Utilization of FPGA for Onboard Inference of Landmark Localization in CNN-Based Spacecraft Pose Estimation
Open accessThe DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
In the recent past, research on the utilization of deep learning algorithms for space applications has been widespread. One of the areas where such algorithms are gaining attention is in spacecraft pose estimation, which is a fundamental requirement in many spacecraft rendezvous and navigation operations. Nevertheless, the application of such algorithms in space operations faces unique challenges compared to application in terrestrial operations. In the latter, they are facilitated by powerful computers, servers, and shared resources, such as cloud services. However, these resources are limited in space environment and spacecrafts. Hence, to take advantage of these algorithms, an on-board inferencing that is power- and cost-effective is required. This paper investigates the use of a hybrid Field Programmable Gate Array (FPGA) and Systems-on-Chip (SoC) device for efficient onboard inferencing of the Convolutional Neural Network (CNN) part of such pose estimation methods. In this study, Xilinx’s Zynq UltraScale+ MPSoC device is used and proposed as an effective onboard-inferencing solution. The performance of the onboard and computer inferencing is compared, and the effectiveness of the hybrid FPGA-CPU architecture is verified. The FPGA-based inference has comparable accuracy to the PC-based inference with an average RMS error difference of less than 0.55. Two CNN models that are based on encoder-decoder architecture have been investigated in this study and three approaches demonstrated for landmarks localization.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures


















Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Among the current research works, only a small fraction of the developed algorithms are tested and evaluated on edge systems for space deployment [43,54,73].”
From A survey on deep learning-based monocular spacecraft pose estimation: Current state, limitations and prospects (2023) · cites this paper as [43]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141 · cited 1×
“The choice of this network is due to its robust and effective performance in many real-time object detection applications [51].”
BackgroundStacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634 · cited 1×
“This approach has been improved over the years, notably by the stacked hourglass network by Newell et al. in [48].”
MethodXNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Rastegari, M., Ordonez, V., Redmon, J., & Farhadi, A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_32 · Cited by 4,408 · cited 1×
“, in [36], implemented two efficient binary variations of convolutional neural networks.”
MethodDeepPose: Human Pose Estimation via Deep Neural Networks
Toshev, A., & Szegedy, C. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.214 · Cited by 3,185 · cited 1×
“This approach has been used to varying success in human pose estimation problems, including the seminal work “DeepPose” by Toshev and Szegedy in [46].”
MethodCourbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016) · arXiv · doi:10.48550/arxiv.1602.02830 · Cited by 2,106
A review of space robotics technologies for on-orbit servicing
Flores-Abad, A., Ma, O., Pham, K., & Ulrich, S. (2014) · Progress in Aerospace Sciences · doi:10.1016/j.paerosci.2014.03.002 · Cited by 1,335 · cited 1×
“On-orbit servicing and the assembly of spacecrafts is another field where pose estimation is fundamental [6].”
BackgroundGoing Deeper with Embedded FPGA Platform for Convolutional Neural Network
Qiu, J., Wang, J., Yao, S., Guo, K., Li, B., Zhou, E., Yu, J., Tang, T., Xu, N., Song, S., et al. (2016) · Proceedings of the 2016 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2847263.2847265 · Cited by 1,252 · cited 1×
“One of the seminal works on FPGA-based inference accelerators was presented by Qiu et al. in [39].”
BackgroundFINN: A Framework for Fast, Scalable Binarized Neural Network Inference
Umuroglu, Y., Fraser, N. J., Gambardella, G., Blott, M., Leong, P., Jahre, M., & Vissers, K. (2017) · Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/3020078.3021744 · Cited by 1,189 · cited 1×
“Umuroglu, in [37], presented a framework (named FINN) for building scalable and fast inference accelerators on FPGAs.”
BackgroundJoint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation
Tompson, J., Jain, A., LeCun, Y., & Bregler, C. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.2984 · Cited by 915 · cited 1×
“This approach was first utilized by Tompson et al. in [47].”
