Green area index (GAI), leaf chlorophyll content (LCC) and canopy chlorophyll content (CCC) are key variables that are closely related to crop growth. Concurrent and continuous monitoring of GAI, LCC and CCC is critical to keep consistency among variables and make decisions for field precision managements. Previous studies have developed several instruments and algorithms to monitor continuous GAI, while the autonomous monitoring of three variables simultaneously has been lacking. This study presents a novel algorithm to retrieve daily GAI, LCC and CCC from continuous directional observations acquired by a fixed and economic affordable multi-band spectrometer (6 bands covering red, red-edge and near infrared domains) and a photosynthetically active radiation (PAR) sensor in the field. It is composed of three main steps, corresponding to three crucial questions when retrieving variables under natural environments using multi-band spectrometer installed on a near-surface platform: diffuse fraction in each spectral band, radiometric calibration and diurnal sun variation of daily acquisitions. First, we estimated diffuse fraction in each spectral band from the relationship with PAR diffuse fraction based on simulations of the 6S atmospheric radiative transfer model. Second, we computed the relative value of each band to the reference of mean of measurements on all six bands from near-surface measurements, in place of absolute radiometric calibration to limit the influence of changing illumination conditions. In the third step, we combined PROSAIL canopy radiative transfer model and kernel-driven models to retrieved GAI, LCC and CCC from artificial neural network using above spectral diffuse fraction and diurnal multi-angle relative observations. The algorithm was evaluated over 43 IoTA (Internet of things for Agriculture) systems that were installed in 29 wheat fields in France from March to May 2019. Results showed that our method provides good estimates of GAI with root mean square error (RMSE) of 0.54, relative RMSE (RRMSE) of 26.95%, R2 of 0.86, LCC (RMSE = 12.06 μg/cm2, RRMSE = 33.34%, R2 = 0.52) and CCC (RMSE = 0.23 g/m2, RRMSE = 24.58%, R2 = 0.93). This study shows great potentials for concurrent estimates of GAI, LCC and CCC from continuous ground measurements. It will be useful over other vegetations or other near-surface platforms for simultaneous estimations of biophysical variables.
Plants density is a key information on crop growth. Usually done manually, this task can beneficiate from advances in image analysis technics. Automated detection of individual plants in images is a key step to estimate this density. To develop and evaluate dedicated processing technics, high resolution RGB images were acquired from UAVs during several years and experiments over maize, sugar beet and sunflower crops at early stages. A total of 16247 plants have been labelled interactively. We compared the performances of handcrafted method (HC) to those of deep-learning (DL). HC method consists in segmenting the image into green and background pixels, identifying rows, then objects corresponding to plants thanks to knowledge of the sowing pattern as prior information. DL method is based on the Faster RCNN model trained over 2/3 of the images selected to represent a good balance between plant development stage and sessions. One model is trained for each crop.
Results show that DL generally outperforms HC, particularly for maize and sunflower crops. The quality of images appears mandatory for HC methods where image blur and complex background induce difficulties for the segmentation step. Performances of DL methods are also limited by image quality as well as the presence of weeds. An hybrid method (HY) was proposed to eliminate weeds between the rows using the rules used for the HC method. HY improves slightly DL performances in the case of high weed infestation. A significant level of variability of plant detection performances is observed between the several experiments. This was explained by the variability of image acquisition conditions including illumination, plant development stage, background complexity and weed infestation. We tested an active learning approach where few images corresponding to the conditions of the testing dataset were complementing the training dataset for DL. Results show a drastic increase of performances for all crops, with relative RMSE below 5% for the estimation of the plant density.
The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4,700 RGB images acquired from various acquisition platforms and 7 countries/institutions. With an associated competition hosted in Kaggle, GWHD has successfully attracted attention from both the computer vision and agricultural science communities. From this first experience in 2020, a few avenues for improvements have been identified, especially from the perspective of data size, head diversity and label reliability. To address these issues, the 2020 dataset has been reexamined, relabeled, and augmented by adding 1,722 images from 5 additional countries, allowing for 81,553 additional wheat heads to be added. We would hence like to release a new version of the Global Wheat Head Detection (GWHD) dataset in 2021, which is bigger, more diverse, and less noisy than the 2020 version. The GWHD 2021 is now publicly available at this http URL and a new data challenge has been organized on AIcrowd to make use of this updated dataset.
