Adaptive Clustering for Efficient Phenotype Segmentation of UAV Hyperspectral Data

2025-01-17

AI Summary

To address the fundamental trade-off between real-time performance and accuracy in unmanned aerial vehicle (UAV)-based edge hyperspectral remote sensing for agricultural phenotyping, this paper proposes a lightweight, real-time canopy phenotypic segmentation method driven by biochemical constituents—chlorophyll, carotenoids, and anthocyanins. Our approach features three key innovations: (1) an online hierarchical self-adaptive incremental clustering mechanism (OHSLIC) that dynamically balances clustering fidelity and computational overhead; (2) a synergistic inference framework integrating a lightweight neural network with clustering, enabling low-latency deployment on resource-constrained edge devices; and (3) physics-informed hyperspectral simulation modeling that incorporates leaf optical parameters and light–leaf interaction processes to enhance model generalizability. Experiments demonstrate that our method reduces regression error by 32%, improves segmentation mean Intersection-over-Union (mIoU) by 19%, and accelerates inference speed by 5.8× over conventional pixel- or window-based approaches—significantly advancing the real-time processing capability of UAV-edge platforms.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Hardware-aware ML
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Unmanned Aerial Vehicles (UAVs) combined with Hyperspectral imaging (HSI) offer potential for environmental and agricultural applications by capturing detailed spectral information that enables the prediction of invisible features like biochemical leaf properties. However, the data-intensive nature of HSI poses challenges for remote devices, which have limited computational resources and storage. This paper introduces an Online Hyperspectral Simple Linear Iterative Clustering algorithm (OHSLIC) framework for real-time tree phenotype segmentation. OHSLIC reduces inherent noise and computational demands through adaptive incremental clustering and a lightweight neural network, which phenotypes trees using leaf contents such as chlorophyll, carotenoids, and anthocyanins. A hyperspectral dataset is created using a custom simulator that incorporates realistic leaf parameters, and light interactions. Results demonstrate that OHSLIC achieves superior regression accuracy and segmentation performance compared to pixel- or window-based methods while significantly reducing inference time. The method`s adaptive clustering enables dynamic trade-offs between computational efficiency and accuracy, paving the way for scalable edge-device deployment in HSI applications.

Problem

• Real-time Processing
• Hyperspectral Data
• Plant Species Identification

Innovation

• OHSLIC
• Adaptive Clustering
• Real-time Plant Identification