دورية أكاديمية
Heuristic data-driven anchor generation for UAV-based maritime rescue image object detection
| العنوان: | Heuristic data-driven anchor generation for UAV-based maritime rescue image object detection |
|---|---|
| المؤلفون: | Beigeng Zhao, Rui Song, Ye Zhou, Lizhi Yu, Xia Zhang, Jiren Liu |
| المصدر: | Heliyon, Vol 10, Iss 10, Pp e30485- (2024) |
| بيانات النشر: | Elsevier, 2024. |
| سنة النشر: | 2024 |
| المجموعة: | LCC:Science (General) LCC:Social sciences (General) |
| مصطلحات موضوعية: | Object detection, Unmmaned aerial vehicles, Deep learning, Maritime rescue, Anchor boxes optimization, Science (General), Q1-390, Social sciences (General), H1-99 |
| الوصف: | The specificity of scenarios and tasks in Unmanned Aerial Vehicles (UAV)-based maritime rescue poses challenges for detecting targets within images captured by drones in such environments. This study focuses on leveraging heuristic methods to extract data features from specific UAV maritime rescue images to optimize the generation of anchor boxes in detection models. Experiments conducted on the large-scale SeaDronesSee maritime rescue dataset, using the MMDetection object detection framework, demonstrated that the optimized anchor boxes, improved model performance by 48.9% to 62.8% compared to the framework's default configuration, with the most proficient model surpassing the official highest SeaDronesSee baseline by over 49.3%. Further analysis of the results revealed the variation in detection difficulty for different objects within the dataset and identified the reasons behind these differences. The methodology and analysis presented in this study hold promise for optimizing UAV-based maritime rescue object detection models as well as refining data analysis and enhancement. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2405-8440 |
| العلاقة: | http://www.sciencedirect.com/science/article/pii/S2405844024065162Test; https://doaj.org/toc/2405-8440Test |
| DOI: | 10.1016/j.heliyon.2024.e30485 |
| الوصول الحر: | https://doaj.org/article/b2bf9d3a9ab94365b5d5e6e2ada791adTest |
| رقم الانضمام: | edsdoj.b2bf9d3a9ab94365b5d5e6e2ada791ad |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 24058440 |
|---|---|
| DOI: | 10.1016/j.heliyon.2024.e30485 |