MethodIntegral Human Pose Regression
Sun, X., Xiao, B., Wei, F., Liang, S., & Wei, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_33 · Cited by 874
Research works printed but not linked: 4
- 12. Diebel, J. Representing attitude: Euler angles, unit quaternions, and rotation vectors. Matrix 2006, 58, 1-35.
- 17. Hirano, D.; Kato, H.; Saito, T. Deep Learning based Pose Estimation in Space. In Proceedings of the International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS), Madrid, Spain, 4-6 June 2018.
- 18. Sharma, S. Pose Estimation of Uncooperative Spacecraft Using Monocular Vision and Deep Learning. Ph.D. Thesis, Stanford University, Stanford, CA, USA, 2019.
- 22. Sonawani, S.; Alimo, R.; Detry, R.; Jeong, D.; Hess, A.; Amor, H.B. Assistive Relative Pose Estimation for On-orbit Assembly using Convolutional Neural Networks. arXiv 2020, arXiv:2001.10673. · arXiv
Cited by
Giuffrida, G., Fanucci, L., Meoni, G., Batic, M., Buckley, L., Dunne, A., van Dijk, C., Esposito, M., Hefele, J., Vercruyssen, N., et al. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3125567 · Cited by 225
“DNNs have demonstrated remarkable results in several space applications, such as scene classi-fication [22] object recognition [23], pose-estimation [24], change-detection [25], and others [26].”
BackgroundPauly, L., Rharbaoui, W., Shneider, C., Rathinam, A., Gaudillière, V., & Aouada, D. (2023) · Acta Astronautica · doi:10.1016/j.actaastro.2023.08.001 · Cited by 121
“- Multi-stage detectors [23, 58, 126] - Single-stage detectors [114, 60, 120, 12, 29, 92, 81, 172] - Regression of keypoint locations [58, 115, 92] - Segmentation-driven approach [41, 57, 75] - Heatmap prediction [23, 126, 60, 120, 29] - Bounding box prediction [81, 172] - PnP solver [23, 41, 115,…”
BackgroundMethodInfluentialDeep learning-based spacecraft relative navigation methods: A survey
Song, J., Rondao, D., & Aouf, N. (2022) · Acta Astronautica · doi:10.1016/j.actaastro.2021.10.025 · Cited by 106
“Indirect DNN methods Develop from popular networks AlexNet [6],[23],[21]”
BackgroundMethodInfluentialNalepa, J., Myller, M., Cwiek, M., Zak, L., Łakota, T., Tulczyjew, Ł., & Kawulok, M. (2021) · Remote Sensing · doi:10.3390/rs13081532 · Cited by 71
Diana, L., & Dini, P. (2024) · Remote Sensing · doi:10.3390/rs16213957 · Cited by 57
Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs
Vandendriessche, J., Wouters, N., da Silva, B., Lamrini, M., Chkouri, M. Y., & Touhafi, A. (2021) · Electronics · doi:10.3390/electronics10212622 · Cited by 41
“The authors of [24] compare the performance of ResNet34-U-Net running on a Deep Processing Unit (DPU) inside an Ultra96v2 against the performance of the same CNN model running on a PC.”
MethodAldao, E., González-deSantos, L. M., Sanjurjo-Rivo, M., & González-Jorge, H. (2023) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2023.3262505 · Cited by 29
“Both works distinguish two categories of methods: the direct methods that use convolutional neural networks (CNNs) to directly calculate the pose [17], [18], and the indirect methods based on 3-D models, which first use CNNs [19], [20] or image processing methods [21], [22] to detect features in the image, then these…”
MethodComputer vision tasks for intelligent aerospace perception: An overview
Chen, H., Sun, Q., Li, F., & Tang, Y. (2024) · Science China Technological Sciences · doi:10.1007/s11431-024-2714-4 · Cited by 31
“The most prospective AI chips for space applications are Field Programmable Gate Array (FPGA) [191,192], heterogeneous System-on-Chips (SoC) [193] and neuromorphic processors (NPs) [194].”
