Multi-Scale Deep Neural Network Based on Dilated Convolution for Spacecraft Image Segmentation

doi:10.3390/s22114222

CIOMP OpenIR

	Multi-Scale Deep Neural Network Based on Dilated Convolution for Spacecraft Image Segmentation
	Y. Liu; M. Zhu; J. Wang; X. J. Guo; Y. F. Yang and J. R. Wang
	2022
发表期刊	Sensors
卷号	22 期号:11 页码:22
摘要	In recent years, image segmentation techniques based on deep learning have achieved many applications in remote sensing, medical, and autonomous driving fields. In space exploration, the segmentation of spacecraft objects by monocular images can support space station on-orbit assembly tasks and space target position and attitude estimation tasks, which has essential research value and broad application prospects. However, there is no segmentation network designed for spacecraft targets. This paper proposes an end-to-end spacecraft image segmentation network using the semantic segmentation network DeepLabv3+ as the basic framework. We develop a multi-scale neural network based on sparse convolution. First, the feature extraction capability is improved by the dilated convolutional network. Second, we introduce the channel attention mechanism into the network to recalibrate the feature responses. Finally, we design a parallel atrous spatial pyramid pooling (ASPP) structure that enhances the contextual information of the network. To verify the effectiveness of the method, we built a spacecraft segmentation dataset on which we conduct experiments on the segmentation algorithm. The experimental results show that the encoder+ attention+ decoder structure proposed in this paper, which focuses on high-level and low-level features, can obtain clear and complete masks of spacecraft targets with high segmentation accuracy. Compared with DeepLabv3+, our method is a significant improvement. We also conduct an ablation study to research the effectiveness of our network framework.
DOI	10.3390/s22114222
URL	查看原文
收录类别	sci ; ei
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/66882
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	Y. Liu,M. Zhu,J. Wang,et al. Multi-Scale Deep Neural Network Based on Dilated Convolution for Spacecraft Image Segmentation[J]. Sensors,2022,22(11):22.
APA	Y. Liu,M. Zhu,J. Wang,X. J. Guo,&Y. F. Yang and J. R. Wang.(2022).Multi-Scale Deep Neural Network Based on Dilated Convolution for Spacecraft Image Segmentation.Sensors,22(11),22.
MLA	Y. Liu,et al."Multi-Scale Deep Neural Network Based on Dilated Convolution for Spacecraft Image Segmentation".Sensors 22.11(2022):22.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Multi-Scale Deep Neu（7177KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载