Adaptive Clustering for Efficient Phenotype Segmentation of UAV Hyperspectral Data

TL;DR

This paper presents OHSLIC, an adaptive online clustering algorithm for real-time UAV hyperspectral data segmentation, improving efficiency and accuracy for environmental and agricultural applications on resource-limited devices.

Contribution

The paper introduces a novel adaptive incremental clustering framework with a lightweight neural network for real-time hyperspectral phenotyping on UAVs.

Findings

OHSLIC outperforms pixel- and window-based methods in accuracy and speed.

The adaptive clustering balances computational efficiency with segmentation quality.

The approach enables scalable deployment on edge devices for hyperspectral analysis.

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.