Advertisement

PolSAR Marine Aquaculture Detection Based on Nonlocal Stacked Sparse Autoencoder

  • Jianchao FanEmail author
  • Xiaoxin Liu
  • Yuanyuan Hu
  • Min Han
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11555)

Abstract

Marine aquaculture plays an important role in marine economic, which distributes widely around the coast. Using satellite remote sensing monitoring, it can achieve large scale dynamic monitoring. As a classic model of deep learning, stacked sparse autoencoder (SSAE) has the advantages of simple model and self-learning of features. Nonlocal spatial information is utilized to assist SSAE construct NSSAE to improve the precision in this paper. Experimental results demonstrate the superiority of nonlocal SSAE methods on marine target recognition.

Keywords

Polarimetric SAR Remote sensing images Nonlocal spatial information Stacked sparse autoencoder Classification 

References

  1. 1.
    Fan, J., Chu, J., Geng, J., Zhang, F.: Floating raft aquaculture information automatic extraction based on high resolution SAR images. In: 2015 IEEE International Geoscience and Remote Sensing Symposium, Milan, pp. 3898–3901 (2015)Google Scholar
  2. 2.
    Hu, Y., Fan, J., Wang, J.: Target recognition of floating raft aquaculture in SAR image based on statistical region merging. In: 2017 Seventh International Conference on Information Science and Technology, Da Nang, pp. 429–432 (2017)Google Scholar
  3. 3.
    Geng, J., Fan, J., Wang, H.: Weighted fusion-based representation classifiers for marine floating raft detection of SAR images. IEEE Geosci. Remote Sens. Lett. 14, 444–448 (2017)Google Scholar
  4. 4.
    Shao, Z., Zhang, L., Wang, L.: Stacked sparse autoencoder modeling using the synergy of airborne LiDAR and satellite optical and SAR data to map forest above-ground biomass. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 10, 5569–5582 (2017)Google Scholar
  5. 5.
    Hu, Y., Fan, J., Wang, J.: Classification of PolSAR images based on adaptive nonlocal stacked sparse autoencoder. IEEE Geosci. Remote Sens. Lett. 15, 1050–1054 (2018)Google Scholar
  6. 6.
    Tao, C., Pan, H., Li, Y., Zou, Z.: Unsupervised spectral-spatial feature learning with stacked sparse autoencoder for hyperspectral imagery classification. IEEE Geosci. Remote Sens. Lett. 12, 2438–2442 (2015)Google Scholar
  7. 7.
    Wan, L., Zhang, T., Xiang, Y., You, H.: A robust fuzzy C-means algorithm based on Bayesian nonlocal spatial information for SAR image segmentation. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 11, 896–906 (2018)Google Scholar
  8. 8.
    Song, W., Li, M., Zhang, P., Wu, Y., Jia, L., An, L.: Unsupervised PolSAR image classification and segmentation using Dirichlet process mixture model and Markov random fields with similarity measure. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 10, 3556–3568 (2017)Google Scholar
  9. 9.
    Bi, H., Xu, L., Cao, X., Xu, Z.: PolSAR image classification based on three-dimensional wavelet texture features and Markov random field. In: 2017 IEEE International Geoscience and Remote Sensing Symposium, Fort Worth, pp. 3921–3928 (2017)Google Scholar
  10. 10.
    Zhang, L., Ma, W., Zhang, D.: Stacked sparse autoencoder in PolSAR data classification using local spatial information. IEEE Geosci. Remote Sens. Lett. 13, 1359–1363 (2016)Google Scholar
  11. 11.
    Buades, A., Coll, B., Morel, J.: A non-local algorithm for image denoising. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, vol. 2, pp. 60–65 (2005)Google Scholar
  12. 12.
    Zhang, X., Gao, Z., Jiao, L., Zhou, H.: Multifeature hyperspectral image classification with local and nonlocal spatial information via Markov random field in semantic space. IEEE Trans. Geosci. Remote Sens. 56, 1409–1424 (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jianchao Fan
    • 1
    Email author
  • Xiaoxin Liu
    • 2
  • Yuanyuan Hu
    • 3
  • Min Han
    • 3
  1. 1.Department of Ocean Remote SensingNational Marine Environmental Monitoring CenterDalianChina
  2. 2.Computer Science and EngineeringWashington University in St. LouisSaint LouisUSA
  3. 3.Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalianChina

Personalised recommendations