Advanced

A novel change detection approach for multi-temporal high-resolution remote sensing images based on rotation forest and coarse-to-fine uncertainty analyses

Feng, Wenqing; Sui, Haigang; Tu, Jihui; Huang, Weiming LU ; Xu, Chuan and Sun, Kaimin (2018) In Remote Sensing 10(7).
Abstract

In the process of object-based change detection (OBCD), scale is a significant factor related to extraction and analyses of subsequent change data. To address this problem, this paper describes an object-based approach to urban area change detection (CD) using rotation forest (RoF) and coarse-to-fine uncertainty analyses of multi-temporal high-resolution remote sensing images. First, highly homogeneous objects with consistent spatial positions are identified through vector-raster integration and multi-scale fine segmentation. The multi-temporal images are stacked and segmented under the constraints of a historical land use vector map using a series of optimal segmentation scales, ranging from coarse to fine. Second, neighborhood... (More)

In the process of object-based change detection (OBCD), scale is a significant factor related to extraction and analyses of subsequent change data. To address this problem, this paper describes an object-based approach to urban area change detection (CD) using rotation forest (RoF) and coarse-to-fine uncertainty analyses of multi-temporal high-resolution remote sensing images. First, highly homogeneous objects with consistent spatial positions are identified through vector-raster integration and multi-scale fine segmentation. The multi-temporal images are stacked and segmented under the constraints of a historical land use vector map using a series of optimal segmentation scales, ranging from coarse to fine. Second, neighborhood correlation image analyses are performed to highlight pixels with high probabilities of being changed or unchanged, which can be used as a prerequisite for object-based analyses. Third, based on the coarse-to-fine segmentation and pixel-based pre-classification results, change possibilities are calculated for various objects. Furthermore, changed and unchanged objects identified at different scales are automatically selected to serve as training samples. The spectral and texture features of each object are extracted. Finally, uncertain objects are classified using the RoF classifier. Multi-scale classification results are combined using a majority voting rule to generate the final CD results. In experiments using two pairs of real high-resolution remote sensing datasets, our proposed approach outperformed existing methods in terms of CD accuracy, verifying its feasibility and effectiveness.

(Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Change detection, Features, Majority voting, Neighborhood correlation image analyses, Rotation forest, Scale, Segmentation
in
Remote Sensing
volume
10
issue
7
publisher
MDPI AG
external identifiers
  • scopus:85050493392
ISSN
2072-4292
DOI
10.3390/rs10071015
language
English
LU publication?
yes
id
a7a8095f-857c-4f2e-b2a5-14b63dd8cdea
date added to LUP
2018-09-07 14:40:58
date last changed
2019-07-16 03:55:19
@article{a7a8095f-857c-4f2e-b2a5-14b63dd8cdea,
  abstract     = {<p>In the process of object-based change detection (OBCD), scale is a significant factor related to extraction and analyses of subsequent change data. To address this problem, this paper describes an object-based approach to urban area change detection (CD) using rotation forest (RoF) and coarse-to-fine uncertainty analyses of multi-temporal high-resolution remote sensing images. First, highly homogeneous objects with consistent spatial positions are identified through vector-raster integration and multi-scale fine segmentation. The multi-temporal images are stacked and segmented under the constraints of a historical land use vector map using a series of optimal segmentation scales, ranging from coarse to fine. Second, neighborhood correlation image analyses are performed to highlight pixels with high probabilities of being changed or unchanged, which can be used as a prerequisite for object-based analyses. Third, based on the coarse-to-fine segmentation and pixel-based pre-classification results, change possibilities are calculated for various objects. Furthermore, changed and unchanged objects identified at different scales are automatically selected to serve as training samples. The spectral and texture features of each object are extracted. Finally, uncertain objects are classified using the RoF classifier. Multi-scale classification results are combined using a majority voting rule to generate the final CD results. In experiments using two pairs of real high-resolution remote sensing datasets, our proposed approach outperformed existing methods in terms of CD accuracy, verifying its feasibility and effectiveness.</p>},
  articleno    = {1015},
  author       = {Feng, Wenqing and Sui, Haigang and Tu, Jihui and Huang, Weiming and Xu, Chuan and Sun, Kaimin},
  issn         = {2072-4292},
  keyword      = {Change detection,Features,Majority voting,Neighborhood correlation image analyses,Rotation forest,Scale,Segmentation},
  language     = {eng},
  month        = {07},
  number       = {7},
  publisher    = {MDPI AG},
  series       = {Remote Sensing},
  title        = {A novel change detection approach for multi-temporal high-resolution remote sensing images based on rotation forest and coarse-to-fine uncertainty analyses},
  url          = {http://dx.doi.org/10.3390/rs10071015},
  volume       = {10},
  year         = {2018},
}