Abstract | ||
---|---|---|
The detection of dim target in star image is a challenging task because of the low SNR target and complex background. In this paper, we present a deep learning approach to detecting dim small targets in single-frame star image under uneven background and different kinds of noises. We propose a fully convolutional neural network to achieve pixel-wise classification, which can complete target-background separation in a single stage rapidly. To train this network, we also build a synthetic star image dataset covering various noises and background distribution. The precise annotations of the target regions and centroid positions provided by this dataset make the supervised learning approach possible. Experimental results show that the proposed method outperforms the state-of-the-art in terms of higher detection rate and less false alarm caused by noises. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1007/s11042-019-7412-z | Multimedia Tools and Applications |
Keywords | Field | DocType |
Dim small target detection, Low SNR, Semantic segmentation, Convolutional neural network | Computer vision,False alarm,Pattern recognition,Computer science,Convolutional neural network,Supervised learning,Artificial intelligence,Deep learning,Artificial neural network,Centroid | Journal |
Volume | Issue | ISSN |
79 | 7 | 1380-7501 |
Citations | PageRank | References |
0 | 0.34 | 5 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Danna Xue | 1 | 0 | 1.01 |
Jinqiu Sun | 2 | 9 | 4.51 |
Yaoqi Hu | 3 | 5 | 1.46 |
Yushu Zheng | 4 | 0 | 0.68 |
Yu Zhu | 5 | 88 | 12.65 |
Yanning Zhang | 6 | 1613 | 176.32 |