Recently,deep learning-based image inpainting methods have made great strides in reconstructing damaged regions.However,these methods often struggle to produce satisfactory results when dealing with missing images wit...Recently,deep learning-based image inpainting methods have made great strides in reconstructing damaged regions.However,these methods often struggle to produce satisfactory results when dealing with missing images with large holes,leading to distortions in the structure and blurring of textures.To address these problems,we combine the advantages of transformers and convolutions to propose an image inpainting method that incorporates edge priors and attention mechanisms.The proposed method aims to improve the results of inpainting large holes in images by enhancing the accuracy of structure restoration and the ability to recover texture details.This method divides the inpainting task into two phases:edge prediction and image inpainting.Specifically,in the edge prediction phase,a transformer architecture is designed to combine axial attention with standard self-attention.This design enhances the extraction capability of global structural features and location awareness.It also balances the complexity of self-attention operations,resulting in accurate prediction of the edge structure in the defective region.In the image inpainting phase,a multi-scale fusion attention module is introduced.This module makes full use of multi-level distant features and enhances local pixel continuity,thereby significantly improving the quality of image inpainting.To evaluate the performance of our method.comparative experiments are conducted on several datasets,including CelebA,Places2,and Facade.Quantitative experiments show that our method outperforms the other mainstream methods.Specifically,it improves Peak Signal-to-Noise Ratio(PSNR)and Structure Similarity Index Measure(SSIM)by 1.141~3.234 db and 0.083~0.235,respectively.Moreover,it reduces Learning Perceptual Image Patch Similarity(LPIPS)and Mean Absolute Error(MAE)by 0.0347~0.1753 and 0.0104~0.0402,respectively.Qualitative experiments reveal that our method excels at reconstructing images with complete structural information and clear texture details.Furthermore,our model exhibits impressive performance in terms of the number of parameters,memory cost,and testing time.展开更多
Focused on the task of fast and accurate armored target detection in ground battlefield,a detection method based on multi-scale representation network(MS-RN) and shape-fixed Guided Anchor(SF-GA)scheme is proposed.Firs...Focused on the task of fast and accurate armored target detection in ground battlefield,a detection method based on multi-scale representation network(MS-RN) and shape-fixed Guided Anchor(SF-GA)scheme is proposed.Firstly,considering the large-scale variation and camouflage of armored target,a new MS-RN integrating contextual information in battlefield environment is designed.The MS-RN extracts deep features from templates with different scales and strengthens the detection ability of small targets.Armored targets of different sizes are detected on different representation features.Secondly,aiming at the accuracy and real-time detection requirements,improved shape-fixed Guided Anchor is used on feature maps of different scales to recommend regions of interests(ROIs).Different from sliding or random anchor,the SF-GA can filter out 80% of the regions while still improving the recall.A special detection dataset for armored target,named Armored Target Dataset(ARTD),is constructed,based on which the comparable experiments with state-of-art detection methods are conducted.Experimental results show that the proposed method achieves outstanding performance in detection accuracy and efficiency,especially when small armored targets are involved.展开更多
This paper introduces a multi-scale morphological edge detection algorithm to extract SAR image edge which suffers seriously from noise. Combining the basic theme of morphology with that of multi-scale analysis, the a...This paper introduces a multi-scale morphological edge detection algorithm to extract SAR image edge which suffers seriously from noise. Combining the basic theme of morphology with that of multi-scale analysis, the algorithm presents the outstanding characteristics of accuracy and robustness. Comparative Experiments reveal its fine performance.展开更多
Automatic generalization of geographic information is the core of multi_scale representation of spatial data,but the scale_dependent generalization methods are far from abundant because of its extreme complicacy.This ...Automatic generalization of geographic information is the core of multi_scale representation of spatial data,but the scale_dependent generalization methods are far from abundant because of its extreme complicacy.This paper puts forward a new consistency model about scale_dependent representations of relief based on wavelet analysis,and discusses the thresholds in the model so as to acquire the continual representations of relief with different details between scales.The model not only meets the need of automatic generalization but also is scale-dependent completely.Some practical examples are given.展开更多
