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

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 spac...

Full description

Saved in:
Bibliographic Details
Published in:Sensors (Basel, Switzerland) Vol. 22; no. 11; p. 4222
Main Authors: Liu, Yuan, Zhu, Ming, Wang, Jing, Guo, Xiangji, Yang, Yifan, Wang, Jiarong
Format: Journal Article
Language:English
Published: Switzerland MDPI AG 01.06.2022
MDPI
Subjects:
Algorithms
Annotations
Datasets
Deep learning
DeepLabv3
dilated convolution
Discovery and exploration
Image processing
Machine learning
Methods
multi-scale
Neural networks
Outer space
Remote sensing
Satellites
semantic segmentation
Semantics
Space exploration
Space ships
Space vehicles
China
deep learning
DeepLabv3
semantic segmentation
dilated convolution
multi-scale
ISSN:1424-8220, 1424-8220
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s22114222