Deep learning for superpixel-based classification of remote sensing images
Recently deep learning-based methods have demonstrated excellent performance on different artificial-intelligence tasks. Even though, in the last years, several related works are found in the literature in the remote sensing field, a small percentage of them address the classification problem. These...
Lưu vào:
Tác giả chính: | |
---|---|
Định dạng: | BB |
Ngôn ngữ: | eng |
Thông tin xuất bản: |
2020
|
Chủ đề: | |
Truy cập trực tuyến: | http://tailieuso.tlu.edu.vn/handle/DHTL/4573 |
Từ khóa: |
Thêm từ khóa bạn đọc
Không có từ khóa, Hãy là người đầu tiên gắn từ khóa cho biểu ghi này!
|
id |
oai:localhost:DHTL-4573 |
---|---|
record_format |
dspace |
spelling |
oai:localhost:DHTL-45732020-03-30T02:14:14Z Deep learning for superpixel-based classification of remote sensing images Gonzalo-Martin, C Superpixels Remote Sensing Image Classification Convolutional Neural Networks Recently deep learning-based methods have demonstrated excellent performance on different artificial-intelligence tasks. Even though, in the last years, several related works are found in the literature in the remote sensing field, a small percentage of them address the classification problem. These works propose schemes based on image patches to perform pixel-based image classification. Due to the typical remote sensing image size, the main drawback of these schemes is the time required by the window-sliding process implied in them. In this work, we propose a strategy to reduce the time spent on the classification of a new image through the use of superpixel segmentation. Several experiments using CNNs trained with different sizes of patches and superpixels have been performed on the ISPRS semantic labeling benchmark. Obtained results show that while the accuracy of the classification carried out by using superpixels is similar to the results generated by pixel-based approach, the expended time is dramatically decreased by means of reducing the number of elements to label. https://proceedings.utwente.nl/401/1/Gonzalo-Mart%C2%A1n-Deep%20Learning%20for%20Superpixel-based%20Classification-98.pdf 2020-02-18T02:25:55Z 2020-02-18T02:25:55Z 2016 20181226085413.0 130605s2016 BB In: GEOBIA 2016 : Solutions and Synergies., 14 September 2016 - 16 September 2016, University of Twente Faculty of Geo-Information and Earth Observation (ITC) . http://tailieuso.tlu.edu.vn/handle/DHTL/4573 eng |
institution |
Trường Đại học Thủy Lợi |
collection |
DSpace |
language |
eng |
topic |
Superpixels Remote Sensing Image Classification Convolutional Neural Networks |
spellingShingle |
Superpixels Remote Sensing Image Classification Convolutional Neural Networks Gonzalo-Martin, C Deep learning for superpixel-based classification of remote sensing images |
description |
Recently deep learning-based methods have demonstrated excellent performance on different artificial-intelligence tasks. Even though, in the last years, several related works are found in the literature in the remote sensing field, a small percentage of them address the classification problem. These works propose schemes based on image patches to perform pixel-based image classification. Due to the typical remote sensing image size, the main drawback of these schemes is the time required by the window-sliding process implied in them. In this work, we propose a strategy to reduce the time spent on the classification of a new image through the use of superpixel segmentation. Several experiments using CNNs trained with different sizes of patches and superpixels have been performed on the ISPRS semantic labeling benchmark. Obtained results show that while the accuracy of the classification carried out by using superpixels is similar to the results generated by pixel-based approach, the expended time is dramatically decreased by means of reducing the number of elements to label. |
format |
BB |
author |
Gonzalo-Martin, C |
author_facet |
Gonzalo-Martin, C |
author_sort |
Gonzalo-Martin, C |
title |
Deep learning for superpixel-based classification of remote sensing images |
title_short |
Deep learning for superpixel-based classification of remote sensing images |
title_full |
Deep learning for superpixel-based classification of remote sensing images |
title_fullStr |
Deep learning for superpixel-based classification of remote sensing images |
title_full_unstemmed |
Deep learning for superpixel-based classification of remote sensing images |
title_sort |
deep learning for superpixel-based classification of remote sensing images |
publishDate |
2020 |
url |
http://tailieuso.tlu.edu.vn/handle/DHTL/4573 |
work_keys_str_mv |
AT gonzalomartinc deeplearningforsuperpixelbasedclassificationofremotesensingimages |
_version_ |
1768590163181568000 |