In this article, we apply the total variation method to remotesensingimage restoration. A new method to calculate the regularization parameter by using an improved Generalized Cross-Validation (GCV) method is propos...
详细信息
ISBN:
(纸本)9780819483478
In this article, we apply the total variation method to remotesensingimage restoration. A new method to calculate the regularization parameter by using an improved Generalized Cross-Validation (GCV) method is proposed. Classical GCV can not be directly used in total variation regularization due to the nonlinearity of the total variation. In our method, the GCV method and the fixed point iterative method are combined. In order to use the GCV method, we separate a new linear regularization operator from the definition of the fixed point iterative method. Based on the linear regularization operator, we change the form of the classical GCV function and make it suitable for total variation regularization. A new GCV function suitable for total variation regularization is constructed. By using the new GCV method, the regularization parameter is automatically changing in total variation remotesensingimage restoration and a higher signal-noise-ratio is acquired. Experiments confirm that the adaptability and the stability of the total variation remotesensingimage restoration are improved.
Recently, a supervised classifier called twin support vector machines (twin-SVM) has been introduced, and it has been compared to classical support vector machines (SVM) on UCI dataset in terms of classification perfo...
详细信息
ISBN:
(纸本)9781467373869
Recently, a supervised classifier called twin support vector machines (twin-SVM) has been introduced, and it has been compared to classical support vector machines (SVM) on UCI dataset in terms of classification performance. As a result of the studies, it has been stated that twin support vector machines provide higher classification performance compared to SVM. The main advantage of using twin-SVM is its lower computational complexity than classical SVM. In the context of this work, twin-SVM will be firstly applied to remotesensingimage classification, and its performance will be analyzed in detail in comparison to SVM. The performance of the method will be evaluated with some criteria such as the sensitivity analysis of model selection, effects of number of training samples to the classification performance, analysis of nonlinear twin-SVM methods with different type of kernels and effects of feature selection to the performance. All the analysis will be conducted with some benchmark dataset frequently used in the remotesensing literature.
In this study, a novel unsupervised incremental neural network is proposed for the segmentation of remotesensingimages. Feature vectors are formed by the intensity of one pixel of each channel. The trainning set of ...
详细信息
ISBN:
(纸本)0780383184
In this study, a novel unsupervised incremental neural network is proposed for the segmentation of remotesensingimages. Feature vectors are formed by the intensity of one pixel of each channel. The trainning set of DAYS network is formed by using all pixels of the image. The remotesensingimage is segmented according to the decision of the network. In the study, the segmentation results of DAYS and Kohonen networks are compared
As the annotation of remotesensingimages requires domain expertise, it is difficult to construct a large-scale and accurate annotated dataset. image-level annotation data learning has become a research hotspot. In a...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
As the annotation of remotesensingimages requires domain expertise, it is difficult to construct a large-scale and accurate annotated dataset. image-level annotation data learning has become a research hotspot. In addition, due to the difficulty in avoiding mislabeling, label noise cleaning is also a concern. In this paper, a semantic segmentation method for remotesensingimages based on uncertainty perception with noisy labels is proposed. The main contributions are three-fold. First, a label cleaning method based on iterative learning is presented to handle noise labels such as missing or incorrect annotations. Second, a two-stage semantic segmentation model is proposed for image-level annotation, which eliminates the need for post-processing steps during testing. Lastly, a complementary uncertainty perception function is introduced to improve the utilization of dataset features and enhance the accuracy of segmentation. The effectiveness of this method was verified through comprehensive evaluation with 7 models on four datasets.
Vector quantization is a developing method utilized not in image correction but in image coding. And it is based on the conception that each several intensities of pixels have no correlation. On the other side, it is ...
详细信息
ISBN:
(纸本)0780309715
Vector quantization is a developing method utilized not in image correction but in image coding. And it is based on the conception that each several intensities of pixels have no correlation. On the other side, it is said that images have much spatial diffuseness and several adjacent pixels have much correlation in those images. So merging this inconsistent two ideas we propose an unprecedented predictive interpolation method which can predict an intensity of a center unknown pixel only from intensities of its adjacent known pixels. We yield a smooth and reasonable high-resolution image from a low-resolution image and consider propriety of application of vector quantization to prediction in this study.