Towards employing FPGA and ASIP acceleration to enable onboard AI/ML in space applications
Leon, V., Lentaris, G., Soudris, D., Vellas, S., & Bernou, M. (2022) · 2022 IFIP/IEEE 30th International Conference on Very Large Scale Integration (VLSI-SoC) · doi:10.1109/vlsi-soc54400.2022.9939566 · Cited by 20
“FPGAs are integrated in space avionics architectures mainly for accelerating high-performance DSP/AI algorithms [3], [4], [6], [7], performing fast data transformations (e.g., compression) [5], and handling the space-qualified sensors/instruments (e.g., SpaceWire and SpaceFibre) [8].”
BackgroundMethodRobust deep learning LiDAR-based pose estimation for autonomous space landers
Chekakta, Z., Zenati, A., Aouf, N., & Dubois-Matra, O. (2022) · Acta Astronautica · doi:10.1016/j.actaastro.2022.08.049 · Cited by 19
DeepArUco++: Improved detection of square fiducial markers in challenging lighting conditions
Berral-Soler, R., Muñoz‐Salinas, R., Medina-Carnicer, R., & Marín-Jiménez, M. J. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105313 · Cited by 17
CNN-Based Pose Estimation of a Noncooperative Spacecraft With Symmetries From LiDAR Point Clouds
Renaut, L., Frei, H., & Nüchter, A. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3517574 · Cited by 18
“To enable faster inference time compatible with real-time applications, neural network based pose estimation is implemented on a Field Programmable Gate Array (FPGA) [34].”
End-to-end Neural Estimation of Spacecraft Pose with Intermediate Detection of Keypoints
Legrand, A., Detry, R. J., & Vleeschouwer, C. D. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25056-9_11 · Cited by 19
Deep learning on 3D point clouds for fast pose estimation during satellite rendezvous
Renaut, L., Frei, H., & Nüchter, A. (2025) · Acta Astronautica · doi:10.1016/j.actaastro.2025.03.009 · Cited by 17
Silva, A., Fernandes, D., Névoa, R., Monteiro, J. L., Nováis, P., Girão, P., Afonso, T., & Melo‐Pinto, P. (2021) · Sensors · doi:10.3390/s21237933 · Cited by 17
“A study was conducted to compare different dedicated hardware accelerators for vision-based navigation applications, namely FPGA, CPU, GPU, and DSP [1].”
BackgroundMethodInfluentialPirayeshshirazinezhad, R., Biedroń, S. G., Cruz, J. D., Güitrón, S. S., & Martínez‐Ramón, M. (2022) · IEEE Access · doi:10.1109/access.2022.3170438 · Cited by 18
“These advantages have resulted in using EI for spacecraft communication systems [73] and spacecraft GNC [74], [75].”
BackgroundHardware Platforms Enabling Edge AI for Space Applications: A Critical Review
Mystkowska, G., Monopoli, M., Nannipieri, P., Zulberti, L., Codinachs, D. M., & Fanucci, L. (2025) · IEEE Access · doi:10.1109/access.2025.3596326 · Cited by 15
“Several survey articles reviewing AI hardware accelerators have been published, but either do not focus on the architecture aspect of different chips [5], [6], [7] or do not evaluate space industry implementation [8], [9], [10], [11], [12].”
GPU@SAT DevKit: Empowering Edge Computing Development Onboard Satellites in the Space-IoT Era
Benelli, G., Todaro, G., Monopoli, M., Giuffrida, G., Donati, M., & Fanucci, L. (2024) · Electronics · doi:10.3390/electronics13193928 · Cited by 13
FPGA-Based Neural Network Accelerators for Space Missions: A Survey
Antunes, P., & Podobas, A. (2026) · ACM Computing Surveys · doi:10.1145/3857797 · Cited by 11
“Cosmas and Kenichi (2020) [37] presented CNN acceleration for spacecraft pose estimation, leveraging Vitis AI [6] on an Ultra96-V2 board featuring an UltraScale+ MPSoC.”
