数字农科院2.0

STANet-TLA: leveraging deep learning and prior knowledge for large-scale soybean breeding plot segmentation and high-yielding variety screening from UAV time-series data

文献类型： 外文期刊

作者： Shaochen Li;Yinmeng Song;Ke Wang;Yiqiang Liu;Junhong Xian;Hongshan Wu;Xintong Zhang;Yanjun Su;Jin Wu;Qinghua Guo;Shan Xu;Dong Jiang;Jiao Wang;Jinming Zhao;Xianzhong Feng;Lijuan Qiu;Yanfeng Ding;Shichao Jin

作者机构：

关键词： Canopy semantic segmentation;Deep learning;High-yielding variety screening;Plot instance segmentation;Soybean;Time-series dataset

期刊名称： ISPRS Journal of Photogrammetry and Remote Sensing

ISSN： 0924-2716

年卷期： 2025 年 227 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： High-yielding varieties screening is essential for food security, which requires the monitoring of canopy growth, the extraction of dynamic traits, and the estimation of yield at the variety level. Unmanned Aerial Vehicle (UAV) provides a valuable source of high-resolution spatio-temporal data, which can accelerate plot-level phenotyping and variety screening. However, the automatic extraction of breeding plot boundaries from UAV images is challenging due to complex backgrounds, dynamic canopies, and varying row and plot intervals. In this study, we introduce a novel method called STANet-TLA for breeding plot extraction to screen high-yielding varieties. STANet-TLA leverages a self-designed spatio-temporal feature alignment network (STANet) for semantic segmentation and a prior knowledge-constrained traction line aggregation method (TLA) for instance segmentation. To evaluate our model, we constructed a comprehensive dataset named SoyUAV, which includes 21,319 images of more than 977 genotypes at almost all growth stages. The results demonstrated that: (1) STANet achieved an intersection over union (IoU) of 85.43 % and an F1-score (F1) of 91.89% for canopy semantic segmentation, outperforming eight state-of-the-art deep learning networks with average improvements of 5.80 % in IoU and 4.65 % in F1. Based on the semantic segmentation results, TLA achieved an IoU of 93.31 % and an F1 of 95.13 % for plot instance segmentation; (2) STANet demonstrated effective transferability across different years, locations, and data types, achieving high IoU scores of 88.22%, 89.53%, and 79.16%, respectively. STANet-TLA was suitable for plot instance segmentation with different planting designs; (3) The accuracy of high-yielding varieties screening was 60 % using Random Forest with static phenotypes in the plots obtained by STANet-TLA segmentation. This accuracy was improved to 70.59 % and 75 % when incorporating time-series and dynamic-fitting phenotypes, respectively. Our datasets and models are publicly available, which we believe will significantly facilitate advanced UAV-based plant phenotyping and widespread large-scale breeding applications.

分类号：

  • 相关文献

[1]Deep learning based weed detection and target spraying robot system at seedling stage of cotton field. Xiangpeng Fan,Xiujuan Chai,Jianping Zhou,Tan Sun. 2023

[2]Inter-Continental Transfer of Pre-Trained Deep Learning Rice Mapping Model and Its Generalization Ability. Lingbo Yang,Ran Huang,Jingcheng Zhang,Jingfeng Huang,Limin Wang,Jiancong Dong,Jie Shao. 2023

[3]Semantic Segmentation Based on Temporal Features: Learning of Temporal-Spatial Information From Time-Series SAR Images for Paddy Rice Mapping. Yang, Lingbo,Huang, Ran,Huang, Jingfeng,Lin, Tao,Wang, Limin,Mijiti, Ruzemaimaiti,Wei, Pengliang,Tang, Chao,Shao, Jie,Li, Qiangzi,Du, Xin. 2021

