Leaf Area Index Estimation in Vineyards From Uav Hyperspectral Data, 2d Image Mosaics and 3d Canopy Surface Models

Abstract

Commission I,WG ICWG I/Vb KEY WORDS: Precision agriculture, biomass, crop, narrow band indices ABSTRACT:The indirect estimation of leaf area index (LAI) in large spatial scales is crucial for several environmental and agricultural applications. To this end, in this paper, we compare and evaluate LAI estimation in vineyards from different UAV imaging datasets. In particular, canopy levels were estimated from i.e., (i) hyperspectral data, (ii) 2D RGB orthophotomosaics and (iii) 3D crop surface models. The computed canopy levels have been used to establish relationships with the measured LAI (ground truth) from several vines in Nemea, Greece. The overall evaluation indicated that the estimated canopy levels were correlated (r 2 >73%) with the in-situ, ground truth LAI measurements. As expected the lowest correlations were derived from the calculated greenness levels from the 2D RGB orthomosaics. The highest correlation rates were established with the hyperspectral canopy greenness and the 3D canopy surface models. For the later the accurate detection of canopy, soil and other materials in between the vine rows is required. All approaches tend to overestimate LAI in cases with sparse, weak, unhealthy plants and canopy.

Allometric Method to Estimate Leaf Area Index for Row Crops

“…Mathews and Jensen (2013) compared LAI estimated by a digital camera aboard an unmanned aerial vehicle to indirect, ground-based estimates of LAI using a ceptometer for vineyards, and reported r 2 = 0.57. Kalisperakis et al (2015) also estimated LAI of vineyards using an unmanned aerial vehicle, but they used both digital photography and hyperspectral sensors, and compared LAI estimated by remote sensing to Table 7. Discrepancies between measured and calculated LAI for each allometric model tested.…”

“…Nonetheless, studies using unmanned aerial vehicles, high spatial resolution satellites, active lasers, and novel algorithms have demonstrated that remote sensing can provide meaningful LAI estimates (provided these can be tied to minimal groundtruth estimates). Some examples include row crops (Marshall and Thenkabail, 2015;Kross et al, 2015), vineyards (Mathews and Jensen, 2013;Kalisperakis et al, 2015), spruce forests (Solberg et al, 2009), and rugged terrain dominated by mixed pine forests (Morsdorf et al, 2006).…”

Detection and Segmentation of Vine Canopy in Ultra-High Spatial Resolution RGB Imagery Obtained from Unmanned Aerial Vehicle (UAV): A Case Study in a Commercial Vineyard

“…[15] estimated the leaf area index (LAI) of a vineyard with a conventional digital camera (Canon PowerShot) mounted on a micro-UAV using the structure from motion (SfM) technique. In the same way, [16] estimated LAI of a vineyard using data from a hyperspectral camera (VNIR imaging sensor) and a low-cost standard RGB camera (GoPro Hero3) onboard a UAV system. In this study, the determination coefficient (r 2 ) for the relationship between ground truth LAI and 2D GRVI map from the aerial RGB ortho-mosaic was 0.73.…”

“…Furthermore, the vineyards can be frequently surveyed to study ongoing phenomena at different phenological stages. Recent studies have demonstrated that high-resolution RGB images obtained by low-cost cameras can be used to monitor spatial variability of vine biophysical parameters [15,16]. Nevertheless, for an accurate evaluation of vineyard attributes from very high-resolution RGB imagery, automated procedures are required to rapidly extract the information coming from the vegetation (vine canopy pixels).…”

Land Cover Classification Using a Uav-Borne Spectrometer

“…Thermal imager and hyperspectral sensor in visible-NIR bands have been used on fixed wing and quadcopter platforms (Buettner and Roeser, 2013;Chrétien et al, 2015). UAS hyperspectral imagery has been used for leaf area index estimation (Kalisperakis et al, 2015;Proctor and He, 2015), while UAS thermal images have been used to monitor stream temperatures (Jensen et al, 2012) and roof heat losses (Zhang et al, 2015).…”