English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning has become the gold standard for image processing over the pastdecade. Simultaneously, we have seen growing interest in orbital activitiessuch as satellite servicing and debris removal that depend on proximityoperations between spacecraft. However, two key challenges currently pose amajor barrier to the use of deep learning for vision-based on-orbit proximityoperations. Firstly, efficient implementation of these techniques relies on aneffective system for model development that streamlines data curation,training, and evaluation. Secondly, a scarcity of labeled training data (imagesof a target spacecraft) hinders creation of robust deep learning models. Thispaper presents an open-source deep learning pipeline, developed specificallyfor on-orbit visual navigation applications, that addresses these challenges.The core of our work consists of two custom software tools built on top of acloud architecture that interconnects all stages of the model developmentprocess. The first tool leverages Blender, an open-source 3D graphics toolset,to generate labeled synthetic training data with configurable model poses(positions and orientations), lighting conditions, backgrounds, and commonlyobserved in-space image aberrations. The second tool is a plugin-basedframework for effective dataset curation and model training; it provides commonfunctionality like metadata generation and remote storage access to allprojects while giving complete independence to project-specific code.Time-consuming, graphics-intensive processes such as synthetic image generationand model training run on cloud-based computational resources which scale toany scope and budget and allow development of even the largest datasets andmodels from any machine. The presented system has been used in the TexasSpacecraft Laboratory with marked benefits in development speed and quality.

A Pipeline for Vision-Based On-Orbit Proximity Operations Using Deep Learning and Synthetic Imagery