The random-value impulse noise(RVIN)detection approach in image denoising,which is dependent on manually defined detection thresholds or local window information,does not have strong generalization performance and can...The random-value impulse noise(RVIN)detection approach in image denoising,which is dependent on manually defined detection thresholds or local window information,does not have strong generalization performance and cannot successfully cope with damaged pictures with high noise levels.The fusion of the K-means clustering approach in the noise detection stage is reviewed in this research,and the internal relationship between the flat region and the detail area of the damaged picture is thoroughly explored to suggest an unique two-stage method for gray image denoising.Based on the concept of pixel clustering and grouping,all pixels in the damaged picture are separated into various groups based on gray distance similarity features,and the best detection threshold of each group is solved to identify the noise.In the noise reduction step,a partition decision filter based on the gray value characteristics of pixels in the flat and detail areas is given.For the noise pixels in flat and detail areas,local consensus index(LCI)weighted filter and edge direction filter are designed respectively to recover the pixels damaged by the RVIN.The experimental results show that the accuracy of the proposed noise detection method is more than 90%,and is superior to most mainstream methods.At the same time,the proposed filtering method not only has good noise reduction and generalization performance for natural images and medical images with medium and high noise but also is superior to other advanced filtering technologies in visual effect and objective quality evaluation.展开更多
Due to their adaptability,Unmanned Aerial Vehicles(UAVs)play an essential role in the Internet of Things(IoT).Using wireless power transfer(WPT)techniques,an UAV can be supplied with energy while in flight,thereby ext...Due to their adaptability,Unmanned Aerial Vehicles(UAVs)play an essential role in the Internet of Things(IoT).Using wireless power transfer(WPT)techniques,an UAV can be supplied with energy while in flight,thereby extending the lifetime of this energy-constrained device.This paper investigates the optimization of resource allocation in light of the fact that power transfer and data transmission cannot be performed simultaneously.In this paper,we propose an optimization strategy for the resource allocation of UAVs in sensor communication networks.It is a practical solution to the problem of marine sensor networks that are located far from shore and have limited power.A corresponding system model is summarized based on the scenario and existing theoretical works.The minimum throughputmaximizing object is then formulated as an optimization problem.As swarm intelligence algorithms are utilized effectively in numerous fields,this paper chose to solve the formed optimization problem using the Harris Hawks Optimization and Whale Optimization Algorithms.This paper introduces a method for translating multi-decisions into a row vector in order to adapt swarm intelligence algorithms to the problem,as joint time and energy optimization have two sets of variables.The proposed method performs well in terms of stability and duration.Finally,performance is evaluated through numerical experiments.Simulation results demonstrate that the proposed method performs admirably in the given scenario.展开更多
In this paper,a novel directional modulation(DM)network utilizing the distributed active intelligent reflecting surface(IRS)to enhance the secrecy sum-rate(SSR)performance is established,with each unmanned aerial vehi...In this paper,a novel directional modulation(DM)network utilizing the distributed active intelligent reflecting surface(IRS)to enhance the secrecy sum-rate(SSR)performance is established,with each unmanned aerial vehicle(UAV)hanging an IRS.The degree of freedom(DoF)is only two in the single-IRS-aided DM network,which will seriously limit its rate performance.Multiple active IRSs will create more DoFs for DM network and dramatically enhance its rate.Three IRS-user matching methods,path loss coefficient(PLC)matching,distance matching,and signal-to-interference-plus-noise ratio(SINR)matching,are proposed to enhance the SSR performance,where all IRSs are equipartitioned into two parts,one part is matched to Bob and the other part to Eve.The double layer leakage(DLL)and minimum-mean square error(MMSE)rules,called DLL-MMSE,are adopted to construct beamforming at transmitter,IRS and receiver,respectively.The double layer null-space projection(DLNSP),Rayleigh ratio(RR)and MMSE schemes,called DLNSP-RR-MMSE,are used to acquire the transmit beamforming vector,phase shift matrix(PSM)and receive beamforming vector,respectively.Simulation results show that the proposed SINR matching scheme outperforms the remaining two ones in terms of SSR.It is also verified that a significant SSR enhancement over single IRS is achieved by using multiple distributed IRSs.展开更多
Remote sensing image(RSI)with concurrently high spatial,temporal,and spectral resolutions cannot be produced by a single sensor.Multisource RSI fusion is a convenient technique to realize high spatial resolution multi...Remote sensing image(RSI)with concurrently high spatial,temporal,and spectral resolutions cannot be produced by a single sensor.Multisource RSI fusion is a convenient technique to realize high spatial resolution multispectral(MS)images(spatial spectral fusion,i.e.SSF)and high temporal and spatial resolution MS images(spatiotemporal fusion,i.e.STF).Currently,deep learning-based fusion models can only implement SSF or STF,lacking models that perform both SSF and STF.Multiresolution generative adversarial networks with bidirectional adaptive-stage progressive guided fusion(BAPGF)for RSI are proposed to implement both SSF and STF,namely BPF-MGAN.A bidirectional adaptive-stage feature extraction architecture infine-scale-to-coarse-scale and coarse-scale-to-fine-scale modes is introduced.The designed BAPGF introduces a previous fusion result-oriented cross-stage-level dual-residual attention fusion strategy to enhance critical information and suppress superfluous information.Adaptive resolution U-shaped discriminators are implemented to feed multiresolution context into the generator.A generalized multitask loss function unlimited by no-reference images is developed to strengthen the model via constraints on the multiscale feature,structural,and content similarities.The BPF-MGAN model is validated on SSF datasets and STF datasets.Compared with the state-of-the-art SSF and STF models,results demonstrate the superior performance of the proposed BPF-MGAN model in both subjective and objective evaluations.展开更多
基金This work is supported by the Hainan Provincial Natural Science Foundation of China(621MS019)Major Science and Technology Project of Haikou(Grant:2020-009)+2 种基金Innovative Research Project of Postgraduates in Hainan Province(Qhyb2021-10)National Natural Science Foundation of China(Grant:62062030)Key R&D Project of Hainan province(Grant:ZDYF2021SHFZ243).
