Research Article
Compressed Sensing Joint Image Reconstruction Based on Multiple Measurement Vectors
@INPROCEEDINGS{10.1007/978-3-031-04245-4_28, author={Juntao Sun and Guoxing Huang and Weidang Lu and Yu Zhang and Hong Peng}, title={Compressed Sensing Joint Image Reconstruction Based on Multiple Measurement Vectors}, proceedings={6GN for Future Wireless Networks. 4th EAI International Conference, 6GN 2021, Huizhou, China, October 30--31, 2021, Proceedings}, proceedings_a={6GN}, year={2022}, month={5}, keywords={Compressed sensing Image reconstruction Joint reconstruction Single measurement vector (SMV) Multiple measurement vectors (MMV)}, doi={10.1007/978-3-031-04245-4_28} }- Juntao Sun
Guoxing Huang
Weidang Lu
Yu Zhang
Hong Peng
Year: 2022
Compressed Sensing Joint Image Reconstruction Based on Multiple Measurement Vectors
6GN
Springer
DOI: 10.1007/978-3-031-04245-4_28
Abstract
In order to improve the quality of the reconstructed image for compressed sensing, a novel compressed sensing joint image reconstruction method based on multiple measurement vectors is put forward in this paper. Firstly, the original image is processed under the multiple measurement vectors (MWV) mode and random measured by two compressive imaging cameras, in vertical direction and horizontal direction, separately. Secondly, the vertical sampling image and horizontal sampling image are reconstructed with the multiple measurement vectors. Finally, the mean image is used to capture the correlation between these two similar images, and the original image is reconstructed. The experiment result showed that the visual effect and peak signal to noise ratio (PSNR) of the joint reconstructed image by this method is much better than the independent reconstructed images. So, it is an effective compressed sensing joint image reconstruction method.
