Power transmission lines are a critical component of the entire power system,and ice accretion incidents caused by various types of power systems can result in immeasurable harm.Currently,network models used for ice d...Power transmission lines are a critical component of the entire power system,and ice accretion incidents caused by various types of power systems can result in immeasurable harm.Currently,network models used for ice detection on power transmission lines require a substantial amount of sample data to support their training,and their drawback is that detection accuracy is significantly affected by the inaccurate annotation among training dataset.Therefore,we propose a transformer-based detection model,structured into two stages to collectively address the impact of inaccurate datasets on model training.In the first stage,a spatial similarity enhancement(SSE)module is designed to leverage spatial information to enhance the construction of the detection framework,thereby improving the accuracy of the detector.In the second stage,a target similarity enhancement(TSE)module is introduced to enhance object-related features,reducing the impact of inaccurate data on model training,thereby expanding global correlation.Additionally,by incorporating a multi-head adaptive attention window(MAAW),spatial information is combined with category information to achieve information interaction.Simultaneously,a quasi-wavelet structure,compatible with deep learning,is employed to highlight subtle features at different scales.Experimental results indicate that the proposed model in this paper outperforms existing mainstream detection models,demonstrating superior performance and stability.展开更多
The resolution of most spatially resolved transcriptomic technologies usually cannot attain the single-cell level,limiting their applications in biological discoveries.Here,we introduce ImSpiRE,an image feature-aided ...The resolution of most spatially resolved transcriptomic technologies usually cannot attain the single-cell level,limiting their applications in biological discoveries.Here,we introduce ImSpiRE,an image feature-aided spatial resolution enhancement method for in situ capturing spatial transcriptome.Taking the information stored in histological images,ImSpiRE solves an optimal transport problem to redistribute the expression profiles of spots to construct new transcriptional profiles with enhanced resolution,together with extending the gene expression profiles into unmeasured regions.Applications to multiple datasets confirm that ImSpiRE can enhance spatial resolution to the subspot level while contributing to the discovery of tissue domains,signaling communication patterns,and spatiotemporal characterization.展开更多
Gamma-ray imaging systems are powerful tools in radiographic diagnosis.However,the recorded images suffer from degradations such as noise,blurring,and downsampling,consequently failing to meet high-precision diagnosti...Gamma-ray imaging systems are powerful tools in radiographic diagnosis.However,the recorded images suffer from degradations such as noise,blurring,and downsampling,consequently failing to meet high-precision diagnostic requirements.In this paper,we propose a novel single-image super-resolution algorithm to enhance the spatial resolution of gamma-ray imaging systems.A mathematical model of the gamma-ray imaging system is established based on maximum a posteriori estimation.Within the plug-and-play framework,the half-quadratic splitting method is employed to decouple the data fidelit term and the regularization term.An image denoiser using convolutional neural networks is adopted as an implicit image prior,referred to as a deep denoiser prior,eliminating the need to explicitly design a regularization term.Furthermore,the impact of the image boundary condition on reconstruction results is considered,and a method for estimating image boundaries is introduced.The results show that the proposed algorithm can effectively addresses boundary artifacts.By increasing the pixel number of the reconstructed images,the proposed algorithm is capable of recovering more details.Notably,in both simulation and real experiments,the proposed algorithm is demonstrated to achieve subpixel resolution,surpassing the Nyquist sampling limit determined by the camera pixel size.展开更多
Quantum imaging with spatially entangled photons offers advantages such as enhanced spatial resolution,robustness against noise,and counterintuitive phenomena,while a biphoton spatial aberration generally degrades its...Quantum imaging with spatially entangled photons offers advantages such as enhanced spatial resolution,robustness against noise,and counterintuitive phenomena,while a biphoton spatial aberration generally degrades its performance.Biphoton aberration correction has been achieved by using classical beams to detect the aberration source or scanning the correction phase on biphotons if the source is unreachable.Here,a new method named position-correlated biphoton Shack-Hartmann wavefront sensing is introduced,where the phase pattern added on photon pairs with a strong position correlation is reconstructed from their position centroid distribution at the back focal plane of a microlens array.Experimentally,biphoton phase measurement and adaptive imaging against the disturbance of a plastic film are demonstrated.This single-shot method is a more direct and efficient approach toward quantum adaptive optics,suitable for integration into quantum microscopy,remote imaging,and communication.展开更多
