基于混合专家模型的航天遥感图像目标检测

doi:10.7527/S1000-6893.2025.32599

Abstract

Abstract:

As an important application direction in the field of spaceborne remote sensing， object detection is of great significance in disaster emergency response， resource management， environmental monitoring and other fields. We take ship targets as an example to study object detection in spaceborne remote sensing images. Spaceborne remote sensing covers sea areas in different regions worldwide， and these sea areas have significant differences in geomorphic features. Existing ship target detection methods mostly use a unified structure to handle different scenarios， making it difficult to adapt to changes in ground object features in different regions and with different resolutions. To address this， we introduce the Mixture of Experts （MoE） model into the task of spaceborne remote sensing image object detection， and propose a spaceborne remote sensing image object detection model based on the Mixture of Experts model. It adaptively selects corresponding expert processing for the differential features of different geographical regions to achieve more accurate ship target detection in different sea areas. The model includes two groups of experts： one group is guided by spatial resolution information to capture differences in ground object scales under different resolutions； the other group uses latitude and longitude information for guidance to adapt to the distribution characteristics of ground objects in different geographical regions. Through the collaborative work of the two groups of experts， the model can more accurately perceive and locate ship targets in images， significantly improving detection performance. In addition， we construct a dataset containing multi-resolution information and latitude and longitude information-the Geographic In-formation Ship Detection Dataset （GISD） to provide data support for the research. We conduct experimental verification on the GISD dataset and the public dataset LEVIR-ship. The average precision AP50 of the proposed method reaches 80.6% and 85.7% respectively， which is 3.8% and 2.0% higher than that of the best-performing models on the two datasets.

Key words: remote-sensing image, ship detection, optical remote sensing, geographical information, mixture of experts

CLC Number:

Guangyu LU, Bowen CHEN, Keyan CHEN, Zhengxia ZOU, Zhenwei SHI. Spaceborne remote sensing image object detection based on mixture of experts model[J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(10): 532599.

