DM_CorrMatch: a semi-supervised semantic segmentation framework for rapeseed flower coverage estimation using UAV imagery
文献类型: 外文期刊
作者: Li, Jie;Zhu, Chengyong;Yang, Chenbo;Zheng, Quan;Wang, Binhui;Tu, Jingmin;Zhang, Qian;Liu, Sheng;Wang, Xinfa;Qiao, Jiangwei
作者机构:
关键词: Semi-supervised semantic segmentation;Rapeseed;Diffusion model;Vision mamba
期刊名称: PLANT METHODS
ISSN:
年卷期: 2025 年 21 卷 1 期
页码:
收录情况: SCIE(2025版)
摘要: Rapeseed (Brassica napus L.) inflorescence coverage is a crucial phenotypic parameter for assessing crop growth and estimating yield. Accurate crop cover assessment is typically performed using Unmanned Aerial Vehicles (UAVs) in combination with semantic segmentation methods. However, the irregular and variable morphology of rapeseed inflorescences presents significant challenges in segmentation. To address these challenges, advanced methods that can improve segmentation accuracy, particularly under limited data conditions, are needed. In this study, we propose a cost-effective and high-throughput approach using a semi-supervised learning framework, DM_CorrMatch. This method enhances input images through strong and weak data augmentation techniques, while leveraging the Denoising Diffusion Probabilistic Model (DDPM) to generate additional samples in data-scarce scenarios. We propose an automatic update strategy for labeled data to dilute the proportion of erroneous labels in manual segmentation. Furthermore, a novel network architecture, Mamba-Deeplabv3+, is proposed, combining the strengths of Mamba and Convolutional Neural Networks (CNNs) for both global and local feature extraction. This architecture effectively captures key inflorescence features, even under varying poses, while reducing the influence of complex backgrounds. The proposed method is validated on the Rapeseed Flower Segmentation Dataset (RFSD), which consists of 720 UAV images from the Yangluo experimental station of the Oil Crops Research Institute of the Chinese Academy of Agricultural Sciences (CAAS). The experimental results showed that our method outperforms four traditional segmentation methods and eleven deep learning methods, achieving an Intersection over Union (IoU) of 0.886, Precision of 0.942, and Recall of 0.940. The proposed semi-supervised learning-based method, combined with the Mamba-Deeplabv3+ architecture, demonstrates superior performance in accurately segmenting rapeseed inflorescences under challenging conditions. Our approach effectively handles complex backgrounds and various poses of inflorescences, providing a reliable tool for rapeseed flower cover estimation. This method can aid in the development of high-yield cultivars and improve crop monitoring through UAV-based technologies.
分类号:
- 相关文献
作者其他论文 更多>>
-
Transcriptome-Metabolome Integration Uncovers Salt Stress Effects on Flavonoid Biosynthesis in Two Self-Selected Breeding Alfalfa Varieties
作者:Zhu, Xinqiang;Yang, Yang;Fu, Yunxing;Leng, Feifan;Li, Shaowei;Wang, Yonggang;Cao, Zhonghua;Wang, Xiaoli;Yang, Hongshan;Wu, Fang;Zhang, Qian;Duan, Huirong
关键词:alfalfa;differential genes;differential metabolites;flavonoids biosynthesis;salt stress
-
Plant species loss reduces rare soil microbes through diversity effects amplified by multitrophic interactions
作者:Li, Jie;Wei, Yanan;Lv, Ruixue;Liu, Weixing;Niu, Kechang
关键词:above-ground-below-ground interactions;distinctive functionality;functional diversity;plant species loss;rarity;soil microbial diversity;species removal
-
Green pretreatment of Xanthoceras sorbifolia Bunge husks via hydrogen peroxide presoftening, liquid hot water pretreatment and enzymatic hydrolysis for the co-production of functional xylo-oligosaccharides and glucose
作者:Ma, Kedong;Li, Guo;Cui, Yubo;Li, Jie;He, Mingxiong;Ruan, Zhiyong
关键词:Lignocellulosic biomass;Xylo-oligosaccharides;Hydrogen peroxide;Liquid hot water pretreatment;Enzymatic hydrolysis
-
Beyond species and spatial boundaries: Enabling long-distance gene silencing in plants via guanidinium-siRNA nanoparticles
作者:Lin, Shujin;Zhang, Qian;Bai, Shiyan;Yang, Liwen;Qin, Guannan;Wang, Liyuan;Wang, Wenbin;Cheng, Cui;Zhang, Da;Lu, Chunhua;Yuan, Jifeng;Li, Jingying;Yang, Huanghao;Gu, Xiaofeng;Han, Xiao
关键词:RNA interference;nanoparticle;systematically deliver;thiolated;long-distance movement
-
Available Nitrogen as the Determinant of Variability in Soil Microbial Communities Throughout Lycium chinense Growth Zones in the Qaidam Basin, Qinghai, China
作者:Su, Qianqian;Li, Jie;Wang, Jingui;Li, Gang;Sun, Yang;Liu, Xiaoqin;Luo, Lan;Wang, Xinrui;Zhang, Guilong
关键词:Lycium chinense cultivated region;soil fertility;soil microbial communities;keystone taxa
-
Spatiotemporal Transcriptomic Profiling Reveals the Dynamic Immunological Landscape of Alveolar Echinococcosis
作者:Ou, Zhihua;Li, Li;Ren, Peidi;Zhou, Ting-Ting;He, Fan;Chen, Jialing;Cai, Huimin;Han, Xiumin;Wu, Yao-Dong;Li, Jiandong;Li, Xiu-Rong;Tan, Qiming;Li, Wenhui;Chen, Qi;Zhang, Nian-Zhang;He, Xiuju;Chen, Wei-Gang;Zhao, Yanping;Sun, Jiwen;Zhang, Qian;Wu, Yan-Tao;Liang, Yingan;You, Jie;Hu, Guohai;Tian, Xue-Qi;Liao, Sha;Fu, Bao-Quan;Chen, Ao;Cai, Xue-Peng;Yang, Huanming;Wang, Jian;Jin, Xin;Xu, Xun;Jia, Wan-Zhong;Li, Junhua;Yan, Hong-Bin
关键词:Echinococcus multilocularis;macrophages;neutrophils;single-cell RNA sequencing;spatial transcriptomics
-
A chaperonin BnaC01.CCT8 contributes to silique length and seed weight by affecting auxin and jasmonic acid signalling in Brassica napus
作者:Qu, Zhaoyang;Tian, Ze;Wei, Liqing;Wang, Chao;Kuang, Lieqiong;Yan, Jiaqi;Wang, Furong;Wang, Nian;Tu, Jinxing;Wang, Xinfa;Wang, Hanzhong;Dun, Xiaoling
关键词:silique length;seed weight;auxin;jasmonic acid;BnaC01.CCT8;CCT complex