Consistent bio-optical properties across multiple ocean color satellites are the key prerequisite to merging products from these satellites,thereby enhancing spatial coverage and extending temporal spans.However,due t...Consistent bio-optical properties across multiple ocean color satellites are the key prerequisite to merging products from these satellites,thereby enhancing spatial coverage and extending temporal spans.However,due to factors such as sensor specifics and separate data processing algorithms,bio-optical properties(e.g.,remote sensing reflectance,R_(rs))from different ocean color missions exhibit varying discrepancies in oceanic,coastal,and inland waters.Here,we introduce a cross-satellite atmospheric correction(CSAC)scheme,which could greatly improve the consistency of R_(rs)products between MODIS-Aqua and other satellite ocean color missions.Specifically,using an inclusive high-quality R_(rs)dataset of oceanic waters obtained from MODIS-Aqua as the reference,and as an example,top-of-atmosphere reflectance from SeaWiFS(Sea-Viewing Wide Field-of-View Sensor)is directly processed to MODIS-Aqua-equivalent R_(rs)(R^(MA−eqv)_(rs))via CSAC.As a demonstration,for independent space-time matched measurements between MODIS-Aqua and SeaWiFS,the mean absolute percent difference(MAPD)between RMA−eqv rs and MODIS-Aqua R_(rs)ranges from 5.9%to 22.2%across wavelengths from 412 to 667 nm.In contrast,the MAPD values between the NASA standard SeaWiFS and MODIS-Aqua R_(rs)products range from 10.1%to 55.1%for the same spectral bands.These results highlight the potential of CSAC in obtaining consistent R_(rs)products and,subsequently,R_(rs)-derived bio-optical properties,from various ocean color satellites,facilitating extensive and long-term ocean color observations of the global ocean.展开更多
文摘Power transmission lines are a critical component of the entire power system,and ice accretion incidents caused by various types of power systems can result in immeasurable harm.Currently,network models used for ice detection on power transmission lines require a substantial amount of sample data to support their training,and their drawback is that detection accuracy is significantly affected by the inaccurate annotation among training dataset.Therefore,we propose a transformer-based detection model,structured into two stages to collectively address the impact of inaccurate datasets on model training.In the first stage,a spatial similarity enhancement(SSE)module is designed to leverage spatial information to enhance the construction of the detection framework,thereby improving the accuracy of the detector.In the second stage,a target similarity enhancement(TSE)module is introduced to enhance object-related features,reducing the impact of inaccurate data on model training,thereby expanding global correlation.Additionally,by incorporating a multi-head adaptive attention window(MAAW),spatial information is combined with category information to achieve information interaction.Simultaneously,a quasi-wavelet structure,compatible with deep learning,is employed to highlight subtle features at different scales.Experimental results indicate that the proposed model in this paper outperforms existing mainstream detection models,demonstrating superior performance and stability.
基金supported by the National Key Research and Development Program of China(2021YFA1302500)the National Natural Science Foundation of China(32030022,32325012,31970642)the Science and Technology Commission of Shanghai Municipality(23JS1401200).
文摘The resolution of most spatially resolved transcriptomic technologies usually cannot attain the single-cell level,limiting their applications in biological discoveries.Here,we introduce ImSpiRE,an image feature-aided spatial resolution enhancement method for in situ capturing spatial transcriptome.Taking the information stored in histological images,ImSpiRE solves an optimal transport problem to redistribute the expression profiles of spots to construct new transcriptional profiles with enhanced resolution,together with extending the gene expression profiles into unmeasured regions.Applications to multiple datasets confirm that ImSpiRE can enhance spatial resolution to the subspot level while contributing to the discovery of tissue domains,signaling communication patterns,and spatiotemporal characterization.
