外观
论文arXiv 2609.117661 个月前
面向机器人化采摘，基于 Hierarchical Localization 和 GLOMAP 的温室隐藏番茄检测 Visual-SLAM
原文链接：Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAP for robotized harvesting（arXiv 2609.11766 · 发布日期：2026-09-10）
Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAP for robotized harvesting
该工作用单目相机 Visual-SLAM 结合 GLOMAP 与 Hierarchical Localization，在真实温室番茄串上验证低成本三维建图与遮挡果实识别。
核心要点
- 温室作物监测常依赖 LiDAR 或双目相机，成本较高；本文面向番茄作物提出低成本单目方案。
- 系统通过 ROS 2 Humble 节点在机器人上采集作物图像，并存储后用于离线三维建图处理。
- 方法集成基于 Structure-From-Motion 的 GLOMAP mapper 与 Hierarchical Localization toolbox。
- 结果显示系统能正确识别番茄簇和被遮挡番茄，三维模型经人工尺寸、质心和方向测量验证。
验证范围与局限：验证范围为 Agroconnect 实验温室中的一个真实番茄串，图像采集后进行离线处理。
英文摘要 (Abstract)
Advanced crop monitoring inside greenhouses is becoming one of the primary objectives of research centers. High-performance sensors, such as LiDAR or stereo cameras, have traditionally been employed for this purpose, though these often have a high cost. This work proposes a Visual-SLAM system using a monocular camera, which is significantly more cost-effective and specifically tailored for agricultural applications, such as mapping tomato crops in a greenhouse. Tests were carried out on a real tomato bunch, located in the Agroconnect experimental greenhouse. A ROS 2 Humble node was developed to run on the robot in order to capture images of these crops, which were then stored for offline processing. To generate a 3D mapped model for the crop in the greenhouse, the GLOMAP mapper, based on Structure-From-Motion, was integrated with the Hierarchical Localization toolbox. This initial mapping is a foundation for future, more advanced algorithms to analyze growth patterns, and optimize agricultural management. The system leverages a hierarchical localization paradigm based on a coarse-to-fine strategy: it first performs global retrieval to generate location hypotheses, then combines local features within the identified candidate regions. The results show a correct identification of the tomato cluster, correctly characterising the tomato that is occluded and inaccessible by classical vision technologies. The reconstructed 3D model was further validated against manual ground-truth measurements of fruit size, centroid position, and orientation, confirming the geometric accuracy of the proposed low-cost monocular pipeline.
作者：Fernando Cañadas-Aránega, Jose C. Moreno, Jose Luis Blanco-Claraco, Francisco Rodríguez
来源
本页事实对应的公开页面，以原文为准。