Küstenliniendetektion in der Antarktis mit Hilfe von Snakes

Klinger, T.; Ziems, Marcel; Heipke, Christian; Schenke, Hans Werner; Ott, Norbert

doi:10.1127/1432-8364/2011/0095

Cited by 13 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Throughout the year, backscatter characteristics and reflectance spectra of the ice sheet and sea ice surface vary [62,63] (an example is given in Figure S2 in the Supplementary Material). Additional challenges are wind roughening in SAR scenes [26], clouds in optical imagery [64], the spectral similarity of sea ice, fast ice, and shelf ice [65] (see Figure S3 for reflectance spectra of ice, snow, and clouds), and icebergs surrounded by sea ice (mélange) [62]. Ice sheet signatures vary due to different glacier facies and extensive snow melt in summer [66], whereas sea ice appears differently depending on salinity, air content, and temperature [62].…”

Section: Remote Sensing Of Calving Fronts With Optical and Sar Sensormentioning

confidence: 99%

“…Additionally, each satellite image has to be orientated correctly, as glacier flow has to be in the same direction for classification. The only fully automated approach for Antarctica is based on active contours (also known as "snakes") [65]. This technique is based on an initial coastline that is "pulled" toward the new front position based on classification parameters.…”

Section: Automatic Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Remote Sensing of Antarctic Glacier and Ice-Shelf Front Dynamics—A Review

et al. 2018

View full text Add to dashboard Cite

The contribution of Antarctica’s ice sheet to global sea-level rise depends on the very dynamic behavior of glaciers and ice shelves. One important parameter of ice-sheet dynamics is the location of glacier and ice-shelf fronts. Numerous remote sensing studies on Antarctic glacier and ice-shelf front positions exist, but no long-term record on circum-Antarctic front dynamics has been established so far. The article outlines the potential of remote sensing to map, extract, and measure calving front dynamics. Furthermore, this review provides an overview of the spatial and temporal availability of Antarctic calving front observations for the first time. Single measurements are compiled to a circum-Antarctic record of glacier and ice shelf retreat/advance. We find sufficient frontal records for the Antarctic Peninsula and Victoria Land, whereas on the West Antarctic Ice Sheet (WAIS), measurements only concentrate on specific glaciers and ice sheets. Frontal records for the East Antarctic Ice Sheet exist since the 1970s. Studies agree on the general retreat of calving fronts along the Antarctic Peninsula. East Antarctic calving fronts also showed retreating tendencies between 1970s until the early 1990s, but have advanced since the 2000s. Exceptions of this general trend are Victoria Land, Wilkes Land, and the northernmost Dronning Maud Land. For the WAIS, no clear trend in long-term front fluctuations could be identified, as observations of different studies vary in space and time, and fronts highly fluctuate. For further calving front analysis, regular mapping intervals as well as glacier morphology should be included. We propose to exploit current and future developments in Earth observations to create frequent standardized measurements for circum-Antarctic assessments of glacier and ice-shelf front dynamics in regard to ice-sheet mass balance and climate forcing.

show abstract

Section: Remote Sensing Of Calving Fronts With Optical and Sar Sensormentioning

confidence: 99%

Section: Automatic Approachesmentioning

confidence: 99%

Remote Sensing of Antarctic Glacier and Ice-Shelf Front Dynamics—A Review

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The surface texture of glacier tongue and ice mélange can be quite similar, making it difficult to separate both, even for an experienced mapper. Hence, automating the glacier (front) segmentation method is a challenge that has been actively studied in the past decades [3], [4], [5], [6], [7], [8]. Various (semi-)automatic routines were developed based on image classification, edge detection, and edge enhancement.…”

Section: Introductionmentioning

confidence: 99%

“…They performed a multi-temporal analysis on the image and used a Sobel operator and the brightness gradient to detect the edges. Klinger et al [4], on the other hand, formulated a fully automated approach for delineating the calving fronts based on the active contours (also referred to as "snakes") and Nearest Neighbor (NN) classifier [9]. This method takes the initial coastline position and uses the classification parameters and the NN classifier to calculate the extent to which the new front position has been warped.…”

