ABSTRACT
With the rapid increasing of urban areas, impervious surfaces play an important role as an indicator of urban development and the change of the city's environment. Due to the wide variety of materials of impervious surfaces, it is an arduous task to draw impervious surfaces. Fortunately, the Sentinel-2 satellite provides accessible multi-spectral imagery with a high spatial resolution to solve this problem. However, huge volumes of Sentinel-2 imagery produced every 5 days need a fast and accurate classifier for impervious mapping. In this paper, a novel spectral spatial residual convolution neural network (SSRCNN) has been designed to deal with the massive imagery for impervious classification with high speed and accuracy. Compared to typical algorithms, deep learning methods are more suitable in this task. The CNN demonstrates great success in image classification. In this study, a comparison between CNN and SSRCNN has been done, and the result shows that the SSRCNN model outperforms the CNN model by about 0.74 percent in terms of overall classification accuracy (OA). The use of the NVIDIA 1080Ti graphics processing unit (GPU) can improve the computational efficiency of the SSRCNN model.
- Hu, X., & Weng, Q. 2009. Estimating impervious surfaces from medium spatial resolution imagery using the self-organizing map and multi-layer perceptron neural networks. Remote Sensing of Environment, 113(10), 2089--2102.Google ScholarCross Ref
- Panshi, W., Chengquan, H., & Eric, B. D. C. 2017. Mapping 2000-2010 impervious surface change in india using global land survey landsat data. Remote Sensing, 9(4), 366-.Google ScholarCross Ref
- Zhang, H., Lin, H., & Wang, Y. 2018. A new scheme for urban impervious surface classification from sar images. ISPRS Journal of Photogrammetry and Remote Sensing, 139, 103--118.Google ScholarCross Ref
- Xu, R., Liu, J., & Xu, J. 2018. Extraction of high-precision urban impervious surfaces from sentinel-2 multispectral imagery via modified linear spectral mixture analysis. Sensors, 18(9).Google Scholar
- Weng, Q. (2012). Remote sensing of impervious surfaces in the urban areas: requirements, methods, and trends. Remote Sensing of Environment, 117(none), 0--49.Google Scholar
- Guo, W., Lu, D., & Kuang, W. 2017. Improving fractional impervious surface mapping performance through combination of dmsp-ols and modis ndvi data. Remote Sensing, 9(4).Google Scholar
- Sun, G., Chen, X., Jia, X., Yao, Y., & Wang, Z. 2017. Combinational build-up index (cbi) for effective impervious surface mapping in urban areas. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 9(5), 2081--2092.Google ScholarCross Ref
- Zhongchang, S., Cuizhen, W., Huadong, G., & Ranran, S. 2017. A modified normalized difference impervious surface index (mndisi) for automatic urban mapping from landsat imagery. Remote Sensing, 9(9), 942-.Google ScholarCross Ref
- Binaghi, E., Madella, P., Grazia Montesano, M., & Rampini, A. (1997). Fuzzy contextual classification of multisource remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 35(2), 0--340.Google ScholarCross Ref
- Lei, Z., Ming, Z., & Yao, Y. (2018). Mapping seasonal impervious surface dynamics in wuhan urban agglomeration, china from 2000 to 2016. International Journal of Applied Earth Observation & Geoinformation, 70, 51--61.Google ScholarCross Ref
- Schmidhuber, & Jürgen. 2015. Deep learning in neural networks: an overview. Neural Networks, 61, 85--117.Google ScholarDigital Library
- Bengio, Y., Courville, A., & Vincent, P. 2013. Representation learning: a review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1798--1828.Google ScholarDigital Library
- Jin, K. H., Mccann, M. T., Froustey, E., & Unser, M. 2017. Deep convolutional neural network for inverse problems in imaging. IEEE Transactions on Image Processing, 1--1.Google ScholarDigital Library
- Lecun, Y., Bengio, Y., & Hinton, G. 2015. Deep learning. Nature, 521(7553), 436.Google ScholarCross Ref
- Krizhevsky, A., Sutskever, I., & Hinton, G. 2012. ImageNet Classification with Deep Convolutional Neural Networks. NIPS (Vol.25). Curran Associates Inc.Google Scholar
- Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., & Darrell, T. 2014. Caffe: Convolutional Architecture for Fast Feature Embedding. Acm International Conference on Multimedia.Google ScholarDigital Library
- Mario, H. J., Paoletti, M. E., Javier, P., Jun, L., & Antonio, P. 2018. Active learning with convolutional neural networks for hyperspectral image classification using a new bayesian approach. IEEE Transactions on Geoscience and Remote Sensing, 1--22.Google Scholar
- Zhong, Z., Li, J., Luo, Z., & Chapman, M. 2017. Spectral-spatial residual network for hyperspectral image classification: a 3-d deep learning framework. IEEE Transactions on Geoscience and Remote Sensing, 1--12.Google Scholar
- Wong, A., Shafiee, M. J., & Jules, M. S. 2018. Micronnet: a highly compact deep convolutional neural network architecture for real-time embedded traffic sign classiffication. IEEE Access, PP(99).Google Scholar
Index Terms
- The identification of Impervious Area from Sentinel-2 Imagery Using A Novel Spectral Spatial Residual Convolution Neural Network
Recommendations
Developing a fused vegetation temperature condition index for drought monitoring at field scales using Sentinel-2 and MODIS imagery
Highlights- A quantitative drought monitoring framework at field scales using ESTARFM between MODIS and Sentinel-2 has been developed.
AbstractTime-series high spatial resolution drought monitoring is essential for effective agricultural management. For more than a decade, the multiyear vegetation temperature condition index (VTCI) based on the Advanced Very High Resolution ...
A new method for pixel classification for rice variety identification using spectral and time series data from Sentinel-2 satellite imagery
Highlights- A new method for rice variety identification.
- The classifier takes both ...
AbstractIn the agriculture sector food productivity, security, and sustainability, imposed challenges on farmers, regulatory bodies, and policymakers due to increasing demand and depleting natural resources and environmental concerns. Rice ...
Automatic Classification of Glaciers from Sentinel-2 Imagery Using A Novel Deep Learning Model
ICAIP '19: Proceedings of the 2019 3rd International Conference on Advances in Image ProcessingThe Sentinel-2 imagery provides accessible multispectral imagery, allowing better operation monitoring of glacier for climate change research, sea level rise and human life. Nevertheless, automatic glacial classification from Sentinel-2 is a challenging ...
Comments