Robust and Efficient Star Identification Algorithm based on 1-D Convolutional Neural Network

Yang, Shaofei; Liu, Longjun; Zhou, Jiantao; Zhao, Yunfu; Hua, Gengxin; Sun, Hongbin; Zheng, Nanning

doi:10.1109/taes.2022.3160134

Cited by 12 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the pattern recognition algorithm category, we choose the representative LPT algorithm and the radial and cyclic algorithm for comparison. In order to better show the upper limit of recognition accuracy of this algorithm, we adopted N_center_map and N_range_map as three parameters (9,15), (7,11) and (5,8) respectively.…”

Section: B Algorithm Performance Analysismentioning

confidence: 99%

“…The second category is the artificial intelligence method. Artificial intelligence algorithms mainly use neural networks [8], [9] to identify the imaging stars captured by star sensors. For example, methods based on convolutional neural networks [10], [11], [12], multi-layer SOM neural networks [13], and representative learning algorithms [14]have been designed to solve the star identification problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Star Identification Algorithm Based on Multi-Dimensional Features and Multi-Layered Joint Screening for Star Sensors

et al. 2023

View full text Add to dashboard Cite

The algorithm for star identification is a crucial technology for determining the orientation of spacecraft using star sensors. Traditional star identification algorithms achieve matching by seeking a unique or a few optimal solutions. However, in high-noise environments, some solutions may be lost, which could result in matching failure. A new lost-in-space architecture algorithm aimed at rapid identification under high star position noise conditions by directly using star positions for final matching is proposed in this paper. The main idea of this algorithm is to construct sufficiently redundant navigation triangles, fully utilizing the physical relationships of the features and forming a screening method from high to low dimensions and from loose to strict. During identification, a multi-layer joint screening matching method is adopted to screen triangles as a whole, narrowing the range of matches quickly while retaining error tolerance. In a series of simulation experiments, this algorithm achieved identification rates of 99.51%, 99.06%, and 98.42% for 2.0 pixel star position noise, 1.0 Mv star magnitude noise, and 5 false stars, respectively. In terms of practical application, all 1000 star images taken by the star sensor in orbit have been successfully identified, and it only takes 28ms to identify each image. In addition, star images taken by consumer-grade cameras from the ground also show that the algorithm has strong robustness to star position noise, magnitude error and false star interference in more severe environments. This method provides partial algorithmic reference for non-specialized design of star sensors for low-cost, large-scale satellites in the future.INDEX TERMS Multi-dimensional features, multi-layered joint screening, star identification, star sensor, star tracker.

show abstract

Section: B Algorithm Performance Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Star Identification Algorithm Based on Multi-Dimensional Features and Multi-Layered Joint Screening for Star Sensors

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Another similar approach is used by Yang et al [10] where the authors proposed a one-dimensional Convolutional Neural Network (1D CNN) to identify stars in catalogs, being highly robust to position and magnitude noise with an identification accuracy of 98%.…”

Section: Related Workmentioning

confidence: 99%

A Novel Deep Learning-Based Relabeling Architecture for Space Objects Detection from Partially Annotated Astronomical Images

et al. 2022

View full text Add to dashboard Cite

Space Surveillance and Tracking is a task that requires the development of systems that can accurately discriminate between natural and man-made objects that orbit around Earth. To manage the discrimination between these objects, it is required to analyze a large amount of partially annotated astronomical images collected using a network of on-ground and potentially space-based optical telescopes. Thus, the main objective of this article is to propose a novel architecture that improves the automatic annotation of astronomical images. To achieve this objective, we present a new method for automatic detection and classification of space objects (point-like and streaks) in a supervised manner, given real-world partially annotated images in the FITS (Flexible Image Transport System) format. Results are strongly dependent on the preprocessing techniques applied to the images. Therefore, different techniques were tested including our method for object filtering and bounding box extraction. Based on our relabeling pipeline, we can easily follow how the number of detected objects is gradually increasing after each iteration, achieving a mean average precision of 98%.

show abstract

“…They also exhibit low complexity in online searching and matching tasks. Typical algorithms in this category include the improved grid pattern star recognition algorithm based on backpropagation (BP) networks [13], the mixed feature star pattern recognition algorithm based on one-dimensional convolutional networks [14], and the radial star pattern recognition algorithm based on multi-layer representation learning networks (RPNet) [15]. However, the aforementioned algorithms still require the manual design of star pattern features, and the neural network only handles the online feature pattern-matching task.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Grid Pattern Star Identification Algorithm Based on Multi-Calibration Star Verification

Shen,

Ma,

Gao

et al. 2024

Sensors

View full text Add to dashboard Cite

In order to solve the star identification problem in the lost space mode for scientific cameras with small fields of view and higher instruction magnitudes, this paper proposes a star identification algorithm based on a hybrid grid pattern. The application of a hybrid pattern generated by multi-calibration stars in the initial matching enables the position distribution features of neighboring stars around the main star to be more comprehensively described and avoids the interference of position noise and magnitude noise as much as possible. Moreover, calibration star filtering is adopted to eliminate incorrect candidates and pick the true matched navigation star from candidate stars in the initial match. Then, the reference star image is utilized to efficiently verify and determine the final identification results of the algorithm via the nearest principle. The performance of the proposed algorithm in simulation experiments shows that, when the position noise is 2 pixels, the identification rate of the algorithm is 96.43%, which is higher than that of the optimized grid algorithm by 2.21% and the grid algorithm by 4.05%; when the magnitude noise is 0.3 mag, the star identification rate of the algorithm is 96.45%, which is superior to the optimized grid algorithm by 2.03% and to the grid algorithm by 3.82%. In addition, in the actual star image test, star magnitude values of ≤12 mag can be successfully identified using the proposed algorithm.

show abstract

Robust and Efficient Star Identification Algorithm based on 1-D Convolutional Neural Network

Cited by 12 publications

References 21 publications

Star Identification Algorithm Based on Multi-Dimensional Features and Multi-Layered Joint Screening for Star Sensors

Star Identification Algorithm Based on Multi-Dimensional Features and Multi-Layered Joint Screening for Star Sensors

A Novel Deep Learning-Based Relabeling Architecture for Space Objects Detection from Partially Annotated Astronomical Images

Hybrid Grid Pattern Star Identification Algorithm Based on Multi-Calibration Star Verification

Contact Info

Product

Resources

About