An active deep learning approach for minimally supervised polsar image classification

Journal article


Xue, Yong 2019. An active deep learning approach for minimally supervised polsar image classification. IEEE Transactions on Geoscience and Remote Sensing. 57 (11), pp. 9378-9395. https://doi.org/10.1109/TGRS.2019.2926434
AuthorsXue, Yong
Abstract

Recently, deep neural networks have received intense interests in polarimetric synthetic aperture radar (PolSAR) image classification. However, its success is subject to the availability of large amounts of annotated data which require great efforts of experienced human annotators. Aiming at improving the classification performance with greatly reduced annotation cost, this paper presents an active deep learning approach for minimally supervised PolSAR image classification, which integrates active learning and fine-tuned convolutional neural network (CNN) into a principled framework. Starting from a CNN trained using a very limited number of labeled pixels, we iteratively and actively select the most informative candidates for annotation, and incrementally fine-tune the CNN by incorporating the newly annotated pixels. Moreover, to boost the performance and robustness of the proposed method, we employ Markov random field (MRF) to enforce class label smoothness, and data augmentation technique to enlarge the training set. We conducted extensive experiments on four real benchmark PolSAR images, and experiments demonstrated that our approach achieved state-of-the-art classification results with significantly reduced annotation cost.

KeywordsActive learning; convolutional neural network (CNN); data augmentation; fine-tuning; Markov random field (MRF); polarimetric synthetic aperture radar (PolSAR); image classification
Year2019
JournalIEEE Transactions on Geoscience and Remote Sensing
Journal citation57 (11), pp. 9378-9395
PublisherIEEE
ISSN01962892
15580644
Digital Object Identifier (DOI)https://doi.org/10.1109/TGRS.2019.2926434
Web address (URL)http://hdl.handle.net/10545/624528
http://creativecommons.org/licenses/by/4.0/
hdl:10545/624528
Publication dates01 Aug 2019
Publication process dates
Deposited25 Feb 2020, 16:44
Accepted2019
Rights

Attribution 4.0 International

ContributorsUniversity of Derby, Fudan University, Shanghai, China and X'ian Electronics and Engineering Institute, China
File
File Access Level
Open
File
File Access Level
Open
File
File Access Level
Open
Permalink -

https://repository.derby.ac.uk/item/923q2/an-active-deep-learning-approach-for-minimally-supervised-polsar-image-classification

Download files

  • 32
    total views
  • 0
    total downloads
  • 0
    views this month
  • 0
    downloads this month

