Online Tree Reconstruction and Forest Inventory on a Mobile Robotic System

2024-03-26

IEEE/RJS International Conference on Intelligent RObots and Systems

AI Summary

Traditional terrestrial laser scanning (TLS) faces critical bottlenecks in forest inventory—time-consuming data acquisition, massive storage requirements, and reliance on offline post-processing. To address these limitations, this paper proposes a real-time single-tree reconstruction and inventory system tailored for mobile robotic platforms. Methodologically, we introduce a novel online framework that integrates Voronoi-inspired clustering with Hough transform for robust single-stem detection and modeling; further coupled with LiDAR SLAM–driven incremental pose optimization and dynamic point-cloud database updating, the system achieves end-to-end real-time stem detection, 3D reconstruction, and dynamic estimation of biometric attributes (e.g., diameter at breast height, DBH). Evaluated across coniferous, broadleaf, and mixed forests, the system achieves a DBH estimation RMSE of 1.93 cm and mean bias of 0.65 cm—comparable in accuracy to TLS and manual measurements—while requiring zero post-processing.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Biometrics, Face, Gesture & Pose

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Terrestrial laser scanning (TLS) is the standard technique used to create accurate point clouds for digital forest inventories. However, the measurement process is demanding, requiring up to two days per hectare for data collection, significant data storage, as well as resource-heavy post-processing of 3D data. In this work, we present a real-time mapping and analysis system that enables online generation of forest inventories using mobile laser scanners that can be mounted e.g. on mobile robots. Given incrementally created and locally accurate submaps—data payloads—our approach extracts tree candidates using a custom, Voronoi-inspired clustering algorithm. Tree candidates are reconstructed using an algorithm based on the Hough transform, which enables robust modeling of the tree stem. Further, we explicitly incorporate the incremental nature of the data collection by consistently updating the database using a pose graph LiDAR SLAM system. This enables us to refine our estimates of the tree traits if an area is revisited later during a mission. We demonstrate competitive accuracy to TLS or manual measurements using laser scanners that we mounted on backpacks or mobile robots operating in conifer, broad-leaf and mixed forests. Our results achieve RMSE of 1.93 cm, a bias of 0.65 cm and a standard deviation of 1.81 cm (averaged across these sequences)—with no post-processing required after the mission is complete.

Problem

• Real-time forest inventory using mobile laser scanners.
• Online tree reconstruction with incremental data updates.
• Competitive accuracy to TLS without post-processing.

Innovation

• Mobile robotic system for real-time forest mapping
• Voronoi-inspired clustering for tree candidate extraction
• Pose graph LiDAR SLAM for incremental data updates