基于残差自注意力和分离集合匹配的高效端到端航天器组件检测

doi:10.19678/j.issn.1000-3428.0068524

计算机工程 ›› 2024, Vol. 50 ›› Issue (8): 301-309. doi: 10.19678/j.issn.1000-3428.0068524

基于残差自注意力和分离集合匹配的高效端到端航天器组件检测

陈明¹, 牛燕菲¹, 段莉²^,*(), 高铁梁³, 楚杨阳¹, 曹洁¹

1. 郑州轻工业大学软件学院, 河南郑州 450000
2. 北京交通大学计算机与信息技术学院, 北京 100000
3. 新乡学院商学院, 河南新乡 453000

收稿日期:2023-10-08 出版日期:2024-08-15 发布日期:2024-03-19
通讯作者: 段莉
基金资助:
国家自然科学基金(62072414); 河南省重点研发与推广专项(212102210104); 河南省重点研发与推广专项(162102210214)

Efficient End-to-End Spacecraft Component Detection Based on Residual Self-attention and Separated Set Matching

Ming CHEN¹, Yanfei NIU¹, Li DUAN²^,*(), Tieliang GAO³, Yangyang CHU¹, Jie CAO¹

1. College of Software Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, Henan, China
2. School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100000, China
3. Bussiness School, Xinxiang University, Xinxiang 453000, Henan, China

Received:2023-10-08 Online:2024-08-15 Published:2024-03-19
Contact: Li DUAN

摘要/Abstract

摘要：

随着我国航天技术的迅猛发展, 各种航天器相继发射, 然而航天器在运行时将受到辐射、温度变化等不可控因素的影响, 这会导致地面站无法精确测量和定位航天器的位置与姿态, 从而对通信和航天器之间的对接或抓捕等空间在轨服务产生影响。为了解决上述问题, 首先对包含检测、分割与部件识别的航天器数据集SDDSP中的部件进行人工标注, 该数据集共包含3 117张航天器图片, 标注后得到11 001个检测目标; 然后提出一种空间在轨服务中基于残差自注意力(RS)和分离集合匹配(SSM)的高效端到端航天器组件检测模型, 该模型在Sparse DETR模型的基础上引入残差自注意力机制解决了稀疏标记(token)导致的收敛速度降低并影响模型预测精度的问题, 引入分离集合匹配机制解决了二分匹配过程中可能出现的不稳定性现象。实验结果表明, 在SDDSP数据集上, 该模型的平均精确率(AP)和收敛速度相比于基线DETR模型提升了17.9个百分点和10倍, 相比于Sparse DETR模型提升了3.1个百分点和20%。

关键词: 航天器组件检测, Sparse DETR模型, 残差自注意力, 分离集合匹配, 航天器数据集

Abstract:

The rapid development of space technology in China has led to a multitude of spacecraft launches. However, these spacecraft are expected to experience the influence of uncontrollable factors such as radiation and temperature changes during operation. These changes may impede the accurate measurement of spacecraft positions and behaviors by ground stations, thereby impacting on-orbit services such as communications and docking, as well as grappling between spacecraft. To solve these problems, the present study first annotates the SDDSP spacecraft dataset which encompasses detection, segmentation, and component recognition with 3 117 spacecraft images and 11 001 detection targets. An efficient end-to-end spacecraft component detection model is then proposed based on Residual Self-attention (RS) and Separated Set Matching (SSM) in space on-orbit services. The RS mechanism is introduced on the basis of the Sparse DEtection TRansformer (DETR) model to solve the problem of sparse tokens, which slows convergence and degrades the prediction accuracy of the model. Furthermore, SSM is deployed to address the phenomenon of instability that may occur in the process of dichotomous matching. The experimental results show that the Average Precision (AP) and convergence speed of the model are improved by 17.9 percentage points and 10 times, respectively, compared with those of the baseline DETR model, as well as 3.1 percentage points and 20%, respectively, compared with those of the Sparse DETR model.

Key words: spacecraft component detection, Sparse DERT model, Residual Self-attention(RS), Separated Set Matching(SSM), aircraft dataset

陈明, 牛燕菲, 段莉, 高铁梁, 楚杨阳, 曹洁. 基于残差自注意力和分离集合匹配的高效端到端航天器组件检测[J]. 计算机工程, 2024, 50(8): 301-309.

