在自然环境中对果叶病进行分类的轻量级模型
Yuanyuan Jiao1, Honghui Li1, Xueliang Fu1
1College of Computer and Information Engineering, Inner Mongolia Agricultural University, Hohhot, China.
Frontiers in plant science
|August 28, 2025
概括
一个新的轻量级网络,LCAMNet,准确地分类果叶病. 这种模型可以平衡高精度和效率,使其适合现实世界果园条件和资源有限的设备.
科学领域:
- 农业科学
- 计算机视觉
- 机器学习
背景情况:
- 果叶病对作物产量和质量产生重大影响.
- 准确的疾病分类对于有效的管理至关重要.
- 由于背景损伤的相似性,现有的模型在自然环境中难以实现轻量化设计和高精度.
研究的目的:
- 开发一种轻量级且准确的果叶疾病分类模型.
- 解决现有模型在自然果园环境中的局限性.
- 提高疾病检测系统的实用性.
主要方法:
- 引入轻量化聚焦多分支网络 (LCAMNet).
- 集成深度可分离的卷积和结构重新参数化以实现高效的建模.
- 一个双分支降低采样模块的设计,以防止特征损失.
- 实现多尺度结构和改善三重重点,以增强特征表示.
主要成果:
- 在构建的SCEBD数据集上,LCAMNet的准确度为92.60%,在公开的数据集上为95.31%.
- 该模型具有轻量级设计,只有0.03GFLOP和1.30M参数.
- 该网络有效地处理各种干扰因素的复杂自然环境.
结论:
- 对于果叶病的分类,LCAMNet提供了一个高准确度,轻量级的解决方案.
- 该模型的效率和准确性使其适合在现实世界果园中的资源有限设备上部署.
- 开发的SCEBD数据集真实地代表了果园条件,有助于未来的研究.
更多相关视频
10:14Author Spotlight: Leaf Trait Analysis for Climate and Ecology Reconstruction in Modern and Ancient Plant Communities
Published on: October 25, 2024
3.9K
09:31Author Spotlight: High-Throughput In Vivo Leaf Inoculation for Accelerating Disease Resistance Screening in Poplar Hybrid Breeding
Published on: September 20, 2024
806
相关概念视频
02:16Light Acquisition
8.6K
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.
8.6K
01:57Adaptations that Reduce Water Loss
26.3K
Though evaporation from plant leaves drives transpiration, it also results in loss of water. Because water is critical for photosynthetic reactions and other cellular processes, evolutionary pressures on plants in different environments have driven the acquisition of adaptations that reduce water loss.
26.3K