High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level
High-resolution remote sensing images are abundant in texture information, and the detection method of the change of pixel-level mainly analyzes the spectral information of the image, which has certain limitations. In this paper, a high-resolution remote sensing image change detection method combini...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8736213/ |
id |
doaj-9c5385b8850142028cb82820544794f7 |
---|---|
record_format |
Article |
spelling |
doaj-9c5385b8850142028cb82820544794f72021-03-29T23:28:29ZengIEEEIEEE Access2169-35362019-01-017789097891810.1109/ACCESS.2019.29228398736213High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-LevelLu Xu0Weipeng Jing1https://orcid.org/0000-0001-7933-6946Houbing Song2https://orcid.org/0000-0003-2631-9223Guangsheng Chen3College of Information and Computer Engineering, Northeast Forestry University, Harbin, ChinaCollege of Information and Computer Engineering, Northeast Forestry University, Harbin, ChinaDepartment of Electrical, Computer, Software, and Systems Engineering, Embry-Riddle Aeronautical University, Daytona Beach, FL, USACollege of Information and Computer Engineering, Northeast Forestry University, Harbin, ChinaHigh-resolution remote sensing images are abundant in texture information, and the detection method of the change of pixel-level mainly analyzes the spectral information of the image, which has certain limitations. In this paper, a high-resolution remote sensing image change detection method combining pixel and object levels is proposed to solve the problem that many pepper and salt phenomenon and false detection in the change detection of pixel-level and object-level change detection method are cumbersome for image segmentation process. We integrate the multi-dimensional features of high-resolution remote sensing images and use random forest classifiers to classify to obtain the pixel-level change detection results. Then, we use the improved U-net network to semantically segment the post-phase remote sensing image to obtain the image object segmentation result. Finally, the consequences of pixel-level change detection and image object segmentation result are fused to obtain the image changing area and the unchanging area. The experimental results demonstrate that the algorithm has a higher accuracy rate and detection precision.https://ieeexplore.ieee.org/document/8736213/Change detectionrandom forestremote sensingsemantic segmentationU-net |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Lu Xu Weipeng Jing Houbing Song Guangsheng Chen |
spellingShingle |
Lu Xu Weipeng Jing Houbing Song Guangsheng Chen High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level IEEE Access Change detection random forest remote sensing semantic segmentation U-net |
author_facet |
Lu Xu Weipeng Jing Houbing Song Guangsheng Chen |
author_sort |
Lu Xu |
title |
High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level |
title_short |
High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level |
title_full |
High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level |
title_fullStr |
High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level |
title_full_unstemmed |
High-Resolution Remote Sensing Image Change Detection Combined With Pixel-Level and Object-Level |
title_sort |
high-resolution remote sensing image change detection combined with pixel-level and object-level |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
High-resolution remote sensing images are abundant in texture information, and the detection method of the change of pixel-level mainly analyzes the spectral information of the image, which has certain limitations. In this paper, a high-resolution remote sensing image change detection method combining pixel and object levels is proposed to solve the problem that many pepper and salt phenomenon and false detection in the change detection of pixel-level and object-level change detection method are cumbersome for image segmentation process. We integrate the multi-dimensional features of high-resolution remote sensing images and use random forest classifiers to classify to obtain the pixel-level change detection results. Then, we use the improved U-net network to semantically segment the post-phase remote sensing image to obtain the image object segmentation result. Finally, the consequences of pixel-level change detection and image object segmentation result are fused to obtain the image changing area and the unchanging area. The experimental results demonstrate that the algorithm has a higher accuracy rate and detection precision. |
topic |
Change detection random forest remote sensing semantic segmentation U-net |
url |
https://ieeexplore.ieee.org/document/8736213/ |
work_keys_str_mv |
AT luxu highresolutionremotesensingimagechangedetectioncombinedwithpixellevelandobjectlevel AT weipengjing highresolutionremotesensingimagechangedetectioncombinedwithpixellevelandobjectlevel AT houbingsong highresolutionremotesensingimagechangedetectioncombinedwithpixellevelandobjectlevel AT guangshengchen highresolutionremotesensingimagechangedetectioncombinedwithpixellevelandobjectlevel |
_version_ |
1724189451045830656 |