AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Advanced Manufacturing Science and Technology Article
PDF (3.8 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access | Online First

An improved Yolov7-tiny model for modular satellite component identification

Xiaoyu FAN( ), Jingfeng BI, Ming CHU
School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications, Beijing 100876
Show Author Information

Abstract

At present, modular satellite is an important development direction of satellite technology, and in order to realize the function of autonomous identification and transfer of satellite modules by robotic arm, a modular satellite component recognition algorithm based on improved Yolov7-tiny is proposed. By introducing the FasterNet structure, the backbone network is improved to reduce the number of parameters and calculations of the model, and improve the detection efficiency and frame rate of the model. At the same time, the loss function Repulsion Loss is introduced to improve the detection accuracy of occluded images in the dataset. In addition, a dataset containing multi-class modular satellite component models was created, and the improved algorithm on this dataset had an mAP of up to 95.6% and a FPS of 121.95 frames per second at an interaction ratio of 0.5, which was about 3% higher than that of the original algorithm, and the FPS was increased by about 12 frames per second. Finally, the improved algorithm model was pruned to further reduce the size of the model.

Keywords

Model pruningModular satelliteYolov7-tinyFasterNetRepulsion Loss

References

1
Wang C, Bochkovskiy A, Liao H. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022.
Crossref
2
Chen J, Kao S, He H, et al. Run, don't walk: Chasing higher FLOPS for faster neural networks. arXiv:2303.03667.
3
Wang X, Xiao T, Jiang Y, et al. Repulsion loss: Detecting pedestrians in a crowd. arXiv:1711.07752.
4
Fang G, Ma X, Song M, et al. DepGraph: Towards any structural pruning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023.
Crossref
5
Fronterhouse D, Lyke J, Achramowicz S. Plug-and-play satellite (PnPSat). 2007.
Crossref
6
McDermott S, Jordan L. AeroAstro’s SMART-BusTM: a low-cost modular approach enabling responsive space missions. In: Proceedings of AIAA 3rd Responsive Space Conference. 2005.
7
Hideyuki Tanaka, Noritaka Yamamoto, Takehisa Yairi, et al. Autonomous assembly of cellular satellite by robot for sustainable space system. In: Proceedings of the 8th International Symposium on Artifical Intelligence, Robotics and Automation in Space(i-SAIRAS). 2005.
Crossref
8
Xu Y, Zheng J, Wang T, et al. Modular design and integration method of micro-nano-satellite for space station on-orbit assembly. 2022.
9

Hinton G, Salakhutdinov R. Reducing the dimensionality of data with neural networks. Science 2006; 313(5786):504-507.
Crossref Google Scholar
10
Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2014.
Crossref
11

He K, Zhang X, Ren S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 2015; 37(9):1904-1916.
Crossref Google Scholar
12
Girshick R. Fast R-CNN. IEEE International Conference on Computer Vision (ICCV). 2015
Crossref
13
Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems. 2015.
14
Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multi box detector. European Conference on Computer Vision. 2016.
Crossref
15
Bochkovskiy A, Wang C, and Liao H. YOLOv4: Optimal speed and accuracy of object detection. arXiv:2004.10934. 2004.
16
Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016.
Crossref
Journal of Advanced Manufacturing Science and Technology
Article number: 2025014
DOI: 10.51393/j.jamst.2025014
Cite this article:
FAN X, BI J, CHU M. An improved Yolov7-tiny model for modular satellite component identification. Journal of Advanced Manufacturing Science and Technology, 2024, https://doi.org/10.51393/j.jamst.2025014

79

Views

4

Downloads

0

Crossref

0

Scopus

Altmetrics
Received: 23 June 2023
Revised: 23 July 2024
Accepted: 09 September 2024
Published: 27 September 2024
© 2025 JAMST

This is an Open Access article distributed under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0)，which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Return