基金supported by the National Natural Science Foundation of China(Grant No.12175183)。
文摘Gamma-ray imaging systems are powerful tools in radiographic diagnosis.However,the recorded images suffer from degradations such as noise,blurring,and downsampling,consequently failing to meet high-precision diagnostic requirements.In this paper,we propose a novel single-image super-resolution algorithm to enhance the spatial resolution of gamma-ray imaging systems.A mathematical model of the gamma-ray imaging system is established based on maximum a posteriori estimation.Within the plug-and-play framework,the half-quadratic splitting method is employed to decouple the data fidelit term and the regularization term.An image denoiser using convolutional neural networks is adopted as an implicit image prior,referred to as a deep denoiser prior,eliminating the need to explicitly design a regularization term.Furthermore,the impact of the image boundary condition on reconstruction results is considered,and a method for estimating image boundaries is introduced.The results show that the proposed algorithm can effectively addresses boundary artifacts.By increasing the pixel number of the reconstructed images,the proposed algorithm is capable of recovering more details.Notably,in both simulation and real experiments,the proposed algorithm is demonstrated to achieve subpixel resolution,surpassing the Nyquist sampling limit determined by the camera pixel size.
基金funded by the Innovation Program for Quantum Science and Technology(Grant Nos.2021ZD0301200 and 2021ZD0301400)the National Natural Science Foundation of China(Grant Nos.92365205,11821404,and W2411001)the USTC Major Frontier Research Program(Grant No.LS2030000002).
文摘Quantum imaging with spatially entangled photons offers advantages such as enhanced spatial resolution,robustness against noise,and counterintuitive phenomena,while a biphoton spatial aberration generally degrades its performance.Biphoton aberration correction has been achieved by using classical beams to detect the aberration source or scanning the correction phase on biphotons if the source is unreachable.Here,a new method named position-correlated biphoton Shack-Hartmann wavefront sensing is introduced,where the phase pattern added on photon pairs with a strong position correlation is reconstructed from their position centroid distribution at the back focal plane of a microlens array.Experimentally,biphoton phase measurement and adaptive imaging against the disturbance of a plastic film are demonstrated.This single-shot method is a more direct and efficient approach toward quantum adaptive optics,suitable for integration into quantum microscopy,remote imaging,and communication.
基金support from the National Natural Science Foundation of China(#42430107 and#42250710150)the National Key Research and Development Program of China(2022YFC3104903)Fujian Satellite Data Development,Co.,Ltd.,and Fujian Haisi Digital Technology Co.,Ltd.
文摘Consistent bio-optical properties across multiple ocean color satellites are the key prerequisite to merging products from these satellites,thereby enhancing spatial coverage and extending temporal spans.However,due to factors such as sensor specifics and separate data processing algorithms,bio-optical properties(e.g.,remote sensing reflectance,R_(rs))from different ocean color missions exhibit varying discrepancies in oceanic,coastal,and inland waters.Here,we introduce a cross-satellite atmospheric correction(CSAC)scheme,which could greatly improve the consistency of R_(rs)products between MODIS-Aqua and other satellite ocean color missions.Specifically,using an inclusive high-quality R_(rs)dataset of oceanic waters obtained from MODIS-Aqua as the reference,and as an example,top-of-atmosphere reflectance from SeaWiFS(Sea-Viewing Wide Field-of-View Sensor)is directly processed to MODIS-Aqua-equivalent R_(rs)(R^(MA−eqv)_(rs))via CSAC.As a demonstration,for independent space-time matched measurements between MODIS-Aqua and SeaWiFS,the mean absolute percent difference(MAPD)between RMA−eqv rs and MODIS-Aqua R_(rs)ranges from 5.9%to 22.2%across wavelengths from 412 to 667 nm.In contrast,the MAPD values between the NASA standard SeaWiFS and MODIS-Aqua R_(rs)products range from 10.1%to 55.1%for the same spectral bands.These results highlight the potential of CSAC in obtaining consistent R_(rs)products and,subsequently,R_(rs)-derived bio-optical properties,from various ocean color satellites,facilitating extensive and long-term ocean color observations of the global ocean.
