An artificial intelligence enhanced star identification algorithm is proposed for star trackers in lost-inspace mode.A convolutional neural network model based on Vgg16 is used in the artificial intelligence algorithm...An artificial intelligence enhanced star identification algorithm is proposed for star trackers in lost-inspace mode.A convolutional neural network model based on Vgg16 is used in the artificial intelligence algorithm to classify star images.The training dataset is constructed to achieve the networks’optimal performance.Simulation results show that the proposed algorithm is highly robust to many kinds of noise,including position noise,magnitude noise,false stars,and the tracker’s angular velocity.With a deep convolutional neural network,the identification accuracy is maintained at 96%despite noise and interruptions,which is a significant improvement to traditional pyramid and grid algorithms.展开更多
We propose an efficient, specific method for estimating camera parameters from a single starry night image. Such an image consists of a collection of disks representing stars, so traditional estimation methods for com...We propose an efficient, specific method for estimating camera parameters from a single starry night image. Such an image consists of a collection of disks representing stars, so traditional estimation methods for common pictures do not work. Our method uses a database, a star catalog, that stores the positions of stars on the celestial sphere. Our method computes magnitudes(i.e., brightnesses) of stars in the input image and uses them to find the corresponding stars in the star catalog. Camera parameters can then be estimated by a simple geometric calculation. Our method is over ten times faster and more accurate than a previous method.展开更多
基金the National Natural Science Foundation of China(No.6152403)。
文摘An artificial intelligence enhanced star identification algorithm is proposed for star trackers in lost-inspace mode.A convolutional neural network model based on Vgg16 is used in the artificial intelligence algorithm to classify star images.The training dataset is constructed to achieve the networks’optimal performance.Simulation results show that the proposed algorithm is highly robust to many kinds of noise,including position noise,magnitude noise,false stars,and the tracker’s angular velocity.With a deep convolutional neural network,the identification accuracy is maintained at 96%despite noise and interruptions,which is a significant improvement to traditional pyramid and grid algorithms.
文摘We propose an efficient, specific method for estimating camera parameters from a single starry night image. Such an image consists of a collection of disks representing stars, so traditional estimation methods for common pictures do not work. Our method uses a database, a star catalog, that stores the positions of stars on the celestial sphere. Our method computes magnitudes(i.e., brightnesses) of stars in the input image and uses them to find the corresponding stars in the star catalog. Camera parameters can then be estimated by a simple geometric calculation. Our method is over ten times faster and more accurate than a previous method.