Discrete Gaussian Process Representations for Optimising UAV-based Precision Weed Mapping

2025-03-10

AI Summary

This paper addresses the challenge of discretizing weed distribution maps for precision agriculture using unmanned aerial vehicles (UAVs). It systematically evaluates five Gaussian process (GP) discretization methods—quadtree, wedge partitioning, top-down/bottom-up binary space partitioning (BSP), and variable-resolution hexagonal tiling—analyzing how weed patch characteristics (size, density, coverage) influence optimal discretization choice, and proposes a scene-adaptive selection strategy. Experiments on real-world farmland data show that quadtree achieves the best overall performance; hexagonal tiling and BSP-LSE reduce mean squared error by 12.7%, improve visual similarity by 19.3%, and accelerate computation by 2.1× for large, dominant weed patches. The work overcomes two key limitations of conventional approaches: the high computational cost of orthomosaic-based mapping and the incompatibility of continuous GP models with path planning. It establishes an interpretable, efficient, and adaptive discretization paradigm for GP-driven intelligent pesticide-spraying path planning.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Accurate agricultural weed mapping using UAVs is crucial for precision farming applications. Traditional methods rely on orthomosaic stitching from rigid flight paths, which is computationally intensive and time-consuming. Gaussian Process (GP)-based mapping offers continuous modelling of the underlying variable (i.e. weed distribution) but requires discretisation for practical tasks like path planning or visualisation. Current implementations often default to quadtrees or gridmaps without systematically evaluating alternatives. This study compares five discretisation methods: quadtrees, wedgelets, top-down binary space partition (BSP) trees using least square error (LSE), bottom-up BSP trees using graph merging, and variable-resolution hexagonal grids. Evaluations on real-world weed distributions measure visual similarity, mean squared error (MSE), and computational efficiency. Results show quadtrees perform best overall, but alternatives excel in specific scenarios: hexagons or BSP LSE suit fields with large, dominant weed patches, while quadtrees are optimal for dispersed small-scale distributions. These findings highlight the need to tailor discretisation approaches to weed distribution patterns (patch size, density, coverage) rather than relying on default methods. By choosing representations based on the underlying distribution, we can improve mapping accuracy and efficiency for precision agriculture applications.

Problem

• Optimizing UAV-based weed mapping for precision agriculture.
• Comparing discretisation methods for Gaussian Process-based mapping.
• Tailoring discretisation approaches to weed distribution patterns.

Innovation

• Compares five discretisation methods for UAV mapping
• Evaluates quadtrees, wedgelets, BSP trees, hexagonal grids
• Tailors discretisation to weed distribution patterns