Export as

Related outputs

An Improved Geographically and Temporally Weighted Regression for Surface Ozone Estimation from Satellite-Based Precursor Data
Wang, X., Xue, Y., Sun, Y., Jin, C. and Wu, S. 2023. An Improved Geographically and Temporally Weighted Regression for Surface Ozone Estimation from Satellite-Based Precursor Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. pp. 1-14. https://doi.org/10.1109/JSTARS.2023.3327881
Studying the Regional Transmission of Air Pollution Based on Spatiotemporal Multivariable Data
Lu, X., Xue, Y., He, B., Jiang, X., Wu, S. and Wang, X. 2023. Studying the Regional Transmission of Air Pollution Based on Spatiotemporal Multivariable Data. Atmosphere. 14 (9), pp. 1-17. https://doi.org/10.3390/atmos14091438
Improved Bi-Angle Aerosol Optical Depth Retrieval Algorithm from AHI Data Based on Particle Swarm Optimization
Jin, Chunlin, Jiang, Xingxing, Sun, Yuxin, Wu, Shuhui and Xue, Yong 2021. Improved Bi-Angle Aerosol Optical Depth Retrieval Algorithm from AHI Data Based on Particle Swarm Optimization. Remote Sensing. 13 (22), p. 4689. https://doi.org/10.3390/rs13224689
Estimation of the PM2.5 and PM10 Mass Concentration over Land from FY-4A Aerosol Optical Depth Data
Xue, Yong 2021. Estimation of the PM2.5 and PM10 Mass Concentration over Land from FY-4A Aerosol Optical Depth Data. Remote Sensing. 13 (21), p. 4276. https://doi.org/10.3390/rs13214276
COVID-19 pandemic decision support system for a population defense strategy and vaccination effectiveness
Varotsos, Costas A, Krapivin, Vladimir F, Xue, Yong, Soldatov, Vladimir and Voronova, Tatiana 2021. COVID-19 pandemic decision support system for a population defense strategy and vaccination effectiveness. Safety Science. 142, p. 105370. https://doi.org/10.1016/j.ssci.2021.105370
Nowcasting of air pollution episodes in megacities: A case study for Athens, Greece
Varotsos, Costas A., Mazei, Yuri, Saldaev, Damir, Efstathiou, Maria, Voronova, Tatiana and Xue, Yong 2021. Nowcasting of air pollution episodes in megacities: A case study for Athens, Greece. Atmospheric Pollution Research. 12 (7), p. 101099. https://doi.org/10.1016/j.apr.2021.101099
Remote sensing evaluation of total suspended solids dynamic with markov model: a case study of inland reservoir across administrative boundary in south China
Zhao, Jing, Zhang, Fujie, Chen, Shuisen, Wang, Chongyang, Chen, Jinyue, Zhou, Hui and Xue, Yong 2020. Remote sensing evaluation of total suspended solids dynamic with markov model: a case study of inland reservoir across administrative boundary in south China. Sensors. 20 (23), p. 6911. https://doi.org/10.3390/s20236911
Diagnostic model for the society safety under COVID-19 pandemic conditions
Varotsos, Costas A., Krapivin, Vladimir F. and Xue, Yong 2021. Diagnostic model for the society safety under COVID-19 pandemic conditions. Safety Science. 136, p. 105164. https://doi.org/10.1016/j.ssci.2021.105164
Polarimetric SAR image semantic segmentation with 3D discrete wavelet transform and Markov random field
Bi, Haixia, Xu, Lin, Cao, Xiangyong, Xue, Yong and Xu, Zongben 2020. Polarimetric SAR image semantic segmentation with 3D discrete wavelet transform and Markov random field. IEEE Transactions on Image Processing. https://doi.org/10.1109/TIP.2020.2992177
Deriving a global and hourly data set of aerosol optical depth over land using data from four geostationary satellites: goes-16, msg-1, msg-4, and himawari-8
Xie, Yanqing, Xue, Yong, Guang, Jie, Mei, Linlu, She, Lu, Li, Ying, Che, Yahui and Fan, Cheng 2019. Deriving a global and hourly data set of aerosol optical depth over land using data from four geostationary satellites: goes-16, msg-1, msg-4, and himawari-8. IEEE Transactions on Geoscience and Remote Sensing. https://doi.org/10.1109/TGRS.2019.2944949
A Heterogeneous and Interactive Big Earth Data Framework
Bi, H., Xue, Y., Merritt, P., Windmill, C. and Davis, B. 2019. A Heterogeneous and Interactive Big Earth Data Framework. 2019 International Conference on Big Data Engineering. IEEE. https://doi.org/10.1145/3341620.3341628
Big earth data: a comprehensive analysis of visualization analytics issues
Merritt, Patrick, Bi, Haixia, Davis, Bradley, Windmill, Christopher and Xue, Yong 2019. Big earth data: a comprehensive analysis of visualization analytics issues. Big Earth Data. 2 (4), pp. 321-350. https://doi.org/10.1080/20964471.2019.1576260
High Performance Time Series Quantitative Retrieval from Satellite Images on a GPU Cluster
Liu, J., Xue, Y., Ren, K., Song, J., Windmill, C. and Merritt, P. 2019. High Performance Time Series Quantitative Retrieval from Satellite Images on a GPU Cluster. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 12 (8). https://doi.org/10.1109/JSTARS.2019.2920077
Joint retrieval of aerosol optical depth and surface reflectance over land using geostationary satellite data.
She, Lu, Xue, Yong, Yang, Xihua, Leys, John, Guang, Jie, Che, Yahui, Fan, Cheng, Xie, Yanqing and Li, Ying 2018. Joint retrieval of aerosol optical depth and surface reflectance over land using geostationary satellite data. IEEE Transactions on Geoscience and Remote Sensing. https://doi.org/10.1109/TGRS.2018.2867000
Evaluation of the AVHRR DeepBlue aerosol optical depth dataset over mainland China.
Che, Yahui, Xue, Yong, Guang, Jie, She, Lu and Guo, Jianping 2018. Evaluation of the AVHRR DeepBlue aerosol optical depth dataset over mainland China. ISPRS Journal of Photogrammetry and Remote Sensing. https://doi.org/10.1016/j.isprsjprs.2018.09.004
