An Efficient Tool for Automatic Delimitation of Moroccan Coastal Upwelling Using SST Images

Abstract

An unsupervised classification method is developed for the coarse segmentation of Moroccan coastal upwelling using the Sea Surface Temperature (SST) satellite images. The algorithm is started with the generation of c-partitioned labeled image using Otsu's method for the purpose of finding regions of homogenous temperatures. Then two well-known validity indices are used to select the c-partition which best reproduce the shape of upwelling area. A region-growing algorithm is developed that is used to remove the noisy structures in the offshore waters not belonging to the upwelling area. The algorithm is used to provide a seasonal variability of upwelling activity in the southern Moroccan Atlantic coast using 70 SST images of the years 2007 and 2008. The performance of the proposed methodology has been validated by an oceanographer, showing its effectiveness for automatic delimitation of Moroccan upwelling region.

Physical and Biological Satellite Observations of the Northwest African Upwelling: Spatial Extent and Dynamics

“…The goal of this article is to develop an upwelling segmentation method that allows the identification and extraction of the upwelling areas from the SST and CHL a images. First, the method seeks to overcome the problems encountered when applying the method developed in [14] over the SST images, and to provide an upwelling segmentation from biological observations. The approach developed in [14] consists of two steps: first, applying a clustering algorithm over the SST images with a number of clusters c = 2 in order to separate the upwelling cold waters from the warmer ones offshore and then labeling the cluster with the minimal centroid as upwelling waters.…”

“…They used the fuzzy c-means (FCM) algorithm together with a threshold procedure to provide an automatic segmentation and extraction of upwelling regions on the SST images. This last approach has been modified and improved in [12]- [14] and applied to the southern part of the Moroccan Atlantic coast.…”

“…Various techniques have been proposed for the subject of the upwelling detection and delimitation for different upwelling ecosystems. However, none of the previous work has successfully been able to delineate the central part of the Canary Upwelling Ecosystem from the SST images [12]- [14], [24], [25]. The proposed method is capable of extracting upwelling regions from the SST and CHL a images.…”

An improved method for accurate computation of coastal upwelling index using Sea Surface Temperature Images

“…The Region-growing algorithm is a simple region-based image segmentation method that examines neighboring pixels of initial seed points and determines whether the adjacent pixel should be added to the region [3] [16]. This method aims at grouping a set of pixels according to homogeneity and adjacency criteria [13].…”

Vision-based line detection for underwater inspection of breakwater construction using an ROV

“…The basic idea of the Otsu's approach is to find the optimum threshold by maximizing between-class variance in the image histogram. Because of simplicity and effectiveness in automatic thresholding, the Otsu method has been widely used in a variety of applications such as coastal zone monitoring (Kuleli et al, 2011), geoscience and remote sensing (Liu et al, 2011;Tamim et al, 2015;Zhang et al, 2012), document retrieval (Moghaddam and Cheriet, 2012), biomedical (Huang et al, 2012;Sathya and Kayalvizhi, 2011), etc.…”