您好,欢迎访问吉林省农业科学院 机构知识库!

GCF-DeepLabv3+: An Improved Segmentation Network for Maize Straw Plot Classification

文献类型: 外文期刊

作者: Liu, Yuanyuan 1 ; Zhang, Jiaxin 1 ; Wang, Yueyong 3 ; Luo, Yang 4 ; Sui, Pengxiang 4 ; Ren, Ying 4 ; Liu, Xiaodan 4 ; Wang, Jun 3 ;

作者机构: 1.Jilin Agr Univ, Coll Informat & Technol, Changchun 130118, Peoples R China

2.Jilin Agr Univ, Smart Agr Res Inst, Changchun 130118, Peoples R China

3.Jilin Agr Univ, Coll Engn & Technol, Changchun 130118, Peoples R China

4.Jilin Acad Agr Sci, Changchun 130033, Peoples R China

关键词: conservation tillage; DeepLabv3+; remote sensing; straw coverage; semantic segmentation

期刊名称:AGRONOMY-BASEL ( 影响因子:3.4; 五年影响因子:3.8 )

ISSN:

年卷期: 2025 年 15 卷 5 期

页码:

收录情况: SCI

摘要: To meet the need of rapid identification of straw coverage types in conservation tillage fields, we investigated the use of unmanned aerial vehicle (UAV) low-altitude remote sensing images for accurate detection. UAVs were used to capture images of conservation tillage farmlands. An improved GCF-DeepLabv3+ model was utilized for detecting straw coverage types. The model incorporates StarNet as its backbone, reducing parameter count and computational complexity. Furthermore, it integrates a Multi-Kernel Convolution Feedforward Network with Fast Fourier Transform Convolutional Block Attention Module (MKC-FFN-FTCM) and a Gated Conv-Former Block (Gated-CFB) to improve the segmentation of fine plot details. Experimental results demonstrate that GCF-DeepLabv3+ outperforms other methods in segmentation accuracy, computational efficiency, and model robustness. The model achieves a parameter count of 3.19M and its FLOPs (Floating Point Operations) is 41.19G, with a mean Intersection over Union (MIoU) of 93.97%. These findings indicate that the proposed GCF-DeepLabv3+-based rapid detection method offers robust support for straw return detection.

  • 相关文献
作者其他论文 更多>>