An Enhanced Target Detection Algorithm for Maritime Search and Rescue Based on Aerial Images
Remote Sensing · 03.10.2023 · 15 (19) · 4818
DOI: 10.3390/rs15194818 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 03.10.2023. Verfasst von Yijian Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ship Maneuvering Simulation in Yunnan Inland Navigation, National Key R&D Program of China, Liaoning Provincial Science and Technology Plan (Key) project.
Abstract (Originalsprache)
Unmanned aerial vehicles (UAVs), renowned for their rapid deployment, extensive data collection, and high spatial resolution, are crucial in locating distressed individuals during search and rescue (SAR) operations. Challenges in maritime search and rescue include missed detections due to issues including sunlight reflection. In this study, we proposed an enhanced ABT-YOLOv7 algorithm for underwater person detection. This algorithm integrates an asymptotic feature pyramid network (AFPN) to preserve the target feature information. The BiFormer module enhances the model’s perception of small-scale targets, whereas the task-specific context decoupling (TSCODE) mechanism effectively resolves conflicts between localization and classification. Using quantitative experiments on a curated dataset, our model outperformed methods such as YOLOv3, YOLOv4, YOLOv5, YOLOv8, Faster R-CNN, Cascade R-CNN, and FCOS. Compared with YOLOv7, our approach enhances the mean average precision (mAP) from 87.1% to 91.6%. Therefore, our approach reduces the sensitivity of the detection model to low-lighting conditions and sunlight reflection, thus demonstrating enhanced robustness. These innovations have driven advancements in UAV technology within the maritime search and rescue domains.
Förderung
- Ship Maneuvering Simulation in Yunnan Inland Navigation
- National Key R&D Program of China
- Liaoning Provincial Science and Technology Plan (Key) project
- International cooperation training program for innovative talents of Chinese Scholarships Council
Zitieren
APA
Zhang, Y., Yin, Y., & Shao, Z. (2023). An Enhanced Target Detection Algorithm for Maritime Search and Rescue Based on Aerial Images. Remote Sensing, 15(19), 4818. https://doi.org/10.3390/rs15194818
Vancouver
Zhang Y, Yin Y, Shao Z. An Enhanced Target Detection Algorithm for Maritime Search and Rescue Based on Aerial Images. Remote Sensing. 2023;15(19):4818. doi:10.3390/rs15194818
BibTeX
@article{Zhang2023,
author = {Zhang, Yijian and Yin, Yong and Shao, Zeyuan},
title = {An Enhanced Target Detection Algorithm for Maritime Search and Rescue Based on Aerial Images},
journal = {Remote Sensing},
year = {2023},
volume = {15},
number = {19},
pages = {4818},
doi = {10.3390/rs15194818}
}
EUVIMED