SeeTree -- A modular, open-source system for tree detection and orchard localization

2025-04-14

AI Summary

Reliable, open-source localization solutions for precise tree positioning and robust full-scenario navigation—including inter-row turning—in orchard precision management remain scarce. Method: This paper proposes a modular embedded visual-inertial-GNSS fusion localization system. It innovatively supports headland turning localization outside rows, employs a configurable multi-source motion model, and integrates a particle-filter-based real-time visual localization framework with an embedded real-time processing architecture. Contribution/Results: The system is fully open-source, including hardware schematics, sensor calibration datasets, and complete software implementation. In evaluation, it achieves 99% convergence success across 800 localization trials and 99% tracking accuracy across 860 inter-row turning trials, covering 43 distinct row-transition patterns. These results significantly enhance the robustness and generalization capability of autonomous orchard operation systems.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Multi-modal Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Accurate localization is an important functional requirement for precision orchard management. However, there are few off-the-shelf commercial solutions available to growers. In this paper, we present SeeTree, a modular, open source embedded system for tree trunk detection and orchard localization that is deployable on any vehicle. Building on our prior work on vision-based in-row localization using particle filters, SeeTree includes several new capabilities. First, it provides capacity for full orchard localization including out-of-row headland turning. Second, it includes the flexibility to integrate either visual, GNSS, or wheel odometry in the motion model. During field experiments in a commercial orchard, the system converged to the correct location 99% of the time over 800 trials, even when starting with large uncertainty in the initial particle locations. When turning out of row, the system correctly tracked 99% of the turns (860 trials representing 43 unique row changes). To help support adoption and future research and development, we make our dataset, design files, and source code freely available to the community.

Problem

• Lack of commercial solutions for orchard localization
• Need for modular tree detection and localization system
• Integration of multiple sensors for accurate orchard navigation

Innovation

• Modular open-source tree detection system
• Integrates visual GNSS wheel odometry
• Accurate orchard localization and turning