Next Article in Journal
Mapping and Quantifying the Human-Environment Interactions in Middle Egypt Using Machine Learning and Satellite Data Fusion Techniques
Previous Article in Journal
Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network
Open AccessArticle

Enhanced Delaunay Triangulation Sea Ice Tracking Algorithm with Combining Feature Tracking and Pattern Matching

1
Information Science and Technology College, Dalian Maritime University, Dalian 116026, China
2
Inner Mongolia Key Laboratory of Pattern Recognition and Intelligent Image Processing, Inner Mongolia University of Science and Technology, Baotou 014010, China
3
First Institute of Oceanography, Ministry of Natural Resources, Qingdao 266061, China
4
Inner Mongolia University of Technology, Hohhot 010051, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(3), 581; https://doi.org/10.3390/rs12030581
Received: 13 January 2020 / Revised: 7 February 2020 / Accepted: 7 February 2020 / Published: 10 February 2020
Sea ice drift detection has the key role of global climate analysis and waterway planning. The ability to detect sea ice drift in real-time also contributes to the safe navigation of ships and the prevention of offshore oil platform accidents. In this paper, an Enhanced Delaunay Triangulation (EDT) algorithm for sea ice tracking was proposed for dual-polarization sequential Synthetic Aperture Radar (SAR) images, which was implemented by combining feature tracking with pattern matching based on integrating HH and HV polarization feature information. A sea ice retrieval algorithm for feature detection, matching, fusion, and outlier detection was specifically developed to increase the system’s accuracy and robustness. In comparison with several state-of-the-art sea ice drift retrieval algorithms, including Speeded Up Robust Features (SURF) and the Oriented FAST and Rotated BRIEF (ORB) method, the results of the experiment provided compelling evidence that our algorithm had a higher accuracy than the SURF and ORB method. Furthermore, the results of our method were compared with the drift vector and direction of buoys data. The drift direction is consistent with buoys, and the velocity deviation was about 10 m. It was proved that this method can be applied effectively to the retrieval of sea ice drift. View Full-Text
Keywords: Delaunay Triangulation; dual-polarization; feature tracking; pattern matching; sea ice tracking; Sentinel-1; Synthetic Aperture Radar (SAR) Delaunay Triangulation; dual-polarization; feature tracking; pattern matching; sea ice tracking; Sentinel-1; Synthetic Aperture Radar (SAR)
Show Figures

Graphical abstract

MDPI and ACS Style

Zhang, M.; An, J.; Zhang, J.; Yu, D.; Wang, J.; Lv, X. Enhanced Delaunay Triangulation Sea Ice Tracking Algorithm with Combining Feature Tracking and Pattern Matching. Remote Sens. 2020, 12, 581.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop