[an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive]
[an error occurred while processing this directive]

植物学报 >

2025 , Vol. 60 >Issue 1: 1 - 0

DOI: https://doi.org/10.11983/CBB24027

研究报告

北方草地植物物种智能识别模型构建及应用

  • 宣晶 ,
  • 付其迪 ,
  • 谢淦 ,
  • 薛凯 ,
  • 雒海瑞 ,
  • 魏泽 ,
  • 赵明月 ,
  • 智亮 ,
  • 万华伟 ,
  • 高吉喜 ,
  • 李敏
展开
  • 1中国科学院植物研究所, 植物多样性与特色经济作物全国重点实验室&系统与进化植物学重点实验室, 北京 100093; 2中国科学院植物研究所大数据与AI生物多样性保护研究中心, 北京 100093； 3国家植物园, 北京 100093； 4生态环境部卫星环境应用中心, 北京 100094



收稿日期: 2024-02-23

  修回日期: 2024-05-24

  网络出版日期: 2024-06-24

基金资助

国家重点研发计划“对地观测与导航”专项（NO. 2021YFB3901102）

收起

Construction of intelligent identification model and application for grassland plants in northern China #br#

  • XUAN Jing ,
  • FU Ji-Di ,
  • XIE Gan ,
  • XUE Kai ,
  • LUO Hai-Rui ,
  • WEI Ze ,
  • DIAO Meng-Ru ,
  • ZHI Liang ,
  • WAN Hua-Wei ,
  • GAO Ji-Xi ,
  • LI Min
Expand
  • 1State Key Laboratory of Plant Diversity and Specialty Crops & Key Laboratory of Systematic and Evolutionary Botany, Institute of Botany, Chinese Academy of Sciences, Beijing 100093, China; 2Big Data and AI Research Center of Biodiversity Conservation, Institute of Botany, Chinese Academy of Sciences, Beijing 100093, China; 3China National Botanical Garden, Beijing 100093, China; 4Satellite Application Center for Ecology and Environment, MEE, Beijing 100094, China

Received date: 2024-02-23

  Revised date: 2024-05-24

  Online published: 2024-06-24

Fold

摘要

近年来，图像智能识别已逐步从理论走向了实践，大量植物图像智能识别相关的软件、应用被开发出来供研究者、管理者和公众使用。目前可用的智能识别软件多是针对全国范围内的常见物种，对特定区域、特定植被类型的植物物种识别的研究和应用较少。本研究借助中国植物图像库的分类图片，针对内蒙古呼伦贝尔湿润草原和锡林浩特典型草原，建立了北方草地优势和建群植物的识别模型，在实际野外测试中种级TOP5识别准确率达到94.6%，为实现特定区域的植物物种智能识别提供了一个可参考的案例。


关键词： 草地植物; 人工智能; 图像识别; 呼伦贝尔; 锡林浩特

本文引用格式

宣晶 , 付其迪 , 谢淦 , 薛凯 , 雒海瑞 , 魏泽 , 赵明月 , 智亮 , 万华伟 , 高吉喜 , 李敏 . 北方草地植物物种智能识别模型构建及应用[J]. 植物学报, 2025 , 60(1) : 1 -0 . DOI: 10.11983/CBB24027

Abstract

A large number of applications on plant intelligent identification have been developed for use by researchers, managers and the public in recent years, and image identification has gradually moved from theory to practice. However, most of those applications is for the identification of widespread species or common species in the whole country, which is difficult to meet the needs of plant identification in specific regions and vegetation types. In this study, we have completed an identification model of dominant plants in Hulunbeier and Xilinhot grassland in Inner Mongolia using image dataset from Plant Photo Bank of China. The TOP1 accuracy of this model reaches more than 85% in the actual field identification activities, which provides a referable case for the realization of intelligent identification of plant species in a specific area.


Key words： Grassland plants; artificial intelligence; image recognition; Hulunbuir; Xilinhot

[an error occurred while processing this directive]

参考文献

李敏 (2018). “花伴侣”: 人工智能时代知识服务的新媒介. 出版参考 (08): 23–24.
许展慧, 刘诗尧, 赵莹, 涂文琴, 常诏峰, 张恩涛, 郭靖, 郑迪, 耿鋆, 顾高营, 郭淳鹏, 郭璐璐, 王静, 徐春阳, 彭钏, 杨腾, 崔梦琪, 孙伟成, 张剑坛, 刘皓天, 巴超群, 王鹤琪, 贾竞超, 武金洲, 肖翠, 马克平 (2020). 国内8款常用植物识别软件的识别能力评价. 生物多样性 28, 524–533.
杨旭光 (2022). 基于卷积神经网络模型水生植物分类识别研究与系统研发. 山东农业大学.
张勇辉, 冯琦胜, 梁天刚, 高新华, 黄晓东, 孙德伟, 吴安东 (2023). 草地资源调查与智能分析系统简介. 草业科学 40(08), 2171–2178.
LeCun Y, Bengio Y, Hinton G (2015). Deep learning. Nature 521, 436–444.
Liu Z, Wang J, Tian Y, Dai S (2019). Deep learning for image-based large-flowered chrysanthemum cultivar recognition. Plant Methods 15, 146. https://doi.org/10.1186/s13007-019-0532-7.
Joly A., Go?au H., Botella C., Glotin H, Bonnet P, Vellinga W-P, Planqué R, Müller H (2018). Overview of LifeCLEF 2018: A Large-Scale Evaluation of Species Identification and Recommendation Algorithms in the Era of AI. In: Bellot P, Trabelsi C, Mothe J, Murtagh F, Nie JY, Soulier L, SanJuan E, Cappellato L, Ferro N (Eds.) CLEF 2018: Experimental IR Meets Multilinguality, Multimodality, and Interaction. Lecture Notes in Computer Science, 11018, 247–266. https: //doi.org/10.1007/978-3-319-98932-7_24
Szegedy C, Loffe S, Vanhoucke V, Alemi A (2016a). Inception-v4, inception-ResNet and the impact of residual connections on learning. In: Singh S, Markovitch S (Eds.). AAAI'17: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. AAAI Press, 4278–4284.
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016b). Rethinking the Inception Architecture for Computer Vision. In: Conference on Computer Vision and Pattern Recognition (CVPR). 2818–2826.
Grinblat L G, Uzal C L, Larese G M, Granitto P M (2016). Deep learning for plant identification using vein morphological patterns. Computers and Electronics in Agriculture 127, 418–424.
Ledford H (2017). Artificial intelligence identifies plant species for science. Nature. https://doi.org/10.1038/nature.2017.22442
Marco S, Michael R, David B, W?ldchen J, M?der P (2019). Image-based classification of plant genus and family for trained and untrained plant species. BMC bioinformatics 20: 4.
Nguyen T H, Nguyen T L, Sidorov D N, Dreglea A I (2017). Machine learning algorithms application to road defects classification. Intelligent Decision Technologies 12(1): 59–66.
Cerutti G, Tougne L, Mille J, Vacavant A, Coquin D (2013). Understanding leaves in natural images – A model-based approach for tree species identification. Computer Vision and Image Understanding 117(10): 1482–1501.
Kumar N, Belhumeur P N, Biswas A, Jacobs D W, Kress W J, Lopez I C, Soares J V B (2012). Leafsnap: A computer vision system for automatic plant species identification. In: Fitzgibbon A., Lazebnik S., Perona P., Sato Y., Schmid C. (Eds.) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science 7573. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33709-3_36
Options
文章导航

/

〈 〉

[an error occurred while processing this directive]