Current Trends and Future Directions in Sea-Land Segmentation for Remote Sensing Images | ||||
| Mansoura Journal for Computer and Information Sciences | ||||
| Volume 15, Issue 2, December 2019, Page 11-26 PDF (1.72 MB) | ||||
| Document Type: Original Research Articles. | ||||
| DOI: 10.21608/mjcis.2019.321064 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| Eman Elkhateeb* ; Nagham Mekky; Ahmed Atwan; Hassan Soliman | ||||
| Faculty of computers and information systems, I.T dep. Mansoura University, Egypt | ||||
| Abstract | ||||
| Nowadays, sea-land segmentation for remote sensing images has a valuable role in water resources monitoring, maritime safety, and coastal zones management. However, it has faced many challenges such as the complicated distribution of land area, noise, poor contrast between sea and land regions, different weather conditions, the development of sensors, and high-resolution images provide more information. Consequently, there are considerable efforts have been made to develop various methods to overcome these challenges. Therefore, this paper introduces the description of the main steps of the sea-land segmentation procedure and the main characteristics of each step. Also, the paper focuses on the taxonomy of the current sea-land segmentation methods. These methods are broadly categorized into six main groups namely thresholding-based methods, region-based methods, energy minimization-based methods, machine learning-based methods, watershed transformation-based methods, and hybrid methods. Finally, this paper also shows and discusses the common challenges which are facing the sea-land segmentation. Besides, the paper introduces promising future research directions in the sea-land segmentation field. | ||||
| Keywords | ||||
| Sea-land segmentation; Remote Sensing; Coastline/shoreline Extraction; Machine Learning; Energy Minimization | ||||
|
Statistics Article View: 90 PDF Download: 107 |
||||