Sparse representation models have been shown promising results for image denoising. However, conventional sparse representation-based models cannot obtain satisfactory estimations for sparse coefficients and the dicti...Sparse representation models have been shown promising results for image denoising. However, conventional sparse representation-based models cannot obtain satisfactory estimations for sparse coefficients and the dictionary. To address this weakness, in this paper, we propose a novel fractional-order sparse representation(FSR) model. Specifically, we cluster the image patches into K groups, and calculate the singular values for each clean/noisy patch pair in the wavelet domain. Then the uniform fractional-order parameters are learned for each cluster.Then a novel fractional-order sample space is constructed using adaptive fractional-order parameters in the wavelet domain to obtain more accurate sparse coefficients and dictionary for image denoising. Extensive experimental results show that the proposed model outperforms state-of-the-art sparse representation-based models and the block-matching and 3D filtering algorithm in terms of denoising performance and the computational efficiency.展开更多
Aimed at solving the problems of road network object selection at any unknown scale, the existing methods on object selection are integrated and extended in this paper, and a new object interpolation method is propose...Aimed at solving the problems of road network object selection at any unknown scale, the existing methods on object selection are integrated and extended in this paper, and a new object interpolation method is proposed, which reflects the inheritable and transferable characteristics of related information among multi-scale representation objects, and takes the attribute effects into account. Then the basic idea, the overall framework and the technical flow of the interpolation are put forward, at the samet：me synthetical weight function of the interpolation method is defined and described. The method and technical strategies of object selection are extended, and the key problems are solved, including the dejign of the objective quantitative and structural selections based on the weight values, the interpolation experiment strategies and technical flows, the result of the test shows that the object interpolation method not only inherits the objects at smaller scales, but also takes the attribute effect into account when deriving objects from larger scales according to the road importance, which is a guarantee to objective selection of the road objects at middle scales.展开更多
This paper contains a review of the development of research on multiple representations compiled from Geographic Information Systems (GIS), including data structure, formalization and storage, and intelligent zoom. A ...This paper contains a review of the development of research on multiple representations compiled from Geographic Information Systems (GIS), including data structure, formalization and storage, and intelligent zoom. A summary is also included of the problems of interconnectivity, consistency maintenance, dynamic query and coexisting updates, as well as a research review of multi-scale databases and related studies. Finally,research directions and foci are proposed for the future design and implementation of multi-scale GIS.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 62062061/in part by the Major Project Cultivation Fund of Xizang Minzu University under Grant 324112300447.
文摘Recently,deep learning-based image inpainting methods have made great strides in reconstructing damaged regions.However,these methods often struggle to produce satisfactory results when dealing with missing images with large holes,leading to distortions in the structure and blurring of textures.To address these problems,we combine the advantages of transformers and convolutions to propose an image inpainting method that incorporates edge priors and attention mechanisms.The proposed method aims to improve the results of inpainting large holes in images by enhancing the accuracy of structure restoration and the ability to recover texture details.This method divides the inpainting task into two phases:edge prediction and image inpainting.Specifically,in the edge prediction phase,a transformer architecture is designed to combine axial attention with standard self-attention.This design enhances the extraction capability of global structural features and location awareness.It also balances the complexity of self-attention operations,resulting in accurate prediction of the edge structure in the defective region.In the image inpainting phase,a multi-scale fusion attention module is introduced.This module makes full use of multi-level distant features and enhances local pixel continuity,thereby significantly improving the quality of image inpainting.To evaluate the performance of our method.comparative experiments are conducted on several datasets,including CelebA,Places2,and Facade.Quantitative experiments show that our method outperforms the other mainstream methods.Specifically,it improves Peak Signal-to-Noise Ratio(PSNR)and Structure Similarity Index Measure(SSIM)by 1.141~3.234 db and 0.083~0.235,respectively.Moreover,it reduces Learning Perceptual Image Patch Similarity(LPIPS)and Mean Absolute Error(MAE)by 0.0347~0.1753 and 0.0104~0.0402,respectively.Qualitative experiments reveal that our method excels at reconstructing images with complete structural information and clear texture details.Furthermore,our model exhibits impressive performance in terms of the number of parameters,memory cost,and testing time.
