Automatic Classification of Ice Sheet Subsurface Targets in Radar Sounder Data based on the Capsule Network

Exhaustive investigations of the ice sheet subsurface can be carried out by analyzing the information contained in the huge archives of radar grams acquired by dedicated radar sounder (RS) instruments. In particularly, an automatic segmentation technique enables a fast and objective extraction of ice subsurface target properties on wide areas. Here, an approach which automatically segment radar image at the pixel level using capsule Network was proposed. Our work expands the use of capsule networks to the task of extraction of ice subsurface target in the literature. In this paper, we adopts three kinds of network frameworks for the task of extraction of ice subsurface target. We also discuss the performance of squashing function on the segmentation result. Experimental results on MCoRDS datasets confirm the performanceiveness of our methods.

[1]  Eric Rignot,et al.  A Reconciled Estimate of Ice-Sheet Mass Balance , 2012, Science.

[2]  Geoffrey C. Fox,et al.  Estimating bedrock and surface layer boundaries and confidence intervals in ice sheet radar imagery using MCMC , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[3]  Max Q.-H. Meng,et al.  A deep convolutional neural network for bleeding detection in Wireless Capsule Endoscopy images , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[4]  Geoffrey C. Fox,et al.  Automated Tracking of 2D and 3D Ice Radar Imagery Using Viterbi and TRW-S , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[5]  Lorenzo Bruzzone,et al.  A technique for the automatic estimation of ice thickness and bedrock properties from radar sounder data acquired at Antarctica , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[6]  Lorenzo Bruzzone,et al.  A Model-Based Technique for the Automatic Detection of Earth Continental Ice Subsurface Targets in Radar Sounder Data , 2014, IEEE Geoscience and Remote Sensing Letters.

[7]  Pinar Wennerberg,et al.  Ontology modularization to improve semantic medical image annotation , 2011, J. Biomed. Informatics.

[8]  Ulas Bagci,et al.  Capsules for Object Segmentation , 2018, ArXiv.

[9]  Antoine Rosset,et al.  Comparing features sets for content-based image retrieval in a medical-case database , 2004, SPIE Medical Imaging.

[10]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[11]  Antoine Geissbühler,et al.  A Review of Content{Based Image Retrieval Systems in Medical Applications { Clinical Bene(cid:12)ts and Future Directions , 2022 .

[12]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[13]  Geoffrey C. Fox,et al.  Automatic estimation of ice bottom surfaces from radar imagery , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[14]  Geoffrey Fox,et al.  Layer-finding in radar echograms using probabilistic graphical models , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[15]  Maryam Rahnemoonfar,et al.  Automatic Ice Surface and Bottom Boundaries Estimation in Radar Imagery Based on Level-Set Approach , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[16]  Geoffrey C. Fox,et al.  Deep Hybrid Wavelet Network for Ice Boundary Detection in Radra Imagery , 2018, IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium.

[17]  Arvin Agah,et al.  Automated Polar Ice Thickness Estimation From Radar Imagery , 2010, IEEE Transactions on Image Processing.

[18]  Lorenzo Bruzzone,et al.  A System for the Automatic Classification of Ice Sheet Subsurface Targets in Radar Sounder Data , 2015, IEEE Transactions on Geoscience and Remote Sensing.