Section: Introductionmentioning

confidence: 99%

How to Get the Most Out of U-Net for Glacier Calving Front Segmentation

Periyasamy

Davari

Seehaus

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The melting of ice sheets and glaciers is one of the main contributors to global sea-level rise. Hence, continuous monitoring of glacier changes and in particular the mapping of positional changes of their calving front is of significant importance. This delineation process, in general, has been carried out manually, which is time-consuming and not feasible for the abundance of available data within the past decade. Automatic delineation of the glacier fronts in synthetic aperture radar (SAR) images can be performed using deep learningbased U-Net models. This article aims to study and survey the components of a U-Net model and optimize the model to get the most out of U-Net for glacier (calving front) segmentation. We trained the U-Net to segment the SAR images of Sjogren-Inlet and Dinsmoore-Bombardier-Edgworth glacier systems on the Antarctica Peninsula region taken by ERS-1/2, Envisat, RadarSAT-1, ALOS, TerraSAR-X, and TanDEM-X missions. The U-Net model was optimized in six aspects. The first two aspects, namely data pre-processing and data augmentation, enhanced the representation of information in the image. The remaining four aspects optimized the feature extraction of U-Net by finding the best-suited loss function, bottleneck, normalization technique, and dropouts for the glacier segmentation task. The optimized U-Net model achieves a dice coefficient score of 0.9378 with a 20% improvement over the baseline U-Net model, which achieved a score of 0.7377. This segmentation result is further post-processed to delineate the calving front. The optimized U-Net model shows 23% improvement in the glacier front delineation compared to the baseline model.

show abstract

“…Different methods for delineating coastlines based on optical images have been proposed in the past few decades. An approach for automatic coastline detection based on snakes (parametric active contours) has been applied to Landsat images of Antarctica [5]. A new approach combining histogram thresholding and band ratio has been applied to extract the Urmia Lake coastlines from Landsat-7 Enhanced Thematic Mapper Plus (ETM+) and Thematic Mapper (TM) images [6].…”

Section: Introductionmentioning

confidence: 99%

Automatically Extracted Antarctic Coastline Using Remotely-Sensed Data: An Update

Zhang

Shokr

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

The temporal and spatial variability of the Antarctic coastline is a clear indicator of change in extent and mass balance of ice sheets and shelves. In this study, the Canny edge detector was utilized to automatically extract high-resolution information of the Antarctic coastline for 2005, 2010, and 2017, based on optical and microwave satellite data. In order to improve the accuracy of the extracted coastlines, we developed the Canny algorithm by automatically calculating the local low and high thresholds via the intensity histogram of each image to derive thresholds to distinguish ice sheet from water. A visual comparison between extracted coastlines and mosaics from remote sensing images shows good agreement. In addition, comparing manually extracted coastline, based on prior knowledge, the accuracy of planimetric position of automated extraction is better than two pixels of Landsat images (30 m resolution). Our study shows that the percentage of deviation (<100 m) between automatically and manually extracted coastlines in nine areas around the Antarctica is 92.32%, and the mean deviation is 38.15 m. Our results reveal that the length of coastline around Antarctica increased from 35,114 km in 2005 to 35,281 km in 2010, and again to 35,672 km in 2017. Meanwhile, the total area of the Antarctica varied slightly from 1.3618 × 10 7 km 2 (2005) to 1.3537 × 10 7 km 2 (2010) and 1.3657 × 10 7 km 2 (2017). We have found that the decline of the Antarctic area between 2005 and 2010 is related to the breakup of some individual ice shelves, mainly in the Antarctic Peninsula and off East Antarctica. We present a detailed analysis of the temporal and spatial change of coastline and area change for the six ice shelves that exhibited the largest change in the last decade. The largest area change (a loss of 4836 km 2 ) occurred at the Wilkins Ice Shelf between 2005 and 2010.

show abstract

Küstenliniendetektion in der Antarktis mit Hilfe von Snakes

Cited by 13 publications

References 16 publications

Remote Sensing of Antarctic Glacier and Ice-Shelf Front Dynamics—A Review

Remote Sensing of Antarctic Glacier and Ice-Shelf Front Dynamics—A Review

How to Get the Most Out of U-Net for Glacier Calving Front Segmentation

Automatically Extracted Antarctic Coastline Using Remotely-Sensed Data: An Update

Contact Info

Product

Resources

About