相关实验视频

Updated: May 2, 2026

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

利用对抗式的风格在大米田里进行通用和强大的杂草细分

Yaoxuan Zhang¹, Hao Cai¹, Jiahui Ye¹

¹College of Engineering, South China Agricultural University, Guangzhou, China.

Frontiers in plant science

|December 17, 2025

概括

这项研究提出了一种新的深度学习方法,用于在田中识别杂草. 风格导向杂草实例分割 (SWIS) 方法提高了精准农业的准确性.

科学领域:

农业科学农业科学
计算机视觉计算机视觉
深度学习 (Deep Learning) 是一种深度学习.

背景情况:

有效的杂草管理对于精准农业的水产量和质量至关重要.
准确区分杂草和大米作物是精确除草技术的持续挑战.

研究的目的:

引入一种创新的深度学习方法,用于在田中识别和细分杂草.
提高杂草识别模型的跨环境概括性和特征稳定性.

主要方法:

开发了一种以风格为导向的杂草实例分割 (SWIS) 方法.
集成的随机自适应实例规范化 (RAIN) 用于随机风格转换.
采用动态梯度反向传播 (DGB) 进行对抗特征优化.

主要成果:

在现场数据上实现了70.49%的Weed Intersection over Union (Weed IoU). 在现场数据上实现了70.49%的Weed IoU.
与现有的比较方法相比,表现出显著的性能改善.
验证了该方法在现实世界农业应用中的有效性.

结论:

在精准农业中,SWIS方法为杂草识别和细分提供了有效的解决方案.
这项研究推动了计算机视觉在农业中的应用.
为开发更先进的杂草识别模型提供了基础.

关键词:

精准农业精准农业精准农业精密除草精确除草准确除草米幼苗的种植方式风格转移风格转移风格转移杂草检测检测器杂草检测器

更多相关视频

Repeatable Stair-step Assay to Access the Allelopathic Potential of Weedy Rice Oryza sativa ssp.

Repeatable Stair-step Assay to Access the Allelopathic Potential of Weedy Rice Oryza sativa ssp.

Published on: January 28, 2020

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

相关概念视频

Light Acquisition

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.