MSNet: multispectral semantic segmentation network for remote sensing images
Open Access
- 5 August 2022
- journal article
- research article
- Published by Taylor & Francis in GIScience & Remote Sensing
- Vol. 59 (1) , 1177-1198
Abstract
In the research of automatic interpretation of remote sensing images, semantic segmentation based on deep convolutional neural networks has been rapidly developed and applied, and the feature segmentation accuracy and network model generalization ability have been gradually improved. However, most of the network designs are mainly oriented to the three visible RGB bands of remote sensing images, aiming to be able to directly borrow the mature natural image semantic segmentation networks and pre-trained models, but simultaneously causing the waste and loss of spectral information in the invisible light bands such as near-infrared (NIR) of remote sensing images. Combining the advantages of multispectral data in distinguishing typical features such as water and vegetation, we propose a novel deep neural network structure called the multispectral semantic segmentation network (MSNet) for semantic segmentation of multi-classified feature scenes. The multispectral remote sensing image bands are split into two groups, visible and invisible, and ResNet-50 is used for feature extraction in both coding stages, and cascaded upsampling is used to recover feature map resolution in the decoding stage, and the multi-scale image features and spectral features from the upsampling process are fused layer by layer using the feature pyramid structure to finally obtain semantic segmentation results. The training and validation results on two publicly available datasets show that MSNet has competitive performance. The code is available: https://github.com/taochx/MSNet.Keywords
Funding Information
- National Key Research and Development Program of China (2021YFB3900603)
This publication has 51 references indexed in Scilit:
- Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks2016
- Deep Residual Learning for Image Recognition2016
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- SUN RGB-D: A RGB-D scene understanding benchmark suite2015
- Fully convolutional networks for semantic segmentation2015
- Maximum F1-Score Discriminative Training Criterion for Automatic Mispronunciation DetectionIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2015
- Using colour, texture, and hierarchial segmentation for high-resolution remote sensingISPRS Journal of Photogrammetry and Remote Sensing, 2008
- The relationship between Precision-Recall and ROC curves2006
- NDWI—A normalized difference water index for remote sensing of vegetation liquid water from spaceRemote Sensing of Environment, 1996