Vision-based attitude estimation for spacecraft docking operation through deep learning algorithm

Phisannupawong, Thaweerath; Kamsing, Patcharin; Tortceka, Peerapong; Yooyen, Soemsak

doi:10.23919/icact48636.2020.9061445

Cited by 8 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In conventional Deep Neural Networks (DNNs) [14] or Convolutional Neural Networks (CNNs) [15], the input and output are relatively independent, i.e., the network output is dependent only on the parameters at the time of training. In comparison, the output of the reusable prediction network proposed in this paper consists of the current moment's input and the previous moment's output, and the network generates new "input" as data ows through it.…”

Section: B Reusable Predictive Networkmentioning

confidence: 99%

Reusable prediction network for target 6D attitude real-time estimation

Dounan

jin

Wang

2022

Preprint

View full text Add to dashboard Cite

This paper proposes a rigid body 6D attitude estimation method based on a reusable prediction network. Method: First, two independent feature encoders extract the feature information matrix from taking the RGB-D image at the current time and the target rendering model at a previous time. Second, The above two characteristic information matrices are fused and introduced into the multiplexing prediction network, and the prediction rotation matrix is obtained by decoupling the feature information fusion matrix. Finally, by decoupling the fused matrix, the rotation and translation matrices are obtained. Additionally, a channel weight allocation module in conjunction with a residual network is added to improve the accuracy of real-time attitude estimation. Conclusions: Training the reusable prediction network with the YCBInEOAT dataset, the network can converge faster. In addition, the mean distance values and symmetric mean distance values in the evaluation metrics are greater than those obtained using the se(3)-TrackNet method, with a 7.29% increase in mean distance values and a 13.78% increase in symmetric mean distance values.

show abstract

Section: B Reusable Predictive Networkmentioning

confidence: 99%

Reusable prediction network for target 6D attitude real-time estimation

Dounan

jin

Wang

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The information from the images passes through the layers of neurons until the poses is determined at the final layer (Figure 4). For the application of spacecraft pose estimation, the trained CNN model contains the direct empirical correlation of the images and estimated poses [26]. In this study, the pretrained convolutional neural model GoogLeNet was employed as the base architecture for pose estimation.…”

Section: Pose Estimation Algorithm and Preprocessingmentioning

confidence: 99%

Vision-Based Spacecraft Pose Estimation via a Deep Convolutional Neural Network for Noncooperative Docking Operations

et al. 2020

Self Cite

View full text Add to dashboard Cite

The capture of a target spacecraft by a chaser is an on-orbit docking operation that requires an accurate, reliable, and robust object recognition algorithm. Vision-based guided spacecraft relative motion during close-proximity maneuvers has been consecutively applied using dynamic modeling as a spacecraft on-orbit service system. This research constructs a vision-based pose estimation model that performs image processing via a deep convolutional neural network. The pose estimation model was constructed by repurposing a modified pretrained GoogLeNet model with the available Unreal Engine 4 rendered dataset of the Soyuz spacecraft. In the implementation, the convolutional neural network learns from the data samples to create correlations between the images and the spacecraft’s six degrees-of-freedom parameters. The experiment has compared an exponential-based loss function and a weighted Euclidean-based loss function. Using the weighted Euclidean-based loss function, the implemented pose estimation model achieved moderately high performance with a position accuracy of 92.53 percent and an error of 1.2 m. The in-attitude prediction accuracy can reach 87.93 percent, and the errors in the three Euler angles do not exceed 7.6 degrees. This research can contribute to spacecraft detection and tracking problems. Although the finished vision-based model is specific to the environment of synthetic dataset, the model could be trained further to address actual docking operations in the future.

show abstract

“…One important technology in many space applications is the accurate localisation of space objects via visual sensor, such as object detection and segmentation in images, because localisation is a key step towards vision-based pose estimation which is critical for tasks like docking [7], servicing [8], or debris removal [9]. However, a severe challenge for space-based object detection and instance segmentation is the lack of accessible large datasets that have been well annotated.…”

Section: Introductionmentioning

confidence: 99%

A Spacecraft Dataset for Detection, Segmentation and Parts Recognition

Dung

Chen

Chin

2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Virtually all aspects of modern life depend on space technology. Thanks to the great advancement of computer vision in general and deep learning-based techniques in particular, over the decades, the world witnessed the growing use of deep learning in solving problems for space applications, such as selfdriving robot, tracers, insect-like robot on cosmos and health monitoring of spacecraft. These are just some prominent examples that has advanced space industry with the help of deep learning. However, the success of deep learning models requires a lot of training data in order to have decent performance, while on the other hand, there are very limited amount of publicly available space datasets for the training of deep learning models. Currently, there is no public datasets for space-based object detection or instance segmentation, partly because manually annotating object segmentation masks is very time consuming as they require pixel-level labelling, not to mention the challenge of obtaining images from space. In this paper, we aim to fill this gap by releasing a dataset for spacecraft detection, instance segmentation and part recognition. 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. We also provide evaluations with state-of-the-art methods in object detection and instance segmentation as a benchmark for the dataset. The link for downloading the proposed dataset can be found on https://github.com/Yurushia1998/SatelliteDataset.

show abstract

Vision-based attitude estimation for spacecraft docking operation through deep learning algorithm

Cited by 8 publications

References 8 publications

Reusable prediction network for target 6D attitude real-time estimation

Reusable prediction network for target 6D attitude real-time estimation

Vision-Based Spacecraft Pose Estimation via a Deep Convolutional Neural Network for Noncooperative Docking Operations

A Spacecraft Dataset for Detection, Segmentation and Parts Recognition

Contact Info

Product

Resources

About