期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 16, 期 1, 页码 115-119出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2018.2868880
关键词
Aerial images; convolutional neural networks (CNNs); object segmentation
类别
资金
- ICT Research and Development Program of MSIT/IITP through the Geo-Data Generation and Applicable Service Development Based on Satellite Imagery Data Conversion Platform [2018-0-01573]
- Samsung Research Funding Center of Samsung Electronics [SRFC-IT1502-10]
- Ministry of Trade Industry and Energy
- Ministry of Science and ICT
- Ministry of Health and Welfare Technology [20001533]
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 72400 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).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据