Phenocams that capture images of a given area in the RGB or near-infrared (NIR) spectrum have been used for more than a decade to estimate phenology in natural landscapes and crop fields. The aim of our study is to estimate phenological parameters, start (SOS) and end (EOS) of season, for barley, from RGB and NIR Phenocam and compare them with in-situ observations from two sites, one with growing season 2014/2015 and the other with growing season 2021/2022. Time series of Phenocam Green Chromatic Coordinate (GCC) and Normalized Difference Vegetation Index (NDVI) were computed then scaled to Harmonized Landsat-8 and Sentinel-2 surface (HLS), available for both sites, and Sentinel-2 (S2), available for only one site, datasets. The HLS and S2 datasets were gap filled with classical and machine learning methods before the scaling. Phenological parameters were extracted from the scaled GCC and NDVI Phenocam data and from the gap filled HLS and S2 datasets. Our preliminary results show that the SOS can be modelled with one day difference compared with the in-situ observed with the scaled Phenocam NDVI and a week difference compared with the in-situ observed with gap filled HLS and S2 datasets with both vegetation indices.
Parametric and nonparametric regression methods have been proven to successfully retrieve crop canopy parameters. However, once those models are calibrated for certain crops or geographical place their applicability to other crops and places is still unclear and it is an important consideration in an operational context. The tested models are parametric with two or three bands Vegetation Indices and different fitting functions and nonparametric linear and non-linear kernel based. The studied crop canopy parameters are aboveground fresh and dry biomass, vegetation fraction, mean plant height and nitrogen concentration in biomass. For calibration of the models, in-situ data from winter rapeseed and wheat crops with bare soil pixel added and remote sensing data from Sentinel-2 is used. In this study two different scenarios are considered in order to determine the applicability of both types of models for rapeseed and wheat crop parameters retrieval: 1) When applying models to the crop and period they are calibrated for: only the models for wheat before and after winter period give very good results for all studies parameters. Gaussian Processes Regression and its Variational Heteroscedastic variant with dimensionality reduction are the best performing for most of the parameters’ retrieval. Three bands Vegetation Index are the best parametric methods; 2) When applying the models to the crop and period they are not calibrated for: no model gives satisfactory results for any of the studied parameters.
Accurately monitoring agriculture with satellite data is in constant demand. However, correctly relating the satellite data to ground data is not a trivial task. This study explores the possibility to use RGB digital images as ground truth in remote estimation of the flowering duration for the winter rapeseed crop (Brassica napus). I used a DJI Phantom 3 Advanced drone and camera. The flowering of the rapeseed crop is characterized by a very distinctive yellow color. The beginning and end of flowering is not an exact notion, but a user estimated one, based on the percentage of the flowering plants in the study area. Therefore, the aim is to pixel segment the acquired RGB digital images and identify the flowering pixels. The RGB color model is transformed into a Hue Saturation Value (HSV) color model that decouples the intensity information from the color information in the image. This transformation is used to improve the image classification in variable lighting conditions. Unsupervised image classification on the color transformed images gives satisfactory results in identifying the flowering pixels in the image in full and end flowering, if the images are taken under cloudless sky. The estimation of the results is done by visual user check. The experiment started after the beginning of flowering therefore this part will be performed and evaluated during the next flowering period.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.