数字农科院2.0

Detection of Fusarium Head Blight in Individual Wheat Spikes Using Monocular Depth Estimation with Depth Anything V2

文献类型： 外文期刊

作者： Jiacheng Wang;Jianliang Wang;Yuanyuan Zhao;Fei Wu;Wei Wu;Zhen Li;Chengming Sun;Tao Li;Tao Liu

作者机构：

关键词： depth estimation;feature fusion;fusarium head blight;monocular image;wheat

期刊名称： Agronomy

ISSN： 2073-4395

年卷期： 2025 年 15 卷 11 期

页码：

收录情况： SCIE（2025版）

摘要： Fusarium head blight (FHB) poses a significant threat to global wheat yields and food security, underscoring the importance of timely detection and severity assessment. Although existing approaches based on semantic segmentation and stereo vision have shown promise, their scalability is constrained by limited training datasets and the high maintenance cost and complexity of visual sensor systems. In this study, AR glasses were employed for image acquisition, and wheat spike segmentation was performed using Depth Anything V2, a monocular depth estimation model. Through geometric localization methods—such as identifying abrupt changes in stem width—redundant elements (e.g., awns and stems) were effectively excluded, yielding high-precision spike masks (Precision: 0.945; IoU: 0.878) that outperformed leading semantic segmentation models including Mask R-CNN and DeepLabv3+. The study further conducted a comprehensive analysis of differences between diseased and healthy spikelets across RGB, HSV, and Lab color spaces, as well as three color indices: Excess Green–Excess Red (ExGR), Normalized Difference Index (NDI), and Visible Atmospherically Resistant Index (VARI). A dynamic fusion weighting strategy was developed by combining the Lab-a* component with the ExGR index, thereby enhancing visual contrast between symptomatic and asymptomatic regions. This fused index enabled quantitative assessment of FHB severity, achieving an R2 of 0.815 and an RMSE of 8.91%, indicating strong predictive accuracy. The proposed framework offers an intelligent, cost-effective solution for FHB detection, and its core methodologies—depth-guided segmentation, geometric refinement, and multi-feature fusion—present a transferable model for similar tasks in other crop segmentation applications.

分类号：

  • 相关文献

[1]充分发掘保护利用生物多样性;促进农业可持续发展——《生物多样性与小麦改良》简评. 李祥洲. 1997

[2]Overexpression of wheat lipid transfer protein gene TaLTP5 increases resistances to Cochliobolus sativus and Fusarium graminearum in transgenic wheat. Li, Zhao,Xu, Huijun,Du, Lipu,Zhang, Zengyan,Zhou, Miaoping.

[3]Fungal endophyte Epicoccum nigrum 38L1 inhibits in vitro and in vivo the pathogenic fungus Fusarium graminearum. Clement Nzabanita,Lihang Zhang,Hairong Zhao,Yanfei Wang,Yafei Wang,Manhong Sun,Shuangchao Wang,Lihua Guo. 2022

[4]The Wheat Endophyte Epicoccum layuense J4-3 Inhibits Fusarium graminearum and Enhances Plant Growth. Nzabanita C.,Zhang L.,Wang Y.,Wang S.,Guo L.. 2024

[5]Influence of Wheat Cultivars, Infection Level, and Climate after Anthesis on Efficacy of Fungicide for Control of Fusarium Head Blight in the Huang-Huai-Hai Plain of China. Fei Xu,Hongqi Wang,Chaohong Feng,Ruijie Shi,Jihong Liu,Junmei Wang,Hua Fan,Lei Bai,Xiaoqing Li,Xiaoli Hu,Lijuan Li,Lulu Liu,Yahong Li,Zihang Han,Wei Liu,Yuli Song,Yilin Zhou. 2024

[6]Fusarium commune: A novel fungal endophyte against fungal pathogen Fusarium graminearum. Tao Wan,Clement Nzabanita,Xueyuan Sheng,Chengke Yuan,Shuangchao Wang,Lihua Guo. 2025

[7]3D Indoor Scene Geometry Estimation from a Single Omnidirectional Image: A Comprehensive Survey. Meng, Ming,Zhu, Yonggui,Zhao, Yufei,Li, Zhaoxin,Zhu, Zhe. 2025

[8]30个小麦新品系抗条锈病基因分析及成株期抗病性评价. 冯晶,蔺瑞明,林凤,徐世昌. 2013

[9]小麦抗菌蛋白编码基因BS108的克隆及其转基因抗病小麦的创制. 李钊,周淼平,张增艳,庄洪涛,徐惠君,杜丽璞,叶兴国. 2010

[10]渗透调节物质及有机附加物对小麦体细胞胚发生影响的研究(英文). 孙朝霞,侯思宇,王玉国. 2008

[11]普通小麦品种辐射敏感性模糊聚类分析<英文>. 冯志杰,王琳清. 1992

[12]基因枪转化小麦主要轰击参数的优化. 闵东红,何莎,张彦,夏兰琴. 2013

[13]小麦矮缩病毒分子群体遗传结构研究. 刘艳,王锡锋,周广和. 2008

[14]Noise-tolerant RGB-D feature fusion network for outdoor fruit detection. Qixin Sun,Xiujuan Chai,Zhikang Zeng,Guomin Zhou,Tan Sun. 2022

[15]Intelligent identification on cotton verticillium wilt based on spectral and image feature fusion. Zhihao Lu,Shihao Huang,Xiaojun Zhang,Yuxuan shi,Wanneng Yang,Longfu Zhu,Chenglong Huang. 2023

[16]Exploring Multisource Feature Fusion and Stacking Ensemble Learning for Accurate Estimation of Maize Chlorophyll Content Using Unmanned Aerial Vehicle Remote Sensing. Weiguang Zhai,Changchun Li,Qian Cheng,Fan Ding,Zhen Chen. 2023

[17]Multimodal fusion-based detection method of estrus cows using multisource data inspired by hidden Markov model algorithms. Jun Wang,Yijia Zhao,Xiaoxia Li,Yu Zhou,Kaixuan Zhao,Hui Wang,Waleid Mohamed EL-Sayed Shakweer. 2025

[18]Field Rice Growth Monitoring and Fertilization Management Based on UAV Spectral and Deep Image Feature Fusion. Chen, Bingnan,Su, Qihe,Li, Yansong,Chen, Rui,Yang, Wanneng,Huang, Chenglong. 2025

[19]An Improved Model for Online Detection of Early Lameness in Dairy Cows Using Wearable Sensors: Towards Enhanced Efficiency and Practical Implementation. Xiaofei Dai,Guodong Cheng,Lu Yang,Yali Wang,Zhongkun Li,Shuqing Han,Jifang Liu. 2025

[20]The Bayesian mixture expert recognition model for tobacco leaf curing stages based on feature fusion. Panzhen Zhao,Shijiang Duan,Songfeng Wang,Aihua Wang,Lingfeng Meng,Zhicheng Wang,Yingpeng Dai. 2025

作者其他论文 更多>>