An Enhanced Target Detection Algorithm for Maritime Search and Rescue Based on Aerial Images
Open Access
- 3 October 2023
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 15 (19) , 4818
Abstract
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.Keywords
Funding Information
- Ship Maneuvering Simulation in Yunnan Inland Navigation (851333J, 2022YFB4300803, 2022YFB4301402, 2022JH1/10800096, CSC [2022] 2260)
- National Key Research and Development Program of China (851333J, 2022YFB4300803, 2022YFB4301402, 2022JH1/10800096, CSC [2022] 2260)
- Liaoning Provincial Science and Technology Plan (Key) project (851333J, 2022YFB4300803, 2022YFB4301402, 2022JH1/10800096, CSC [2022] 2260)
- International cooperation training program for innovative talents of Chinese Scholarships Council (851333J, 2022YFB4300803, 2022YFB4301402, 2022JH1/10800096, CSC [2022] 2260)
This publication has 41 references indexed in Scilit:
- A video-based object detection and tracking system for weight sensitive UAVsMultimedia Tools and Applications, 2018
- Real-Time Detection, Tracking and Classification of Multiple Moving Objects in UAV Videos2017
- SSD: Single Shot MultiBox Detector2016
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Fast R-CNN2015
- Deep learningNature, 2015
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- A discriminatively trained, multiscale, deformable part model2008