing recent studies mainly developing using supervised learning models, this paper suggests LIDA‐YOLO, an approach for unsupervised adaptation of low‐illumination object detectors. The model improves the YOLOv3 by using normal illumination images as the source domain and low‐illumination images as the target domain and achieves object detection in low‐illumination images through an unsupervised learning strategy. Specifically, a multi‐scale local feature alignment and global feature alignment module are proposed to align the overall attributes of the image and feature biases such as background, scene, and target layout are thus reduced. The experimental results of LIDA‐YOLO on the ExDark dataset achieved the highest performance mAP score of 56.65% compared to several current state‐of‐the‐art unsupervised domain adaptation object detection methods. Compared to I3Net, the performance improvement is 4.04%, and compared to OSHOT, the performance improvement is 6.5%. LIDA‐YOLO achieves a performance improvement of 2.7% compared to the supervised baseline method YOLOv3. Overall, the suggested LIDA‐YOLO model requires fewer samples and presents a stronger generalization ability than previous works.https://doi.org/10.1049/ipr2.13017computer visionimage enhancementobject detectionunsupervised learning |
| spellingShingle | Yun Xiao Hai Liao LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation IET Image Processing computer vision image enhancement object detection unsupervised learning |
| title | LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation |
| title_full | LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation |
| title_fullStr | LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation |
| title_full_unstemmed | LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation |
| title_short | LIDA‐YOLO: An unsupervised low‐illumination object detection based on domain adaptation |
| title_sort | lida yolo an unsupervised low illumination object detection based on domain adaptation |
| topic | computer vision image enhancement object detection unsupervised learning |
| url | https://doi.org/10.1049/ipr2.13017 |
| work_keys_str_mv | AT yunxiao lidayoloanunsupervisedlowilluminationobjectdetectionbasedondomainadaptation AT hailiao lidayoloanunsupervisedlowilluminationobjectdetectionbasedondomainadaptation |