Infrared visible color night vision image fusion based on deep learning

Author(s):  
Yan Zou ◽  
Linfei Zhang ◽  
Chengqian Liu ◽  
Bowen Wang ◽  
Yan Hu ◽  
...  
2002 ◽  
Author(s):  
Shengxiang Wang ◽  
Zhiyun Gao ◽  
Weiqi Jin ◽  
Shanfeng Hou

2017 ◽  
Vol 46 (5) ◽  
pp. 510002
Author(s):  
吴海兵 WU Hai-bing ◽  
陶声祥 TAO Sheng-xiang ◽  
顾国华 GU Guo-hua ◽  
王书宇 WANG Shu-yu

2014 ◽  
Vol 568-570 ◽  
pp. 663-667
Author(s):  
Jiang Zhou ◽  
Bo Zhai ◽  
Ya Meng Han ◽  
You Shan Qu ◽  
Ya Li Yu

In order to observe night vision image easily, a new image fusion method is designed to improve the detail information of night vision images in a simple and efficient way. Instead of the traditional Multi-resolution analysis and spatial transform approach, the designed method highlights the detail information of night vision images by phase modulation and image enhancement technique. In the designed approach, the phase spectrum and amplitude spectrum of the visible and infrared images are extracted using FFT firstly, and then the phase spectra of two images are exchanged and the IFFT is applied to the processed images to produce phase information images. To compensate for the blurring caused by phase modulation, the high-frequency information of the processed infrared image is segmented and applied to the reconstruction of the color night vision image. Finally, color night vision image is fused by assigning the two-modulated images to red and green channels respectively, and the segmented image to blue channel. The experimental results show that the details of the fused image by the new method are richer than those of the images fused by the traditional methods, and the designed algorithm with a little amount of calculation can be easily realized in real-time processing systems.


Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 863
Author(s):  
Vidas Raudonis ◽  
Agne Paulauskaite-Taraseviciene ◽  
Kristina Sutiene

Background: Cell detection and counting is of essential importance in evaluating the quality of early-stage embryo. Full automation of this process remains a challenging task due to different cell size, shape, the presence of incomplete cell boundaries, partially or fully overlapping cells. Moreover, the algorithm to be developed should process a large number of image data of different quality in a reasonable amount of time. Methods: Multi-focus image fusion approach based on deep learning U-Net architecture is proposed in the paper, which allows reducing the amount of data up to 7 times without losing spectral information required for embryo enhancement in the microscopic image. Results: The experiment includes the visual and quantitative analysis by estimating the image similarity metrics and processing times, which is compared to the results achieved by two wellknown techniques—Inverse Laplacian Pyramid Transform and Enhanced Correlation Coefficient Maximization. Conclusion: Comparatively, the image fusion time is substantially improved for different image resolutions, whilst ensuring the high quality of the fused image.


Author(s):  
Hao Zhang ◽  
Han Xu ◽  
Xin Tian ◽  
Junjun Jiang ◽  
Jiayi Ma
Keyword(s):  

2009 ◽  
Author(s):  
Yi Zhang ◽  
Lian-fa Bai ◽  
Chuang Zhang ◽  
Qian Chen ◽  
Guo-hua Gu

1995 ◽  
Author(s):  
Allen M. Waxman ◽  
David A. Fay ◽  
Alan N. Gove ◽  
Michael Seibert ◽  
Joseph P. Racamato ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document