相关实验视频

Updated: Jul 7, 2025

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Imaging and Analysis for Quantifying Maize (Zea mays) Abiotic Stress Phenotypes

Published on: March 28, 2025

一个弱监督的玉米幼苗和杂草图像的语义细分模型,基于草标签

Lulu Zhao¹, Yanan Zhao¹, Ting Liu¹

¹College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China.

Sensors (Basel, Switzerland)

|December 23, 2023

概括

本研究引入了基于Scrawl标签的弱监督语义分段网络 (SL-Net),以降低玉米和杂草图像分段的注释成本. 在培训中,SL-Net有效地使用草稿标签,在区分玉米和杂草方面达到很高的准确性.

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:

对玉米和杂草细分进行完全监督的深度学习需要广泛的像素级注释,由于复杂的植物形态,这些注释成本高.
现有的方法在有效和准确的农业图像语义细分方面面临挑战.

研究的目的:

开发一个高效的弱监督的语义细分网络 (SL-Net),减少对像素级注释的依赖.
为了提高玉米和杂草图像的语义细分的准确性和降低成本.

主要方法:

拟议的SL-Net包含一个伪标签生成模块,一个编码器和一个解码器,基于DeepLab-V3+模型.
使用草标签转换为伪标签来训练网络,采用迁移学习策略.
使用增强的骨干网络改进了功能提取.

主要成果:

伪标签生成模块实现了83.32%的交叉与联盟 (IoU) 和93.55%的共弦相似性与基本真相.
在对玉米和杂草进行细分时,SL-Net的平均IOU为87.30%和平均精度为94.06%.
与DeepLab-V3+和PSPNet相比,在弱监督和完全监督的条件下都获得了优异的性能.

结论:

SL-Net有效地减少了农业语义细分的注释负担.
拟议的方法证明了高精度和高效率在区分玉米植物从杂草使用拼写标签.
SL-Net为自动化农业图像分析提供了一个有前途的解决方案.

关键词:

图像分割图像细分图像细分标签标签标签标签标签语义细分语义细分语义细分语义细分缺乏监督的学习学习.

更多相关视频

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Volume Segmentation and Analysis of Biological Materials Using SuRVoS Super-region Volume Segmentation Workbench

Published on: August 23, 2017

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

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.