We propose an end-to-end dehazing model based on deep learning(CNN network)and uses the dehazing model re-proposed by AOD-Net based on the atmospheric scattering model for dehazing.Compare to the previously proposed d...We propose an end-to-end dehazing model based on deep learning(CNN network)and uses the dehazing model re-proposed by AOD-Net based on the atmospheric scattering model for dehazing.Compare to the previously proposed dehazing network,the dehazing model proposed in this paper make use of the FPN network structure in the field of target detection,and uses five feature maps of different sizes to better obtain features of different proportions and different sub-regions.A large amount of experimental data proves that the dehazing model proposed in this paper is superior to previous dehazing technologies in terms of PSNR,SSIM,and subjective visual quality.In addition,it achieved a good performance in speed by using EfficientNet B0 as a feature extractor.We find that only using high-level semantic features can not effectively obtain all the information in the image.The FPN structure used in this paper can effectively integrate the high-level semantics and the low-level semantics,and can better take into account the global and local features.The five feature maps with different sizes are not simply weighted and fused.In order to keep all their information,we put them all together and get the final features through decode layers.At the same time,we have done a comparative experiment between ResNet with FPN and EfficientNet with BiFPN.It is proved that EfficientNet with BiFPN can obtain image features more efficiently.Therefore,EfficientNet with BiFPN is chosen as our network feature extraction.展开更多
The attack angle may greatly affect the hypersonic plasma sheaths around the re-entry vehicle,thereby affecting the transmission characteristics of electromagnetic(EM)waves in the sheaths.In this paper,we propose an i...The attack angle may greatly affect the hypersonic plasma sheaths around the re-entry vehicle,thereby affecting the transmission characteristics of electromagnetic(EM)waves in the sheaths.In this paper,we propose an integrated three-dimensional(3D)model with various attack angles and realistic flying conditions of radio attenuation measurement C-II(RAM C-II)re-entry tasks for analyzing the effect of the attack angle on the transmission characteristics of EM waves in the sheaths.It is shown that the electron density and collision frequency of the sheath on the windward side can be increased by an order of magnitude with the increase of the attack angle.Meanwhile,the thickness of the sheath on the leeward side is increased where the electron density and collision frequency are reduced.The EM waves are mainly reflected on the windward plasma sheath due to the cutoff effect,and the radio-frequency(RF)blackout is mitigated if the antenna is positioned on the leeward side.Thus,by planning the trajectory properly and installing the antenna accordingly during the re-entry,it is possible to provide an approach for mitigation of the RF blackout problem to an extent.展开更多
基金the Key Research and Development Program of Hunan Province(No.2019SK2161)the Key Research and Development Program of Hunan Province(No.2016SK2017).
文摘We propose an end-to-end dehazing model based on deep learning(CNN network)and uses the dehazing model re-proposed by AOD-Net based on the atmospheric scattering model for dehazing.Compare to the previously proposed dehazing network,the dehazing model proposed in this paper make use of the FPN network structure in the field of target detection,and uses five feature maps of different sizes to better obtain features of different proportions and different sub-regions.A large amount of experimental data proves that the dehazing model proposed in this paper is superior to previous dehazing technologies in terms of PSNR,SSIM,and subjective visual quality.In addition,it achieved a good performance in speed by using EfficientNet B0 as a feature extractor.We find that only using high-level semantic features can not effectively obtain all the information in the image.The FPN structure used in this paper can effectively integrate the high-level semantics and the low-level semantics,and can better take into account the global and local features.The five feature maps with different sizes are not simply weighted and fused.In order to keep all their information,we put them all together and get the final features through decode layers.At the same time,we have done a comparative experiment between ResNet with FPN and EfficientNet with BiFPN.It is proved that EfficientNet with BiFPN can obtain image features more efficiently.Therefore,EfficientNet with BiFPN is chosen as our network feature extraction.
基金supported by National Natural Science Foundation of China(Nos.92271202 and 92371105)。
文摘The attack angle may greatly affect the hypersonic plasma sheaths around the re-entry vehicle,thereby affecting the transmission characteristics of electromagnetic(EM)waves in the sheaths.In this paper,we propose an integrated three-dimensional(3D)model with various attack angles and realistic flying conditions of radio attenuation measurement C-II(RAM C-II)re-entry tasks for analyzing the effect of the attack angle on the transmission characteristics of EM waves in the sheaths.It is shown that the electron density and collision frequency of the sheath on the windward side can be increased by an order of magnitude with the increase of the attack angle.Meanwhile,the thickness of the sheath on the leeward side is increased where the electron density and collision frequency are reduced.The EM waves are mainly reflected on the windward plasma sheath due to the cutoff effect,and the radio-frequency(RF)blackout is mitigated if the antenna is positioned on the leeward side.Thus,by planning the trajectory properly and installing the antenna accordingly during the re-entry,it is possible to provide an approach for mitigation of the RF blackout problem to an extent.