Efficient automated U-Net based tree crown delineation using UAV multi-spectral imagery on embedded devices

TL;DR

This paper introduces an efficient U-Net based deep learning method for tree crown delineation using UAV multi-spectral imagery, optimized for real-time execution on embedded devices, with promising accuracy and resource efficiency.

Contribution

It presents a novel, resource-efficient U-Net based approach trained on multi-spectral data that can accurately delineate trees from single-spectrum images on embedded hardware.

Findings

High delineation accuracy demonstrated on UAV data

Effective model compression enables real-time processing on embedded devices

Method outperforms traditional segmentation in resource-limited settings

Abstract

Delineation approaches provide significant benefits to various domains, including agriculture, environmental and natural disasters monitoring. Most of the work in the literature utilize traditional segmentation methods that require a large amount of computational and storage resources. Deep learning has transformed computer vision and dramatically improved machine translation, though it requires massive dataset for training and significant resources for inference. More importantly, energy-efficient embedded vision hardware delivering real-time and robust performance is crucial in the aforementioned application. In this work, we propose a U-Net based tree delineation method, which is effectively trained using multi-spectral imagery but can then delineate single-spectrum images. The deep architecture that also performs localization, i.e., a class label corresponds to each pixel, has been successfully used to allow training with a small set of segmented images. The ground truth data were generated using traditional image denoising and segmentation approaches. To be able to execute the proposed DNN efficiently in embedded platforms designed for deep learning approaches, we employ traditional model compression and acceleration methods. Extensive evaluation studies using data collected from UAVs equipped with multi-spectral cameras demonstrate the effectiveness of the proposed methods in terms of delineation accuracy and execution efficiency.