Satellite Pose Estimation Challenge: Dataset, Competition Design, and Results

Kisantal, Máté; Sharma, Sumant; Park, Tae Ha; Izzo, Dario; Märtens, Marcus; D’Amico, Simone

doi:10.1109/taes.2020.2989063

Cited by 157 publications

(103 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Speed is currently the first open source space target pose estimation dataset [55]. To date, only the training set is open source, and the test set is not yet open source.…”

Section: Datasets and Comparison With Mainstream Methodsmentioning

confidence: 99%

An Improved Deep Keypoint Detection Network for Space Targets Pose Estimation

Song

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

The on-board pose estimation of uncooperative target is an essential ability for close-proximity formation flying missions, on-orbit servicing, active debris removal and space exploration. However, the main issues of this research are: first, traditional pose determination algorithms result in a semantic gap and poor generalization abilities. Second, specific pose information cannot be accurately known in a complicated space target imaging environment. Deep learning methods can effectively solve these problems; thus, we propose a pose estimation algorithm that is based on deep learning. We use keypoints detection method to estimate the pose of space targets. For complicated space target imaging environment, we combined the high-resolution network with dilated convolution and online hard keypoint mining strategy. The improved network pays more attention to the obscured keypoints, has a larger receptive field, and improves the detection accuracy. Extensive experiments have been conducted and the results demonstrate that the proposed algorithms can effectively reduce the error rate of pose estimation and, compared with the related pose estimation methods, our proposed model has a higher detection accuracy and a lower pose determination error rate in the speed dataset.

show abstract

“…Speed is currently the first open source space target pose estimation dataset [55]. To date, only the training set is open source, and the test set is not yet open source.…”

Section: Datasets and Comparison With Mainstream Methodsmentioning

confidence: 99%

An Improved Deep Keypoint Detection Network for Space Targets Pose Estimation

Song

Yang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Forecasting competitions are widely recognized as an effective means of determining good predictive models and solutions for a particular problem [18]. The successful designing of such competitions requires a good balance to be determined between the desire to create an interesting and fair ML challenge, motivating and involving a large community of data scientists worldwide, and fulfills the objective of furthering the current understanding by answering a meaningful scientific question [19].…”

Section: Competition Designmentioning

confidence: 99%

Spacecraft collision avoidance challenge: Design and results of a machine learning competition

Uriot

Izzo

Simões³

et al. 2021

Astrodyn

Self Cite

View full text Add to dashboard Cite

Spacecraft collision avoidance procedures have become an essential part of satellite operations. Complex and constantly updated estimates of the collision risk between orbiting objects inform various operators who can then plan risk mitigation measures. Such measures can be aided by the development of suitable machine learning (ML) models that predict, for example, the evolution of the collision risk over time. In October 2019, in an attempt to study this opportunity, the European Space Agency released a large curated dataset containing information about close approach events in the form of conjunction data messages (CDMs), which was collected from 2015 to 2019. This dataset was used in the Spacecraft Collision Avoidance Challenge, which was an ML competition where participants had to build models to predict the final collision risk between orbiting objects. This paper describes the design and results of the competition and discusses the challenges and lessons learned when applying ML methods to this problem domain.

show abstract

“…In the space domain, given the difficulty of obtaining large real datasets, synthetic datasets are currently the default approach for developing DL methods for Space Sitiuational Awareness (SSA) and ADR tasks. To the best of our knowledge, existing datasets [23,12], and more recently [10], do not provide temporal data as they were designed specifically for single image spacecraft pose estimation [6].…”

Section: Data Generationmentioning

confidence: 99%

Leveraging Temporal Information for 3D Trajectory Estimation of Space Objects

Musallam

Castillo

Ismaeil

et al. 2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

This work presents a new temporally consistent space object 3D trajectory estimation from a video taken by a single RGB camera. Understanding space objects' trajectories is an important component of Space Situational Awareness, especially for applications such as Active Debris Removal, On-orbit Servicing, and Orbital Maneuvers. Using only the information from a single image perspective gives temporally inconsistent 3D position estimation. Our approach operates in two subsequent stages. The first stage estimates the 2D location of the space object using a convolution neural network. In the next stage, the 2D locations are lifted to 3D space, using temporal convolution neural network that enforces the temporal coherence over the estimated 3D locations. Our results show that leveraging temporal information yields smooth and accurate 3D trajectory estimations for space objects. A dedicated large realistic synthetic dataset, named SPARK-T, containing 3 spacecrafts, under various sensing conditions, is also proposed and will be publicly shared with the research community.

show abstract

Satellite Pose Estimation Challenge: Dataset, Competition Design, and Results

Cited by 157 publications

References 45 publications

An Improved Deep Keypoint Detection Network for Space Targets Pose Estimation

An Improved Deep Keypoint Detection Network for Space Targets Pose Estimation

Spacecraft collision avoidance challenge: Design and results of a machine learning competition

Leveraging Temporal Information for 3D Trajectory Estimation of Space Objects

Contact Info

Product

Resources

About