摘要 :
In this paper, we address the multiframe super resolution problem from a set of degraded, under-sampled, shifted and rotated low resolution images to obtain a high resolution image using the variational Bayesian methods. In the Ba...
展开
In this paper, we address the multiframe super resolution problem from a set of degraded, under-sampled, shifted and rotated low resolution images to obtain a high resolution image using the variational Bayesian methods. In the Bayesian framework a prior model on the high resolution image need to be specified, its aim is to summarize our knowledge of the image and to constraint the ill-posed image reconstruction problem. Appropriate prior model selection according to the super resolution scenario is a critical issue. Here we propose the one-parameter l_1 prior. Experimental results demonstrate that the proposed method is very effective and compared favorably to state-of-the-art super resolution algorithms.
收起
摘要 :
In this paper, we address the multiframe super resolution problem from a set of degraded, under-sampled, shifted and rotated low resolution images to obtain a high resolution image using the variational Bayesian methods. In the Ba...
展开
In this paper, we address the multiframe super resolution problem from a set of degraded, under-sampled, shifted and rotated low resolution images to obtain a high resolution image using the variational Bayesian methods. In the Bayesian framework a prior model on the high resolution image need to be specified, its aim is to summarize our knowledge of the image and to constraint the ill-posed image reconstruction problem. Appropriate prior model selection according to the super resolution scenario is a critical issue. Here we propose the one-parameter l_1 prior. Experimental results demonstrate that the proposed method is very effective and compared favorably to state-of-the-art super resolution algorithms.
收起
摘要 :
In this paper, we address the multiframe super resolution problem from a set of degraded, under-sampled, shifted and rotated low resolution images to obtain a high resolution image using the variational Bayesian methods. In the Ba...
展开
In this paper, we address the multiframe super resolution problem from a set of degraded, under-sampled, shifted and rotated low resolution images to obtain a high resolution image using the variational Bayesian methods. In the Bayesian framework a prior model on the high resolution image need to be specified, its aim is to summarize our knowledge of the image and to constraint the ill-posed image reconstruction problem. Appropriate prior model selection according to the super resolution scenario is a critical issue. Here we propose the one-parameter l_1 prior. Experimental results demonstrate that the proposed method is very effective and compared favorably to state-of-the-art super resolution algorithms.
收起
摘要 :
The lack of access to large annotated datasets and legal concerns regarding patient privacy are limiting factors for many applications of deep learning in the retinal image analysis domain. Therefore the idea of generating synthet...
展开
The lack of access to large annotated datasets and legal concerns regarding patient privacy are limiting factors for many applications of deep learning in the retinal image analysis domain. Therefore the idea of generating synthetic retinal images, indiscernible from real data, has gained more interest. Generative adversarial networks (GANs) have proven to be a valuable framework for producing synthetic databases of anatomically consistent retinal fundus images. In Ophthalmology, GANs in particular have shown increased interest. We discuss here the potential advantages and limitations that need to be addressed before GANs can be widely adopted for retinal imaging.
收起
摘要 :
The lack of access to large annotated datasets and legal concerns regarding patient privacy are limiting factors for many applications of deep learning in the retinal image analysis domain. Therefore the idea of generating synthet...
展开
The lack of access to large annotated datasets and legal concerns regarding patient privacy are limiting factors for many applications of deep learning in the retinal image analysis domain. Therefore the idea of generating synthetic retinal images, indiscernible from real data, has gained more interest. Generative adversarial networks (GANs) have proven to be a valuable framework for producing synthetic databases of anatomically consistent retinal fundus images. In Ophthalmology, GANs in particular have shown increased interest. We discuss here the potential advantages and limitations that need to be addressed before GANs can be widely adopted for retinal imaging.
收起
摘要 :
Program of ECH of 4MW at 140 GHz is launched for pressure and current density profile control on EAST. Several ECE diagnostics are under development as important ingredient of the research program of EAST. HT-7 is equipped with a ...
展开
Program of ECH of 4MW at 140 GHz is launched for pressure and current density profile control on EAST. Several ECE diagnostics are under development as important ingredient of the research program of EAST. HT-7 is equipped with a heterodyne radiometer containing 16 channels and a ECE image system with 8(radial)xl6(vertical) channels. Physical issues including fluctuation by electron and ion modes, low frequency Zonal Flow, magnetic reconnection mechanism, anomalous Doppler resonance effect, etc were investigated on HT-7. These two systems have been moved to EAST after some modifications. New ECE systems including a 32-channel ECE system covering 104?68 GHz and a ECEI system of 24(radial)xl6(vertical) channels are under developing. These two systems are designed to fit the ECH plasma regimes and synergetic work for long range correlation research of plasma turbulence. A grating polychromator ECE system will be installed soon for Te profile measurement covering whole operation range of toroidal magnetic field on EAST.
收起
摘要 :
Program of ECH of 4MW at 140 GHz is launched for pressure and current density profile control on EAST. Several ECE diagnostics are under development as important ingredient of the research program of EAST. HT-7 is equipped with a ...
展开
Program of ECH of 4MW at 140 GHz is launched for pressure and current density profile control on EAST. Several ECE diagnostics are under development as important ingredient of the research program of EAST. HT-7 is equipped with a heterodyne radiometer containing 16 channels and a ECE image system with 8(radial)xl6(vertical) channels. Physical issues including fluctuation by electron and ion modes, low frequency Zonal Flow, magnetic reconnection mechanism, anomalous Doppler resonance effect, etc were investigated on HT-7. These two systems have been moved to EAST after some modifications. New ECE systems including a 32-channel ECE system covering 104?68 GHz and a ECEI system of 24(radial)xl6(vertical) channels are under developing. These two systems are designed to fit the ECH plasma regimes and synergetic work for long range correlation research of plasma turbulence. A grating polychromator ECE system will be installed soon for Te profile measurement covering whole operation range of toroidal magnetic field on EAST.
收起
摘要 :
The safety situation of coal mining in China, especially the southwest is serious for the complex methane and geological conditions. The permeability of coal seam in these areas is as low as 9.37e-5~1.73 e-3 m~3/(MPa2.d), the met...
展开
The safety situation of coal mining in China, especially the southwest is serious for the complex methane and geological conditions. The permeability of coal seam in these areas is as low as 9.37e-5~1.73 e-3 m~3/(MPa2.d), the methane pressure is as high as 2.5~6.0 MPa, and the period of rock cross-cut coal uncovering is more than 6 months. To solve those problems, a new idea of drilling and slotting in coal seam with self-excited pulsed water jet is proposed to improve the permeability of seam, increase the methane desorption rate, and shorten the cycle of rock cross-cut coal uncovering. For this purpose, characteristics of self-excited pulsed water jets and effects on cracking coal seam are investigated, and the devices for drilling and slotting with self-excited pulsed water jet are designed. The hydraulic parameters of self-excited pulsed water jet and nozzle structure are optimized by analysing the relationships between the pump pressure, flow rate, the depth and width of cutting, and the methane adsorption rate. Practical applications in Feng-Chun coal mine, Songzao Coal-Electricity Co. Ltd. Chongqing, China show that this technology can produce over 1.5 m deep slots in coal seam, and the methane can be desorbed more freely. Investigation indicated that and the amount of gas drainage of cut hole increases by 4.4 times over uncut hole. The quantity of holes and the construction period decrease by 60% and 70 days respectively.
收起