Thematic information detection is an important application of remotesensingimage. Support vector machine (SVM) has been widely used in MODIS remotesensing detection. However, the difficulty of SVM application is ho...
详细信息
ISBN:
(纸本)9781479989201
Thematic information detection is an important application of remotesensingimage. Support vector machine (SVM) has been widely used in MODIS remotesensing detection. However, the difficulty of SVM application is how to select the suitable kernel function for remotesensingimage. In this paper, the Sangeang Api volcanic ash cloud on May 30, 2014 is taken as an example, and the linear, polynomial, radial basis function (RBF) and sigmoid kernel functions are used to detect volcanic ash cloud from MODIS remotesensingimage. And then the detected volcanic ash cloud information is evaluated in terms of simulation experiment and contrastive precision accuracy. The results show that the RBF kernel function is more effective and more robust for MODIS remotesensingimage.
In multispectral and hyperspectral image analysis for remotesensing, variations in contrast due to cloud shadows and topography can cause problems in the demixing process, creating false endmembers and erroneous frac...
详细信息
ISBN:
(纸本)9781479903566
In multispectral and hyperspectral image analysis for remotesensing, variations in contrast due to cloud shadows and topography can cause problems in the demixing process, creating false endmembers and erroneous fractional abundance images. This paper introduces a novel hyperspectral mixing model in which pixel contrast is accounted for explicitly in the image formation. A method is described for estimating the per-pixel contrast for any chosen endmember-based demixing algorithm. Applications of the method to both synthetic and real-world satellite imagery illustrate its efficacy.
This paper studies the problem of training a semantic segmentation neural network with weak annotations, in order to be applied in aerial vegetation images from Teide National Park. It proposes a Deep Seeded Region Gr...
详细信息
ISBN:
(纸本)9781509066315
This paper studies the problem of training a semantic segmentation neural network with weak annotations, in order to be applied in aerial vegetation images from Teide National Park. It proposes a Deep Seeded Region Growing system which consists on training a semantic segmentation network from a set of seeds generated by a Support Vector Machine. A region growing algorithm module is applied to the seeds to progressively increase the pixel-level supervision. The proposed method performs better than an SVM, which is one of the most popular segmentation tools in remotesensingimage applications.
The Intensity Hue Saturation (IHS) transform is a widely used method to enhance the spatial resolution of multispectral images by substituting the Intensity component by the high resolution of the panchromatic image. ...
详细信息
ISBN:
(纸本)081943826X
The Intensity Hue Saturation (IHS) transform is a widely used method to enhance the spatial resolution of multispectral images by substituting the Intensity component by the high resolution of the panchromatic image. However, such a direct substitution introduces important modifications on spectral properties. A more rigorous approach should consist in enhancing the spatial resolution of the intensity component through an appropriate combination with the panchromatic image. Such a combination is performed in the redundant wavelet domain by using a fusion model. SPOT images are used to illustrate the superiority of our approach compared to the MHS method for preserving spectral properties.
remotesensingimage often suffers from the common problems of stripe noise and random noise. In this paper, we present a destriping method with unidirectional gradient L0 norm and L0 sparsity priori. The major novelt...
详细信息
ISBN:
(纸本)9781479983391
remotesensingimage often suffers from the common problems of stripe noise and random noise. In this paper, we present a destriping method with unidirectional gradient L0 norm and L0 sparsity priori. The major novelty of the proposed method is that combining the unidirectional gradient L0 norm with the sparsity priori to address the destriping and denoising issues. Moreover, doubly augmented Lagrangian (DAL) method is adopted to solve the L0 regularized minimization problem. The proposed method is verified on heavily striped remotesensingimages. Comparative results demonstrate that the proposed method outperforms the-state-of-art methods, which can suppress noise effectively as well as preserve image structures well.
暂无评论