Construction of high resolution images from low resolution sequences having rigid or semi-rigid ob-jects with unified motions is often important in surveillance and other applications.In this paper a novelobject-based...Construction of high resolution images from low resolution sequences having rigid or semi-rigid ob-jects with unified motions is often important in surveillance and other applications.In this paper a novelobject-based super resolution reconstruction scheme was proposed,in which a six-parameter affine model-based object tracking and registration method was first used to segment and match objects among a se-quence of low resolution frames.The motion model was then further extended to the traditional maximuma posterior(MAP)super resolution algorithm.The proposed object tracking and registration method wasevaluated by both simulated and real acquired sequences.The results have demonstrated the high accura-cy of the proposed object based method and the enhanced reconstruction performance of the extended ap-proach.展开更多
Construction of high resolution images from low resolution sequences is often im- portant in surveillance applications. In this letter, an affine based multi-scale block-matching image registration algorithm is first ...Construction of high resolution images from low resolution sequences is often im- portant in surveillance applications. In this letter, an affine based multi-scale block-matching image registration algorithm is first proposed. The images to be registered are divided into overlapped blocks of different size according to its motions. The Least Square (LS) image reg- istration algorithm is extended to match the blocks. Then an object based Super Resolution (SR) scheme is designed, the Maximum A Priori (MAP) super resolution algorithm is extended to enhance the resolution of the interest objects. Experimental results show that the proposed multi-scale registration method provides more accurate registration between frames. Further more, the object based super resolution scheme shows an enhanced performance compared with the traditional MAP method.展开更多
Background:Magnetic resonance imaging(MRI)is of considerable importance due to its wide range of applications in both scientific research and clinical diagnostics.Acquiring high-quality MRI data is of paramount import...Background:Magnetic resonance imaging(MRI)is of considerable importance due to its wide range of applications in both scientific research and clinical diagnostics.Acquiring high-quality MRI data is of paramount importance.Super-resolution reconstruction serves as a post-acquisition method capable of improving MRI data quality.Current methods predominantly utilize convolutional neural networks in super-resolution reconstruction.However,convolutional layers have inherent limitations in capturing extensive spatial dependencies due to their localized nature.Methods:We developed a new methodology that enables rapid and high-quality MRI data acquisition through a novel super-resolution approach.We proposed an innovative architecture using transformers to exploit long-range spatial dependencies present in images,allowing for an unsupervised learning framework specifically designed for super-resolution tasks tailored to individual subject.We validated our approach using both simulated data and clinical data comprising 40 scans acquired with a 3-T MRI system.Results:We obtained images with T2 contrast at an isotropic spatial resolution of 500μm in just 4 min of imaging time,and simultaneously,the signal-to-noise ratio and contrast-to-noise ratio were improved by 13.23% and 18.45%,respectively,in comparison to current leading super-resolution techniques.Conclusions:The results demonstrated that incorporating long-range spatial dependencies substantially improved super-resolution reconstruction,thereby allowing for the acquisition of high-quality MRI data with reduced imaging time.展开更多
基金the National Natural Science Foundation of China(No90304001,60472036)the Beijing Natural Science Foundation(4052007)+1 种基金the National Key Lab of Communication Foundation,UEST,China(51434050105QT0101) the PolyU/UGC grants(B-Q698)
文摘Construction of high resolution images from low resolution sequences having rigid or semi-rigid ob-jects with unified motions is often important in surveillance and other applications.In this paper a novelobject-based super resolution reconstruction scheme was proposed,in which a six-parameter affine model-based object tracking and registration method was first used to segment and match objects among a se-quence of low resolution frames.The motion model was then further extended to the traditional maximuma posterior(MAP)super resolution algorithm.The proposed object tracking and registration method wasevaluated by both simulated and real acquired sequences.The results have demonstrated the high accura-cy of the proposed object based method and the enhanced reconstruction performance of the extended ap-proach.
基金Supported by the National Natural Science Founda-tion of China (No.60472036)the Beijing Natural Science Foundation (No.4052007)the Beijing Novel Program (No.2005B08).
文摘Construction of high resolution images from low resolution sequences is often im- portant in surveillance applications. In this letter, an affine based multi-scale block-matching image registration algorithm is first proposed. The images to be registered are divided into overlapped blocks of different size according to its motions. The Least Square (LS) image reg- istration algorithm is extended to match the blocks. Then an object based Super Resolution (SR) scheme is designed, the Maximum A Priori (MAP) super resolution algorithm is extended to enhance the resolution of the interest objects. Experimental results show that the proposed multi-scale registration method provides more accurate registration between frames. Further more, the object based super resolution scheme shows an enhanced performance compared with the traditional MAP method.
基金supported in part by the Beijing Natural Science Foundation under Award Number L258055in part by the Major Program of the National Natural Science Foundation of China under Award Numbers 62394310 and 62394312in part by the National Institutes of Health(NIH)under Award Numbers R01 EB019483,R01 NS106030,R01 NS124212,R01 LM013608,R01 HD109395,R01 EB031849,R01 NS133228,R01 NS121657,R21 EB036105,and S10OD025111.
文摘Background:Magnetic resonance imaging(MRI)is of considerable importance due to its wide range of applications in both scientific research and clinical diagnostics.Acquiring high-quality MRI data is of paramount importance.Super-resolution reconstruction serves as a post-acquisition method capable of improving MRI data quality.Current methods predominantly utilize convolutional neural networks in super-resolution reconstruction.However,convolutional layers have inherent limitations in capturing extensive spatial dependencies due to their localized nature.Methods:We developed a new methodology that enables rapid and high-quality MRI data acquisition through a novel super-resolution approach.We proposed an innovative architecture using transformers to exploit long-range spatial dependencies present in images,allowing for an unsupervised learning framework specifically designed for super-resolution tasks tailored to individual subject.We validated our approach using both simulated data and clinical data comprising 40 scans acquired with a 3-T MRI system.Results:We obtained images with T2 contrast at an isotropic spatial resolution of 500μm in just 4 min of imaging time,and simultaneously,the signal-to-noise ratio and contrast-to-noise ratio were improved by 13.23% and 18.45%,respectively,in comparison to current leading super-resolution techniques.Conclusions:The results demonstrated that incorporating long-range spatial dependencies substantially improved super-resolution reconstruction,thereby allowing for the acquisition of high-quality MRI data with reduced imaging time.
