Medium Resolution SAR Image Time-series Built-up Area Extraction Based on Multilayer Neural Network
-
摘要: 为提高合成孔径雷达(Synthetic Aperture Radar, SAR)图像时间序列建筑区域提取的准确率和稳定性, 该文结合时间序列图像的特点, 提出了一种基于多层神经网络的建筑提取方法。该方法使用单幅SAR图像进行样本的粗略标记, 并从经过直方图规定化处理后的时间序列图像中获得大量样本。通过单幅SAR图像生成的少量样本确定网络的深度, 并从时间序列生成的样本中筛选出具有更高质量的样本作为最终模型的训练样本。利用数量大且质量高的训练样本学习得到模型参数。使用包含38幅25 m分辨率ENVISAT ASAR图像的数据集进行两组对比实验, 实验结果中该文方法的最低准确率和最低Kappa系数分别90.2%和0.725, 均高于其它3种传统方法, 算法的稳定性以及准确率都有显著提高。此外, 该方法还具有人工操作少、推广性强、训练高效等优点。Abstract: To improve the accuracy and stability of built-up area extraction from Synthetic Aperture Radar (SAR) image time series, in this paper, we propose a multilayer neural-network-based built-up area extraction method that combines the characters of time-series images. The proposed method coarsely tags single images and obtains a large number of samples from time-series images that have been processed by a histogram specification procedure. To generate a training sample dataset, we use samples generated from one image to determine network depth and select samples with higher accuracy from the sample set taken from the time-series images. The final model is trained by the selected large and high quality training dataset. We perform two comparison experiments with 38 25-m resolution ENVISAT ASAR images. Using the proposed method, we achieved 90.2% minima accuracy and a 0.725 minima Kappa coefficient, which are much higher than those of the three conventional methods. Thus, the accuracy and stability of built-up area extraction are significantly improved. In addition, the method proposed in this paper has the advantages of requiring minimal manual operation, well generalization, and training efficiency.
-
[1] 王璐, 张帆, 李伟, 等. 基于Gabor滤波器和局部纹理特征提取的SAR目标识别算法[J]. 雷达学报, 2015, 4(6): 658-665. Wang Lu, Zhang Fan, Li Wei, et al.. A method of SAR target recognition based on Gabor filter and local texture feature extraction[J]. Journal of Radars, 2015, 4(6): 658-665. [2] 孙志军, 薛磊, 许阳明, 等. 基于多层编码器的SAR目标及阴影联合特征提取算法[J]. 雷达学报, 2013, 2(2): 195-202. Sun Zhi-jun, Xue Lei, Xu Yang-ming, et al.. Shared representation of SAR target and shadow based on multilayer auto-encoder[J]. Journal of Radars, 2013, 2(2): 195-202. [3] Gamba P, Aldrighi M, and Stasolla M. Robust extraction of urban area extents in HR and VHR SAR images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2011, 4(1): 27-34. [4] Hussain M, Chen D, Cheng A, et al.. Change detection from remotely sensed images: from pixel-based to object-based approaches[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 80: 91-106. [5] Voisin A, Krylov V A, Moser G, et al.. Classification of very high resolution SAR images of urban areas using copulas and texture in a hierarchical Markov random field model[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(1): 96-100. [6] 韩萍, 王欢. 基于改进的稀疏保持投影的SAR目标特征提取与识别[J]. 雷达学报, 2015, 4(6): 674-680. Han Ping and Wang Huan. Synthetic aperture radar target feature extraction and recognition based on improved sparsity preserving projections[J]. Journal of Radars, 2015, 4(6): 674-680. [7] Uslu E and Albayrak S. Curvelet-based synthetic aperture radar image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(6): 1071-1075. [8] Geng J, Fan J, Wang H, et al.. High-resolution SAR image classification via deep convolutional autoencoders[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(11): 2351-2355. [9] Hinton G E, Osindero S, and Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554. [10] Mnih V and Hinton G E. Learning to detect roads in high-resolution aerial images[C]. Computer Vision-ECCV 2010, Springer Berlin Heidelberg, 2010: 210-223. [11] Lv Q, Dou Y, Niu X, et al.. Classification of land cover based on deep belief networks using polarimetric RADARSAT-2 data[C]. 2014 IEEE Geoscience and Remote Sensing Symposium (IGARSS), Quebec City, Canada, 2014: 4679-4682. [12] Gong M, Zhao J, Liu J, et al.. Change detection in synthetic aperture radar images based on deep neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(1): 125-138. [13] Rossetti G, Prati C, and Rucci A. Monitoring the urban environment with multitemporal SAR data[C]. 2015 IEEE Radar Conference (RadarCon),Arlington, VA, USA, 2015: 0622-0627. [14] Gonzalez R C, Woods R E著, 阮秋琦, 阮宇智, 译. 数字图像处理[M]. 第2版, 北京: 电子工业出版社, 2010: 74-79. Gonzalez R C, Woods R E, Ruan Qiuqi and Ruan Yuzhi. Digital Image Processing[M]. Beijing:Publishing House of Electronics Industry, 2010: 74-79. [15] Ioffe S and Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[OL]. arXiv: 1502.03167, 2015. [16] Glorot X, Bordes A, and Bengio Y. Deep sparse rectifier neural networks[C]. International Conference on Artificial Intelligence and Statistics, La Palma, Spain, 2011: 315-323. [17] Srivastava N, Hinton G, Krizhevsky A, et al.. Dropout: a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1): 1929-1958. [18] Kingma D and Ba J. Adam: a method for stochastic optimization[OL]. arXiv: 1412.6980, 2014.
点击查看大图
计量
- 文章访问数: 2215
- HTML全文浏览量: 456
- PDF下载量: 833
- 被引次数: 0