Figures/Tables 17

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Fig.5

Fig.6

Table 2

Table 3

Table 4

Table 5

Table 6

Table 7

Fig.7

Fig.8

Fig.9

Fig.10

References 34

[1]	LIN Y F， LI J X， WEI S Q， et al. OptiShipNet： Efficient ship detection in complex marine environments using optical remote sensing images［J］. Journal of Marine Science and Engineering， 2024， 12（10）： 1786.
[2]	LIU Z H， ZHANG W J， YU H， et al. Improved YOLOv5s for small ship detection with optical remote sensing images［J］. IEEE Geoscience and Remote Sensing Letters， 2023， 20： 8002205.
[3]	肖欣林，施伟超，郑向涛，等. 基于多模型协同的舰船目标检测［J］. 航空学报， 2024， 45（14）： 630241.
	XIAO X L， SHI W C， ZHENG X T， et al. Multiple models collaboration for ship detection［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（14）： 630241 （in Chinese）.
[4]	赵其昌，吴一全，苑玉彬. 光学遥感图像舰船目标检测与识别方法研究进展［J］. 航空学报， 2024， 45（8）： 029025.
	ZHAO Q C， WU Y Q， YUAN Y B. Progress of ship detection and recognition methods in optical remote sensing images［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（8）： 029025 （in Chinese）.
[5]	ZOU Z X， CHEN K Y， SHI Z W， et al. Object detection in 20 years： A survey［J］. Proceedings of the IEEE， 2023， 111（3）： 257-276.
[6]	CHEN B W， LIU L Q， ZOU Z X， et al. Target detection in hyperspectral remote sensing image： Current status and challenges［J］. Remote Sensing， 2023， 15（13）： 3223.
[7]	SHI Z W， YU X R， JIANG Z G， et al. Ship detection in high-resolution optical imagery based on anomaly detector and local shape feature［J］. IEEE Transactions on Geoscience and Remote Sensing， 2014， 52（8）： 4511-4523.
[8]	黎经元，厉小润，赵辽英. 基于边缘线分析与聚合通道特征的港口舰船检测［J］. 光学学报， 2019， 39（8）： 0815004.
	LI J Y， LI X R， ZHAO L Y. Docked ship detection based on edge line analysis and aggregation channel features［J］. Acta Optica Sinica， 2019， 39（8）： 0815004 （in Chinese）.
[9]	WANG H L， ZHU M， LIN C B， et al. Ship detection in optical remote sensing image based on visual saliency and AdaBoost classifier［J］. Optoelectronics Letters， 2017， 13（2）： 151-155.
[10]	GIRSHICK R， DONAHUE J， DARRELL T， et al. Rich feature hierarchies for accurate object detection and semantic segmentation［C］∥ 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2014.
[11]	REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： Unified， real-time object detection［C］∥2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2016.
[12]	CARION N， MASSA F， SYNNAEVE G， et al. End-to-end object detection with transformers［C］∥ 2020 European Conference on Computer Vision. 2020.
[13]	LIN H N， SHI Z W， ZOU Z X. Fully convolutional network with task partitioning for inshore ship detection in optical remote sensing images［J］. IEEE Geoscience and Remote Sensing Letters， 2017， 14（10）： 1665-1669.
[14]	CHEN J Q， CHEN K Y， CHEN H， et al. A degraded reconstruction enhancement-based method for tiny ship detection in remote sensing images with a new large-scale dataset［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022， 60： 5625014.
[15]	王子玲，熊振宇，杨璐铖，等. AIS和光学遥感图像引导的星载SAR舰船目标识别网络［J］. 航空学报， 2024， 45（2）： 328672.
	WANG Z L， XIONG Z Y， YANG L C， et al. Spaceborne SAR ship target recognition network guided by AIS and optical remote sensing images［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（2）： 328672 （in Chinese）.
[16]	XING Z J， REN J， FAN X Z， et al. S-DETR： A transformer model for real-time detection of marine ships［J］. Journal of Marine Science and Engineering， 2023， 11（4）： 696.
[17]	WANG P L， LIU B X， LI Y， et al. IceRegionShip： Optical remote sensing dataset for ship detection in ice-infested waters［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2024， 17： 1007-1020.
[18]	YAN Y M， HE Y M， SU N， et al. PNBT-CR： A cloud removal method for ship detection［J］. IEEE Geoscience and Remote Sensing Letters， 2024， 21： 1501905.
[19]	刘子力，杨家俊，王文静，等. 遥感图像云检测方法综述［J］. 中国空间科学技术， 2023， 43（1）： 1-17.
	LIU Z L， YANG J J， WANG W J， et al. Cloud detection methods for remote sensing images： A survey［J］. Chinese Space Science and Technology， 2023， 43（1）： 1-17 （in Chinese）.
[20]	LI Y X， HOU Q B， ZHENG Z H， et al. Large selective kernel network for remote sensing object detection［C］∥2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE Press， 2024.
[21]	MA D Q， LI S J， DANG B， et al. Fostc3net： A lightweight YOLOv5 based on the network structure optimization［J］. Journal of Physics： Conference Series， 2024， 2824（1）： 012004.
[22]	QIN C， WANG X Q， LI G， et al. An improved attention-guided network for arbitrary-oriented ship detection in optical remote sensing images［J］. IEEE Geoscience and Remote Sensing Letters， 2022， 19： 6514805.
[23]	ZOU Z X， SHI Z W. Ship detection in spaceborne optical image with SVD networks［J］. IEEE Transactions on Geoscience and Remote Sensing， 2016， 54（10）： 5832-5845.
[24]	BI F K， HOU J Y， CHEN L， et al. Ship detection for optical remote sensing images based on visual attention enhanced network［J］. Sensors， 2019， 19（10）： 2271.
[25]	JACOBS R A， JORDAN M I， NOWLAN S J， et al. Adaptive mixtures of local experts［J］. Neural Computation， 1991， 3（1）： 79-87.
[26]	FEDUS W， ZOPH B， SHAZEER N. Switch transformers： Scaling to trillion parameter models with simple and efficient sparsity［J］. Journal of Machine Learning Research， 2022， 23（120）： 1-39.
[27]	CHEN B W， CHEN K Y， YANG M H， et al. Heterogeneous mixture of experts for remote sensing image super-resolution［J］. IEEE Geoscience and Remote Sensing Letters， 2025， 22： 6006405.
[28]	XIA G S， BAI X， DING J， et al. DOTA： A large-scale dataset for object detection in aerial images［C］∥ 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2018.
[29]	LIU Z， LIN Y T， CAO Y， et al. Swin transformer： Hierarchical vision transformer using shifted windows［C］∥ 2021 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE Press， 20221.
[30]	SONG J N， ZHOU M L， LUO J， et al. Boundary-aware feature fusion with dual-stream attention for remote sensing small object detection［J］. IEEE Transactions on Geoscience and Remote Sensing， 2025， 63： 5600213.
[31]	TIAN Z， SHEN C H， CHEN H， et al. FCOS： Fully convolutional one-stage object detection［C］∥ 2019 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE Press， 2019.
[32]	HE K M， GKIOXARI G， DOLLÁR P， et al. Mask R-CNN［C］∥ 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE Press， 2017.
[33]	ZHANG H， LI F， LIU S L， et al. DINO： DETR with improved DeNoising anchor boxes for end-to-end object detection［DB/OL］. arXiv preprint： 2203.03605， 2022.
[34]	ZONG Z F， SONG G L， LIU Y. DETRs with collaborative hybrid assignments training［C］∥ 2023 IEEE/CVF International Conference on Computer Vision. Piscataway： IEEE Press， 2023.

