摘要
A small target detection method based on deep learning is proposed. First, random background parts are sampled from some cloud-sky images. Then, random generated target spots are added to the backgrounds with controlled signal to background noise ratio (SNR) to generate target samples. Then training and testing results show that the performance of deep nets is superior to tradition small target detection techniques and the selection of sampling SNRhas an important effect on nets training performances. SNR = 1 is a good selection for deep nets training, not onlyfor small target detection,but also for other applications.
| 源语言 | 英语 |
|---|---|
| 主期刊名 | Current Trends in Computer Science and Mechanical Automation Vol.1 |
| 主期刊副标题 | Selected Papers from CSMA2016 |
| 出版商 | de Gruyter |
| 页 | 211-220 |
| 页数 | 10 |
| ISBN（电子版） | 9783110584974 |
| ISBN（印刷版） | 9783110584967 |
| 出版状态 | 已出版 - 9 1月 2018 |
指纹
探究 'Image small target detection based on deep learning with SNR controlled sample generation' 的科研主题。它们共同构成独一无二的指纹。引用此
Liu, M., Du, H. Y., Zhao, Y. J., Dong, L. Q., & Hui, M. (2018). Image small target detection based on deep learning with SNR controlled sample generation. 在 Current Trends in Computer Science and Mechanical Automation Vol.1: Selected Papers from CSMA2016 (页码 211-220). de Gruyter.