Data downlink prioritization using image classification on-board a 6U CubeSat
Keenan A. A. Chatar, Ezra Fielding, Kei Sano, Kentaro Kitamura
TL;DR
The paper tackles the challenge of limited downlink bandwidth for nanosatellite astronomy by proposing an onboard data management pipeline that autonomously classifies and compresses captured images. It employs a lean CNN architecture, CubeSatNet, running on a Raspberry Pi Compute Module 4 to assign priority to data, paired with GZip, RICE, or HCOMPRESS compression to maximize downlink efficiency. Using a SDSS-based star-field dataset for training and validation, the approach reports near-perfect on-board classification performance and favorable compression behavior, supporting substantial reductions in required downlink time. This work demonstrates the viability of onboard autonomous data selection and compression for CubeSats, enabling more efficient use of limited communication resources in data-intensive astronomical missions, with VERTECS slated for completion in late 2024.
Abstract
Nanosatellites are proliferating as low-cost dedicated sensing systems with lean development cycles. Kyushu Institute of Technology and collaborators have launched a joint venture for a nanosatellite mission, VERTECS. The primary mission is to elucidate the formation history of stars by observing the optical-wavelength cosmic background radiation. The VERTECS satellite will be equipped with a small-aperture telescope and a high-precision attitude control system to capture the cosmic data for analysis on the ground. However, nanosatellites are limited by their onboard memory resources and downlink speed capabilities. Additionally, due to a limited number of ground stations, the satellite mission will face issues meeting the required data budget for mission success. To alleviate this issue, we propose an on-orbit system to autonomously classify and then compress desirable image data for data downlink prioritization and optimization. The system comprises a prototype Camera Controller Board (CCB) which carries a Raspberry Pi Compute Module 4 which is used for classification and compression. The system uses a lightweight Convolutional Neural Network (CNN) model to classify and determine the desirability of captured image data. The model is designed to be lean and robust to reduce the computational and memory load on the satellite. The model is trained and tested on a novel star field dataset consisting of data captured by the Sloan Digital Sky Survey (SDSS). The dataset is meant to simulate the expected data produced by the 6U satellite. The compression step implements GZip, RICE or HCOMPRESS compression, which are standards for astronomical data. Preliminary testing on the proposed CNN model results in a classification accuracy of about 100\% on the star field dataset, with compression ratios of 3.99, 5.16 and 5.43 for GZip, RICE and HCOMPRESS that were achieved on tested FITS image data.