Assessment of Levee Erosion Using Image Processing and Contextual Cueing
Received Date: Jul 13, 2018 / Accepted Date: Jul 23, 2018 / Published Date: Jul 30, 2018
Soil erosion is one of the most severe land degradation problems afflicting many parts of the world where topography of the land is relatively steep. Due to inaccessibility to steep terrain, such as slopes in levees and forested mountains, advanced data processing techniques can be used to identify and assess high risk erosion zones. Unlike existing methods that require human observations, which can be expensive and error-prone, the proposed approach uses a fully automated algorithm to indicate when an area is at risk of erosion; this is accomplished by processing Landsat and aerial images taken using drones. In this paper the image processing algorithm is presented, which can be used to identify the scene of an image by classifying it in one of six categories: levee, mountain, forest, degraded forest, cropland, grassland or orchard. This paper focuses on automatic scene detection using global features with local representations to show the gradient structure of an image. The output of this work counts as a contextual cueing and can be used in erosion assessment, which can be used to predict erosion risks in levees. We also discuss the environmental implications of deferred erosion control in levees.
Keywords: Contextual cueing; Machine learning; Soil erosion; Erosion control; Image processing
Citation: Khazaeli M, Javadpour L, Estrada H, Takbiri-Borujeni A (2018) Assessment of Levee Erosion Using Image Processing and Contextual Cueing. J Ecosys Ecograph 8: 255.
Copyright: © 2018 Khazaeli M, et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Select your language of interest to view the total content in your interested language
Share This Article
- Total views: 1323
- [From(publication date): 0-0 - Dec 04, 2020]
- Breakdown by view type
- HTML page views: 1203
- PDF downloads: 120