ALNet:通过线网络实现实时和准确的玉米排列检测
Bofeng Feng1, Qingliang He1, Yun Hu2
1College of Engineering, South China Agricultural University, Guangzhou, China.
Frontiers in plant science
|December 17, 2025
概括
一个新的轻量级深度学习模型,ALNet (线网络),可以有效和准确地检测农业机械导航的作物行. 它在边缘设备上实现了高性能,改善了精准农业.
科学领域:
- 计算机视觉 计算机视觉
- 农业机器人农业机器人
- 机器学习 机器学习
背景情况:
- 准确的作物排列检测对于自主农机导航至关重要.
- 现有的深度学习方法面临着计算成本,边缘部署和平衡准确性与速度的挑战.
- 玉米行检测需要专业的方法,因为延长的几何结构.
研究的目的:
- 开发一个轻量级的深度学习模型 (ALNet) 进行高效和准确的玉米行检测.
- 在具有挑战性的现场条件下提高行检测的稳定性.
- 为了在边缘设备上实现导航系统的实时部署.
主要方法:
- 作为回归任务,引入了端到端行检测的线机制.
- 用行对齐的内核操作取代了像素智能的卷积,以减少计算.
- 整合了一个以注意力引导的ROI Align模块与双轴挤出变压器 (DAE-Former) 进行增强的功能交互.
- 开发了一种Row IoU (RIoU) 损失函数,以提高本地化准确度.
主要成果:
- ALNet获得了59.60的mF1评分,超过了竞争方法的9.24分.
- 演示了161.26 FPS的高推理速度,低11.9 GFlops的计算成本.
- 在具有挑战性的条件下表现出强性,如杂草侵袭,低光和风力扭曲等.
结论:
- ALNet为精准农业中的智能视觉导航提供了一种实用且可扩展的解决方案.
- 轻量化设计和高效率使ALNet适合实时边缘部署.
- 拟议的线机制和注意力模块显著提升了作物排列检测能力.
相关概念视频
02:16Light Acquisition
9.3K
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.
9.3K
02:35Key Elements for Plant Nutrition
23.9K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
23.9K