Change detection of satellite time series images based on spatial-temporal-spectral features
QIN Le1(), HE Peng2, MA Yuzhong3, LIU Jianqiang4, YANG Bin1()
1. College of Electrical and Information Engineering, Hunan University, Changsha 410082, China 2. School of Mechanical Engineering, University of South China, Hengyang 421000, China 3. Shandong Provincial Institute of Land Surveying and Mapping, Jinan 250014, China 4. Key Laboratory of Space Ocean Remote Sensing and Application, Ministry of Natural Resources, Beijing 100081, China
Compared with common dual-temporal satellite images, satellite time series images contain richer surface information and can alleviate the impact of foreign objects with the same spectrum and the same object with different spectra. Therefore, they play an important role in change detection. However, the change detection methods for satellite time series images are mostly based on pixels and ignore the spatial relationship between pixels and their surroundings. This causes noise in the change detection result. Accordingly, this study proposed a method of change detection based on spatial-temporal-spectral features(CDSTS) for satellite time series images. First, the temporal, spatial (textural and statistical), and spectral features of each pixel were extracted from Landsat time series images using a gray-level co-occurrence matrix and local statistical calculation methods. Then, anomalies of time series features were automatically screened according to the time series performance regularity of each pixel in different bands. These anomalies were then fused with the detection results of the continuous change detection and classification method (CCDC) to obtain high-precision changed/unchanged training sample points. Finally, the SVM classifier was trained using the training sample points and their corresponding spatial-temporal-spectral features for full graph classification. The results show that the CDSTS algorithm significantly outperforms the commonly used time series change detection algorithms CCDC and COLD (continuous monitoring of land disturbance) in terms of change detection precision, with the overall precision improved by 4.8 to 11.7 percentage points.
Le QIN,Peng HE,Yuzhong MA, et al. Change detection of satellite time series images based on spatial-temporal-spectral features[J]. Remote Sensing for Natural Resources,
2022, 34(4): 105-112.
Silveira E M O, Bueno I T, Acerbi-Junior F W, et al. Using spatial features to reduce the impact of seasonality for detecting tropical forest changes from Landsat time series[J]. Remote Sensing, 2018, 10(6):808.
doi: 10.3390/rs10060808
url: http://www.mdpi.com/2072-4292/10/6/808
Zhang L P, Wu C. The status quo and prospects of multi-temporal remote sensing image change detection[J]. Journal of Surveying and Mapping, 2017, 46(10):1447-1459.
Wang Z Y, Li H, Liu Z Z, et al. Satellite image change monitoring based on deep learning algorithm[J]. Computer System Applications, 2020, 29(1):40-48.
Gong M G, Zhan T, Zhang P Z, et al. Superpixel-based difference representation learning for change detection in multispectral remote sensing images[J]. IEEE Transactions on Geoscience and Remote sensing, 2017, 55(5):2658-2673.
doi: 10.1109/TGRS.2017.2650198
url: http://ieeexplore.ieee.org/document/7839934/
Wang Z H, Yao W Y, Tang Q H, et al. Continuous change detection of forest/grassland and cropland in the Loess Plateau of China using all available Landsat data[J]. Remote Sensing, 2018, 10(11):1775.
doi: 10.3390/rs10111775
url: http://www.mdpi.com/2072-4292/10/11/1775
Zhang H, Gong M G, Zhang P Z, et al. Feature-level change detection using deep representation and feature change analysis for multispectral imagery[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(11):1666-1670.
doi: 10.1109/LGRS.2016.2601930
url: http://ieeexplore.ieee.org/document/7559716/
ZENG Hui, REN Huazhong, ZHU Jinshun, GUO Jinxin, YE Xin, TENG Yuanjian, NIE Jing, QIN Qiming. Impacts of the Syrian Civil War on vegetation[J]. Remote Sensing for Natural Resources, 2022, 34(3): 121-128.