Abstract
The rich data provided by satellites and unmanned aerial vehicles bring opportunities to directly model aerial image features by extracting their spatial and structural patterns. Although convolutional autoencoders (CAEs) have been attained a remarkable performance in ideal aerial image feature extraction, they are still challenging to extract information from noisy images which are generated from capture and transmission. In this paper, a novel CAE-based noise-robust unsupervised learning method is proposed for extracting high-level features accurately from aerial images and mitigating the effect of noise. Different from conventional CAEs, the proposed method introduces the noise-robust module between the encoder and the decoder. Besides, several pooling layers in CAEs are replaced by convolutional layers with stride=2. The performance of feature extraction is evaluated by the prediction accuracy and the accuracy loss in image classification experiments. A 5-classes aerial optical scene and a 9-classes hyperspectral image (HSI) data set are utilized for optical image and HSI feature extraction, respectively. High-level features extracted from aerial images are utilized for image classification by a linear support vector machine (SVM) classifier. Experimental results indicate that the proposed method improves the classification accuracy for noisy images (Gaussian noise 2D σ=0.1, 3D σ=60) in both optical images (2D 87.5%) and HSIs (3D 85.6%) compared with the traditional CAE (2D 78.6%, 3D 84.2%). The accuracy loss in classification experiments increases with the increment of noise. Compared with the traditional CAE (2D 15.7%, 3D 11.8%), the proposed method shows the lower classification accuracy loss in experiments (2D 0.3%, 3D 6.3%). The proposed unsupervised noise-robust feature extraction method attains desirable classification accuracy in ideal input and enhances the feature extraction capability from noisy input.
Similar content being viewed by others
References
Sivic J, Zisserman A. Video Google: A text retrieval approach to object matching in videos. In: Proceedings of Ninth IEEE International Conference on Computer Vision. France, 2003. 1470
Licciardi G, Marpu P R, Chanussot J, et al. Linear versus nonlinear PCA for the classification of hyperspectral data based on the extended morphological profiles. IEEE Geosci Remote Sens Lett, 2012, 9: 447–451
Villa A, Benediktsson J A, Chanussot J, et al. Hyperspectral image classification with independent component discriminant analysis. IEEE Trans Geosci Remote Sens, 2011, 49: 4865–4876
Bandos T V, Bruzzone L, Camps-Valls G. Classification of hyperspectral images with regularized linear discriminant analysis. IEEE Trans Geosci Remote Sens, 2009, 47: 862–873
Xu X, Li W, Ran Q, et al. Multisource remote sensing data classification based on convolutional neural network. IEEE Trans Geosci Remote Sens, 2018, 56: 937–949
Van Etten Adam. You only look twice: Rapid multi-scale object detection in satellite imagery. arXiv: 1805.09512
Sokalski J, Breckon T, Cowling I. Automatic salient object detection in UAV imagery. In: Proceedings of the 25th International Unmanned Air Vehicle Systems. Bristol, 2010. 1–12
Mou L, Zhu X X. Vehicle instance segmentation from aerial image and video using a multitask learning residual fully convolutional network. IEEE Trans Geosci Remote Sens, 2018, 56: 6699–6711
Chen Y, Jiang H, Li C, et al. Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans Geosci Remote Sens, 2016, 54: 6232–6251
Maggiori E, Tarabalka Y, Charpiat G, et al. Convolutional neural networks for large-scale remote-sensing image classification. IEEE Trans Geosci Remote Sens, 2017, 55: 645–657
Baccouche M, Mamalet F, Wolf C, et al. Spatio-temporal convolutional sparse auto-encoder for sequence classification. In: Proceedings of the British Machine Vision Conference. Surrey, 2012. 1–12
Han X, Zhong Y, He L, et al. The unsupervised hierarchical convolutional sparse auto-encoder for neuroimaging data classification. In: International Conference on Brain Informatics and Health. Cham: Springer, 2015. 156–166
Romero A, Gatta C, Camps-Valls G. Unsupervised deep feature extraction for remote sensing image classification. IEEE Trans Geosci Remote Sens, 2016, 54: 1349–1362
Luo W, Li J, Yang J, et al. Convolutional sparse autoencoders for image classification. IEEE Trans Neural Netw Learning Syst, 2017, 29: 1–6