Domain Generalization for In-Orbit 6D Pose Estimation
Legrand, A., Detry, R., & De Vleeschouwer, C. (2025) · Journal of Aerospace Information Systems · doi:10.2514/1.i011498 · Cited by 10
“Finally, the pose estimation pipeline must run on limited resources provided by space-grade hardware [9, 10].”
MethodFilterformerPose: Satellite Pose Estimation Using Filterformer
Ye, R., Wang, L., Ren, Y., Wang, Y., Chen, X., & Liu, Y. (2023) · Sensors · doi:10.3390/s23208633 · Cited by 11
“Kiruki et al. [31] used YOLO for satellite object detection, provided the cropped RoI to the U-Net network for key point prediction, and used PnP and RANSAC for pose inference.”
MethodResearch on Spaceborne Neural Network Accelerator and Its Fault Tolerance Design
Shao, Y., Wang, J., Han, X., Li, Y., Li, Y., & Tao, Z. (2024) · Remote Sensing · doi:10.3390/rs17010069 · Cited by 8
Single event effects evaluation on convolution neural network in Xilinx 28 nm system on chip
Zhao, X., Du, X., 熊, X. 旭. X., Ma, C., Yang, W., Zheng, B., & Zhou, C. Y. (2024) · Chinese Physics B · doi:10.1088/1674-1056/ad3b82 · Cited by 8
Review of Spacecraft Pose-Estimation Techniques for Close-Proximity Operations
Vishal, K., Nair, V. G., & D’Souza, J. M. (2025) · IEEE Access · doi:10.1109/access.2025.3647636 · Cited by 7
“To mitigate this shortcoming researchers explored the utilization of hybrid Field Programmable Gate Array (FPGA) and Systems-on-Chip (SoC) devices for efficient onboard inferencing of Convolutional Neural Networks (CNNs) [156].”
Monocular Vision and Machine Learning for Pose Estimation
Tran, Q., Choate, J., Taylor, C. N., Nykl, S. L., & Curtis, D. H. (2023) · IEEE/ION Position Location and Navigation Symposium · doi:10.1109/plans53410.2023.10140128 · Cited by 8
“Another similar approach to Chen et al. [4] and Cosmas et al. [8] is Black et al. [9], which utilizes a CNN with 2D keypoint regression and an E-PnP [10] solver to estimate pose on uncooperative known target using monocular vision for autonomous on-orbit proximity operations scenarios.”
MethodHybrid deep learning based monocular pose estimation for autonomous space docking operations
Khalil, S., Wang, Z., & Aouf, N. (2025) · Acta Astronautica · doi:10.1016/j.actaastro.2025.10.010 · Cited by 7
Optimization of the Versatile Tensor Accelerator (VTA) Load Module in a Time-Triggered Memory Access
Ezekiel, A. M., Onwuchekwa, D., & Obermaisser, R. (2023) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd60849.2023.00030 · Cited by 5
“The PL of the TE0802 holds the extended VTA with its TTLC as the prediction engine [19].”
MethodPosso, J., Bois, G., & Savaria, Y. (2024) · IEEE Interregional NEWCAS Conference (NEWCAS) · doi:10.1109/newcas58973.2024.10666317 · Cited by 6
“However, challenges persist in the area of real-time SPE inference, with only a few publications addressing this issue [6], [11]–[13].”
