期刊
REMOTE SENSING
卷 12, 期 9, 页码 -出版社
MDPI
DOI: 10.3390/rs12091443
关键词
ship detection; training data; AIS; SAR; machine learning
类别
资金
- Disaster-Safety Industry Promotion Program - Ministry of Interior and Safety (MOIS, Korea) [20009742]
- UAV-based Marine Safety, Illegal Fishing and Marine Ecosystem Management Technology Development - Ministry of Ocean and Fisheries (MOF, Korea) [20190497]
- Korea Evaluation Institute of Industrial Technology (KEIT) [20009742] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
- Korea Institute of Marine Science & Technology Promotion (KIMST) [201904972] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Development of convolutional neural network (CNN) optimized for object detection, led to significant developments in ship detection. Although training data critically affect the performance of the CNN-based training model, previous studies focused mostly on enhancing the architecture of the training model. This study developed a sophisticated and automatic methodology to generate verified and robust training data by employing synthetic aperture radar (SAR) images and automatic identification system (AIS) data. The extraction of training data initiated from interpolating the discretely received AIS positions to the exact position of the ship at the time of image acquisition. The interpolation was conducted by applying a Kalman filter, followed by compensating the Doppler frequency shift. The bounding box for the ship was constructed tightly considering the installation of the AIS equipment and the exact size of the ship. From 18 Sentinel-1 SAR images using a completely automated procedure, 7489 training data were obtained, compared with a different set of training data from visual interpretation. The ship detection model trained using the automatic training data obtained 0.7713 of overall detection performance from 3 Sentinel-1 SAR images, which exceeded that of manual training data, evading the artificial structures of harbors and azimuth ambiguity ghost signals from detection.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据