[4]A Novel Physics-Statistical Coupled Paradigm for Retrieving Integrated Water Vapor Content Based on Artificial Intelligence. Ruyu Mei,Kebiao Mao,Jiancheng Shi,Jeffrey Nielson,Sayed M. Bateni,Fei Meng,Guoming Du. 2023

[5]Machine learning for image-based multi-omics analysis of leaf veins. Yubin Zhang,Ning Zhang,Xiujuan Chai,Tan Sun. 2023

[6]Auction-based deep learning-driven smart agricultural supply chain mechanism. Yu Feng,Dong Mei,Hua Zhao. 2023

[7]Research on machine vision and deep learning based recognition of cotton seedling aphid infestation level. Xin Xu,Jing Shi,Yongqin Chen,Qiang He,Liangliang Liu,Tong Sun,Ruifeng Ding,Yanhui Lu,Chaoqun Xue,Hongbo Qiao. 2023

[8]Integrating satellite-derived climatic and vegetation indices to predict smallholder maize yield using deep learning. Liangliang Zhang,Zhao Zhang,Yuchuan Luo,Juan Cao,Ruizhi Xie,Shaokun Li. 2021

[9]A rapid, low-cost deep learning system to classify strawberry disease based on cloud service. Guo feng YANG,Yong YANG,Zi kang HE,Xin yu ZHANG,Yong HE. 2022

[10]Deep learning for change detection in remote sensing: a review. Bai, Ting,Wang, Le,Yin, Dameng,Sun, Kaimin,Chen, Yepei,Li, Wenzhuo,Li, Deren. 2022

[11]Mapping of lakes in the Qinghai-Tibet Plateau from 2016 to 2021: trend and potential regularity. Zhichong Yang,Si Bo Duan,Xiaoai Dai,Yingwei Sun,Meng Liu. 2022

[12]Bionic technology and deep learning in agricultural engineering: Current status and future prospects. Chunlei Tu,Jinxia Li,Xingsong Wang,Shen Cheng,Jie Li. 2021

[13]Automatic freezing-tolerant rapeseed material recognition using UAV images and deep learning. Lili Li,Jiangwei Qiao,Jian Yao,Jie Li,Li Li. 2022

[14]Evaluation of deep learning for automatic multi‐view face detection in cattle. Beibei Xu,Wensheng Wang,Leifeng Guo,Guipeng Chen,Yaowu Wang,Wenju Zhang,Yongfeng Li. 2021

[15]Semi-Supervised Transformation and Deep Embedding-Based Anomaly Identification for Agricultural Internet of Things. Xiang Yin,Letian Wang,Weikuan Jia,Chengqian Jin. 2021

[16]Identification method of wheat cultivars by using a convolutional neural network combined with images of multiple growth periods of wheat. Jiameng Gao,Chengzhong Liu,Junying Han,Qinglin Lu,Hengxing Wang,Jianhua Zhang,Xuguang Bai,Jiake Luo. 2021

[17]A synthetic datasets based instance segmentation network for High-throughput soybean pods phenotype investigation. Yang, Si,Zheng, Lihua,Yang, Huijun,Zhang, Man,Wu, Tingting,Sun, Shi,Tomasetto, Federico,Wang, Minjuan. 2022

[18]A method for land surface temperature retrieval based on model-data-knowledge-driven and deep learning. Han Wang,Kebiao Mao,Zijin Yuan,Jiancheng Shi,Mengmeng Cao,Zhihao Qin,Sibo Duan,Bohui Tang. 2021

[19]Predicting equivalent water thickness in wheat using UAV mounted multispectral sensor through deep learning techniques. Adama Traore,Syed Tahir Ata-Ul-karim,Aiwang Duan,Mukesh Kumar Soothar,Seydou Traore,Ben Zhao. 2021

[20]Culling Double Counting in Sequence Images for Fruit Yield Estimation. Xue Xia,Xiujuan Chai,Ning Zhang,Zhao Zhang,Qixin Sun,Tan Sun. 2022

作者其他论文 更多>>