Automated Tracking of 2D and 3D Ice Radar Imagery Using Viterbi and TRW-S

Berger, Victor; Xu, Mingze; Chu, Shane; Crandall, David J.; Paden, John; Fox, Geoffrey

doi:10.1109/igarss.2018.8519411

Cited by 8 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another critical area of innovation in radioglaciological data processing and analysis is automatic methods for radargram image interpretation. These include algorithms for layer tracking, bed and surface mapping and basal feature categorization (Sime and others, 2011;Crandall and others, 2012;Ferro and Bruzzone, 2012; Ilisei and Bruzzone, 2015;Panton and Karlsson, 2015;Carrer and Bruzzone, 2016;Rahnemoonfar and others, 2017;Berger and others, 2018;Donini and others, 2019). Success of these approaches is a prerequisite to be able to cope efficiently with the data volume of future surveys and effectively exploit their information content.…”

Section: Processingmentioning

confidence: 99%

Five decades of radioglaciology

et al. 2020

View full text Add to dashboard Cite

Radar sounding is a powerful geophysical approach for characterizing the subsurface conditions of terrestrial and planetary ice masses at local to global scales. As a result, a wide array of orbital, airborne, ground-based, and in situ instruments, platforms and data analysis approaches for radioglaciology have been developed, applied or proposed. Terrestrially, airborne radar sounding has been used in glaciology to observe ice thickness, basal topography and englacial layers for five decades. More recently, radar sounding data have also been exploited to estimate the extent and configuration of subglacial water, the geometry of subglacial bedforms and the subglacial and englacial thermal states of ice sheets. Planetary radar sounders have observed, or are planned to observe, the subsurfaces and near-surfaces of Mars, Earth's Moon, comets and the icy moons of Jupiter. In this review paper, and the thematic issue of the Annals of Glaciology on ‘Five decades of radioglaciology’ to which it belongs, we present recent advances in the fields of radar systems, missions, signal processing, data analysis, modeling and scientific interpretation. Our review presents progress in these fields since the last radio-glaciological Annals of Glaciology issue of 2014, the context of their history and future prospects.

show abstract

Section: Processingmentioning

confidence: 99%

Five decades of radioglaciology

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Lee et al [19] proposed a more accurate and efficient method by using Gibbs sampling from a joint distribution over all candidate layers, while Carrer and Bruzzone [4] further re-duced the computational cost with a divide-and-conquer strategy. Xu et al [28] first extended the work to the 3D domain and estimate 3D ice surfaces using a Markov Random Field (MRF), and Berger et al [1] followed up with better cost functions that incorporate domain-specific priors into the cost computation and provide more specific characterizations of the ice sheets as additional evidence. Kamangir et al [14] detected ice boundaries using wavelet transform with convolutional neural networks.…”

Section: Related Workmentioning

confidence: 99%

“…where N +1 is the true number of layers (N is the number of gaps between layers), and l indicates the number of thresholds (we use 10, t l = [1,4,7,10,13,16,19,22,25,27], which assume 300 × 256 input images).…”

Section: Evaluation Metricsmentioning

confidence: 99%

Deep Tiered Image Segmentation For Detecting Internal Ice Layers in Radar Imagery

Wang¹,

Xu²,

Paden³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Understanding the structure of the ice at the Earth's poles is important for modeling how global warming will impact polar ice and, in turn, the Earth's climate. Groundpenetrating radar is able to collect observations of the internal structure of snow and ice, but the process of manually labeling these observations with layer boundaries is slow and laborious. Recent work has developed automatic techniques for finding ice-bed boundaries, but finding internal boundaries is much more challenging because the number of layers is unknown and the layers can disappear, reappear, merge, and split. In this paper, we propose a novel deep neural network-based model for solving a general class of tiered segmentation problems. We then apply it to detecting internal layers in polar ice, and evaluate on a large-scale dataset of polar ice radar data with humanlabeled annotations as ground truth.

show abstract

“…Newer work in this field utilizes image processing, computer vision, and deep learning techniques to automatically or semi-automatically determine ice surface and bottom boundaries from echograms [1][2][3][4][5][6][7]. Gifford et al [1] employs both the edge-based and active contour methodologies to automate the task of locating polar ice and bedrock layers from airborne radar data acquired over Greenland and Antarctica.…”

Section: Introductionmentioning

confidence: 99%

“…Xu et al [6] revisits this issue and uses a tree-reweighted message passing (TRW) technique, which first generates a seed surface subject with a set of constraints, and then incorporates additional sources of evidence to refine it via discrete energy minimization. Berger et al [7] further improves upon the method of Xu et al [6] by incorporating additional domain-specific knowledge into the cost functions and modeling algorithms.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Classification Network for Ice Sheet Subsurface Targets in Radar Imagery

Yuan-hu

Lang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Sea level rise, caused by the accelerated melting of glaciers in Greenland and Antarctica in recent decades, has become a major concern in the scientific, environmental, and political arenas. A comprehensive study of the properties of the ice subsurface targets is particularly important for a reliable analysis of their future evolution. Newer deep learning techniques greatly outperform the traditional techniques based on hand-crafted feature engineering. Therefore, we propose an efficient end-to-end network for the automatic classification of ice sheet subsurface targets in radar imagery. Our network uses bilateral filtering to reduce noise and consists of ResNet module, improved Atrous Spatial Pyramid Pooling (ASPP) module, and decoder module. With radar images provided by the Center of Remote Sensing of Ice Sheets (CReSIS) from 2009 to 2011 as our training and testing data, experimental results confirm the robustness and effectiveness of the proposed network in radargram.

show abstract

Automated Tracking of 2D and 3D Ice Radar Imagery Using Viterbi and TRW-S

Cited by 8 publications

References 9 publications

Five decades of radioglaciology

Five decades of radioglaciology

Deep Tiered Image Segmentation For Detecting Internal Ice Layers in Radar Imagery

End-to-End Classification Network for Ice Sheet Subsurface Targets in Radar Imagery

Contact Info

Product

Resources

About