Adaptive Clustering for Efficient Phenotype Segmentation of UAV Hyperspectral Data
This work addresses the problem of efficient phenotype segmentation for environmental and agricultural applications using UAVs, offering an incremental improvement through adaptive clustering for edge-device deployment.
The paper tackled the challenge of processing hyperspectral data from UAVs for real-time tree phenotype segmentation by introducing the OHSLIC algorithm, which achieved superior regression accuracy and segmentation performance while significantly reducing inference time compared to existing methods.
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.