Early-stage plant density is an essential trait that determines the fate of a genotype under given environmental conditions and management practices. The use of RGB images taken from UAVs may replace traditional visual counting in fields with improved throughput, accuracy and access to plant localization. However, high-resolution (HR) images are required to detect small plants present at early stages. This study explores the impact of image ground sampling distance (GSD) on the performances of maize plant detection at 3-5 leaves stage using Faster-RCNN. Data collected at HR (GSD=0.3cm) over 6 contrasted sites were used for model training. Two additional sites with images acquired both at high and low (GSD=0.6cm) resolution were used for model evaluation. Results show that Faster-RCNN achieved very good plant detection and counting (rRMSE=0.08) performances when native HR images are used both for training and validation. Similarly, good performances were observed (rRMSE=0.11) when the model is trained over synthetic low-resolution (LR) images obtained by down-sampling the native training HR images, and applied to the synthetic LR validation images. Conversely, poor performances are obtained when the model is trained on a given spatial resolution and applied to another spatial resolution. Training on a mix of HR and LR images allows to get very good performances on the native HR (rRMSE=0.06) and synthetic LR (rRMSE=0.10) images. However, very low performances are still observed over the native LR images (rRMSE=0.48), mainly due to the poor quality of the native LR images. Finally, an advanced super-resolution method based on GAN (generative adversarial network) that introduces additional textural information derived from the native HR images was applied to the native LR validation images. Results show some significant improvement (rRMSE=0.22) compared to bicubic up-sampling approach.
Several crops bear reproductive organs (RO) at the top of the canopy after the flowering stage, such as ears for wheat, tassels for maize, and heads for sunflowers. RO present specific architecture and optical properties as compared to leaves and stems, which may impact canopy reflectance. This study aims to understand and quantify the influence of RO on the bi-directional variation of canopy reflectance and NDVI.
Multispectral camera observations from a UAV were completed over wheat, maize, and sunflower just after flowering when the RO are fully developed and the leaf layer with only marginal senescence. The flights were designed to sample the BRDF with view zenith angles spanning from nadir to 60°and many compass directions. Three flights corresponding to three sun positions were completed under clear sly conditions. The camera was always pointing to two adjacent plots of few tenths of square meters: the RO were manually removed on one plot, while the other plot was kept undisturbed.
Results showed that the three visible bands (450 nm, 570 nm, 675 nm), and in a lesser way the red edge band (730 nm) were strongly correlated. We, therefore, focused on the 675 nm and 850 nm bands. The Bi-Directional Reflectance (BRF) of the canopy without RO shows that the BRF values were almost symmetrical across the principal plane, even for maize and sunflower canopies with a strong row structure. Examination of the BRF difference between the canopy with and without RO indicate that the RO impact canopy BRDF for the three crops. The magnitude of the impacts depends on crop, wavelength and observational geometry. These observations are generally consistent with realistic 3D reflectance simulations. However, some discrepancies were noticed, mainly explained by the small magnitude of the RO effect on canopy BRF, and the approximations made when simulating the RO layer and its coupling with the bottom canopy layer. We finally demonstrated that the RO layer impact the estimates of canopy traits such as GAI as derived from the multispectral observations.
