Design and Validation of a U-Net-Based Algorithm for Star Sensor Image Segmentation
Source abstract
Abstract
The present work focuses on the investigation of an artificial intelligence (AI) algorithm for brightest objects segmentation in night sky images’ field of view (FOV). This task is mandatory for many applications that want to focus on the brightest objects in an optical sensor image with a particular shape: point-like or streak. The algorithm is developed as a dedicated application for star sensors both for attitude determination (AD) and onboard space surveillance and tracking (SST) tasks. Indeed, in the former, the brightest objects of most concern are stars, while in the latter they are resident space objects (RSOs). Focusing attention on these shapes, an AI-based segmentation approach can be investigated. This will be carried out by designing, developing and testing a convolutional neural network (CNN)-based algorithm. In particular, a U-Net will be used to tackle this problem. A dataset for the design process of the algorithm, network training and tests is created using both real and simulated images. In the end, comparison with traditional segmentation algorithms will be performed, and results will be presented and discussed together with the proposal of an electro-optical payload for a small satellite for an in-orbit validation (IOV) mission.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Inertial Sensor and Navigation · Infrared Target Detection Methodologies · CCD and CMOS Imaging Sensors
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Aerospace Engineering, Sapienza University of Rome, 00138 Roma, Italy
References (50)
Show source-provided references
1. A novel star image thresholding method for effective segmentation and centroid statistics10.1016/j.ijleo.2013.01.067 ↗
2. Accuracy performance of star trackers-a tutorial10.1109/TAES.2002.1008988 ↗
3. Rijlaarsdam, D., Yous, H., Byrne, J., Oddenino, D., Furano, G., and Moloney, D. (2020). Efficient Star Identification Using a Neural Network. Sensors, 20.10.3390/s20133684 ↗
4. RPNet: A Representation Learning-Based Star Identification Algorithm10.1109/ACCESS.2019.2927684 ↗
5. Algorithm for CCD star image rapid locating10.11728/cjss2006.03.209 ↗
6. A geometrical approach for the angular velocity determination using a star sensor10.1016/j.actaastro.2020.11.043 ↗
7. Bernsen, J. (, January January). Dynamic thresholding of gray-level images. Proceedings of the International Conference on Pattern Recognition, Berlin, Germany.
8. Liu, D., and Yu, J. (2009, January 12–14). Otsu method and K-means. Proceedings of the 2009 Ninth International Conference on Hybrid Intelligent Systems, Shenyang, China.10.1109/HIS.2009.74 ↗
9. Niblack, W. (1986). An Introduction to Image Processing, Strandberg Publishing Company.
10. A modified valley-emphasis method for automatic thresholding10.1016/j.patrec.2011.12.009 ↗
11. A Patch-to-Pixel Convolutional Neural Network for Small Ship Detection With PolSAR Images10.1109/TGRS.2020.2978268 ↗
12. Zhao, D., Zhou, H., Rang, S., and Jia, X. (2018, January 22–27). An Adaptation of Cnn for Small Target Detection in the Infrared. Proceedings of the IGARSS 2018—2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.10.1109/IGARSS.2018.8518464 ↗
13. Dim infrared image enhancement based on convolutional neural network10.1016/j.neucom.2017.07.017 ↗
14. The mnist database of handwritten digit images for machine learning research10.1109/MSP.2012.2211477 ↗
15. DeepTarget: An Automatic Target Recognition Using Deep Convolutional Neural Networks10.1109/TAES.2019.2894050 ↗
16. Infrared dim and small target detection based on denoising autoencoder network10.1007/s11036-019-01377-6 ↗
17. Tong, X., Sun, B., Wei, J., Zuo, Z., and Su, S. (2021). EAAU-Net: Enhanced asymmetric attention U-Net for infrared small target detection. Remote Sens., 13.10.3390/rs13163200 ↗
18. Xue, D., Sun, J., Hu, Y., Zheng, Y., Zhu, Y., and Zhang, Y. (2018, January 13–16). StarNet: Convolutional neural network for dim small target extraction in star image. Proceedings of the 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM), Xi’an, China.10.1109/BigMM.2018.8499101 ↗
