Fourier Ptychography is a phase recovery technique that uses synthetic aperture concept to recover high-resolution sample images. It has made great breakthroughs in microscopic fields such as biological cells. However, Fourier Ptychography is still restricted by many macroscopic fields of remote detection such as sea, land and air due to its non-active imaging. In this paper, a fast Fourier Ptychography technique based on via deep learning is proposed. Firstly, different from the previous macro scanning, a 3-3 array camera is used to quickly obtain part of the spectrum of the object to be measured. Secondly, the network is constructed by using the large aperture imaging results under non-laser irradiation as the ground truth. Finally, 9 low-resolution images are used to obtain high resolution results. Compared with other advanced methods, the results obtained in this paper have satisfactory resolution and eliminate most of the influence of speckle caused by laser irradiation.
Aiming at the problem of poor fusion quality of traditional algorithms, especially the lack of texture information in infrared images or visible images inability to obtain sufficiently bright images results in images with poor signal-to-noise ratios and superimposed significant read noise in lousy weather conditions, a deep learning method of infrared-visible images fusion based on encoder-decoder architecture is proposed. The image fusion problem is cleverly transformed into the issue of maintaining the structure and intensity ratio of the infrared-visible image. The corresponding loss function is designed to expand the weight difference between thermal target and background. In addition, a single image super-resolution reconstruction based on a regression network is introduced to tackle the traditional network mapping function not suitable for natural scenes. The forward generation and reverse regression models are considered to reduce the irrelevant function mapping space and approach the authentic scene data through double mapping constraints. Compared with other state-of-the-art approaches, our experimental results achieve appealing performance on visual effects and objective assessments. In addition, we can stably provide high-resolution reconstruction results consistent with the human visual observation in different scenes while avoiding the trade-off between spatial resolution and thermal radiation information typical of conventional fusion imaging.
Imaging systems with different imaging sensors are widely used in the surveillance, military, and medical fields. Infrared imaging sensors are widely used because they are less affected by the environment and can fully obtain the radiation information of objects, but they also have the characteristics of being insensitive to the brightness changes in the visual field and losing color information. The visible light imaging sensor can obtain rich texture information and color information but will lose scene information under bad weather conditions. Pseudo-color of infrared image and visible image can synthesize new image with complementary information of source image. This paper proposed a pseudo-color deep learning method for infrared and visible images based on a dual-path propagation codec structure. Firstly, the residual channel attention module is introduced to extract features at different scales, which can retain more meaningful information and enhance important information. Secondly, an improved fusion strategy based on visual saliency is used to pseudo-color the feature map. Finally, the pseudo-color results are recovered by reconstructing the network. Compared with other advanced methods, our experimental results achieve the satisfactory visual effect and objective evaluation performance.
The wide application of the image super-resolution algorithms significantly improves the visual quality of infrared images. In this paper, an infrared image super-resolution reconstruction method based on a closed-loop regression network is proposed. The residual channel attention block is introduced into the up-sampling module group, which effectively improves the capacity of the network and increases the number of feature maps, enhances the extraction and recovery ability of infrared image features, and is conducive to the recovery of image details. Compared with other infrared information recovery methods previously proposed, the proposed method has obvious advantages in high-resolution detail acquisition capability. Neural network through closed-loop regression, this scheme overcomes the LR image to HR image defects in nonlinear mapping function, by introducing additional constraints on the LR data to reduce the space of the possible functions.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.