Visual-SLAM for the detection of hidden tomatoes in greenhouses by Hierarchical Localization and GLOMAP for robotized harvesting
作者: Fernando Cañadas-Aránega, José C. Moreno, José L. Blanco-Claraco, Francisco Rodríguez
分类: cs.RO
发布日期: 2026-09-10 (更新: 2026-09-11)
💡 一句话要点
提出视觉SLAM以解决温室中隐藏番茄检测问题
🎯 匹配领域: 支柱三：空间感知与语义 (Perception & Semantics)
关键词: 视觉SLAM 农业监测 单目相机 3D映射 自动化采摘 分层定位 GLOMAP 温室作物
📋 核心要点
- 现有方法主要依赖高成本的传感器，难以实现经济高效的温室作物监测。
- 本文提出了一种基于单目相机的视觉SLAM系统，结合GLOMAP和分层定位技术，专注于番茄作物的3D映射。
- 实验结果表明，该系统能够准确识别被遮挡的番茄，并与手动测量的几何数据相符，验证了其有效性。
📝 摘要（中文）
温室内先进作物监测已成为研究中心的主要目标之一。传统上，LiDAR或立体相机等高性能传感器被广泛应用，但成本较高。本文提出了一种基于单目相机的视觉SLAM系统，具有更高的性价比，专门针对农业应用，如温室内番茄作物的映射。通过在Agroconnect实验温室中对真实番茄串进行测试，开发了一个ROS 2 Humble节点以捕获作物图像并进行离线处理。为生成温室作物的3D映射模型，将基于运动结构的GLOMAP映射器与分层定位工具箱集成。该系统采用粗到细的分层定位范式，首先进行全局检索以生成位置假设，然后在识别的候选区域内结合局部特征。结果显示，该系统能够正确识别番茄簇，并准确表征被经典视觉技术遮挡和无法接触的番茄。
🔬 方法详解
问题定义：本文旨在解决温室中隐藏番茄的检测问题，现有方法依赖于高成本的传感器，难以满足经济性和实用性需求。
核心思路：提出了一种基于单目相机的视觉SLAM系统，结合GLOMAP映射器和分层定位工具箱，以实现低成本的作物3D映射和检测。
技术框架：系统整体架构包括图像捕获、GLOMAP映射、分层定位和3D模型重建四个主要模块。首先通过ROS 2节点捕获图像，然后利用GLOMAP生成3D模型，最后进行分层定位以提高定位精度。
关键创新：最重要的创新在于将分层定位与GLOMAP映射相结合，采用粗到细的策略，显著提高了对遮挡番茄的识别能力，与传统方法相比具有更高的准确性和效率。
关键设计：在参数设置上，采用了适合农业环境的特定特征提取算法，损失函数设计上注重几何精度，确保重建模型的准确性。
🖼️ 关键图片
📊 实验亮点
实验结果显示，系统能够准确识别被遮挡的番茄，重建的3D模型在果实大小、质心位置和方向上与手动测量结果一致，验证了该低成本单目管道的几何精度，具有显著的实用价值。
🎯 应用场景
该研究的潜在应用领域包括智能农业、自动化采摘和作物监测等。通过低成本的视觉SLAM系统，农民和农业企业能够更高效地监测作物生长，优化管理策略，提高产量和经济效益。
📄 摘要（原文）
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.