Stacked U-Nets for Ground Material Segmentation in Remote Sensing Imagery

被引：45

作者：

Ghosh, Arthita ^{[1
]}

Ehrlich, Max ^{[1
]}

Shah, Sohil ^{[1
]}

Davis, Larry ^{[1
]}

Chellappa, Rama ^{[1
]}

机构：

[1] Univ Maryland, College Pk, MD 20742 USA

来源：

PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) | 2018年

关键词：

CLASSIFICATION;

D O I：

10.1109/CVPRW.2018.00047

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a semantic segmentation algorithm for RGB remote sensing images. Our method is based on the Dilated Stacked U-Nets architecture. This state-of-the-art method has been shown to have good performance in other applications. We perform additional post-processing by blending image tiles and degridding the result. Our method gives competitive results on the DeepGlobe dataset.

引用

页码：252 / 256

页数：5

共 30 条

[1]

[Anonymous], COMMUNICATION

[2]

[Anonymous], 2017, ICCV

[3]

[Anonymous], 2016, PROC CVPR IEEE, DOI DOI 10.1109/CVPR.2016.348

[4]

[Anonymous], 2017, CVPR