Detection of ocean internal waves based on Faster R-CNN in SAR images     

Bao  Sude  Meng  Junmin  Sun  Lina  Liu  Yongxin 《中国海洋湖沼学报》2020,38(1):55-63

Ocean internal waves appear as irregular bright and dark stripes on synthetic aperture radar(SAR) remote sensing images. Ocean internal waves detection in SAR images consequently constituted a difficult and popular research topic. In this paper, ocean internal waves are detected in SAR images by employing the faster regions with convolutional neural network features(Faster R-CNN) framework; for this purpose, 888 internal wave samples are utilized to train the convolutional network and identify internal waves. The experimental results demonstrate a 94.78% recognition rate for internal waves, and the average detection speed is 0.22 s/image. In addition, the detection results of internal wave samples under dif ferent conditions are analyzed. This paper lays a foundation for detecting ocean internal waves using convolutional neural networks.  相似文献   

Remote sensing survey and research on internal solitary waves in the South China Sea-Western Pacific-East Indian Ocean (SCS-WPAC-EIND)     

Junmin Meng  Lina Sun  Hao Zhang  Beilei Hu  Fucheng Hou  Sude Bao 《海洋学报(英文版)》2022,41(10):154-170

Internal solitary waves (ISWs) are common mesoscale dynamic processes in the ocean that are spread throughout the world’s oceans. The South China Sea (SCS), Western Pacific (WPAC) and Indian Ocean (EIND) (SCS-WPAC-EIND) are areas where ISWs frequently occur. In particular, in the northern part of the South China Sea, Sulu Sea, Celebes Sea, Andaman Sea, Lombok Strait and northeastern part of Taiwan Island, ISWs exist almost year-round. Remote sensing is an important technique to carry out investigations and research on ISWs on a large scale. In particular, optical sensors represented by the Moderate Resolution Imaging Spectroradiometer (MODIS) can observe ISWs for a long time and on a large scale, while SAR sensors such as Sentinel-1 A/B can compensate for the deficiencies in optical sensors and comprehensively observe ISWs. Based on many years of remote sensing surveys of ISWs, this paper uses MODIS and Sentinel-1 satellite remote sensing images of more than 70 000 scenes from 2010 to 2020 to carry out survey studies of ISWs in the SCS-WPAC-EIND. The survey systematically gives the temporal and spatial distribution characteristics of ISWs in the SCS-WPAC-EIND and focuses on the analysis of the ISW characteristics in main areas in the SCS-WPAC-EIND, thereby providing basic data for further research on ISWs.  相似文献