In hazy weather, the obtained images of optical instruments are severely degraded due to the multiple atmospheric light scattering, which will significantly influence subsequent image processing such as target recognition and location. In this paper, we propose an efficient image dehazing network based on the framework of the Wasserstein generative adversarial network (WGAN). Inspired by the classic U-net network architecture, we first use a transformer-based image restoration architecture Uformer to modify the generator of WGAN. Then for loss function design, according to the requirement of the image dehazing task, the overall network training is constrained from two aspects, i.e., the pixel loss and the adversarial loss. Finally, the synthetic haze dataset was used to train and evaluate the effectiveness of the network. The results show that the proposed method can obtain high quality restored images, which is comparable to some current methods.
In cases of insufficient lighting conditions, the obtained images of optical systems usually suffer from heavy noise, which subsequently has a negative impact on tasks like image segmentation, target detection, and edge extraction. Image denoising requires preserving the integrity of original information while eliminating irrelevant data from the signal. Regularization is an effective way to improve the performance of denoising algorithms, it achieves this by introducing additional constraints to ensure stable solutions. In this paper, we propose a hybrid regularization method which is based on the weighted combination of the L0-norm and L1-norm of image gradients. In order to obtain reliable denoising results, we have also developed a highly efficient alternately minimization algorithm to solve the resulting complex optimization problem. The algorithm utilizes variable splitting and Lagrange multipliers to determine the optimal solution, effectively transforming the initial problem into a simple convex optimization problem and a quadratic optimization problem, which can be rapidly solved in frequency domain. In the end, we conducted experiments to prove the efficiency of the proposed method. The results show that it is stable, efficient and the quality of the denoised images is comparable to some state-of-the-art methods.
In this paper, we propose a conditional generative adversarial network (CGAN) for restoring blurred image. The design of the generator derives from classic U-net network, but to improve its expression ability, we first modify the U-net by replacing some deep layers with stacked residual modules. Furthermore, we combine the channel and spatial attention modules and embed them into the generator to force it paying more attention to important channels and blurred local space. For loss function design, we comprehensively incorporate the pixel loss, perception loss and adversarial loss to enhance the performance of the proposed CGAN. Finally, the GoPro dataset is used for training and evaluating the effectiveness of the network. The results show that the proposed CGAN can achieve restored image of very high quality which is comparable with some state of the art methods.
In the fields of astronomical observation and fluorescence microscopic imaging, the obtained image is usually degraded by blur effects and Poisson noise. In this paper, we propose a robust hybrid regularization method consisting of total variation and L0-norm of image gradients and combine it with the Poisson distribution to formulate this kind of ill-posed problem. We also propose an efficient alternately minimization algorithm based on variable splitting and Lagrange multipliers to find the optimal solution, which can transform the original problem into a regularized deconvolution problem with quadratic fidelity term and a simple convex optimization problem. In the end, we carry out experiments to prove its convergence and effectiveness, the results show that the proposed method is stable, efficient and the quality of the restored image is comparable with some state-of-the-art methods.
KEYWORDS: Signal detection, Time-frequency analysis, Wavelets, Optical fibers, Signal processing, Optical tracking, Signal attenuation, Fourier transforms, Signal analyzers, Light scattering
Thanks to the rapid development of phase sensitive optical fiber sensing technology, it provides advanced solution to detect the track of trains. In this study, by the use of signals collected from optical fiber sensors, a time-frequency analysis method called short-time Fourier transform (STFT) is used to extract the time-frequency characteristics, based on which power spectrum can be obtained. The power spectrum with high values can be clustered via k-means, which is then used for tracking the train positions. The experimental results show that the proposed method can effectively eliminate effects caused by different subgrades on the vibration signal, reduce false alarm rate, and verify the flexibility and reliability.
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.