相关实验视频

Updated: Jun 16, 2025

Author Spotlight: Sieving Fruit Pulp to Detect Immature Tephritid Fruit Flies in the Field

Author Spotlight: Sieving Fruit Pulp to Detect Immature Tephritid Fruit Flies in the Field

Published on: July 28, 2023

ELD-YOLO:在植物研究中检测隐藏的普通果的轻量级框架

Xianyao Wang¹, Yutong Huang¹, Siyu Wei²

¹College of Information Engineering, Sichuan Agriculture University, Ya'an 625014, China.

Plants (Basel, Switzerland)

|June 13, 2025

概括

通过增强边缘细节和处理封闭的水果,ELD-YOLO提高了在果园中的普通果检测. 这种轻量级模型提供了更高的精度和回忆,同时降低了计算成本,以实现高效的收获.

科学领域:

计算机视觉计算机视觉
农业技术农业技术
机器学习机器学习

背景情况:

果检测对于产量预测和收获至关重要.
复杂的果园环境带来了诸如水果封闭和小水果可见性等挑战.
在这些场景中,现有的模型在效率和准确性方面扎.

研究的目的:

开发一个轻量级检测框架 (ELD-YOLO) 来增强小型和封闭的果检测.
在复杂的果园环境中提高边缘细节的保存和模型效率.

主要方法:

提出了ELD-YOLO,一个轻量级的检测框架.
集成的边缘意识处理,以加强特征表示.
引入了精简的检测头和自适应式上采样策略.

主要成果:

实现了89.7%的精度,83.7%的回忆,92.1%的mAP@50和68.6%的mAP@50:95.
与基线模型相比,参数数量减少了15.4%.
在检测小和封闭的水果方面表现出卓越的性能.

结论:

ELD-YOLO为在具有挑战性的果园环境中检测普通果提供了有效和高效的解决方案.
该框架平衡了高精度与降低计算成本.
允许精确的水果识别和收获支持.

关键词:

复杂的果园环境复杂的果园环境.边缘功能边缘功能边缘功能果实检测检测器果实检测检测器机器视觉机器视觉机器视觉在普通话中使用普通话.

更多相关视频

Deep Fluorescence Observation in Rice Shoots via Clearing Technology

Deep Fluorescence Observation in Rice Shoots via Clearing Technology

Published on: June 27, 2022

Fruit Volatile Analysis Using an Electronic Nose

Fruit Volatile Analysis Using an Electronic Nose

Published on: March 30, 2012

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.