This paper presents a trainable Generative Adversarial Network(GAN)-based end-to-end system for image dehazing,which is named the DehazeGAN.DehazeGAN can be used for edge computing-based applications,such as roadside ...This paper presents a trainable Generative Adversarial Network(GAN)-based end-to-end system for image dehazing,which is named the DehazeGAN.DehazeGAN can be used for edge computing-based applications,such as roadside monitoring.It adopts two networks:one is generator(G),and the other is discriminator(D).The G adopts the U-Net architecture,whose layers are particularly designed to incorporate the atmospheric scattering model of image dehazing.By using a reformulated atmospheric scattering model,the weights of the generator network are initialized by the coarse transmission map,and the biases are adaptively adjusted by using the previous round's trained weights.Since the details may be blurry after the fog is removed,the contrast loss is added to enhance the visibility actively.Aside from the typical GAN adversarial loss,the pixel-wise Mean Square Error(MSE)loss,the contrast loss and the dark channel loss are introduced into the generator loss function.Extensive experiments on benchmark images,the results of which are compared with those of several state-of-the-art methods,demonstrate that the proposed DehazeGAN performs better and is more effective.展开更多
Mobile Edge Computing(MEC)can support various high-reliability and low-delay applications in Maritime Networks(MNs).However,security risks in computing task offloading exist.In this study,the location privacy leakage ...Mobile Edge Computing(MEC)can support various high-reliability and low-delay applications in Maritime Networks(MNs).However,security risks in computing task offloading exist.In this study,the location privacy leakage risk of Maritime Mobile Terminals(MMTs)is quantified during task offloading and relevant Location Privacy Protection(LPP)schemes of MMT are considered under two kinds of task offloading scenarios.In single-MMT and single-time offloading scenario,a dynamic cache and spatial cloaking-based LPP(DS-CLP)algorithm is proposed;and under the multi-MMTs and multi-time offloading scenario,a pseudonym and alterable silent period-based LPP(PA-SLP)strategy is proposed.Simulation results show that the DS-CLP can save the response time and communication cost compared with traditional algorithms while protecting the MMT location privacy.Meanwhile,extending the alterable silent period,increasing the number of MMTs in the maritime area or improving the pseudonym update probability can enhance the LPP effect of MMTs in PA-SLP.Furthermore,the study results can be effectively applied to MNs with poor communication environments and relatively insufficient computing resources.展开更多
基金This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(grant number NRF-2018R1D1A1B07043331).
文摘This paper presents a trainable Generative Adversarial Network(GAN)-based end-to-end system for image dehazing,which is named the DehazeGAN.DehazeGAN can be used for edge computing-based applications,such as roadside monitoring.It adopts two networks:one is generator(G),and the other is discriminator(D).The G adopts the U-Net architecture,whose layers are particularly designed to incorporate the atmospheric scattering model of image dehazing.By using a reformulated atmospheric scattering model,the weights of the generator network are initialized by the coarse transmission map,and the biases are adaptively adjusted by using the previous round's trained weights.Since the details may be blurry after the fog is removed,the contrast loss is added to enhance the visibility actively.Aside from the typical GAN adversarial loss,the pixel-wise Mean Square Error(MSE)loss,the contrast loss and the dark channel loss are introduced into the generator loss function.Extensive experiments on benchmark images,the results of which are compared with those of several state-of-the-art methods,demonstrate that the proposed DehazeGAN performs better and is more effective.
基金supported by the National Key Research and Development Program of China (2021YFE0105500)the National Natural Science Foundation of China (61801166).
文摘Mobile Edge Computing(MEC)can support various high-reliability and low-delay applications in Maritime Networks(MNs).However,security risks in computing task offloading exist.In this study,the location privacy leakage risk of Maritime Mobile Terminals(MMTs)is quantified during task offloading and relevant Location Privacy Protection(LPP)schemes of MMT are considered under two kinds of task offloading scenarios.In single-MMT and single-time offloading scenario,a dynamic cache and spatial cloaking-based LPP(DS-CLP)algorithm is proposed;and under the multi-MMTs and multi-time offloading scenario,a pseudonym and alterable silent period-based LPP(PA-SLP)strategy is proposed.Simulation results show that the DS-CLP can save the response time and communication cost compared with traditional algorithms while protecting the MMT location privacy.Meanwhile,extending the alterable silent period,increasing the number of MMTs in the maritime area or improving the pseudonym update probability can enhance the LPP effect of MMTs in PA-SLP.Furthermore,the study results can be effectively applied to MNs with poor communication environments and relatively insufficient computing resources.