Abstract
A lost-in-space star identification algorithm based on a one-dimensional Convolutional Neural Network (1D CNN) is proposed. The lost-in-space star identification aims to identify stars observed with corresponding catalog stars when there is no prior attitude information. With the help of neural networks, the robustness and the speed of the star identification are improved greatly. In this paper, a modified log-Polar mapping is used to constructed rotation-invariant star patterns. Then a 1D CNN is utilized to classify the star patterns associated with guide stars. In the 1D CNN model, a global average pooling layer is used to replace fully-connected layers to reduce the number of parameters and the risk of overfitting. Experiments show that the proposed algorithm is highly robust to position noise, magnitude noise, and false stars. The identification accuracy is with 5 pixels position noise, with 5 false stars, and with 0.5 Mv magnitude noise, respectively, which is significantly higher than the identification rate of the pyramid, optimized grid and modified log-polar algorithms. Moreover, the proposed algorithm guarantees a reliable star identification under dynamic conditions. The identification accuracy is with angular velocity of 10 degrees per second. Furthermore, its identification time is as short as 32.7 miliseconds and the memory required is about 1920 kilobytes. The algorithm proposed is suitable for current embedded systems.
Highlights
Attitude information is required for most spacecraft missions, such as telecommunication, Earth observation, space exploration, celestial navigation, and so on
Star trackers are widely used for attitude determination because they provide more accurate attitude information than other attitude measurement devices
The stochastic gradient descent (SGD) method with a batch size of 8 examples was employed for the training
Summary
Attitude information is required for most spacecraft missions, such as telecommunication, Earth observation, space exploration, celestial navigation, and so on. Schiattarella et al [7] improved the multi-pole algorithm and proposed the rolling shutter compensation method to deal with the false stars and high angular velocity Another kind of approaches are pattern based algorithms. The modified algorithm based on log-polar transform is proposed to reduce the time consumed and enhance the robustness of star identification [15], but similar to the grid algorithm, it needs to find the correct closest neighboring star. Comparing with the pyramid, optimized grid and modified LPT algorithms, the proposed method is more robust to varies of noise It requires less memory than other neural network based algorithms and can be implemented on current embedded systems.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
