浏览全部资源
扫码关注微信
收稿：2019-07-05，
修回：2019-12-12，
纸质出版：2020-06-16
移动端阅览
目的
2
随着遥感影像空间分辨率的提升，相同地物的空间纹理表现形式差异变大，地物特征更加复杂多样，传统的变化检测方法已很难满足需求。为提高高分辨率遥感影像的变化检测精度，尤其对相同地物中纹理差异较大的区域做出有效判别，提出结合深度学习和超像元分割的高分辨率遥感影像变化检测方法。
方法
2
将有限带标签数据分割成切片作训练样本，按照样本形式设计一个多切片尺度特征融合网络并对其训练，获得测试图像的初步变化检测结果；利用超像元分割算法将测试图像分割成许多无重叠的同质性区域，并将分割结果与前述检测结果叠合，得到带分割标记的变化检测结果；用举手表决算法统计带分割标记的变化检测结果中超像元的变化状况，得到最终变化检测结果。
结果
2
在变化检测实验结果中，本文提出的多切片尺度特征融合卷积网络模型在广东数据集和香港数据集上，优于单一切片尺度下卷积神经网络模型，并且结合超像元的多切片尺度特征融合卷积网络模型得到的Kappa系数分别达到80%和82%，比相应的非超像元算法分别提高了6%和8%，在两个测试集上表现均优于长短时记忆网络、深度置信网络等对比算法。
结论
2
本文提出的卷积神经网络变化检测方法可以充分学习切片的空间信息和其他有效特征，避免过拟合现象；多层尺度切片特征融合的方法优于单一切片尺度训练神经网络的方法；结合深度学习和超像元分割算法，检测单元实现了由切片到超像元的转变，能对同物异谱的区域做出有效判决，有利于提升变化检测精度。
Objective
2
The resolution of a remote sensing image increases with the rapid development of remote sensing technology. A high-resolution image has high spatial and temporal resolutions
providing conditions for real-time monitoring and change detection. Change detection in remote sensing is used to detect changes in the same regions at different periods. The purpose of this study is to find a change in the same region between specific periods. However
with the improvement in the spatial resolution of remote sensing images
the difference in the spatial texture information of the same object increases. The features of remote sensing images are becoming increasingly complex and diverse. Traditional change detection methods experience difficulty in obtaining good results from high-resolution remote sensing images. Unsupervised deep learning algorithms suffer from difficulty in extracting valid features and making them equal in areas wherein different objects have the same spectra and similar objects have different spectra. To improve the change detection accuracy of high-resolution remote sensing images
particularly for effective judgment in areas with considerable texture differences in different periods at the same location
this study proposes a deep learning and superpixel segmentation method for high-resolution remote sensing image change detection.
Method
2
The algorithm of the deep learning and superpixel-based method for high-resolution remote sensing image change detection exhibits the following characteristics. First
finite labeled data are divided into patches as training samples. Simultaneously
a multiscale patch feature fusion network-based convolutional neural network (MPFF-CNN) is designed. The final model parameters and patch size are determined by testing the different sizes of patches. A preliminary change detection result of the test image can be obtained using this network. Second
the superpixel segmentation algorithm is used to segment the test image into many nonoverlapping homogenous regions and transfer the segmentation result to the preliminary test result to obtain the change detection result with a segmentation mark. An optimal segmentation scale is difficult to obtain in high-resolution remote sensing images. Thus
a multiscale segmentation algorithm is used in this work. Third
the quantities of changed and unchanged pixels of each superpixel in the change detection result with the segmentation marker are statistically evaluated using the hand-crank voting algorithm. All the pixel values of the superpixel are replaced with the pixel values. The categories are more under this superpixel. All the change detection results are stacked to a hypercolumn. Lastly
the quantities of changed and unchanged pixels of each spectrum in the hypercolumn is counted using the hand-crank voting algorithm. If the number of changed pixels is more than that of the unchanged pixels in each spectrum
then the spatial position of the spectrum has a pixel value of 1; otherwise
the pixel value is 0.
Result
2
To estimate the accuracy of the proposed change detection algorithm
experiments are conducted on the Guangdong change detection dataset and the Hong Kong change detection dataset. Four widely used methods are selected for comparison
including the fuzzy C-means-based
support vector machine-based
deep belief network-based
and long short-term memory-based methods. The experimental results of change detection in both datasets indicate that MPFF-CNN exhibits an outstanding performance
which is better than the results of the CNN-based model at a single patch size. The change detection results obtained by the multiple superpixel scale are better than those of the single superpixel scale in both datasets. The percentages of correct classification and kappa obtained by deep learning combined with superpixel (MPFF-CNN-SP) are 97% and 80% for the Guangdong change detection dataset
respectively. MPFF-CNN-SP is 1% and 6% higher than MPFF-CNN. MPFF-CNN-SP is better than all the compared algorithms. Similarly
the percentages of correct classification and kappa obtained by MPFF-CNN-SP for the Hong Kong change detection dataset are 99% and 81%
respectively. MPFF-CNN-SP is 1% and 8% higher than MPFF-CNN. MPFF-CNN-SP is superior to all the compared algorithms.
