Abstract
Sea ice is one of the typical causes of marine disasters. Sea ice image classification is an important component of sea ice detection. Optical data contain rich spectral information, but they do not allow one to easily distinguish between ground objects with a similar spectrum and foreign objects with the same spectrum. Synthetic aperture radar (SAR) data contain rich texture information, but the data usually have a single source. The limitation of single-source data is that they do not allow for further improvements of the accuracy of remote sensing sea ice classification. In this paper, we propose a method for sea ice image classification based on deep learning and heterogeneous data fusion. Utilizing the advantages of convolutional neural networks (CNNs) in terms of depth feature extraction, we designed a deep learning network structure for SAR and optical images and achieve sea ice image classification through feature extraction and a feature-level fusion of heterogeneous data. For the SAR images, the improved spatial pyramid pooling (SPP) network was used and texture information on sea ice at different scales was extracted by depth. For the optical data, multi-level feature information on sea ice such as spatial and spectral information on different types of sea ice was extracted through a path aggregation network (PANet), which enabled low-level features to be fully utilized due to the gradual feature extraction of the convolution neural network. In order to verify the effectiveness of the method, two sets of heterogeneous sentinel satellite data were used for sea ice classification in the Hudson Bay area. The experimental results show that compared with the typical image classification methods and other heterogeneous data fusion methods, the method proposed in this paper fully integrates multi-scale and multi-level texture and spectral information from heterogeneous data and achieves a better classification effect (96.61%, 95.69%).
Highlights
Sea ice, which accounts for 5–8% of the global ocean area, is the most prominent cause of marine disaster in polar seas and some high-dimensional regions
In order to verify the effectiveness of the experimental method presented in this paper, two sets of sea ice image data at different times were used for evaluation and compared to single-source data network models, such as SVM, 2D-convolutional neural networks (CNNs), 3D-CNN, and path aggregation network (PANet), as well as with classification methods of fusion models, such as the two-Branch CNN [20] and deep fusion [21]
Synthetic aperture radar (SAR) data and the optical characteristics of a remote sensing data fusion are applied in the classification of sea ice, making full use of the abundant sea ice texture features in SAR data and optical remote sensing images to provide high-resolution spectral characteristics, design a sea ice deep learning model to extract heterogeneous multi-scale feature and multi-level feature information, and improve classification accuracy
Summary
Sea ice, which accounts for 5–8% of the global ocean area, is the most prominent cause of marine disaster in polar seas and some high-dimensional regions. Polar sea ice anomalies affect atmospheric circulation, destroy the balance of fresh water, and affect the survival of organisms. Mid–high latitude sea ice disasters affect human marine fisheries, coastal construction, and manufacturing industries, and they cause serious economic losses [1]. Sea ice detection has important research significance, and sea ice image classification is an important part of it. It is necessary to obtain effective data in a timely manner for sea ice detection. Remote sensing technology provides an important means for large-scale sea ice detection
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