港口编号	港口名称	纬度坐标	经度坐标	数据集总数
1	Ellefsen Harbor	60.733 333°S	45.033 333°W	21
2	Surabaya	7.2°S	112.733 333°E	197
3	Panjang	5.466 667°S	105.316 667°E	124
4	Aksaz Limani	36.833 333°N	28.383 333°E	44
5	Pyeongtaek Hang	37°N	126.8°E	127
6	Lavrio	37.7°N	24.066 667°E	271
7	Annapolis	38.983 333°N	76.483 333°W	7
8	Baltimore	39.266 667°N	76.583 333°W	86
9	Gemlik	40.416 667°N	29.116 667°E	50
10	Port Reading	40.566 667°N	74.233 333°W	52
11	Salerno	40.666 667°N	14.75°E	51
12	Brooklyn	40.666 667°N	74.016 667°W	197
13	Midland	44.75°N	79.916 667°W	122
14	Carillon	45.566 667°N	74.366 667°W	66
15	Mykolayiv	46.95°N	31.983 333°E	71
16	Maassluis	51.916 667°N	4.25°E	129
17	Bella	52.166 667°N	128.15°W	213
18	Bird Port	51.566 667°N	2.966 667°W	17
19	Pevek	69.716 667°N	170.3°E	15

网络模型	AP	AP50	AP75	APs	APm	APl
基准模型	0.393	0.768	0.360	0.280	0.458	0.604
MoE	0.396	0.770	0.366	0.276	0.462	0.624
MoE+L	0.416	0.786	0.401	0.263	0.498	0.637
本文模型	0.428	0.806	0.408	0.268	0.537	0.662

损失权重	AP	AP50	AP75	APs	APm	APl
0	0.387	0.763	0.353	0.233	0.496	0.613
0.1	0.401	0.783	0.379	0.238	0.511	0.635
0.5	0.428	0.806	0.408	0.268	0.537	0.662
1.0	0.423	0.794	0.401	0.253	0.536	0.674
5.0	0.411	0.796	0.377	0.255	0.520	0.630

专家数量	AP	AP50	AP75	FLOPs/G	Params/M
2	0.417	0.785	0.394	535	383
4	0.428	0.806	0.408	535	559
6	0.414	0.799	0.385	535	735
8	0.404	0.785	0.365	535	911

网络模型	AP	AP50	AP75	APs	APm	APl
Mask-RCNN^［32］	0.288	0.536	0.283	0.093	0.438	0.598
DRENet^［14］	0.273	0.608	0.199	0.145	0.368	0.481
FCOS^［31］	0.315	0.648	0.273	0.152	0.415	0.585
DINO^［33］	0.359	0.732	0.305	0.242	0.437	0.573
CO-DETR^［34］	0.386	0.762	0.343	0.265	0.456	0.616
BAFNet^［30］	0.393	0.768	0.36	0.280	0.458	0.604
本文模型	0.428	0.806	0.408	0.268	0.537	0.662

Spaceborne remote sensing image object detection based on mixture of experts model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 34

Related Articles 4

Recommended Articles

Metrics

Comments

网络模型	AP	AP50	AP75	APs	APm
Mask-RCNN^［32］	0.255	0.749	0.054	0.249	0.368
DRENet^［14］	0.280	0.822	0.064	0.282	0.272
FCOS^［31］	0.272	0.837	0.058	0.265	0.338
DINO^［33］	0.272	0.758	0.103	0.261	0.403
CO-DETR^［34］	0.262	0.796	0.060	0.255	0.312
BAFNet^［30］	0.273	0.795	0.075	0.268	0.316
本文模型	0.338	0.857	0.173	0.335	0.368

网络模型	AP50	FLOPs/G	Params/M	FPS
Mask-RCNN^［32］	0.749	247	213	20.73
DRENet^［14］	0.822	218	216	29.90
FCOS^［31］	0.837	236	204	27.00
DINO^［33］	0.758	405	218	18.96
CO-DETR^［34］	0.796	460	235	12.75
BAFNet^［30］	0.795	481	250	11.20
本文模型	0.857	535	559	10.20

[1]	Qichang ZHAO, Yiquan WU, Yubin YUAN. Progress of ship detection and recognition methods in optical remote sensing images [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(8): 29025-029025.
[2]	Xinlin XIAO, Weichao SHI, Xiangtao ZHENG, Yueming GAO, Xiaoqiang LU. Multiple models collaboration for ship detection [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(14): 630241-630241.
[3]	Liqun CHEN, Xu ZOU, Lei ZHANG, Yingpan ZHU, Gang WANG, Jinyong CHEN. On⁃board intelligent target detection technology based on domestic commercial components [J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(S2): 728860-728860.
[4]	SU Hang, XU Congan, YAO Libo, LI Jianwei, LING Qing, GAO Long. A lightweight oriented ship detection method in SAR images [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(S1): 726922-726922.