相关实验视频
Updated: Jan 13, 2026

13:11
Video Bioinformatics Analysis of Human Embryonic Stem Cell Colony Growth
Published on: May 20, 2010
13.1K
在植物组织培养中实时实例细分,使用连续几代YOLO架构
Yunus Egi1, Tülay Oter2, Mortaza Hajyzadeh2
1Department of Electrical and Electronics Engineering, Sirnak University, Sirnak 73000, Türkiye.
Plants (Basel, Switzerland)
|January 10, 2026
概括
研究人员开发了第一个 (Lens culinaris) 数据集,例如细分. 无的YOLOv8模型实现了卓越的精度和实时推断,用于监测植物组织培养.
科学领域:
- 植物生物技术 植物生物技术
- 计算机视觉 计算机视觉
- 农业科学 农业科学
背景情况:
- 诱导对于植物的繁殖,代谢物生产和遗传修饰至关重要.
- 手动监测形成是劳动密集型和主观的.
- 需要自动化方法来准确评估植物组织培养中的发育.
研究的目的:
- 创建第一个精选的 (Lens culinaris) 数据集,例如细分.
- 为了评估连续YOLO深度学习模型对细分的性能.
- 确定最佳的深度学习架构,以精确有效地监测.
主要方法:
- 通过使用三个基因型 (Firat-87,Cagil,Tigris) 和三个发育阶段 (叶子,绿色结质,结结质) 创建了一个结质数据集.
- 获得了122张高分辨率图像,并有1185条注释.
- 评估了YOLOv5,YOLOv7,YOLOv8和YOLOv11模型,使用实例细分指标 (mAP,Dice,Precision,Recall,IoU) 和效率指标 (参数,FLOP,推断速度).
主要成果:
- 无的YOLOv8和YOLOv11模型在结构的边界精度方面超过了基于的YOLOv5和YOLOv7.
- YOLOv8实现了最高的实例细分精度 (mAP50@0.855).
- YOLOv8以高精度和高效率在166 FPS进行实时推断.
结论:
- 开发的豆结质数据集支持了自动化植物组织培养监测方面的进展.
- 没有的深度学习模型,特别是YOLOv8,为准确和高效的实例细分提供了显著的优势.
- 这项研究为通过人工智能驱动的分析改善精准农业和植物育种铺平了道路.
相关概念视频
Plant Tissue Culture
40.1K
Plant tissue culture is widely used in both primary and applied science. Applications range from plant development studies to functional gene studies, crop improvement, commercial micropropagation, virus elimination, and conservation of rare species.
40.1K
Plant Tissues
8.6K
Plants are multicellular eukaryotes with tissue systems made of various cell types that carry out specific functions. Different tissues work together to perform a unique function and form an organ. Organs working together form organ systems. Vascular plants have two distinct organ systems: a shoot system and a root system. The shoot system consists of two portions: the vegetative (non-reproductive) parts of the plant, such as the leaves and the stems, and the reproductive parts of the plant,...
8.6K