Ming CHEN, Yanfei NIU, Li DUAN, Tieliang GAO, Yangyang CHU, Jie CAO. Efficient End-to-End Spacecraft Component Detection Based on Residual Self-attention and Separated Set Matching[J]. Computer Engineering, 2024, 50(8): 301-309.

https://www.ecice06.com/CN/Y2024/V50/I8/301

图/表 10

图1 RSSSM-DETR模型整体框架

Fig.1 Overall framework of RSSSM-DETR model

图2 初始学习率对比结果

Fig.2 Comparative results of initial learning rate

图3 Epoch阈值对比结果

Fig.3 Comparative results of Epoch threshold

图4 Dropout对比结果

Fig.4 Comparative results of Dropout

图5 k参数对比结果

Fig.5 Comparative results of k parameter

图6 航天器组件遮挡对比结果

Fig.6 Comparative results of spacecraft component occlusion

图7 AP变化对比曲线

Fig.7 Comparative curves of AP change

图8 Loss变化对比曲线

Fig.8 Comparative curves of Loss change

参考文献 22

1	DUNG H A, CHEN B, CHIN T J. A spacecraft dataset for detection, segmentation and parts recognition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Washington D. C., USA: IEEE Press, 2021: 2012-2019.
2	FLORES-ABAD A, MA O, PHAM K, et al. A review of space robotics technologies for on-orbit servicing. Progress in Aerospace Sciences, 2014, 68, 1- 26. doi: 10.1016/j.paerosci.2014.03.002
3	逄晨曦, 李文辉. 基于注意力改进的自适应空间特征融合目标检测算法. 吉林大学学报(理学版), 2023, 61(3): 557- 566.
	PANG C X, LI W H. Adaptive spatial feature fusion object detection algorithm based on attention improvement. Journal of Jilin University (Science Edition), 2023, 61(3): 557- 566.
4	KANG G H, ZHANG Q, WU J Q, et al. Pose estimation of a non-cooperative spacecraft without the detection and recognition of point cloud features. Acta Astronautica, 2021, 179, 569- 580. doi: 10.1016/j.actaastro.2020.11.013
5	KOTHARI V, LIBERIS E, LANE N D. The final frontier: deep learning in space[C]//Proceedings of the 21st International Workshop on Mobile Computing Systems and Applications. New York, USA: ACM Press, 2020: 45-49.
6	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL]. [2023-09-05]. http://arxiv.org/abs/1706.03762.
7	CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[C]//Proceedings of the European Conference on Computer Vision. Berlin, Germany: Springer International Publishing, 2020: 213-229.
8	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2016: 779-788.
9	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2017: 6517-6525.
10	REDMON J, FARHADI A. YOLOv3: an incremental improvement[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 1-6.
11	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[M]. Berlin, Germany: Springer International Publishing, 2016.
12	GIRSHICK R, DONAHUE J, DARRELL T, et al. Region-based convolutional networks for accurate object detection and segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(1): 142- 158. doi: 10.1109/TPAMI.2015.2437384
13	GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D. C., USA: IEEE Press, 2015: 1440-1448.
14	REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
15	HE K M, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 386- 397. doi: 10.1109/TPAMI.2018.2844175
16	LOWE D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91- 110. doi: 10.1023/B:VISI.0000029664.99615.94
17	UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T, et al. Selective search for object recognition. International Journal of Computer Vision, 2013, 104(2): 154- 171. doi: 10.1007/s11263-013-0620-5
18	ZHU X Z, SU W J, LU L W, et al. Deformable DETR: deformable Transformers for end-to-end object detection[EB/OL]. [2023-09-05]. http://arxiv.org/abs/2010.04159.
19	ROH B, SHIN J, SHIN W, et al. Sparse DETR: efficient end-to-end object detection with learnable sparsity[EB/OL]. [2023-09-05]. http://arxiv.org/abs/2111.14330.
20	MENG D P, CHEN X K, FAN Z J, et al. Conditional DETR for fast training convergence[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D. C., USA: IEEE Press, 2021: 3631-3640.
21	GAO P, ZHENG M H, WANG X G, et al. Fast convergence of DETR with spatially modulated co-attention[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D. C., USA: IEEE Press, 2021: 3601-3610.
22	DAI Z G, CAI B L, LIN Y G, et al. UP-DETR: unsupervised pre-training for object detection with Transformers[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2021: 1601-1610.

选择文件类型/文献管理软件名称

选择包含的内容

基于残差自注意力和分离集合匹配的高效端到端航天器组件检测

Efficient End-to-End Spacecraft Component Detection Based on Residual Self-attention and Separated Set Matching

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 22

相关文章 0

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于残差自注意力和分离集合匹配的高效端到端航天器组件检测

Efficient End-to-End Spacecraft Component Detection Based on Residual Self-attention and Separated Set Matching

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 22

相关文章 0

编辑推荐

Metrics

本文评价