An End-to-End Identification Algorithm for Smearing Star Image

In the previous study, there were a few direct star identification (star-ID) algorithms for smearing star image. An end-to-end star-ID algorithm is proposed in this article, to directly identify the smearing image from star sensors with fast attitude maneuvering. Combined with convolutional neural n...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jinliang Han, Xiubin Yang, Tingting Xu, Zongqiang Fu, Lin Chang, Chunlei Yang, Guang Jin
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	star identification end-to-end identification smearing image transformer encoder Science Q
Acceso en línea:	https://doaj.org/article/8f4a876727d04fac8f96eb7b077fcbae
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8f4a876727d04fac8f96eb7b077fcbae
record_format	dspace
spelling	oai:doaj.org-article:8f4a876727d04fac8f96eb7b077fcbae2021-11-25T18:54:06ZAn End-to-End Identification Algorithm for Smearing Star Image10.3390/rs132245412072-4292https://doaj.org/article/8f4a876727d04fac8f96eb7b077fcbae2021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4541https://doaj.org/toc/2072-4292In the previous study, there were a few direct star identification (star-ID) algorithms for smearing star image. An end-to-end star-ID algorithm is proposed in this article, to directly identify the smearing image from star sensors with fast attitude maneuvering. Combined with convolutional neural networks and the self-attention mechanism of transformer encoder, the algorithm can effectively classify the smearing image and identify the star. Through feature extraction and position encoding, neural networks learn the position of stars to generate semantic information and realize the end-to-end identification for the smearing star image. The algorithm can also solve the problem of low identification rate due to smearing of long exposure time for images. A dataset of dynamic stars is analyzed and constructed based on multiple angular velocities. Experiment results show that, compared with representative algorithms, the identification rate of the proposed algorithm is improved at high angular velocities. When the three-axis angular velocity is 10°/s, the rate is still 60.4%. At the same time, the proposed algorithm has good robustness to position noise and magnitude noise.Jinliang HanXiubin YangTingting XuZongqiang FuLin ChangChunlei YangGuang JinMDPI AGarticlestar identificationend-to-end identificationsmearing imagetransformer encoderScienceQENRemote Sensing, Vol 13, Iss 4541, p 4541 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	star identification end-to-end identification smearing image transformer encoder Science Q
spellingShingle	star identification end-to-end identification smearing image transformer encoder Science Q Jinliang Han Xiubin Yang Tingting Xu Zongqiang Fu Lin Chang Chunlei Yang Guang Jin An End-to-End Identification Algorithm for Smearing Star Image
description	In the previous study, there were a few direct star identification (star-ID) algorithms for smearing star image. An end-to-end star-ID algorithm is proposed in this article, to directly identify the smearing image from star sensors with fast attitude maneuvering. Combined with convolutional neural networks and the self-attention mechanism of transformer encoder, the algorithm can effectively classify the smearing image and identify the star. Through feature extraction and position encoding, neural networks learn the position of stars to generate semantic information and realize the end-to-end identification for the smearing star image. The algorithm can also solve the problem of low identification rate due to smearing of long exposure time for images. A dataset of dynamic stars is analyzed and constructed based on multiple angular velocities. Experiment results show that, compared with representative algorithms, the identification rate of the proposed algorithm is improved at high angular velocities. When the three-axis angular velocity is 10°/s, the rate is still 60.4%. At the same time, the proposed algorithm has good robustness to position noise and magnitude noise.
format	article
author	Jinliang Han Xiubin Yang Tingting Xu Zongqiang Fu Lin Chang Chunlei Yang Guang Jin
author_facet	Jinliang Han Xiubin Yang Tingting Xu Zongqiang Fu Lin Chang Chunlei Yang Guang Jin
author_sort	Jinliang Han
title	An End-to-End Identification Algorithm for Smearing Star Image
title_short	An End-to-End Identification Algorithm for Smearing Star Image
title_full	An End-to-End Identification Algorithm for Smearing Star Image
title_fullStr	An End-to-End Identification Algorithm for Smearing Star Image
title_full_unstemmed	An End-to-End Identification Algorithm for Smearing Star Image
title_sort	end-to-end identification algorithm for smearing star image
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8f4a876727d04fac8f96eb7b077fcbae
work_keys_str_mv	AT jinlianghan anendtoendidentificationalgorithmforsmearingstarimage AT xiubinyang anendtoendidentificationalgorithmforsmearingstarimage AT tingtingxu anendtoendidentificationalgorithmforsmearingstarimage AT zongqiangfu anendtoendidentificationalgorithmforsmearingstarimage AT linchang anendtoendidentificationalgorithmforsmearingstarimage AT chunleiyang anendtoendidentificationalgorithmforsmearingstarimage AT guangjin anendtoendidentificationalgorithmforsmearingstarimage AT jinlianghan endtoendidentificationalgorithmforsmearingstarimage AT xiubinyang endtoendidentificationalgorithmforsmearingstarimage AT tingtingxu endtoendidentificationalgorithmforsmearingstarimage AT zongqiangfu endtoendidentificationalgorithmforsmearingstarimage AT linchang endtoendidentificationalgorithmforsmearingstarimage AT chunleiyang endtoendidentificationalgorithmforsmearingstarimage AT guangjin endtoendidentificationalgorithmforsmearingstarimage
_version_	1718410601747709952

An End-to-End Identification Algorithm for Smearing Star Image

Ejemplares similares