Object-based detection of Arctic sea ice and melt ponds using high spatial resolution aerial photographs

Miao, Xin; Xie, Hongjie; Ackley, Stephen F.; Perovich, Donald K.; Ke, Changquing

doi:10.1016/j.coldregions.2015.06.014

Cited by 42 publications

(47 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of shadow extractions is assessed through a total of 178 ground reference samples of four general classes (see Table I) that have various light conditions. Shadow shows a high user's accuracy of 88.9% and producer's accuracy of 91.4% [14]. The classification uncertainty…”

Section: A Shadow Classificationmentioning

confidence: 99%

“…The associated independently measured GPS positions and altitude were geotagged to the aerial photographs. More details of this flight mission can be found in [14] and [15].…”

Section: Study Area and Aerial Image Preprocessingmentioning

confidence: 99%

“…boundaries. Therefore, we adopt an object-based classification approach to identify shadows [14]. After image segmentation, a total of 13 spectral, texture, and spatial attributes are imported into the random forest classifier to detect shadows.…”

Section: A Shadow Detectionmentioning

confidence: 99%

“…After image segmentation, a total of 13 spectral, texture, and spatial attributes are imported into the random forest classifier to detect shadows. Interested readers are referred to [14] for details about the method.…”

Section: A Shadow Detectionmentioning

confidence: 99%

“…These shadow detection methods were either manual or semimanual for a limited number of images. In our previous work, we developed a scheme of object-based sea ice, melt pond, and shadow classification from aerial photographs [14]. This letter aims to accomplish the following: 1) to extract reliable sea ice ridge attributes such as normalized ridge density, average ridge length, and average ridge height through local solar illumination geometry and 2) to provide quantitative uncertainty analysis for derived ridge attributes.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Object-Based Arctic Sea Ice Ridge Detection From High-Spatial-Resolution Imagery

Miao¹,

Xie

Ackley

et al. 2016

IEEE Geosci. Remote Sensing Lett.

Self Cite

View full text Add to dashboard Cite

High-spatial-resolution aerial photographs can provide detailed distribution of sea ice features. However, very few studies have ever considered shadows on the photographs for sea ice detection. In this letter, sea ice shadows, retrieved from 163 selected aerial photographs acquired on July 26, 2010, in a marginal-ice-zone area near Barrow, Alaska, utilizing an objectbased classification scheme, are used to estimate the sea ice ridge attributes through local solar illumination geometry. The photograph-averaged ridge frequency (354.6-8908.7 km −2 ), length (1.22-10.33 m), and height (0.15-1.29 m) are obtained from the 163 photographs using batch processing. This letter provides an important batch processing method for ridge detection and ridge attribute retrieval from the high-resolution imagery of sea ice.Index Terms-Aerial photography, pressure ridge, shadow, sea ice.

show abstract

Section: A Shadow Classificationmentioning

confidence: 99%

“…The associated independently measured GPS positions and altitude were geotagged to the aerial photographs. More details of this flight mission can be found in [14] and [15].…”

Section: Study Area and Aerial Image Preprocessingmentioning

confidence: 99%

Section: A Shadow Detectionmentioning

confidence: 99%

Section: A Shadow Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Object-Based Arctic Sea Ice Ridge Detection From High-Spatial-Resolution Imagery

Miao¹,

Xie

Ackley

et al. 2016

IEEE Geosci. Remote Sensing Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

Observations of the summer breakup of an Arctic sea ice cover

Arntsen

Song

Perovich

et al. 2015

Geophysical Research Letters

Self Cite

View full text Add to dashboard Cite

The Arctic sea ice cover evolves dramatically through the summer melt season. Floe size distribution (FSD) is a critical parameter used to examine this change as the ice cover transitions from large rectilinear plates in spring to an ensemble of discrete rounded floes by midsummer. The FSD at a given time impacts the dynamic and thermodynamic behavior of the ice cover. Focusing on the seasonal marginal ice zone in the Beaufort and Chukchi Seas from May to September 2014, we present qualitative and quantitative results derived from National Technical Means high‐resolution imagery and supported by ice mass balance buoy data. Results indicate that as melt accelerates, floe breaking pattern, and therefore FSD, is heavily influenced by the distribution of melt ponds. Discrete element model results using morphological conditions derived from analyzed satellite imagery confirmed that breaking occurs along ponds and perpendicular to applied stress.

show abstract

Classification of Arctic Sea Ice Surface Types During the Melt Season in High-Resolution IceBridge Imagery

Buckley

Farrell

Duncan

et al. 2019

Preprint

View full text Add to dashboard Cite

Object-based detection of Arctic sea ice and melt ponds using high spatial resolution aerial photographs

Cited by 42 publications

References 35 publications

Object-Based Arctic Sea Ice Ridge Detection From High-Spatial-Resolution Imagery

Object-Based Arctic Sea Ice Ridge Detection From High-Spatial-Resolution Imagery

Observations of the summer breakup of an Arctic sea ice cover

Classification of Arctic Sea Ice Surface Types During the Melt Season in High-Resolution IceBridge Imagery

Contact Info

Product

Resources

About