Change Detection Based on Low-Level to High-Level Features Integration With Limited Samples
Open Access
- 7 October 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 13 (19391404) , 6260-6276
Abstract
Detailed land cover change in multitemporal images is an important application for earth science. Many techniques have been proposed to solve this problem in different ways. However, accurately identifying changes still remains a challenge due to the difficulties in describing the characteristics of various change categories by using single-level features. In this article, a multilevel feature representation framework was designed to build robust feature set for complex change detection task. First, four different levels of information from low level to high level, including pixel-level, neighborhood-level, object-level, and scene-level features, were extracted. Through the operation of extracting different level features from multitemporal images, the differences between them can be described comprehensively. Second, multilevel features were fused to reduce the dimension and then used as the input for supervised change detector with initial limited labels. Finally, for reducing the labeling cost and improving the change detection results simultaneously, active learning was conducted to select the most informative samples for labeling, and this step together with the previous steps were iteratively conducted to improve the results in each round. Experimental results of three pairs of real remote sensing datasets demonstrated that the proposed framework outperformed the other state-of-the-art methods in terms of accuracy. Moreover, the influences of scene scale for high-level semantic features in the proposed approach on change detection performance were also analyzed and discussed.Keywords
Funding Information
- National Natural Science Foundation of China (41631176)
- Natural Sciences and Engineering Research Council of Canada (2019-05773)
This publication has 76 references indexed in Scilit:
- Object based image analysis for remote sensingISPRS Journal of Photogrammetry and Remote Sensing, 2010
- Characterizing boreal forest wildfire with multi-temporal Landsat and LIDAR dataRemote Sensing of Environment, 2009
- Object‐based change detection using correlation image analysis and image segmentationInternational Journal of Remote Sensing, 2008
- Forest change detection by statistical object-based methodRemote Sensing of Environment, 2006
- Review ArticleDigital change detection methods in ecosystem monitoring: a reviewInternational Journal of Remote Sensing, 2004
- Detection of deforestation and land conversion in Rondônia, Brazil using change detection techniquesInternational Journal of Remote Sensing, 2004
- Mean shift: a robust approach toward feature space analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Automatic analysis of the difference image for unsupervised change detectionIEEE Transactions on Geoscience and Remote Sensing, 2000
- The impact of misregistration on change detectionIEEE Transactions on Geoscience and Remote Sensing, 1992
- Review Article Digital change detection techniques using remotely-sensed dataInternational Journal of Remote Sensing, 1989