Abstract
Mixed Poisson–Gaussian noise exists in the star images and is difficult to be effectively suppressed via maximum likelihood estimation (MLE) method due to its complicated likelihood function. In this article, the MLE method is incorporated with a state-of-the-art machine learning algorithm in order to achieve accurate restoration results. By applying the mixed Poisson–Gaussian likelihood function as the reward function of a reinforcement learning algorithm, an agent is able to form the restored image that achieves the maximum value of the complex likelihood function through the Markov Decision Process (MDP). In order to provide the appropriate parameter settings of the denoising model, the key hyperparameters of the model and their influences on denoising results are tested through simulated experiments. The model is then compared with two existing star image denoising methods so as to verify its performance. The experiment results indicate that this algorithm based on reinforcement learning is able to suppress the mixed Poisson–Gaussian noise in the star image more accurately than the traditional MLE method, as well as the method based on the deep convolutional neural network (DCNN).
Highlights
A star image is obtained from star sensor, which is a high-accuracy attitude determination instrument
Concerning the goal of star image restoration, the accuracy was evaluated by mean squared error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity (SSIM), which are defined in Equations (6)–(8)
A novel approach for star image denoising based on reinforcement learning is presented in this study
Summary
A star image is obtained from star sensor, which is a high-accuracy attitude determination instrument. Being able to accurately collect and process a star image at all times, is one of the challenges in the application of a star sensor due to the brightness of the sky’s background and the complicated mixture of noise [1]. These conditions lead to a low Signal-to-Noise Ratio (SNR) in the star image obtained in the daytime, and have negative influences on the calculation of attitude and position. Mixed Poisson–Gaussian noise remains after these denoising methods are applied and affects the extraction of the true value of star points [6]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have