基金supported by the National Key Research and Development Program of China under grant 2016YFC0802904National Natural Science Foundation of China under grant61671470the Postdoctoral Science Foundation Funded Project of China under grant 2017M623423。
文摘Focused on the task of fast and accurate armored target detection in ground battlefield,a detection method based on multi-scale representation network(MS-RN) and shape-fixed Guided Anchor(SF-GA)scheme is proposed.Firstly,considering the large-scale variation and camouflage of armored target,a new MS-RN integrating contextual information in battlefield environment is designed.The MS-RN extracts deep features from templates with different scales and strengthens the detection ability of small targets.Armored targets of different sizes are detected on different representation features.Secondly,aiming at the accuracy and real-time detection requirements,improved shape-fixed Guided Anchor is used on feature maps of different scales to recommend regions of interests(ROIs).Different from sliding or random anchor,the SF-GA can filter out 80% of the regions while still improving the recall.A special detection dataset for armored target,named Armored Target Dataset(ARTD),is constructed,based on which the comparable experiments with state-of-art detection methods are conducted.Experimental results show that the proposed method achieves outstanding performance in detection accuracy and efficiency,especially when small armored targets are involved.
基金Supported the NatioIlal Naturel Science Foundation of China(No.69831040)
文摘This paper introduces a multi-scale morphological edge detection algorithm to extract SAR image edge which suffers seriously from noise. Combining the basic theme of morphology with that of multi-scale analysis, the algorithm presents the outstanding characteristics of accuracy and robustness. Comparative Experiments reveal its fine performance.
基金ProjectsupportedbytheNationalScienceFoundationofSurveyingandMappingofChina (No .990 1 3) .
文摘Automatic generalization of geographic information is the core of multi_scale representation of spatial data,but the scale_dependent generalization methods are far from abundant because of its extreme complicacy.This paper puts forward a new consistency model about scale_dependent representations of relief based on wavelet analysis,and discusses the thresholds in the model so as to acquire the continual representations of relief with different details between scales.The model not only meets the need of automatic generalization but also is scale-dependent completely.Some practical examples are given.
基金supported by the National Natural Science Foundation of China(61573219,61402203,61401209,61701192,61671274)the Opening Fund of Shandong Provincial Key Laboratory of Network Based Intelligent Computing+2 种基金the Fostering Project of Dominant DisciplineTalent Team of Shandong Province Higher Education InstitutionsFostering Project of Dominant Discipline and Talent Team of SDUFE
文摘Sparse representation models have been shown promising results for image denoising. However, conventional sparse representation-based models cannot obtain satisfactory estimations for sparse coefficients and the dictionary. To address this weakness, in this paper, we propose a novel fractional-order sparse representation(FSR) model. Specifically, we cluster the image patches into K groups, and calculate the singular values for each clean/noisy patch pair in the wavelet domain. Then the uniform fractional-order parameters are learned for each cluster.Then a novel fractional-order sample space is constructed using adaptive fractional-order parameters in the wavelet domain to obtain more accurate sparse coefficients and dictionary for image denoising. Extensive experimental results show that the proposed model outperforms state-of-the-art sparse representation-based models and the block-matching and 3D filtering algorithm in terms of denoising performance and the computational efficiency.
基金Supported by the National Natural Science Foundation of China （No. 40701147）, the Natural Science Foundation of Beijing （No. 8102014）, and the Posoctoral Science Foundation of China （Special Issue） （No. 200801096）.
文摘Aimed at solving the problems of road network object selection at any unknown scale, the existing methods on object selection are integrated and extended in this paper, and a new object interpolation method is proposed, which reflects the inheritable and transferable characteristics of related information among multi-scale representation objects, and takes the attribute effects into account. Then the basic idea, the overall framework and the technical flow of the interpolation are put forward, at the samet：me synthetical weight function of the interpolation method is defined and described. The method and technical strategies of object selection are extended, and the key problems are solved, including the dejign of the objective quantitative and structural selections based on the weight values, the interpolation experiment strategies and technical flows, the result of the test shows that the object interpolation method not only inherits the objects at smaller scales, but also takes the attribute effect into account when deriving objects from larger scales according to the road importance, which is a guarantee to objective selection of the road objects at middle scales.
基金supported by the National Natural Science Foundation of China(Grant No.40471090)the Science Innovation Group of Beijing.
文摘This paper contains a review of the development of research on multiple representations compiled from Geographic Information Systems (GIS), including data structure, formalization and storage, and intelligent zoom. A summary is also included of the problems of interconnectivity, consistency maintenance, dynamic query and coexisting updates, as well as a research review of multi-scale databases and related studies. Finally,research directions and foci are proposed for the future design and implementation of multi-scale GIS.
