一个基于改进的VGG16的新模型用于玉米杂草识别
Le Yang1, Shuang Xu2, XiaoYun Yu1
1School of Computer and Information Engineering, Jiangxi Agricultural University, Nanchang, China.
Frontiers in plant science
|July 24, 2023
概括
一个新的SE-VGG16模型使用深层卷积神经网络准确地识别了玉米杂草. 这种先进的模型显著改进了农业中有效控制杂草的现有方法.
科学领域:
- 农业科学 农业科学
- 计算机科学 计算机科学
- 人工智能的人工智能
背景情况:
- 杂草对农业中的玉米产量和质量产生重大影响.
- 准确而高效的杂草识别对于有效的作物管理至关重要.
研究的目的:
- 开发一种新的深度卷积神经网络模型,用于准确高效地识别玉米田中的杂草.
- 通过注意力机制和优化的网络架构来增强杂草检测能力.
主要方法:
- 提出了SE-VGG16模型,这是VGG16的调整,包含SE注意力机制.
- 修改了卷积内核和激活功能 (ReLU到泄漏的ReLU),以改善特征提取.
- 用全球平均池化层取代完全连接层,并使用softmax进行输出.
主要成果:
- 在玉米杂草分类中,SE-VGG16模型实现了99.67%的平均准确性.
- 与经典和先进的多尺度模型相比,表现优越,优于原始VGG16 (97.75%).
- 使用精度率,回忆率和F1评分进行评估,显示出高强度和稳定性.
结论:
- SE-VGG16模型提供了一个强大的,准确的解决方案,用于在玉米田中识别杂草.
- 该模型为农业中有效的杂草控制策略提供了实际应用.
- 开发的模型展示了对农业挑战的深度学习中注意力机制的潜力.
相关概念视频
02:16Light Acquisition
8.5K
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.
8.5K
01:59Plant Breeding and Biotechnology
19.0K
Crop cultivation has a long history in human civilization, with records showing the cultivation of cereal plants beginning at around 8000 BC. This early plant breeding was developed primarily to provide a steady supply of food.
19.0K