High-resolution video inpainting based on spatial structure and temporal edge information

Author(s):  
Dezhi Bo ◽  
Ran Ma ◽  
Keke Wang ◽  
Kai Li ◽  
Ping An
1967 ◽  
Vol 31 ◽  
pp. 45-46
Author(s):  
Carl Heiles

High-resolution 21-cm line observations in a region aroundlII= 120°,b11= +15°, have revealed four types of structure in the interstellar hydrogen: a smooth background, large sheets of density 2 atoms cm-3, clouds occurring mostly in groups, and ‘Cloudlets’ of a few solar masses and a few parsecs in size; the velocity dispersion in the Cloudlets is only 1 km/sec. Strong temperature variations in the gas are in evidence.


1991 ◽  
Vol 147 ◽  
pp. 411-412
Author(s):  
S. K. Ghosh ◽  
T. N. Rengarajan ◽  
R. P. Verma

IRAS has provided infrared maps of a large number of galaxies. However the size of IRAS survey detectors is quite large (∼5′ in the cross-scan direction) and there is a need for improving the resolution of these maps. In order to understand the spatial structure of galaxies, we have generated high resolution maps of 18 large galaxies by deconvolving the IRAS pointed observations from survey detectors as well as from Chopped Photometric Channel (CPC) using Maximum Entropy Method (MEM).


Author(s):  
Zichong Chen ◽  
Xianwen Luo

Aiming at the problem of low baud rate of traditional high-resolution image synchronous acquisition fuzzy control method, a high-resolution image synchronous acquisition fuzzy control method based on machine learning is designed. By detecting the fuzzy edge information of high-resolution image, the fuzzy membership function of synchronous acquisition quantity is proposed, and the gradient amplitude of synchronous acquisition quantity of high-resolution image is calculated. The unsupervised learning algorithm based on machine learning is used to cluster the fuzzy control data, so as to determine the fuzzy space of synchronous acquisition quantity of high-resolution image, and calculate the fuzzy feature similarity, the fuzzy control of synchronous acquisition quantity of high resolution image is realized. Experimental results show that the controlled wave rate in this paper solves the problem of low wave rate in 255.63 bps/h-271.33 bps/h, and significantly improves the control accuracy.


1991 ◽  
Vol 147 ◽  
pp. 411-412
Author(s):  
S. K. Ghosh ◽  
T. N. Rengarajan ◽  
R. P. Verma

IRAS has provided infrared maps of a large number of galaxies. However the size of IRAS survey detectors is quite large (∼5′ in the cross-scan direction) and there is a need for improving the resolution of these maps. In order to understand the spatial structure of galaxies, we have generated high resolution maps of 18 large galaxies by deconvolving the IRAS pointed observations from survey detectors as well as from Chopped Photometric Channel (CPC) using Maximum Entropy Method (MEM).


2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Qiao Ke ◽  
Sun Zeng-guo ◽  
Yang Liu ◽  
Wei Wei ◽  
Marcin Woźniak ◽  
...  

A new speckle suppression algorithm is proposed for high-resolution synthetic aperture radar (SAR) images. It is based on the nonlocal means (NLM) filter and the modified Aubert and Aujol (AA) model. This method takes the nonlocal Dirichlet function as a linear regularization item, which constructs the weight by measuring the similarity of images. Then, a new despeckling model is introduced by combining the regularization item and the data item of the AA model, and an iterative algorithm is proposed to solve the new model. The experiments show that, compared with the AA model, the proposed model has more effective performance in suppressing speckle; namely, ENL and DCV measures are 21.75% and 4.5% higher, respectively, than for NLM. Moreover, it also has better performance in keeping the edge information.


Sign in / Sign up

Export Citation Format

Share Document