Multiphase computer-generated holograms for full-color image generation

2002 ◽  
Author(s):  
Kyong S. Choi ◽  
Byong S. Choi ◽  
Yoon S. Choi ◽  
Sun I. Kim ◽  
Jong Man Kim ◽  
...  
Keyword(s):  
Color Image ◽  
Image Generation ◽  
Full Color ◽  
Computer Generated Holograms

scholarly journals Full-color nanorouter for high-resolution imaging

Nanoscale ◽  
2021 ◽  
Author(s):  
Mingjie Chen ◽  
Long Wen ◽  
Dahui Pan ◽  
David Cumming ◽  
Xianguang Yang ◽  
...  
Keyword(s):  
High Resolution ◽  
Color Image ◽  
Image Sensors ◽  
Structural Color ◽  
High Resolution Imaging ◽  
Scaling Effects ◽  
Full Color ◽  
Resolution Imaging

Pixel scaling effects have been a major issue for the development of high-resolution color image sensors due to the reduced photoelectric signal and the color crosstalk. Various structural color techniques...

scholarly journals Compact full-color holographic 3-D display based on undersampled computer-generated holograms and oblique projection imaging

2020 ◽  
Vol 28 (24) ◽  
pp. 35910
Author(s):  
Hong-Kun Cao ◽  
Yong-Seok Hwang ◽  
Eun-Soo Kim ◽  
Xin Jin
Keyword(s):  
Oblique Projection ◽  
Full Color ◽  
Computer Generated Holograms

scholarly journals Color Image Generation from LiDAR Reflection Data by Using Selected Connection UNET

Sensors ◽  
2020 ◽  
Vol 20 (12) ◽  
pp. 3387 ◽  
Author(s):  
Hyun-Koo Kim ◽  
Kook-Yeol Yoo ◽  
Ho-Youl Jung
Keyword(s):  
Color Image ◽  
Signal To Noise Ratio ◽  
Structural Similarity ◽  
Image Generation ◽  
Convolutional Network ◽  
Biomedical Image ◽  
Reflection Data ◽  
Network Connection ◽  
Reflection Image ◽  
Heterogeneous Source

In this paper, a modified encoder-decoder structured fully convolutional network (ED-FCN) is proposed to generate the camera-like color image from the light detection and ranging (LiDAR) reflection image. Previously, we showed the possibility to generate a color image from a heterogeneous source using the asymmetric ED-FCN. In addition, modified ED-FCNs, i.e., UNET and selected connection UNET (SC-UNET), have been successfully applied to the biomedical image segmentation and concealed-object detection for military purposes, respectively. In this paper, we apply the SC-UNET to generate a color image from a heterogeneous image. Various connections between encoder and decoder are analyzed. The LiDAR reflection image has only 5.28% valid values, i.e., its data are extremely sparse. The severe sparseness of the reflection image limits the generation performance when the UNET is applied directly to this heterogeneous image generation. In this paper, we present a methodology of network connection in SC-UNET that considers the sparseness of each level in the encoder network and the similarity between the same levels of encoder and decoder networks. The simulation results show that the proposed SC-UNET with the connection between encoder and decoder at two lowest levels yields improvements of 3.87 dB and 0.17 in peak signal-to-noise ratio and structural similarity, respectively, over the conventional asymmetric ED-FCN. The methodology presented in this paper would be a powerful tool for generating data from heterogeneous sources.

scholarly journals Color Image Generation from Range and Reflection Data of LiDAR

Sensors ◽  
2020 ◽  
Vol 20 (18) ◽  
pp. 5414
Author(s):  
Hyun-Koo Kim ◽  
Kook-Yeol Yoo ◽  
Ho-Youl Jung
Keyword(s):  
Color Image ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Point Clouds ◽  
Range Data ◽  
Fusion Method ◽  
Image Generation ◽  
Learning Networks ◽  
Reflection Data

Recently, it has been reported that a camera-captured-like color image can be generated from the reflection data of 3D light detection and ranging (LiDAR). In this paper, we present that the color image can also be generated from the range data of LiDAR. We propose deep learning networks that generate color images by fusing reflection and range data from LiDAR point clouds. In the proposed networks, the two datasets are fused in three ways—early, mid, and last fusion techniques. The baseline network is the encoder-decoder structured fully convolution network (ED-FCN). The image generation performances were evaluated according to source types, including reflection data-only, range data-only, and fusion of the two datasets. The well-known KITTI evaluation data were used for training and verification. The simulation results showed that the proposed last fusion method yields improvements of 0.53 dB, 0.49 dB, and 0.02 in gray-scale peak signal-to-noise ratio (PSNR), color-scale PSNR, and structural similarity index measure (SSIM), respectively, over the conventional reflection-based ED-FCN. Besides, the last fusion method can be applied to real-time applications with an average processing time of 13.56 ms per frame. The methodology presented in this paper would be a powerful tool for generating data from two or more heterogeneous sources.

scholarly journals Image fusion algorithm based on improved K-singular value decomposition and Hadamard measurement matrix

2018 ◽  
Vol 13 ◽  
pp. 174830181879151
Author(s):  
Qiang Yang ◽  
Huajun Wang
Keyword(s):  
Singular Value Decomposition ◽  
Image Fusion ◽  
Compressive Sensing ◽  
Color Image ◽  
Singular Value ◽  
Measurement Matrix ◽  
Fusion Algorithm ◽  
Full Color ◽  
Value Decomposition ◽  
Time And Space Complexity

To solve the problem of high time and space complexity of traditional image fusion algorithms, this paper elaborates the framework of image fusion algorithm based on compressive sensing theory. A new image fusion algorithm based on improved K-singular value decomposition and Hadamard measurement matrix is proposed. This proposed algorithm only acts on a small amount of measurement data after compressive sensing sampling, which greatly reduces the number of pixels involved in the fusion and improves the time and space complexity of fusion. In the fusion experiments of full-color image with multispectral image, infrared image with visible light image, as well as multispectral image with full-color image, this proposed algorithm achieved good experimental results in the evaluation parameters of information entropy, standard deviation, average gradient, and mutual information.

Sign in / Sign up

Export Citation Format

Share Document