Infrared and Laser Engineering, Volume. 51, Issue 9, 20210868(2022)
Research on the classification of typical crops in remote sensing images by improved U-Net algorithm
Figures & Tables(7)
Fig. 5. Comparison of the experimental results of proposed method and other algorithms
Table 1. Characteristics of network model for different deep learning
View tableView in ArticleTable 1. Characteristics of network model for different deep learning
Deep learning segmentation model Model characteristics FCN For the first time, a fully convolutional network based on the end-to-end concept is proposed, which removes the fully connected layer and samples in the deconvolutional layer SegNet The pooling layer result is used in the decoding and a large amount of coding information is introduced U-Net Based on the end-to-end standard network structure, the decoder is obtained by splicing the results of each layer on the encoder, and the result is more ideal Improve U-Net The ability of semantic recognition is enhanced, and it is more sensitive to feature extraction
Table 2. Experimental results of crop recognition with different methods
View tableView in ArticleTable 2. Experimental results of crop recognition with different methods
Experimental network U-Net SegNet FCN Improve U-Net OA MIoU OA MIoU OA MIoU OA MIoU Precision 85.41% 0.39 84.86% 0.39 86.44% 0.45 88.33% 0.52
Tools
Get Citation
Copy Citation Text
Anqi Li, Li Ma, Helong Yu, Hanbo Zhang. Research on the classification of typical crops in remote sensing images by improved U-Net algorithm[J]. Infrared and Laser Engineering, 2022, 51(9): 20210868
Paper Information
Category: Image processing
Received: Nov. 22, 2021
Accepted: Dec. 16, 2021
Published Online: Jan. 6, 2023
The Author Email: Li Ma (candys_ash@126.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20