3D-based precise evaluation pipeline for maize ear rot using multi-view stereo reconstruction and point cloud semantic segmentation
文献类型： 外文期刊
作者： Yang, Rui 1 ; He, Yong 1 ; Lu, Xiangyu 1 ; Zhao, Yiying 2 ; Li, Yanmei 3 ; Yang, Yinhui 4 ; Kong, Wenwen 4 ; Liu, Fei 1 ;
作者机构： 1.Zhejiang Univ, Coll Biosyst Engn & Food Sci, Hangzhou 310058, Peoples R China
2.Zhejiang Acad Agr Sci, Inst Digital Agr, Hangzhou 310021, Peoples R China
3.China Agr Univ, Natl Maize Improvement Ctr China, Beijing 100193, Peoples R China
4.Zhejiang A&F Univ, Coll Math & Comp Sci, Hangzhou 311300, Peoples R China
关键词： Maize ear rot; Multi-view stereo reconstruction; Point cloud; 3D semantic segmentation; Deep learning
期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.3； 五年影响因子：8.3 ）
ISSN： 0168-1699
年卷期： 2024 年 216 卷
页码：
收录情况： SCI
摘要： Maize ear rot poses a severe threat to maize yield and quality. Breeding and cultivating highly resistant maize varieties is a crucial approach for preventing and controlling maize ear rot. However, traditional methods of visually grading the severity of maize ear infection and resistance lack objectivity and repeatability. To meet the requirement of precise breeding and resistance assessment scenarios, a novel pipeline based on threedimensional (3D) point clouds of maize ear was developed for ear rot precise evaluation. First, multi-view stereo (MVS) reconstruction was employed to obtain high-precision dense point clouds of maize ears. And the coordinate correction and circular sampling approaches were proposed to optimize the data structure of the input maize ear samples. Next, a specialized network called the ear rot segmentation network (ERSegNet) was proposed to detect the infected area of maize ears. This network incorporated an orientation-encoding (OE) module and point transformer (PT) attention, which effectively boosted the performance of PointNet++. The proposed ERSegNet achieved impressive results, including a mean intersection over union (mIoU) of 85.83%, a mean precision (mPrec) of 92.34%, a mean recall (mRec) of 92.23%, a mean F1-score of 92.28%, and an overall accuracy (OA) of 93.76%. This demonstrated the feasibility of using semantic segmentation algorithms to predict 3D point clouds of maize ears. Furthermore, a point cloud resampling method was suggested to enhance the spatial uniformity of maize ear point clouds and a point-level quantitative assessment approach based on the 3D point cloud data was provided for evaluating the severity of ear rot. The results showed an average evaluation error of 1.55% in the testing set, indicating the accuracy of the proposed method. This study provides a reliable and objective method for maize ear rot precise assessment, offering potential and valuable support for the identification of resistant varieties in breeding programs.
- 相关文献
作者其他论文 更多>>
-
Weakly supervised dual-mask marginal segmentation and variable path planning method for bean weed based on UAV remote sensing
作者：Zhang, Jianlin;Lu, Xiangyu;Yang, Rui;Liu, Fei;Xu, Hongxing;Huai, Yan
关键词：Variable path planning; Marginal segmentation; Teacher-to-student; Deep learning; Image processing
-
Developing fluorescence hyperspectral imaging methods for non-invasive detection of herbicide safeners action mechanism and effectiveness
作者：Chu, Hangjian;Zhao, Yiying;Zhang, Xiaobin;Chu, Hangjian;Gouda, Mostafa;He, Yong;Li, Xiaoli;Liu, Yufei;Gouda, Mostafa;Li, Yu
关键词：Visible/near-infrared hyperspectral imaging; Chlorophyll a fluorescence; Chemometric analysis; Machine learning models
-
Application of deep learning for high-throughput phenotyping of seed: a review
作者：Jin, Chen;Zhang, Chu;Qi, Hengnian;Zhou, Lei;Pu, Yuanyuan;Zhao, Yiying
关键词：Seed phenotypes; Computer vision; Hyperspectral imaging; Convolutional neural networks; Transfer learning; Multi-dimensional data
-
A Novel Allelic Variant of OsAGPL2 Influences Rice Eating and Cooking Quality
作者：Dan, Yuqing;He, Yong;Peng, Ruixiao;Tian, Zhihong;Huang, Fudeng;Li, Chunshou;Song, Jiayu;Hao, Yuanyuan;Xu, Junfeng;Xu, Junfeng
关键词：rice quality;
OsAGPL2 ; white-core endosperm mutant; superior haplotype -
Deep learning-based regression of food quality attributes using near-infrared spectroscopy and hyperspectral imaging: A review
作者：Xiao, Yuxin;Qi, Hengnian;Zhang, Chu;Zhou, Lei;Zhao, Yiying;Pu, Yuanyuan
关键词：Deep learning for spectral data analysis; Non-destructive food quality prediction; Near-infrared spectroscopy and hyperspectral imaging regression models; Spectral feature extraction; Transfer learning; Data augmentation
-
Unmanned aerial vehicle-based assessment of rice leaf chlorophyll content dynamics across genotypes
作者：Gu, Qing;Lou, Weidong;Zhu, Yihang;Hu, Hao;Zhao, Yiying;Zhou, Hongkui;Zhang, Xiaobin;Huang, Fudeng
关键词：Oryza sativa L.; Chlorophyll content; Phenotype; Unmanned aerial vehicle; Variety classification
-
Ginkgo biloba Sex Identification Methods Using Hyperspectral Imaging and Machine Learning
作者：Chen, Mengyuan;Yang, Rui;Lu, Xiangyu;Liu, Fei;Lin, Chenfeng;Zhao, Yunpeng;Sun, Yongqi;Lou, Weidong;Deng, Xunfei
关键词：Ginkgo biloba; sex identification; leaf morphology; hyperspectral imaging; machine learning
