Multi-Task Spatiotemporal Neural Networks for Structured Surface Reconstruction

被引:7
作者
Xu, Mingze [1 ]
Fan, Chenyou [1 ]
Paden, John D. [2 ]
Fox, Geoffrey C. [1 ]
Crandall, David J. [1 ]
机构
[1] Indiana Univ, Bloomington, IN 47405 USA
[2] Univ Kansas, Lawrence, KS 66045 USA
来源
2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018) | 2018年
基金
美国国家科学基金会;
关键词
D O I
10.1109/WACV.2018.00144
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep learning methods have surpassed the performance of traditional techniques on a wide range of problems in computer vision, but nearly all of this work has studied consumer photos, where precisely correct output is often not critical. It is less clear how well these techniques may apply on structured prediction problems where fine-grained output with high precision is required, such as in scientific imaging domains. Here we consider the problem of segmenting echogram radar data collected from the polar ice sheets, which is challenging because segmentation boundaries are often very weak and there is a high degree of noise. We propose a multi-task spatiotemporal neural network that combines 3D ConvNets and Recurrent Neural Networks (RNNs) to estimate ice surface boundaries from sequences of tomographic radar images. We show that our model outperforms the state-of-the-art on this problem by (1) avoiding the need for hand-tuned parameters, (2) extracting multiple surfaces (ice-air and ice-bed) simultaneously, (3) requiring less non-visual metadata, and (4) being about 6 times faster.
引用
收藏
页码:1273 / 1282
页数:10
相关论文
共 35 条
[1]  
[Anonymous], 2015, P IEEE C COMP VIS PA
[2]  
[Anonymous], 2014, arXiv
[3]  
[Anonymous], 2016, P 2016 C N AM CHAPT, DOI DOI 10.18653/V1/N16-1181
[4]  
[Anonymous], ARXIV170407754
[5]   Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset [J].
Carreira, Joao ;
Zisserman, Andrew .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :4724-4733
[6]   Automatic Enhancement and Detection of Layering in Radar Sounder Data Based on a Local Scale Hidden Markov Model and the Viterbi Algorithm [J].
Carrer, Leonardo ;
Bruzzone, Lorenzo .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2017, 55 (02) :962-977
[7]  
Chung Joon Son, 2016, ARXIV161105358, P2
[8]  
Chung JY, 2015, PR MACH LEARN RES, V37, P2067
[9]  
Crandall D. J., 2012, INT C PATT REC ICPR
[10]  
Donahue J, 2015, PROC CVPR IEEE, P2625, DOI 10.1109/CVPR.2015.7298878