Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation.

Chen, Siyuan; Yan, Yijun; Ren, Jinchang; Hwang, Byongjun; Marshall, Stephen; Durrani, Tariq

Abstract

By grouping pixels with visual coherence, superpixel algorithms provide an alternative representation of regular pixel grid for precise and efficient image segmentation. In this paper, a multi-stage model is used for sea ice segmentation from the high-resolution optical imagery, including the pre-processing to enhance the image contrast and suppress the noise, superpixel generation and classification, and post-processing to refine the segmented results. Four superpixel algorithms are evaluated within the framework, where the high-resolution imagery of the Chukchi sea is used for validation. Quantitative evaluation in terms of the segmentation quality and floe size distribution, and visual comparison for several selected regions of interest are presented. Overall, the model with TS-SLIC yields the best results, with a segmentation accuracy of 98.19% on average and adhering to the ice edges well.

Citation

CHEN, S., YAN, Y., REN, J., HWANG, B., MARSHALL, S. and DARRANI, T. 2022. Superpixel based sea ice segmentation with high-resolution optical images: analysis and evaluation. In Liang, Q., Wang, W., Liu, X., Na, Z. and Zhang, B. (eds.) Communications, signal processing and systems: proceedings of the 10th International conference on Communications, signal processing and systems 2021 (CSPS 2021), 21-22 August 2021, Baishishan, China. Lecture notes in electrical engineering, 878. Singapore: Springer [online], 1, pages 1004-1012. Available from: https://doi.org/10.1007/978-981-19-0390-8_126

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 10th International Communications, signal processing and systems conference 2021
• Start Date: Aug 21, 2021
• End Date: Aug 22, 2021
• Acceptance Date: Jun 20, 2021
• Online Publication Date: Mar 30, 2022
• Publication Date: Dec 31, 2022
• Deposit Date: Jun 21, 2022
• Publicly Available Date: Jun 21, 2022
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Pages: 1004-1012
• Series Title: Lecture notes in electrical engineering (LNEE)
• Series Number: 878
• Series ISSN: 1876-1119; 1876-1100
• Book Title: Communications, signal processing and systems: proceedings of the 10th International conference on Communications, signal processing and systems
• ISBN: 9789811903892
• DOI: https://doi.org/10.1007/978-981-19-0390-8_126
• Keywords: Sea ice segmentation; Superpixel; Satellite remote sensing
• Public URL: https://rgu-repository.worktribe.com/output/1654079