BackgroundMethodApplications of AI in Space Domain
dos Santos, L. B. R., Basciani, F., & Pelliccione, P. (2025) · ACM Computing Surveys · doi:10.1145/3757317 · Cited by 5
Development and In-Orbit Operation of Deep Learning Attitude Sensor
Kikuya, Y., Ohta, K., Iwasaki, Y., Ozawa, T., Watanabe, K., Yatsu, Y., & Matunaga, S. (2023) · Journal of Spacecraft and Rockets · doi:10.2514/1.a35388 · Cited by 4
Silva, A., Oliveira, P., Durães, D. A., Fernandes, D., Névoa, R., Monteiro, J. L., Melo‐Pinto, P., Machado, J. M., & Nováis, P. (2023) · Sensors · doi:10.3390/s23146427 · Cited by 4
GKNet: Graph-based Keypoints Network for Monocular Pose Estimation of Non-cooperative Spacecraft
Ma, W., Zhou, D., Hu, Y., & He, Z. (2025) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2025.11.335 · Cited by 4
Song, Z., Zhang, Z., Zhang, F., & Bao, W. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.112090 · Cited by 3
FPGA Implementation of Deep Leaning Model for Video Analytics
Khayam, K. N., Mehmood, Z., Chaudhry, H. N., Ashraf, M. U., Tariq, U., Altouri, M. N., & Alsubhi, K. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.019921 · Cited by 3
Relative Pose Estimation of an Uncooperative Target with Camera Marker Detection
Candan, B., & Servadio, S. (2025) · Aerospace · doi:10.3390/aerospace12050425 · Cited by 8
Study on an Estimation Method of On-orbit Single Event Upset Rate Based on Historical Data
He, W., Li, J., Zhou, Y., & Lin, J. (2021) · International Conference on Electronics Technology (ICET) · doi:10.1109/icet51757.2021.9451070 · Cited by 3
“Hence, the estimation of SEU rate of SRAM-based is a problem to be solved([4,5]).”
BackgroundSpacecraft State Estimation Using Neural Radiance Fields
Heintz, A. M., & Peck, M. A. (2023) · Journal of Guidance Control and Dynamics · doi:10.2514/1.g006946 · Cited by 6
Evaluation of Resource-Efficient Crater Detectors on Embedded Systems
Vellas, S., Psomas, B., Karadima, K., Danopoulos, D., Paterakis, A., Lentaris, G., Soudris, D., & Karantzalos, K. G. (2024) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss53475.2024.10642518 · Cited by 6
“This interest is evident in mission-specific applications such as earth observation, remote sensing [56], and spacecraft pose estimation [57].”
BackgroundAdaptive Relative Pose Estimation Framework with Dual Noise Tuning for Safe Approaching ManeuversPreprint
Candan, B., Oktay, M. B., & Servadio, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.16214 · Cited by 4
“In contrast to more computationally demanding models such as L-CNN [44] or other networks [45–49], TinyCornerNET is tailored for simplicity and efficiency, making it ideal for deployment in real-time, resource-constrained spaceborne environments.”
NeRF-based Visualization of 3D Cues Supporting Data-Driven Spacecraft Pose Estimation
Legrand, A., Detry, R. J., & Vleeschouwer, C. D. (2025) · International Conference on Space Robotics (iSpaRo) · doi:10.1109/isparo66239.2025.11436169 · Cited by 3
赵, X. 旭. Z., 杜, X. 雪. D., 马, C. 超. M., 胡, Z. 志. H., 杨, W. 卫. Y., & 郑, B. 波. Z. (2024) · Chinese Physics B · doi:10.1088/1674-1056/ad8b38 · Cited by 2
Elastic computing self-organizing for artificial intelligence space exploration
Semenov, A. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1925/1/012071 · Cited by 2
Napolano, G., Nocerino, A., Fasano, G., Grassi, M., & Opromolla, R. (2025) · Acta Astronautica · doi:10.1016/j.actaastro.2025.06.012 · Cited by 4
Zhao, X., Du, X. C., Ma, C., Yang, W., Zhang, C., Zhang, P., Zheng, B., Wang, X., & Feng, S. (2025) · Nuclear Instruments and Methods in Physics Research Section B Beam Interactions with Materials and Atoms · doi:10.1016/j.nimb.2025.165895 · Cited by 1
Spacecraft Pose Estimation Based on High-Resolution Feature Network
Fu, Z., Ru, B., Wang, Z., Wang, L., Yue, D., Zhou, J., Li, X., & Tang, L. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343011 · Cited by 1
“Figure 6 shows a schematic diagram of heatmap encoding [13], which achieves sub-pixel localization accuracy by probabilistically constructing a probability distribution field through a Gaussian kernel.”
