Abstract
In this paper, a novel data augmentation method was proposed for supervised sea ice scene classification with arctic aerial images. Ice-type classification of sea ice scenes in a region is useful for instant navigation. However, some types of sea ice scenes are difficult to collect. The small number of available samples usually limits the performance in classification. Inspiring by the transfer learning method, the training samples are augmented with simulated sea ice images. Considering the distribution characteristic of sea ice scene, simulation samples are synthesized by algebraic operations on the respective regions of interest from two true samples. One of the two true samples can be an additional image, which is more easily collected than others, such as full ice and snow. Simultaneously, it introduces new information. Generalization and error-correction capability of deep neural networks for training samples make the proposed method feasible. The experiments on true sample sets, simulation sample sets, and mixed sample sets were implemented. Finally, the effectiveness of our data augmentation method was demonstrated, which improved the accuracy of sea ice classification.
Highlights
With the accelerated melting of the Arctic sea ice, more and more ships try an Arctic waterway as a shorter commercial route in special time [1]
We proposed a novel data augmentation method to generate diverse sea ice scenes for limited raw data to guarantee an appropriate amount of input data for deep neural networks
The task of sea ice scene classification from Arctic aerial images is completed by two steps: data augmentation and scene classification based on transfer learning
Summary
With the accelerated melting of the Arctic sea ice, more and more ships try an Arctic waterway as a shorter commercial route in special time [1]. Sea ice is a critical factor of route planning for Arctic navigation. Even though choosing to marine in the warmer months with powerful ice-breakers, the complex and changeable sea-ice environment still poses a great threat. The distribution and type of sea ice is quite important information, which is conductive to short-term route planning of ships. Different types of sea ice scene can affect the ships to varying degrees. Air-crafts are always employed to collect images of the sea ice scenes of Arctic Ocean for scouting, rescue or navigation in a short period of time. Since high cost Arctic flight experiments, images of some special types of
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
