A Spacecraft Dataset for Detection, Segmentation and Parts Recognition

Dung, Hoang Anh; Chen, Bin; Chin, Tat-Jun

doi:10.1109/cvprw53098.2021.00229

Cited by 31 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To resolve this, synthetic datasets are formulated. Dung et al [22] introduced an annotated spacecraft dataset made of real and synthetic images for detection, segmentation, and recognition tasks. Perez et al [20] used images of experimental setups of space objects for machine learning.…”

Section: Related Workmentioning

confidence: 99%

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

et al. 2023

View full text Add to dashboard Cite

Space situational awareness (SSA) system requires recognition of space objects that are varied in sizes, shapes, and types. The space images are challenging because of several factors such as illumination and noise and thus make the recognition task complex. Image fusion is an important area in image processing for various applications including RGB-D sensor fusion, remote sensing, medical diagnostics, and infrared and visible image fusion. Recently, various image fusion algorithms have been developed and they showed a superior performance to explore more information that are not available in single images. In this paper, we compared various methods of RGB and Depth image fusion for space object classification task. The experiments were carried out, and the performance was evaluated using 13 fusion performance metrics. It was found that the guided filter context enhancement (GFCE) outperformed other image fusion methods in terms of average gradient (8.2593), spatial frequency (28.4114), and entropy (6.9486). additionally, due to its ability to balance between good performance and inference speed (11.41 second), GFCE was selected for RGB and Depth image fusion stage before feature extraction and classification stage. The outcome of fusion method is fused images that were used to train a deep ensemble of CoAtNets to classify space objects into ten categories. The deep ensemble learning methods including bagging, boosting, and stacking were trained and evaluated for classification purposes. It was found that combination of fusion and stacking was able to improve classification accuracy largely compared to the baseline methods by producing an average accuracy of 89 % and average F1 score of 89 %.

show abstract

Section: Related Workmentioning

confidence: 99%

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

et al. 2023

View full text Add to dashboard Cite

show abstract

“…al. [40]. Advanced neural computer vision methods have been proposed in two related but different problems.…”

Section: Multi-stage and Single-stage Object Detection Algorithmsmentioning

confidence: 99%

Performance Study of YOLOv5 and Faster R-CNN for Autonomous Navigation around Non-Cooperative Targets

Mahendrakar

Ekblad

Fischer

et al. 2022

2022 IEEE Aerospace Conference (AERO)

View full text Add to dashboard Cite

Autonomous navigation and path-planning around non-cooperative space objects is an enabling technology for onorbit servicing and space debris removal systems. The navigation task includes the determination of target object motion, the identification of target object features suitable for grasping, and the identification of collision hazards and other keep-out zones. Given this knowledge, chaser spacecraft can be guided towards capture locations without damaging the target object or without unduly the operations of a servicing target by covering up solar arrays or communication antennas. One way to autonomously achieve target identification, characterization and feature recognition is by use of artificial intelligence algorithms. This paper discusses how the combination of cameras and machine learning algorithms can achieve the relative navigation task. The performance of two deep learningbased object detection algorithms, Faster Region-based Convolutional Neural Networks (R-CNN) and You Only Look Once (YOLOv5), is tested using experimental data obtained in formation flight simulations in the ORION Lab at Florida Institute of Technology. The simulation scenarios vary the yaw motion of the target object, the chaser approach trajectory, and the lighting conditions in order to test the algorithms in a wide range of realistic and performance limiting situations. The data analyzed include the mean average precision metrics in order to compare the performance of the object detectors. The paper discusses the path to implementing the feature recognition algorithms and towards integrating them into the spacecraft Guidance Navigation and Control system.TABLE OF CONTENTS 1. INTRODUCTION .

show abstract

“…For example, URSO [35] consists of synthetic and spaceborne images of Soyuz and Dragon spacecraft rendered on Unreal Engine 4, but the labels for spaceborne images are missing. Dung et al [15] introduced a dataset comprising about 3,000 synthetic and spaceborne images of random satellites with bounding box and segmentation labels. Other authors have also developed their own datasets, such as synthetic images of the Envisat spacecraft rendered with Blender [9,31] and Cygnus spacecraft rendered with Blender and its Cycles rendering engine [8].…”

Section: Related Workmentioning

confidence: 99%

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

Park,

Märtens,

Lecuyer

et al. 2021

Preprint

View full text Add to dashboard Cite

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 relied on synthetic images for both training and validation, which are easy to mass-produce but fail to resemble the visual features and illumination variability inherent to the target spaceborne images. In order to bridge the gap between the current practices and the intended applications in future space missions, this paper introduces SPEED+: the next generation spacecraft pose estimation dataset with specific emphasis on domain gap. In addition to 60,000 synthetic images for training, SPEED+ includes 9,531 simulated images of a spacecraft mockup model captured from the Testbed for Rendezvous and Optical Navigation (TRON) facility. TRON is a first-of-a-kind robotic testbed capable of capturing an arbitrary number of target images with accurate and maximally diverse pose labels and high-fidelity spaceborne illumination conditions. SPEED+ will be used in the upcoming international Satellite Pose Estimation Challenge co-hosted with the Advanced Concepts Team of the European Space Agency to evaluate and compare the robustness of spaceborne ML models trained on synthetic images.Preprint. Under review.

show abstract

A Spacecraft Dataset for Detection, Segmentation and Parts Recognition

Cited by 31 publications

References 33 publications

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

Performance Study of YOLOv5 and Faster R-CNN for Autonomous Navigation around Non-Cooperative Targets

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

Contact Info

Product

Resources

About