Hyperspectral Data Haze Monitoring Based on Deep Residual Network

被引：0

作者：

Lu Y. ^{[1
]}

Li Y. ^{[1
]}

Liu B. ^{[2
]}

Liu H. ^{[2
]}

Cui L. ^{[3
]}

机构：

[1] School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanghai

[2] Room 15, Institute of Shanghai Satellite Engineering, Shanghai

[3] Satellite Remote Sensing Application Technology Laboratory, Shanghai Institute of Meteorological Science, Shanghai

来源：

Li, Yuanxiang (yuanxli@sjtu.edu.cn) | 2017年 / Chinese Optical Society卷 / 37期

关键词：

Air pollution monitoring; Deep learning; Deep residual network; Haze monitoring; Hyperspectral remote sensing; Machine learning; Remote sensing;

D O I：

10.3788/AOS201737.1128001

中图分类号：

学科分类号：

摘要：

Haze monitoring is one of the key technologies for environmental governance. At present, the cost of the ground haze monitoring is very high and the accuracy of the multispectral remote sensing haze monitoring is low. The hyperspectral sensing data haze monitoring is studied by deep learning. A hyperspectral haze monitoring algorithm based on deep residual network is presented. The features of haze hyperspectral curves are obtained with the deep network. The difficulty of the network training is decreased with the residual leaning method, and a haze monitoring model is achieved. The experimental results of the Suzhou Hyperion hyperspectral data sets show that, compared with other methods of remote haze monitoring, the proposed method has higher recognition accuracy in haze monitoring. © 2017, Chinese Lasers Press. All right reserved.

引用

共 18 条

[1] Wang Z., Chen L., Li Q., Et al., Simulation of multi-angle polarized reflectance of haze, Acta Optica Sinica, 35, 9, (2015)
[2] Liu J., Gui H., Xie P., Et al., Recent progress of atmospheric haze monitoring technology, Journal of Atmospheric and Environmental Optics, 10, 2, pp. 93-101, (2015)
[3] Lee K.H., Kim Y.J., Kim M.J., Characteristics of aerosol observed during two severe haze events over Korea in June and October 2004, Atmospheric Environment, 40, 27, pp. 5146-5155, (2006)
[4] Ghauri B., Estimating area covered by Haze and fog in Pakistan and India during winters, IEEE Conference on Geoscience and Remote Sensing Symposium (IGARSS), (2016)
[5] Dai Y., Li C., Zhou S., Et al., Haze monitoring of Shanghai area based on remote sensing, Engineering of Surveying and Mapping, 12, pp. 29-32, (2015)
[6] Wang Z., Li Q., Li S., Et al., The monitoring of haze from HJ-1, Spectroscopy and Spectral Analysis, 32, 3, pp. 775-780, (2012)
[7] Liu Y., Research on haze identification in Beijing based on NOAA/AVHRR satellite data, Meteorological Monthly, 40, 5, pp. 619-627, (2014)
[8] Niu Z., Jiang S., Li X., Et al., The remote sensing monitoring operational system of haze pollution in Jiangsu province, Environmental Monitoring & Forewarning, 6, 5, pp. 15-18, (2014)
[9] Krizhevsky A., Sutskever I., Hinton G.E., Imagenet classification with deep convolutional neural networks, Neural Information Processing Systems Conference, pp. 1097-1105, (2012)
[10] Girshick R., Donahue J., Darrell T., Et al., Rich feature hierarchies for accurate object detection and semantic segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580-587, (2014)

← 1 2 →