Geng J, Fan J, Wang H, et al. High-resolution SAR image classification via deep convolutional autoencoders. IEEE Geosci Remote Sens Lett, 2015, 12: 2351–2355
Mei S, Ji J, Geng Y, et al. Unsupervised spatial-spectral feature learning by 3D convolutional autoencoder for hyperspectral classification. IEEE Trans Geosci Remote Sens, 2019, 57: 6808–6820
Gondara L. Medical image denoising using convolutional denoising autoencoders. In: Proceedings of 16th International Conference on Data Mining Workshops. Barcelona, 2016. 241–246
Liu W, Lee J. A 3-D atrous convolution neural network for hyperspectral image denoising. IEEE Trans Geosci Remote Sens, 2019, 57: 5701–5715
Mao X, Shen C, Yang Y. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Proceedings of Advances in Neural Information Processing Systems. Barcelona, 2016. 2802–2810
Wang R, Xiao X, Guo B, et al. An effective image denoising method for UAV images via improved generative adversarial networks. Sensors, 2018, 18: 1985
Zhou Z, Cao Z, Pi Y. Background registration-based adaptive noise filtering of LWIR/MWIR imaging sensors for UAV applications. Sensors, 2017, 18: 10–3390
Bioucas-Dias J M, Plaza A, Camps-Valls G, et al. Hyperspectral remote sensing data analysis and future challenges. IEEE Geosci Remote Sens Mag, 2013, 1: 6–36
Dodge S, Karam L. A study and comparison of human and deep learning recognition performance under visual distortions. In: 26th International Conference on Computer Communication and Networks. Vancouver, 2017. 1–7
Geirhos R, Temme M, Rauber J, et al. Generalisation in humans and deep neural networks. In: Proceedings of Advances in Neural Information Processing Systems. Cambridge: MIT Press, 2018. 7538–7550
Li X, Yan G, Li X, et al. Image denoise based on soft-threshold and edge enhancement. In: Second Workshop on Digital Media and its Appli cation in Museum & Heritages. Chongqing, 2007. 53–56
Yi Q, Weng Y, He J. Image denoise based on curvelet transform. In: 2014 IEEE Workshop on Electronics, Computer and Applications. Ottawa, 2014. 412–414
Bijalwan A, Goyal A, Sethi N. Wavelet transform based image denoise using threshold approaches. Int J Eng Adv Tech, 2012, 1: 2249
Jalalvand A, De W, Van R, et al. Towards using reservoir computing networks for noise-robust image recognition. In: Proceedings of International Joint Conference on Neural Networks. Vancouver, 2016. 1666–1672
Chen C, Li W, Tramel E W, et al. Spectral-spatial preprocessing using multihypothesis prediction for noise-robust hyperspectral image classification. IEEE J Sel Top Appl Earth Observ Remote Sens, 2014, 7: 1047–1059
Zhang W C, Zhao Y L, Breckon T P, et al. Noise robust image edge detection based upon the automatic anisotropic Gaussian kernels. Pattern Recognition, 2017, 63: 193–205
Song T, Li H, Meng F, et al. Noise-robust texture description using local contrast patterns via global measures. IEEE Signal Process Lett, 2014, 21: 93–96
Masci J, Meier U, Ciresan D, et al. Stacked convolutional auto-encoders for hierarchical feature extraction. In: Honkela T, Duch W, Girolami M, et al., eds. Artificial Neural Networks and Machine Learning-ICANN 2011. ICANN 2011. Lecture Notes in Computer Science. Berlin: Springer, 2011
Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems. Lake Tahoe, 2012
He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell, 2014, 37: 1904–1916
Cheng G, Zhou P, Han J. Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Trans Geosci Remote Sens, 2016, 54: 7405–7415
Yang Y, Newsam S. Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2010
Na J, Jeon K, Lee W B. Toxic gas release modeling for real-time analysis using variational autoencoder with convolutional neural networks. Chem Eng Sci, 2018, 181: 68–78
Chen P H, Zhu X, Zhang H, et al. A Convolutional autoencoder for multi-subject fMRI data aggregation. arXiv: 1608.04846
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was supported by the National Defense Basic Scientific Research Program of China (Grant No. JCKY2018603C015), and the Cultivation Plan of Major Research Program of Harbin Institute of Technology (Grant No. ZDXMPY20180101).
Rights and permissions
About this article
Cite this article
Liang, Y., Lu, S., Weng, R. et al. Unsupervised noise-robust feature extraction for aerial image classification. Sci. China Technol. Sci. 63, 1406–1415 (2020). https://doi.org/10.1007/s11431-020-1600-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11431-020-1600-9