Engineering Applications of Artificial Intelligence ( IF 7.5 ) Pub Date : 2020-09-16 , DOI: 10.1016/j.engappai.2020.103952 Abhas Maskey , Mengu Cho
A 1U CubeSat has severe limitations on size, power and downlink capabilities. Transferring images taken by imaging payload from orbit can be a challenging. To save time and effort in downlinking and post-processing, a mechanism must be in place to sort quality data before transmitting it to the ground station. This paper presents an innovative approach combining a novel CubeSat image dataset and a lightweight Convolutional Neural Network architecture for automatically selecting images for downlink on a 1U CubeSat. Coined as CubeSatNet, the neural network is trained on 60,000 augmented images, is tiny enough to run on an ARM Cortex MCU and is tested on on-orbit data from Kyushu Institute of Technology’s BIRDS-3 CubeSats with an accuracy of 90% and F1 score of 0.92. CubeSatNet outperformed SVM, DBN and AE trained to classify CubeSat images. If implemented, the CNN could cut down operation time by about 2/3 while significantly improving the quality of received data.
中文翻译:
CubeSatNet:超轻型卷积神经网络,用于在1U CubeSat上进行在轨二进制图像分类
1U CubeSat在大小,功率和下行链路功能方面有严格的限制。从轨道转移有效载荷成像所拍摄的图像可能是一个挑战。为了节省下行链路和后处理的时间和精力,必须有一种机制可以在将质量数据传输到地面站之前对其进行分类。本文提出了一种创新的方法,该方法结合了新颖的CubeSat图像数据集和轻量级的卷积神经网络体系结构,可自动为1U CubeSat上的下行链路选择图像。神经网络被称为CubeSatNet,在60,000张增强图像上进行训练,非常小,可以在ARM Cortex MCU上运行,并经过九州理工学院BIRDS-3 CubeSats的在轨数据测试,准确度达到90%,F1得分为0.92。CubeSatNet的性能优于训练有素的SVM,DBN和AE,可对CubeSat图像进行分类。