دورية أكاديمية
Object Recognition and Tracking in Moving Videos for Maritime Autonomous Surface Ships
| العنوان: | Object Recognition and Tracking in Moving Videos for Maritime Autonomous Surface Ships |
|---|---|
| المؤلفون: | Hyunjin Park, Seung-Ho Ham, Taekyeong Kim, Donghyeok An |
| المصدر: | Journal of Marine Science and Engineering, Vol 10, Iss 7, p 841 (2022) |
| بيانات النشر: | MDPI AG, 2022. |
| سنة النشر: | 2022 |
| المجموعة: | LCC:Naval architecture. Shipbuilding. Marine engineering LCC:Oceanography |
| مصطلحات موضوعية: | object recognition, object tracking, deep learning, maritime autonomous surface ship, Naval architecture. Shipbuilding. Marine engineering, VM1-989, Oceanography, GC1-1581 |
| الوصف: | In autonomous driving technologies, a camera is necessary for establishing a path and detecting an object. Object recognition based on images from several cameras is required to detect impediments in autonomous ships. Furthermore, in order to avoid ship collisions, it is important to follow the movements of recognized ships. In this paper, we use the Singapore Maritime Dataset (SMD) and crawling image for model training. Then, we present four YOLO-based object recognition models and evaluate their performance in the maritime environment. Then, we propose a tracking algorithm to track the identified objects. Specially, in evaluation with high-motion video, the proposed tracking algorithm outperforms deep simple online and real-time tracking (DeepSORT) in terms of object tracking accuracy. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2077-1312 |
| Relation: | https://www.mdpi.com/2077-1312/10/7/841; https://doaj.org/toc/2077-1312 |
| DOI: | 10.3390/jmse10070841 |
| URL الوصول: | https://doaj.org/article/34b02922bdc64346bd714c5d8dfa96a4 |
| رقم الأكسشن: | edsdoj.34b02922bdc64346bd714c5d8dfa96a4 |
| قاعدة البيانات: | Directory of Open Access Journals |
Full Text Finder | تدمد: | 20771312 |
|---|---|
| DOI: | 10.3390/jmse10070841 |