A physically based PM 2.5 estimation method using AERONET data in Beijing Area
Chen, Guili, Guang, Jie, Xue, Yong, Li, Ying, Che, Yahui and Gong, Shaoqi 2018. A physically based PM 2.5 estimation method using AERONET data in Beijing Area. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://doi.org/10.1109/JSTARS.2018.2817243
Dust detection and intensity estimation using Himawari-8/AHI observation.
She, Lu, Xue, Yong, Yang, Xihua, Guang, Jie, Li, Ying, Che, Yahui, Fan, Cheng and Xie, Yanqing 2018. Dust detection and intensity estimation using Himawari-8/AHI observation. Remote Sensing. https://doi.org/10.3390/rs10040490
SAHARA: A Simplified AtmospHeric Correction AlgoRithm for Chinese gAofen Data: 1. Aerosol Algorithm.
She, Lu, Mei, Linlu, Xue, Yong, Che, Yahui and Guang, Jie 2017. SAHARA: A Simplified AtmospHeric Correction AlgoRithm for Chinese gAofen Data: 1. Aerosol Algorithm. Remote Sensing. https://doi.org/10.3390/rs9030253
Validation of aerosol products from AATSR and MERIS/AATSR synergy algorithms—Part 1: Global Evaluation.
Che, Yahui, Mei, Linlu, Xue, Yong, Guang, Jie, She, Lu and Li, Ying 2018. Validation of aerosol products from AATSR and MERIS/AATSR synergy algorithms—Part 1: Global Evaluation. Remote Sensing. https://doi.org/10.3390/rs10091414
Improved aerosol optical depth and ångstrom exponent retrieval over land From MODIS based on the non-lambertian forward model
Leiku, Yang, Xue, Yong, Guang, Jie, Hassan, Kazemian, Zhang, Jiahua and Li, Chi 2014. Improved aerosol optical depth and ångstrom exponent retrieval over land From MODIS based on the non-lambertian forward model. IEEE Geoscience and Remote Sensing Letters. https://doi.org/10.1109/LGRS.2014.2303317
Using SeaWiFS measurements to evaluate radiometric stability of pseudo-invariant calibration sites at top of atmosphere
Li, Chi, Xue, Yong, Liu, Quanhua, Ouazzane, Karim and Zhang, Jiahua 2014. Using SeaWiFS measurements to evaluate radiometric stability of pseudo-invariant calibration sites at top of atmosphere. IEEE Geoscience and Remote Sensing Letters. https://doi.org/10.1109/LGRS.2014.2329138
Ensemble of ESA/AATSR aerosol optical depth products based on the likelihood estimate method with uncertainties
Xie, Yanqing, Xue, Yong, Che, Yahui, Guang, Jie, Mei, Linlu, Voorhis, Dave, Fan, Cheng, She, Lu and Xu, Hui 2017. Ensemble of ESA/AATSR aerosol optical depth products based on the likelihood estimate method with uncertainties. IEEE Transactions on Geoscience and Remote Sensing. https://doi.org/10.1109/TGRS.2017.2757910
Long-time series aerosol optical depth retrieval from AVHRR data over land in North China and Central Europe
Xue, Yong, He, Xingwei, de Leeuw, Gerrit, Mei, Linlu, Che, Yahui, Rippin, Wayne, Guang, Jie and Hu, Yincui 2017. Long-time series aerosol optical depth retrieval from AVHRR data over land in North China and Central Europe. Remote Sensing of Environment. https://doi.org/10.1016/j.rse.2017.06.036
Multicore processors and graphics processing unit accelerators for parallel retrieval of aerosol optical depth from satellite data: Implementation, performance, and energy efficiency
Liu, Jia, Feld, Dustin, Xue, Yong, Garcke, Jochen and Soddemann, Thomas 2015. Multicore processors and graphics processing unit accelerators for parallel retrieval of aerosol optical depth from satellite data: Implementation, performance, and energy efficiency. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. https://doi.org/10.1109/JSTARS.2015.2438893
High-throughput geocomputational workflows in a grid environment
Liu, Jia, Xue, Yong, Palmer-Brown, Dominic, Chen, Ziqiang and He, Xingwei 2015. High-throughput geocomputational workflows in a grid environment. Computer. https://doi.org/10.1109/MC.2015.331
An efficient geosciences workflow on multi-core processors and GPUs: a case study for aerosol optical depth retrieval from MODIS satellite data
Liu, Jia, Feld, Dustin, Xue, Yong, Garcke, Jochen, Soddemann, Thomas, Pan, Peiyuan and Fraunhofer Institute of Algorhithms and Scientific Computing 2016. An efficient geosciences workflow on multi-core processors and GPUs: a case study for aerosol optical depth retrieval from MODIS satellite data. International Journal of Digital Earth. https://doi.org/10.1080/17538947.2015.1130087
Technical note: Intercomparison of three AATSR Level 2 (L2) AOD products over China
Che, Yahui, Xue, Yong, Mei, Linlu, Guang, Jie, She, Lu, Guo, Jianping, Hu, Yincui, Xu, Hui, He, Xingwei, Di, Aojie and Fan, Cheng 2016. Technical note: Intercomparison of three AATSR Level 2 (L2) AOD products over China. Atmospheric Chemistry and Physics. https://doi.org/10.5194/acp-16-9655-2016
Dust aerosol optical depth retrieval and dust storm detection for Xinjiang Region using Indian National Satellite Observations
Di, Aojie, Xue, Yong, Yang, Xihua, Leys, John, Guang, Jie, Mei, Linlu, Wang, Jingli, She, Lu, Hu, Yincui, He, Xingwei, Che, Yahui and Fan, Cheng 2016. Dust aerosol optical depth retrieval and dust storm detection for Xinjiang Region using Indian National Satellite Observations. Remote Sensing. https://doi.org/10.3390/rs8090702
Grid workflow validation using ontology-based tacit knowledge: A case study for quantitative remote sensing applications
Liu, Jia, Liu, Longli, Xue, Yong, Dong, Jing, Hu, Yincui, Hill, Richard, Guang, Jie and Li, Chi 2016. Grid workflow validation using ontology-based tacit knowledge: A case study for quantitative remote sensing applications. Computers & Geosciences. https://doi.org/10.1016/j.cageo.2016.10.002