Investigating the risks of debris-generating ASAT tests in the presence of megaconstellations

Thiele, Sarah; Boley, Aaron C.

doi:10.48550/arxiv.2111.12196

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for larger-sized debris, most of them are formed by explosions, including rocket upper stages, auxiliary engines, and satellites. Kinetic anti-satellite (ASAT) weapon tests also generate significant amounts of space debris, and even form a dangerous debris field, increasing the risk of collision with satellites [2,3]. By 2019, more than 139 million pieces of space debris had been detected [4].…”

Section: Introduction 1backgroundmentioning

confidence: 99%

Co-Correcting: Combat Noisy Labels in Space Debris Detection

Niu

Sun

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Space debris detection is vital to space missions and space situation awareness. Convolutional neural networks are introduced to detect space debris due to their excellent performance. However, noisy labels, caused by false alarms, exist in space debris detection, and cause ambiguous targets for the training of networks, leading to networks overfitting the noisy labels and losing the ability to detect space debris. To remedy this challenge, we introduce label-noise learning to space debris detection and propose a novel label-noise learning paradigm, termed Co-correcting, to overcome the effects of noisy labels. Co-correcting comprises two identical networks, and the predictions of these networks serve as auxiliary supervised information to mutually correct the noisy labels of their peer networks. In this manner, the effect of noisy labels can be mitigated by the mutual rectification of the two networks. Empirical experiments show that Co-correcting outperforms other state-of-the-art methods of label-noise learning, such as Co-teaching and JoCoR, in space debris detection. Even with a high label noise rate, the network trained via Co-correcting can detect space debris with high detection probability.

show abstract

Section: Introduction 1backgroundmentioning

confidence: 99%