文摘The random-value impulse noise(RVIN)detection approach in image denoising,which is dependent on manually defined detection thresholds or local window information,does not have strong generalization performance and cannot successfully cope with damaged pictures with high noise levels.The fusion of the K-means clustering approach in the noise detection stage is reviewed in this research,and the internal relationship between the flat region and the detail area of the damaged picture is thoroughly explored to suggest an unique two-stage method for gray image denoising.Based on the concept of pixel clustering and grouping,all pixels in the damaged picture are separated into various groups based on gray distance similarity features,and the best detection threshold of each group is solved to identify the noise.In the noise reduction step,a partition decision filter based on the gray value characteristics of pixels in the flat and detail areas is given.For the noise pixels in flat and detail areas,local consensus index(LCI)weighted filter and edge direction filter are designed respectively to recover the pixels damaged by the RVIN.The experimental results show that the accuracy of the proposed noise detection method is more than 90%,and is superior to most mainstream methods.At the same time,the proposed filtering method not only has good noise reduction and generalization performance for natural images and medical images with medium and high noise but also is superior to other advanced filtering technologies in visual effect and objective quality evaluation.
基金This research was funded by the National Key Research and Development Program of China under Grant 2018YFB1404400.
文摘Due to their adaptability,Unmanned Aerial Vehicles(UAVs)play an essential role in the Internet of Things(IoT).Using wireless power transfer(WPT)techniques,an UAV can be supplied with energy while in flight,thereby extending the lifetime of this energy-constrained device.This paper investigates the optimization of resource allocation in light of the fact that power transfer and data transmission cannot be performed simultaneously.In this paper,we propose an optimization strategy for the resource allocation of UAVs in sensor communication networks.It is a practical solution to the problem of marine sensor networks that are located far from shore and have limited power.A corresponding system model is summarized based on the scenario and existing theoretical works.The minimum throughputmaximizing object is then formulated as an optimization problem.As swarm intelligence algorithms are utilized effectively in numerous fields,this paper chose to solve the formed optimization problem using the Harris Hawks Optimization and Whale Optimization Algorithms.This paper introduces a method for translating multi-decisions into a row vector in order to adapt swarm intelligence algorithms to the problem,as joint time and energy optimization have two sets of variables.The proposed method performs well in terms of stability and duration.Finally,performance is evaluated through numerical experiments.Simulation results demonstrate that the proposed method performs admirably in the given scenario.
基金supported in part by the National Key Research and Development Program of China(No.2023YFF0612900).
文摘In this paper,a novel directional modulation(DM)network utilizing the distributed active intelligent reflecting surface(IRS)to enhance the secrecy sum-rate(SSR)performance is established,with each unmanned aerial vehicle(UAV)hanging an IRS.The degree of freedom(DoF)is only two in the single-IRS-aided DM network,which will seriously limit its rate performance.Multiple active IRSs will create more DoFs for DM network and dramatically enhance its rate.Three IRS-user matching methods,path loss coefficient(PLC)matching,distance matching,and signal-to-interference-plus-noise ratio(SINR)matching,are proposed to enhance the SSR performance,where all IRSs are equipartitioned into two parts,one part is matched to Bob and the other part to Eve.The double layer leakage(DLL)and minimum-mean square error(MMSE)rules,called DLL-MMSE,are adopted to construct beamforming at transmitter,IRS and receiver,respectively.The double layer null-space projection(DLNSP),Rayleigh ratio(RR)and MMSE schemes,called DLNSP-RR-MMSE,are used to acquire the transmit beamforming vector,phase shift matrix(PSM)and receive beamforming vector,respectively.Simulation results show that the proposed SINR matching scheme outperforms the remaining two ones in terms of SSR.It is also verified that a significant SSR enhancement over single IRS is achieved by using multiple distributed IRSs.
基金funded by the National Key Research and Development Program of China under Grants 2020YFB2104400 and 2020YFB2104401the National Natural Science Foundation of China under Grant 82260362the Hainan Major Science and Technology Program of China under Grant ZDKJ202017.
文摘Remote sensing image(RSI)with concurrently high spatial,temporal,and spectral resolutions cannot be produced by a single sensor.Multisource RSI fusion is a convenient technique to realize high spatial resolution multispectral(MS)images(spatial spectral fusion,i.e.SSF)and high temporal and spatial resolution MS images(spatiotemporal fusion,i.e.STF).Currently,deep learning-based fusion models can only implement SSF or STF,lacking models that perform both SSF and STF.Multiresolution generative adversarial networks with bidirectional adaptive-stage progressive guided fusion(BAPGF)for RSI are proposed to implement both SSF and STF,namely BPF-MGAN.A bidirectional adaptive-stage feature extraction architecture infine-scale-to-coarse-scale and coarse-scale-to-fine-scale modes is introduced.The designed BAPGF introduces a previous fusion result-oriented cross-stage-level dual-residual attention fusion strategy to enhance critical information and suppress superfluous information.Adaptive resolution U-shaped discriminators are implemented to feed multiresolution context into the generator.A generalized multitask loss function unlimited by no-reference images is developed to strengthen the model via constraints on the multiscale feature,structural,and content similarities.The BPF-MGAN model is validated on SSF datasets and STF datasets.Compared with the state-of-the-art SSF and STF models,results demonstrate the superior performance of the proposed BPF-MGAN model in both subjective and objective evaluations.
