Cited 2 time in webofscience Cited 1 time in scopus

Objects Segmentation From High-Resolution Aerial Images Using U-Net With Pyramid Pooling Layers

Title
Objects Segmentation From High-Resolution Aerial Images Using U-Net With Pyramid Pooling Layers
Authors
Kim, Jun HeeYi, Hae YunHong, Seonghwan J.Kim, Se WoongPark, JuhumHwang, Jae YounChoi, Jihwan P.
DGIST Authors
Hwang, Jae YounChoi, Jihwan P.
Issue Date
2019-01
Citation
IEEE Geoscience and Remote Sensing Letters, 16(1), 115-119
Type
Article
Article Type
Article
Author Keyword
Aerial images; convolutional neural networks (CNNs); object segmentation
Keyword
CONVOLUTIONAL NEURAL-NETWORKS; ROAD EXTRACTION; CLASSIFICATION; FEATURES
ISSN
1545-598X
Abstract
Extracting manufactured features such as buildings, roads, and water from aerial images is critical for urban planning, traffic management, and industrial development. Recently, convolutional neural networks (CNNs) have become a popular strategy to capture contextual features automatically. In order to train CNNs, a large training data are required, but it is not straightforward to use free-accessible data sets due to imperfect labeling. To address this issue, we make a large scale of data sets using RGB aerial images and convert them to digital maps with location information such as roads, buildings, and water from the metropolitan area of Seoul in South Korea. The numbers of training and test data are 72 400 and 9600, respectively. Based on our self-made data sets, we design a multiobject segmentation system and propose an algorithm that utilizes pyramid pooling layers (PPLs) to improve U-Net. Test results indicate that U-Net with PPLs, called UNetPPL, learn fine-grained classification maps and outperforms other algorithms of fully convolutional network and U-Net, achieving the mean intersection of union (mIOU) of 79.52 and the pixel accuracy of 87.61% for four types of objects (i.e., building, road, water, and background). © 2004-2012 IEEE.
URI
http://hdl.handle.net/20.500.11750/9365
DOI
10.1109/LGRS.2018.2868880
Publisher
Institute of Electrical and Electronics Engineers Inc.
Related Researcher
  • Author Hwang, Jae Youn MBIS(Multimodal Biomedical Imaging and System) Laboratory
  • Research Interests Multimodal Imaging; High-Frequency Ultrasound Microbeam; Ultrasound Imaging and Analysis; 스마트 헬스케어; Biomedical optical system
Files:
There are no files associated with this item.
Collection:
Department of Information and Communication EngineeringMBIS(Multimodal Biomedical Imaging and System) Laboratory1. Journal Articles
Department of Information and Communication EngineeringNCRG(Networks and Communications Research Group)1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE