Corpus ID: 238419495

SPEED+: Next Generation Dataset for Spacecraft Pose Estimation across Domain Gap

@article{Park2021SPEEDNG,
  title={SPEED+: Next Generation Dataset for Spacecraft Pose Estimation across Domain Gap},
  author={Tae Ha Park and Marcus M{\"a}rtens and Gurvan Lecuyer and Dario Izzo and Simone D’Amico},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.03101}
}
Autonomous vision-based spaceborne navigation is an enabling technology for future on-orbit servicing and space logistics missions. While computer vision in general has benefited from Machine Learning (ML), training and validating spaceborne ML models are extremely challenging due to the impracticality of acquiring a large-scale labeled dataset of images of the intended target in the space environment. Existing datasets, such as Spacecraft PosE Estimation Dataset (SPEED), have so far mostly… Expand

References

SHOWING 1-10 OF 48 REFERENCES
Pose estimation of an uncooperative spacecraft from actual space imagery
TLDR
The aim is to estimate the pose of a passive space resident object using its known three-dimensional model and single low-resolution two-dimensional images collected on-board the active spacecraft. Expand
Satellite Pose Estimation Challenge: Dataset, Competition Design, and Results
TLDR
The main contribution of this article is the analysis of the submissions of the 48 competitors, which compares the performance of different approaches and uncovers what factors make the satellite pose estimation problem especially challenging. Expand
Deep Learning for Spacecraft Pose Estimation from Photorealistic Rendering
TLDR
This paper presents a simulator built on Unreal Engine 4, named URSO, to generate labeled images of spacecraft orbiting the Earth, and proposes a deep learning framework for pose estimation based on orientation soft classification, which allows modelling orientation ambiguity as a mixture model. Expand
Pose estimation for non-cooperative spacecraft rendezvous using convolutional neural networks
TLDR
The proposed architecture is scalable to spacecraft of different structural and physical properties as well as robust to the dynamic illumination conditions of space and can be used to augment the current state-of-the-art monocular vision-based pose estimation techniques used in spaceborne applications. Expand
Real-Time, Flight-Ready, Non-Cooperative Spacecraft Pose Estimation Using Monocular Imagery
TLDR
This work presents a novel convolutional neural network (CNN)-based monocular pose estimation system that achieves state-of-the-art accuracy with low computational demand and demonstrates the ability to generalize from purely synthetic training data to real in-space imagery of the Northrop Grumman Enhanced Cygnus spacecraft. Expand
Robotic Testbed for Rendezvous and Optical Navigation: Multi-Source Calibration and Machine Learning Use Cases
TLDR
This paper addresses the data fusion approach and algorithms used to calibrate the two-robots facility to end-to-end pose accuracies of millimeters (translational) and sub-degrees (rotational). Expand
CNN-Based Pose Estimation System for Close-Proximity Operations Around Uncooperative Spacecraft
TLDR
A novel framework which combines a Convolutional Neural Network for feature detection with a Covariant Efficient Procrustes Perspective-n-Points (CEPPnP) solver and an Extended Kalman Filter to enable robust monocular pose estimation for close-proximity operations around an uncooperative spacecraft. Expand
POSE ESTIMATION FOR NON-COOPERATIVE SPACECRAFT RENDEZVOUS USING NEURAL NETWORKS
This work introduces the Spacecraft Pose Network (SPN) for on-board estimation of the pose, i.e., the relative position and attitude, of a known non-cooperative spacecraft using monocular vision. InExpand
Development of the Stanford GNSS Navigation Testbed for Distributed Space Systems
TLDR
The design, development, and verification of the Stanford GNSS navigation testbed for spacecraft formation-flying and rendezvous are presented and key aspects of the system architecture are illustrated, including the orbital dynamics simulation, the GNSS signal and measurement generation, and the algorithms/software for advanced navigation applications. Expand
A Spacecraft Dataset for Detection, Segmentation and Parts Recognition
  • D. Hoang, Bo Chen, Tat-Jun Chin
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
TLDR
The main contribution of this work is the development of the dataset using images of space stations and satellites, with rich annotations including bounding boxes of spacecrafts and masks to the level of object parts, which are obtained with a mixture of automatic processes and manual efforts. Expand
...
1
2
3
4
5
...