Conclusion
2
The multiscale patch feature fusion method is better than the CNN-based method of training a single patch size. The multiscale patch feature fusion network-based CNN in this work can adequately gain the spatial information and other effective features of patches. Moreover
it does not cause severe overfitting. The multiscale superpixel segmentation results after double hand-raising voting algorithms are significantly stronger than the segmentation results of a single-scale superpixel segmentation. The deep learning and superpixel method transforms the detection unit from patch to superpixel
effectively judging different texture information of the same object and significantly improving change detection accuracy.
Achanta R, Shaji A, Smith K, Lucchi A, Fua P and Süsstrunk S. 2012. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11):2274-2282[DOI:10.1109/TPAMI.2012.120]
Bruzzone L and Prieto D F. 2000. Automatic analysis of the difference image for unsupervised change detection. IEEE Transactions on Geoscience and Remote sensing, 38(3):1171-1182[DOI:10.1109/36.843009]
Celik T. 2009. Unsupervised change detection in satellite images using principal component analysis and k -means clustering. IEEE Geoscience and Remote Sensing Letters, 6(4):772-776[DOI:10.1109/LGRS.2009.2025059]
Daudt R C, Le Saux B and Boulch A. 2018. Fully convolutional siamese networks for change detection//Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). Athens, Greece: IEEE: 4063-4067[DOI: 10.1109/icip.2018.8451652 http://dx.doi.org/10.1109/icip.2018.8451652 ]
Del Frate F, Ortenzi A, Casadio S and Zehner C. 2002. Application of neural algorithms for a real-time estimation of ozone profiles from GOME measurements. IEEE Transactions on Geoscience and Remote Sensing, 40(10):2263-2270[DOI:10.1109/TGRS.2002.803622]
El Amin A M, Liu Q and Wang Y. 2016. Convolutional neural network features based change detection in satellite images//Proceedings of SPIE 10011, First International Workshop on Pattern Recognition. Tokyo, Japan: SPIE: 100110W[DOI: 10.1117/12.2243798 http://dx.doi.org/10.1117/12.2243798 ]
Gong M G, Zhao J J, Liu J and Miao Q G. 2016. Change detection in synthetic aperture radar images based on deep neural networks. IEEE Transactions on Neural Networks and Learning Systems, 27(1):125-138[DOI:10.1109/TNNLS.2015.2435783]
Hall O and Hay G J. 2003. A multiscale object-specific approach to digital change detection. International Journal of Applied Earth Observation and Geoinformation, 4(4):311-327[DOI:10.1016/S0303-2434(03)00010-2]
Hao M, Shi W Z, Zhang H and Li C. 2014. Unsupervised change detection with expectation-maximization-based level set. IEEE Geoscience and Remote Sensing Letters, 11(1):210-214[DOI:10.1109/LGRS.2013.2252879]
Hou B, Wang Y H and Liu Q J. 2017. Change detection based on deep features and low rank. IEEE Geoscience and Remote Sensing Letters, 14(12):2418-2422[DOI:10.1109/LGRS.2017.2766840]
Kingma D P and Ba L J. 2015. Adam: a method for stochastic optimization[EB/OL].[2019-07-01] . https://arxiv.org/pdf/1402.6980.pdf https://arxiv.org/pdf/1402.6980.pdf
Liu J, Gong M G, Qin K and Zhang P Z. 2018. A deep convolutional coupling network for change detection based on heterogeneous optical and radar images. IEEE Transactions on Neural Networks and Learning Systems, 29(3):545-559[DOI:10.1109/TNNLS.2016.2636227]
Lyu H, Lu H and Mou L C. 2016. Learning a transferable change rule from a recurrent neural network for land cover change detection. Remote Sensing, 8(6):506[DOI:10.3390/rs8060506]
Mou L C, Bruzzone L and Zhu X X. 2019. Learning spectral-spatial-temporal features via a recurrent convolutional neural network for change detection in multispectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 57(2):924-935[DOI:10.1109/TGRS.2018.2863224]
Ru H, Yang X L, Peng D Q and Huang P P. 2014. Superparsing based change detection in high resolution remote sensing imagery//Proceedings of the 12th International Conference on Signal Processing (ICSP). Hangzhou, China: IEEE: 996-999[DOI: 10.1109/ICOSP.2014.7015154 http://dx.doi.org/10.1109/ICOSP.2014.7015154 ]
Sui H G, Feng W Q, Li W Z, Sun K M and Xu C. 2018. Review of change detection methods for multi-temporal remote sensing imagery. Geomatics and Information Science of Wuhan University, 43(12):1885-1898
眭海刚, 冯文卿, 李文卓, 孙开敏, 徐川. 2018.多时相遥感影像变化检测方法综述.武汉大学学报(信息科学版), 43(12):1885-1898[DOI:10.13203/j.whugis20180251]
Wang C Y, Chen J Z and Li W. 2014. Review on superpixel segmentation algorithms. Application Research of Computers, 31(1):6-12
王春瑶, 陈俊周, 李炜. 2014.超像素分割算法研究综述.计算机应用研究, 31(1):6-12[DOI:10.3969/j.issn.1001-3695.2014.01.002]
Zhang X L, Chen X W, Li F and Yang T. 2017. Change detection method for high resolution remote sensing images using deep learning. Acta Geodaetica et Cartographica Sinica, 46(8):999-1008
张鑫龙, 陈秀万, 李飞, 杨婷. 2017.高分辨率遥感影像的深度学习变化检测方法.测绘学报, 46(8):999-1008[DOI:10.11947/j.AGCS.2017.20170036]
相关作者
相关机构
京公网安备11010802024621