19. Dim small target detection based on convolutinal neural network in star image10.1007/s11042-019-7412-z ↗
20. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
21. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
22. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
23. Imagenet classification with deep convolutional neural networks
24. Cortes, C., Mohri, M., and Rostamizadeh, A. (2012). L2 Regularization for Learning Kernels. arXiv.
25. Santurkar, S., Tsipras, D., Ilyas, A., and Madry, A. (2018). How does batch normalization help optimization?. arXiv.
26. Mikołajczyk, A., and Grochowski, M. (2018, January 9–12). Data augmentation for improving deep learning in image classification problem. Proceedings of the 2018 International Interdisciplinary PhD Workshop (IIPhDW), Świnoujście, Poland.10.1109/IIPHDW.2018.8388338 ↗
27. Dropout: A simple way to prevent neural networks from overfitting
28. Lunar crater identification via deep learning10.1016/j.icarus.2018.06.022 ↗
29. Iqbal, H. (2021, September 15). HarisIqbal88/PlotNeuralNet v1.0.0. Available online: https://zenodo.org/record/2526396#.Y9tKOepBxPY.
30. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7–13). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.123 ↗
31. Mastrofini, M. (2022, November 10). nightskyUnet Repository. Available online: https://github.com/marco92m/nightskyUnet.
32. Zotti, G., and Wolf, A. (2022, November 15). Stellarium 0.19.0 User Guide. Available online: https://github.com/Stellarium/stellarium.
33. Curti, F., Spiller, D., Ansalone, L., Becucci, S., Procopio, D., Boldrini, F., and Fidanzati, P. (2015, January 12–16). Determining high rate angular velocity from star tracker measurements. Proceedings of the International Astronautical Conference, Jerusalem, Israel.
34. High angular rate determination algorithm based on star sensing
35. Star identification robust to angular rates and false objects with rolling shutter compensation10.1016/j.actaastro.2019.09.040 ↗
36. Efficient star identification algorithm for nanosatellites in harsh environment
37. A novel star identification technique robust to high presence of false objects: The Multi-Poles Algorithm10.1016/j.asr.2017.01.034 ↗
38. A threshold selection method from gray-level histograms10.1109/TSMC.1979.4310076 ↗
39. Adaptive Thresholding using the Integral Image10.1080/2151237X.2007.10129236 ↗
40. On-orbit recognition of resident space objects by using star trackers10.1016/j.actaastro.2020.08.009 ↗
41. Kazemi, L., Enright, J., and Dzamba, T. (2015, January 7–14). Improving star tracker centroiding performance in dynamic imaging conditions. Proceedings of the 2015 IEEE Aerospace Conference, Big Sky, MT, USA.10.1109/AERO.2015.7119226 ↗
42. Gonzalez, R.C., and Woods, R.E. (2002). Digital Image Processing, Prentice Hall.
43. Chollet, F. (2017). Deep Learning with Python, Manning.
44. Chapman, D., Aboobaker, A.M., Araujo, D., Didier, J., Grainger, W., Hanany, S., Hillbrand, S., Limon, M., Miller, A., and Reichborn-Kjennerud, B. (2015, January 7–14). Star camera system and new software for autonomous and robust operation in long duration flights. Proceedings of the 2015 IEEE Aerospace Conference, Big Sky, MT, USA.10.1109/AERO.2015.7119013 ↗
45. (2022, January 11). NASA-Juno Star Reference Unit Camera, Available online: https://www.jpl.nasa.gov/images/pia24436-high-energy-and-junos-stellar-reference-unit.
46. Mastrofini, M., Goracci, G., Agostinelli, I., and Salim, M. (2022, January 7–11). Resident Space Objects Detection And Tracking Based On Artificial Intelligence. Proceedings of the Astrodynamics Specialist Conference AAS/AIAA, Charlotte, NC, USA.
47. (2022, November 20). PHOEBE, School of Aerospace Engineering. Available online: https://sites.google.com/uniroma1.it/stecco-sia/home.
48. Farissi, M.S., Mastrofini, M., Agostinelli, I., Goracci, G., Curti, F., Facchinetti, C., and Ansalone, L. (2022, January 7–11). Real-Time Image Processing Implementation For On-Board Object Detection And Tracking. Proceedings of the Astrodynamics Specialist Conference AAS/AIAA, Charlotte, NC, USA.
49. Cost and risk assessment for spacecraft operation decisions caused by the space debris environment10.1016/j.actaastro.2015.03.028 ↗
50. (2022, October 20). labis7/UNET-FPGA. Available online: https://github.com/labis7/UNET-FPGA.