In response to the problem of inadequate utilization of local information in PolSAR image classification using Vision Transformer in existing studies, this paper proposes a Vision Transformer method considering local ...In response to the problem of inadequate utilization of local information in PolSAR image classification using Vision Transformer in existing studies, this paper proposes a Vision Transformer method considering local information, LIViT. The method replaces image patch sequence with polarimetric feature sequence in the feature embedding, and uses convolution for mapping to preserve image spatial detail information. On the other hand, the addition of the wavelet transform branch enables the network to pay more attention to the shape and edge information of the feature target and improves the extraction of local edge information. The results in Wuhan, China and Flevoland, Netherlands show that considering local information when using Vision Transformer for PolSAR image classification effectively improves the image classification accuracy and shows better advantages in PolSAR image classification.展开更多
Speckle effects on classification results can be sup- pressed to some extent by introducing the contextual information. An unsupervised classification algorithm is proposed for polarimetric synthetic aperture radar （...Speckle effects on classification results can be sup- pressed to some extent by introducing the contextual information. An unsupervised classification algorithm is proposed for polarimetric synthetic aperture radar （POLSAR） images based on the mean shift （MS） segmentation and Markov random field （MRF）. First, polarimetdc features are exacted by target decomposition for MS segmentation. An initial classification is executed by using the target decomposition and the agglomerative hierarchical clus- tering algorithm. Thereafter, a classification step based on MRF is performed by using the mean coherence matrices obtained for each segment. Under the MRF framework, the smoothness term is defined according to the distance between neighboring areas. By using POLSAR images acquired by the German Aerospace Centre and National Aeronautics and Space Administration/Jet Propulsion Laboratory, the experimental results confirm that the proposed method has higher accuracy and better regional connectivity than other classification methods.展开更多
针对传统PolSAR影像建筑区域提取方法对影像特征利用不充分、自动化程度不高的问题,研究一种基于全卷积网络(fully convolutional networks,FCN)和条件随机场(conditional random field,CRF)相结合的建筑区域提取方法。该方法充分利用FC...针对传统PolSAR影像建筑区域提取方法对影像特征利用不充分、自动化程度不高的问题,研究一种基于全卷积网络(fully convolutional networks,FCN)和条件随机场(conditional random field,CRF)相结合的建筑区域提取方法。该方法充分利用FCN网络对影像进行逐像素分类并能自动提取影像高层特征的优势,首先通过制作样本集对FCN网络进行训练;然后利用训练好的模型进行初步的建筑区域提取;最后利用可以联系上下文信息的条件随机场CRF对结果进行优化处理。实验结果表明,该方法可以充分利用影像的语义信息,有效地减少孤立点,提高对细节、轮廓的提取精度,获得较高精度的建筑区域提取结果。展开更多
文摘In response to the problem of inadequate utilization of local information in PolSAR image classification using Vision Transformer in existing studies, this paper proposes a Vision Transformer method considering local information, LIViT. The method replaces image patch sequence with polarimetric feature sequence in the feature embedding, and uses convolution for mapping to preserve image spatial detail information. On the other hand, the addition of the wavelet transform branch enables the network to pay more attention to the shape and edge information of the feature target and improves the extraction of local edge information. The results in Wuhan, China and Flevoland, Netherlands show that considering local information when using Vision Transformer for PolSAR image classification effectively improves the image classification accuracy and shows better advantages in PolSAR image classification.
基金Supported by National Basic Research Development Program of China（973 Program）（2007CB311006） National Natural Science Foundation of China（60602026）,Acknowledgement The authors would like to thank ESA （http：//earth.esa. int/polsarpro/datasets.html） for providing the data.
基金supported by the National Natural Science Foundation of China(6100118741001256+1 种基金40971219)the National High Technology Research and Development Program of China(863 Program)(2013 AA122301)
文摘Speckle effects on classification results can be sup- pressed to some extent by introducing the contextual information. An unsupervised classification algorithm is proposed for polarimetric synthetic aperture radar （POLSAR） images based on the mean shift （MS） segmentation and Markov random field （MRF）. First, polarimetdc features are exacted by target decomposition for MS segmentation. An initial classification is executed by using the target decomposition and the agglomerative hierarchical clus- tering algorithm. Thereafter, a classification step based on MRF is performed by using the mean coherence matrices obtained for each segment. Under the MRF framework, the smoothness term is defined according to the distance between neighboring areas. By using POLSAR images acquired by the German Aerospace Centre and National Aeronautics and Space Administration/Jet Propulsion Laboratory, the experimental results confirm that the proposed method has higher accuracy and better regional connectivity than other classification methods.
文摘针对传统PolSAR影像建筑区域提取方法对影像特征利用不充分、自动化程度不高的问题,研究一种基于全卷积网络(fully convolutional networks,FCN)和条件随机场(conditional random field,CRF)相结合的建筑区域提取方法。该方法充分利用FCN网络对影像进行逐像素分类并能自动提取影像高层特征的优势,首先通过制作样本集对FCN网络进行训练;然后利用训练好的模型进行初步的建筑区域提取;最后利用可以联系上下文信息的条件随机场CRF对结果进行优化处理。实验结果表明,该方法可以充分利用影像的语义信息,有效地减少孤立点,提高对细节、轮廓的提取精度,获得较高精度的建筑区域提取结果。
