AFBF-YOLO:一个改进的YOLO11n算法,用于在温室环境中检测桃番茄的束和成熟度
Bo-Jin Chen1, Jun-Yan Bu1, Jun-Lin Xia1
1College of Engineering, China Agricultural University, 17 Qinghua East Road, Haidian, Beijing 100083, China.
Plants (Basel, Switzerland)
|August 28, 2025
概括
一个新的深度学习模型,AFBF-YOLO, 准确地检测桃番茄群和成熟阶段. 这一进步通过改善果实检测和成熟度评估来支持精准农业的智能收获系统.
科学领域:
- 农业工程
- 计算机视觉
- 机器学习
背景情况:
- 精确检测桃番茄和成熟度对于自动收获至关重要.
- 挑战包括遮蔽,重叠的水果,以及复杂的温室环境中的微妙成熟度变化.
研究的目的:
- 提出基于YOLOv11的改进深度卷积神经网络模型 (AFBF-YOLO) 用于桃番茄检测和成熟度评估.
- 增强特征表示和多尺度融合,在复杂条件下提高准确性.
主要方法:
- 开发了486张RGB图像的数据集,其中有超过15万个在四个成熟阶段的注释实例.
- 将ACmix注意力机制纳入YOLOv11以获得更好的特征表示.
- 设计了一种新的FreqFusion-BiFPN部结构,以改善多尺度特征融合.
- 应用了精细的内焦器-IOU损失函数以增强边界框定位.
主要成果:
- AFBF-YOLO的精度为81.2%,回忆率为81.3%,mAP@0.5的精度为85.6%.
- 该模型的性能超过了几个主流的YOLO系列探测器.
- 在不同成熟阶段具有较低的计算复杂度的高精度.
结论:
- AFBF-YOLO有效地解决了桃番茄检测和成熟度评估方面的挑战.
- 该模型支持同时检测果束和成熟度,这对于自动收获至关重要.
- 这项研究有助于精准农业和智能收获系统的进步.
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
01:27Microbial Growth Measurement: Indirect Methods
162
Estimating microbial growth is essential for understanding population dynamics and environmental adaptations. Indirect methods provide valuable insights by measuring parameters such as turbidity, metabolic activity, and biomass, enabling efficient and reproducible assessments.During exponential growth, microbial cells scatter light proportionally to their biomass, a principle used in turbidity measurements. About one million cells per milliliter produce detectable scattering, which a...
162