Space Debris Detection Using Feature Learning of Candidate Regions in Optical Image Sequences

Xi, Jiangbo; Xiang, Yaobing; Ersoy, Okan K.; Cong, Ming; Wei, Xin; Gu, Jin

doi:10.1109/access.2020.3016761

Cited by 29 publications

(15 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jia et al [29] used ResNet50 as a backbone in feature extraction when using Faster R-CNN for astronomical target recognition; while it was able to surpass older frameworks, it still had lapses in analyzing stimulated data. A CNN based on LeNet was used in debris classification as part of a space debris detection algorithm proposed by Xi et al [30]. A convolutional kernel size of 5 × 5 was selected for testing across image classification of varying signal-to-noise ratios.…”

Section: Related Workmentioning

confidence: 99%

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

et al. 2023

View full text Add to dashboard Cite

Space situational awareness (SSA) system requires recognition of space objects that are varied in sizes, shapes, and types. The space images are challenging because of several factors such as illumination and noise and thus make the recognition task complex. Image fusion is an important area in image processing for various applications including RGB-D sensor fusion, remote sensing, medical diagnostics, and infrared and visible image fusion. Recently, various image fusion algorithms have been developed and they showed a superior performance to explore more information that are not available in single images. In this paper, we compared various methods of RGB and Depth image fusion for space object classification task. The experiments were carried out, and the performance was evaluated using 13 fusion performance metrics. It was found that the guided filter context enhancement (GFCE) outperformed other image fusion methods in terms of average gradient (8.2593), spatial frequency (28.4114), and entropy (6.9486). additionally, due to its ability to balance between good performance and inference speed (11.41 second), GFCE was selected for RGB and Depth image fusion stage before feature extraction and classification stage. The outcome of fusion method is fused images that were used to train a deep ensemble of CoAtNets to classify space objects into ten categories. The deep ensemble learning methods including bagging, boosting, and stacking were trained and evaluated for classification purposes. It was found that combination of fusion and stacking was able to improve classification accuracy largely compared to the baseline methods by producing an average accuracy of 89 % and average F1 score of 89 %.

show abstract

Section: Related Workmentioning

confidence: 99%

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The intuition here is that classical machine learning methods may allow us to effectively grapple with the astrodynamic complexity and multidimensionality of RSO classification. The main focus of research to date has been on improving the accuracy of orbital forecasting or improving the RSO classification value of sensor data [1,22,31,56]. To our knowledge, no attempt has been made to tackle the RSO task with a feature set as limited as the one available to defenders in our threat model.…”

Section: Why Machine Learning?mentioning

confidence: 99%

On Detecting Deception in Space Situational Awareness

Pavur

Martinovic

2021

Proceedings of the 2021 ACM Asia Conference on Computer and Communications Security

View full text Add to dashboard Cite

Space Situational Awareness (SSA) data is critical to the safe piloting of satellites through an ever-growing field of orbital debris. However, measurement complexity means that most satellite operators cannot independently acquire SSA data and must rely on a handful of centralized repositories operated by major space powers. As interstate competition in orbit increases, so does the threat of attacks abusing these information-sharing relationships. This paper offers one of the first considerations of defense techniques against SSA deceptions. Building on historical precedent and real-world SSA data, we simulate an attack whereby an SSA operator seeks to disguise spy satellites as pieces of debris. We further develop and evaluate a machine-learning based anomaly detection tool which allows defenders to detect 90-98% of deception attempts with little to no in-house astrometry hardware.Beyond the direct contribution of this system, the paper takes a unique interdisciplinary approach, drawing connections between cyber-security, astrophysics, and international security studies. It presents the general case that systems security methods can tackle many novel and complex problems in an historically neglected domain and provides methods and techniques for doing so.

show abstract

“…Kong et al 1 used top-hat and a masking method to remove most of stars in the scene, which was realized by using a ground-based telescope. Xi et al 2 used feature learning of candidate regions by a trained deep learning network to detect space debris, and one dimensional mean iteration method was proposed to correct the nonuniform background information. Sun et al 3 presented an image adaptive fast registration algorithm and an enhanced dilation difference algorithm to realize an adaptive real-time detection algorithm for Geosynchronous orbit(GSO) debris.…”

Section: Introductionmentioning

confidence: 99%

A space debris detection and tracking method for wide-field surveillance

Gao

Wang

Liu

et al. 2023

Ninth Symposium on Novel Photoelectronic Detection Technology and Applications

View full text Add to dashboard Cite

Space debris detection is important for space asset protection and space situational awareness. The current environment of man-made satellites and space debris objects in Earth orbits increases rapidly, so does the probability of collision between them. In this paper, we propose a space debris detection method based on image alignment and connected region analysis. First, the median filter and an improved top-hat filter are used for pre-process of the original images, which can eliminate thermal noises and improve optical distribution integrity of targets. Second, a feasible and easy-to-implement connected region labeling method is used for centroid extraction of suspected targets. Meanwhile, several saliency features of targets are used for suspected targets confirmation and false alarms elimination. Then, we use stars in high-brightness magnitude as feature points for accurate interframe registration, which can suppress the influence of platform shaking and background movement on dim target trajectory associations. Finally, data association is used for target trajectory extraction. The experiment is performed using one astronomical image sequence, the results show that the proposed method is robust and efficient on complex backgrounds.

show abstract

Space Debris Detection Using Feature Learning of Candidate Regions in Optical Image Sequences

Cited by 29 publications

References 43 publications

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

On Detecting Deception in Space Situational Awareness

A space debris detection and tracking method for wide-field surveillance

Contact Info

Product

Resources

About