The Impact of Pan-Sharpening and Spectral Resolution on Vineyard Segmentation through Machine Learning

Eriita G Jones,Holly Whittenbury,Joseph Sclauzero,Sebastien Wong,Mark D Mcdonnell,Anthony Milton

doi:10.3390/rs12060934

Eriita G Jones, Holly Whittenbury + Show 4 more

Open Access

https://doi.org/10.3390/rs12060934

Copy DOI

Journal: Remote sensing	Publication Date: Mar 13, 2020
Citations: 23	License type: CC BY 4.0

Affiliation: University of South Australia

Abstract

Precision viticulture benefits from the accurate detection of vineyard vegetation from remote sensing, without a priori knowledge of vine locations. Vineyard detection enables efficient, and potentially automated, derivation of spatial measures such as length and area of crop, and hence required volumes of water, fertilizer, and other resources. Machine learning techniques have provided significant advancements in recent years in the areas of image segmentation, classification, and object detection, with neural networks shown to perform well in the detection of vineyards and other crops. However, what has not been extensively quantitatively examined is the extent to which the initial choice of input imagery impacts detection/segmentation accuracy. Here, we use a standard deep convolutional neural network (CNN) to detect and segment vineyards across Australia using DigitalGlobe Worldview-2 images at ∼50 cm (panchromatic) and ∼2 m (multispectral) spatial resolution. A quantitative assessment of the variation in model performance with input parameters during model training is presented from a remote sensing perspective, with combinations of panchromatic, multispectral, pan-sharpened multispectral, and the spectral Normalised Difference Vegetation Index (NDVI) considered. The impact of image acquisition parameters—namely, the off-nadir angle and solar elevation angle—on the quality of pan-sharpening is also assessed. The results are synthesised into a ‘recipe’ for optimising the accuracy of vineyard segmentation, which can provide a guide to others aiming to implement or improve automated crop detection and classification.

Highlights

Viticultural practices worldwide have been transformed over the last two decades by the application of precision viticulture (PV)
This paper quantitatively investigates how the initial choices in remote sensing imagery for vine block detection impact on the resulting detection accuracy of a deep convolutional neural network, in order to identify what combination of imagery parameters optimises the resulting vine block segmentation
This work quantified the impact of initial choices in Worldview-2 remote sensing imagery– namely the wavelengths used, their spatial resolution, and, implicitly, the image acquisition parameters– on the accuracy of vineyard boundary detection via a machine learning methodology

Summary

Introduction

Viticultural practices worldwide have been transformed over the last two decades by the application of precision viticulture (PV). Before the full capabilities of remotely sensed data and PV can be realised, accurate identification and classification of vineyard boundaries (planting blocks) are frequently required. Depending on the nature of the data users (e.g., government statutory bodies, growers associations, individual vineyard managers), vineyard block identification may be required across a large spatial area. This problem can be successfully addressed using remotely sensed imagery and advanced modern computational techniques, such as artificial neural networks and other methods (e.g., [4,5,6,7,8])

Methods

Results

Discussion

Conclusion