Narrow River Extraction From SAR Images Using Exogenous Information

Abstract

Monitoring of rivers is of major scientific and societal importance, due to the crucial resource they provide to human activities and the threats caused by flood events. Rapid revisit Synthetic Aperture Radar (SAR) sensors such as Sentinel-1 or the future Surface Water and Ocean Topography (SWOT) mission are indispensable tools to achieve all-weather monitoring of water bodies at the global scale. Unfortunately, at the spatial resolution of these sensors, the extraction of narrow rivers is extremely difficult without resorting to exogenous knowledge. This paper introduces an innovative river segmentation method from SAR images using a priori databases such as the Global River Widths from Landsat (GRWL). First, a recently proposed linear structure detector is used to produce a map of likely line structures. Then, a limited number of nodes along the prior river centerline are extracted from the exogenous database, and used to reconstruct the full river centerline from the detection map. Finally, an innovative conditional random field approach is used to delineate accurately the river extent around its centerline. The proposed method has been tested on several Sentinel-1 images and on simulated SWOT data. Both visual and qualitative evaluations demonstrate its efficiency.

Despeckling Sentinel-1 GRD Images by Deep-Learning and Application to Narrow River Segmentation

“…The goal of the second step of our method is to get an accurate segmentation of the rivers in the image. To achieve this, we adapted a framework [2] that uses first a linear features detector and exogenous information to retrieve the river centerline. Then the river is segmented around the centerline using a specific conditional random field (CRF) approach.The exogeneous information on the river consists of control points and can be found in prior databases such as Global River Widths from Landsat (GRWL) [5] in which the rivers centerlines are stored as sets of nodes.…”

“…This stage is identical to its counterpart in [2] and consists in detecting the centerline as the least-cost path between two nodes that belong to the same river in the exogenous database and are a few kilometers apart. The cost array is computed from the previously computed linear features detector response using the same parameter N pow = 10, as for noisy GRD images and with D max being the maximum value of D in the image.…”

“…The last stage of our method consists in segmenting the river around the centerline obtained in the previous step, using a conditional random field (CRF) approach adapted from [2], with a simplified expression. The CRF energy is defined as the sum of a data term, a term that forces centerline pixel to be classified as water, and a regularization term that all depend on the class (land or river) of each pixel.…”

“…The data term depends on the denoised image intensity I and on the class: for the river class, the data term is quadratic: (log(I) − R log ) 2 , where R log is the estimated log-reflectivity of the water. This distribution accounts for the fluctuations of river pixel intensities caused by the remaining speckle, if any, and also for the fluctuations of the river reflectivities caused by varying roughness of the water surface.…”

“…One can ask whether such a denoising step can be beneficial even for approaches that have been designed to be robust to speckle noise. In this paper, we present a modified river detection method that is based on a first denoising step adapted from SAR2SAR [1] and a detection performed on the denoised images using a method that uses exogenous information to guide the river detection [2]. Section 2 presents the rationale behind the proposed method, experimental results are outlined in section 3.…”