气候变化领域集成服务门户(CCPortal): Change detection using deep learning approach with object-based image analysis

CCPortal

DOI	10.1016/j.rse.2021.112308
	Change detection using deep learning approach with object-based image analysis
	Liu T.; Yang L.; Lunga D.
发表日期	2021
ISSN	00344257
卷号	256
英文摘要	In their applications, both deep learning techniques and object-based image analysis (OBIA) have shown better performance separately than conventional methods on change detection tasks. However, efforts to investigate the effect of combining these two techniques for advancing change detection techniques are unexplored in current literature. This study proposes a novel change detection method implementing change feature extraction using convolutional neural networks under an OBIA framework. To demonstrate the effectiveness of our proposed method, we compare the proposed method against benchmark pixel-based counterparts on aerial images for the task of multi-class change detection. To thoroughly assess the performance of our proposed method, this study also for the first time compared three common feature fusion schemes for change detection architecture: concatenation, differencing, and Long Short-Term Memory (LSTM). The proposed method was also tested on simulated misregistered images to evaluate its robustness, a factor that plays an important role in compromising change detection accuracy but has not been investigated for supervised change detection methods in the literature. Finally, the proposed change detection method was also tested using very high resolution (VHR) satellite images for binary class change detection to map an impacted area caused by natural disaster and the result was evaluated using reference data from the Federal Emergency Management Agency (FEMA). With the experimental results from these two sets of experiments, we showed that (1) our proposed method achieved substantially higher accuracy and computational efficiency when compared to pixel-based methods, (2) three feature fusion schemes did not show a significant difference for overall accuracy, (3) our proposed method was robust in image misregistration in both testing and training data, (4) we demonstrate the potential impact of automation to decision making by deploying our method to map a large geographic area affected by a recent natural disaster. © 2021 Elsevier Inc.
英文关键词	Change detection; Deep learning; Feature fusion; OBIA; Pixel-based
语种	英语
scopus关键词	Antennas; Computational efficiency; Convolutional neural networks; Decision making; Deep learning; Disasters; Feature extraction; Learning systems; Object detection; Pixels; Risk management; Conventional methods; Federal Emergency Management Agency; Misregistered images; Object based image analysis; Object based image analysis (OBIA); Pixel-based methods; Supervised change detection; Very high resolution; Long short-term memory; accuracy assessment; aerial photograph; artificial neural network; decision making; detection method; image analysis; learning; natural disaster; performance assessment; pixel
来源期刊	Remote Sensing of Environment
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/178942
作者单位	GeoAI, Geospatial Science and Human Dynamics Division, Oak Ridge National Laboratory, United States; College of Forest Resources and Environmental Science, Michigan Technological University, United States
推荐引用方式 GB/T 7714	Liu T.,Yang L.,Lunga D.. Change detection using deep learning approach with object-based image analysis[J],2021,256.
APA	Liu T.,Yang L.,&Lunga D..(2021).Change detection using deep learning approach with object-based image analysis.Remote Sensing of Environment,256.
MLA	Liu T.,et al."Change detection using deep learning approach with object-based image analysis".Remote Sensing of Environment 256(2021).