StarNet: Convolutional Neural Network for Dim Small Target Extraction in Star Image

Danna Xue, Yushu Zheng, Jinqiu Sun, Yu Zhu, Yaoqi Hu, Yanning Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

The number of space debris increases greatly in the last decades due to the intense outer space exploration, making a deteriorating earth orbit. The detecting, dodging and removing of space debris become a remarkable international issue. Among them, the detection of extremely dim target is still an open question. In this paper, we propose a novel dim target extraction method in single-frame star image based on convolutional neural network. The network is designed to extract the features of different spatial scales, the feature maps are up-sampled by deconvolution, and the multi-layer feature maps are fused to achieve the pixel-level classification. Experiments show that the method proposed outperforms the state-of-the-art especially on the dim target detection.

Original languageEnglish
Title of host publication2018 IEEE 4th International Conference on Multimedia Big Data, BigMM 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538653210
DOIs
StatePublished - 18 Oct 2018
Event4th IEEE International Conference on Multimedia Big Data, BigMM 2018 - Xi'an, China
Duration: 13 Sep 201816 Sep 2018

Publication series

Name2018 IEEE 4th International Conference on Multimedia Big Data, BigMM 2018

Conference

Conference4th IEEE International Conference on Multimedia Big Data, BigMM 2018
Country/TerritoryChina
CityXi'an
Period13/09/1816/09/18

Keywords

  • Convolutional neural network
  • Dim small target
  • Low SNR
  • Semantic segmentation
  • Star image

Fingerprint

Dive into the research topics of 'StarNet: Convolutional Neural Network for Dim Small Target Extraction in Star Image'. Together they form a unique fingerprint.

Cite this