Liu, K., Yu, Y., Liu, T., Han, D., & Liao, W. (2026) · Acta Astronautica · doi:10.1016/j.actaastro.2026.04.033 · Cited by 1
Learning Structured Distance Mappings for Spacecraft Pose Estimation with Feature Degradation
Chuan, Y., Long, H., Cao, Z., Ma, Y., Suo, J., Lu, X., Zhao, R. C., & Peng, Z. (2026) · Remote Sensing · doi:10.3390/rs18101647 · Cited by 1
Guajo, J., Alzate-Anzola, C., Betancur, D., Castaño-Londoño, L., & Márquez-Viloria, D. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-86702-7_38
Juxtaposing Vivado Design Flows in Batch Mode
Dadaliaris, A. N., Tragoudaras, A., Kranas, G. K., Dossis, M. F., & Dimitriou, G. (2021) · Panhellenic Conference on Informatics · doi:10.1145/3503823.3503849
“The benefit of re-configurability has made it possible for FPGAs to be utilized in a diverse set of markets and applications, such as Aerospace [6], [8], Avionics [11], Multimedia and Image Processing [14], [12], [15], [4], Automotive [9], [13], [5], and Bioinformatics [17], [7], [10] while their…”
BackgroundTowards smart acoustic cameras for simultaneous sound localization and recognition
Vandendriessche, J. (2024) · VUBIR (Vrije Universiteit Brussel)
E3S-Net: an efficient end-to-end 6D pose estimation method for non-cooperative space target
Shen, N., & Wang, J. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae6ba8
“Cosmas and Kenichi [40] used a hybrid FPGA-CPU architecture based on the Xilinx Zynq UltraScale + MPSoC for efficient CNN pose estimation, maintaining accuracy while significantly reducing power and latency, achieving a root mean square error of less than 0.55 compared to PC inference.”
InfluentialCAD-Free Learning of Spacecraft Pose Estimators via NeRF-Based AugmentationsPreprint
Legrand, A., Detry, R. J., & Vleeschouwer, C. D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.19649 · Cited by 1
“However, these techniques require access to target-domain data and incur computational costs that exceed the capabilities of current space-grade hardware [43, 44].”
Gonidakis, P., Carella, F., Dineva, E., Jeong, H.-J., Antunes, P., Podobas, A., Raptis, S., Toy, V., Jin, M., Poedts, S., et al. (2026) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2025jh001023
Bridging the domain gap in spacecraft pose estimation: A novel image generative model
Song, Z., Zhang, Z., Zhang, F., & Xiao, X. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.112871
A Geometric‐Nonlinear Optimization Algorithm for Solving Pose Matrices in Aircraft Visual Navigation
Wu, C., Fang, X., Yang, D., & Li, Y. (2026) · Journal of Applied Mathematics · doi:10.1155/jama/9703233
Metadata
- Authors
- Cosmas, K., & Kenichi, A.
- Affiliations
- Kyushu Institute of Technology (JP)
- Embedded Systems Laboratory, Electrical and Space Engineering, Kyushu Institute of Technology, 1-1 Sensui, Tobata, Kitakyushu, Fukuoka 804-8550, Japan
- Corresponding author
- Cosmas, Kiruki
- Venue
- Aerospace
- Publisher
- MDPI AG
- Published
- 2020-11-05
- Volume
- 7
- Issue
- 11
- Pages
- 159
- ISSN
- 2226-4310 (ISSN-L)
- OpenAlex
- W3097559709
- Cited by
- 51
- References
- 40
- Citations by year
- 2026: 7 · 2025: 11 · 2024: 10 · 2023: 10 · 2022: 3 · 2021: 10
- FWCI
- 2.24
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Aerospace (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Embedded Systems Design Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Embedded Systems and FPGA Applications
- Keywords
- FPGA, spacecraft pose estimation, landmark detection, convolutional neural networks, Zynq UltraScale+ MPSoC, encoder-decoder architecture, spacecraft rendezvous, spacecraft navigation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.