Many plant species have distinct optical properties between upper and lower leaf faces. These differences between faces are mainly attributed to the non-homogeneous distribution of absorbing and scattering materials within the leaf depth as well as particular surface features of both epidermises. We proposed the FASPECT model which is an evolution of the PROSPECT model to describe the differences in reflectance and transmittance between leaf faces. The upper and lower epidermis layers are characterized by distinct wavelength-independent reflectivities. Leaf mesophyll is made of a palisade and a spongy parenchyma layers using two parameters that describe the distribution of pigments and leaf structure between these two layers. As compared to the original PROSPECT model that treats the two leaf faces symmetrically, six additional parameters are required to describe the differences in leaf optical…
Selection of sugar beet (Beta vulgaris L.) cultivars that are resistant to Cercospora Leaf Spot (CLS) disease is critical to increase yield. Such selection requires an automatic, fast, and objective method to assess CLS severity on thousands of cultivars in the field. For this purpose, we compare the use of submillimeter scale RGB imagery acquired from an Unmanned Ground Vehicle (UGV) under active illumination and centimeter scale multispectral imagery acquired from an Unmanned Aerial Vehicle (UAV) under passive illumination. Several variables are extracted from the images (spot density and spot size for UGV, green fraction for UGV and UAV) and related to visual scores assessed by an expert. Results show that spot density and green fraction are critical variables to assess low and high CLS severities, respectively, which emphasizes the importance of having submillimeter images to early detect CLS in field conditions. Genotype sensitivity to CLS can then be accurately retrieved based on time integrals of UGV- and UAV-derived scores. While UGV shows the best estimation performance, UAV can show accurate estimates of cultivar sensitivity if the data are properly acquired. Advantages and limitations of UGV, UAV, and visual scoring methods are finally discussed in the perspective of high-throughput phenotyping.
Authors: Kaaviya Velumani, Simon Madec, Benoit de Solan, Raul Lopez-Lozano, Jocelyn Gillet, Jeremy Labrosse, Stephane Jezequel, Alexis Comar, Frederic Baret
Accurate and timely observations of wheat phenology and, particularly, of heading date are instrumental for many scientific and technical domains such as wheat ecophysiology, crop breeding, crop management or precision agriculture. Visual annotation of the heading date in situ is a labour-intensive task that may become prohibitive in scientific and technical activities where high-throughput is needed. This study presents an automatic method to estimate wheat heading date from a series of daily images acquired by a fixed RGB camera in the field. A convolutional neural network (CNN) is trained to identify the presence of spikes in small patches. The heading date is then estimated from the dynamics of the spike presence in the patches over time. The method is applied and validated over a large set of 47 experimental sites located in different regions in France, covering three years with nine wheat cultivars.
Authors: Sylvain Jay, Frédéric Baret, Dan Dutartre, Ghislain Malatesta, Stéphanie Héno, Alexis Comar, Marie Weiss, Fabienne Maupas
The recent emergence of unmanned aerial vehicles (UAV) has opened a new horizon in vegetation remote sensing, especially for agricultural applications. However, the benefits of UAV centimeter-scale imagery are still unclear compared to coarser resolution data acquired from satellites or aircrafts. This study aims (i) to propose novel methods for retrieving canopy variables from UAV multispectral observations, and (ii) to investigate to what extent the use of such centimeter-scale imagery makes it possible to improve the estimation of leaf and canopy variables in sugar beet crops (Beta vulgaris L.). Five important structural and biochemical plant traits are considered: green fraction (GF), green area index (GAI), leaf chlorophyll content (Cab), as well as canopy chlorophyll (CCC) and nitrogen (CNC) contents.
Based on a comprehensive data set encompassing a large variability in canopy structure and biochemistry …
Total above-ground biomass at harvest and ear density are two important traits that characterize wheat genotypes. Two experiments were carried out in two different sites where several genotypes were grown under contrasted irrigation and nitrogen treatments. A high spatial resolution RGB camera was used to capture the residual stems standing straight after the cutting by the combine machine during harvest. It provided a ground spatial resolution better than 0.2 mm. A Faster Regional Convolutional Neural Network (Faster-RCNN) deep-learning model was first trained to identify the stems cross section. Results showed that the identification provided precision and recall close to 95%. Further, the balance between precision and recall allowed getting accurate estimates of the stem density with a relative RMSE close to 7% and robustness across the two experimental sites. The estimated stem density was also compared with the ear density measured in the field with traditional methods. A very high correlation was found with almost no bias, indicating that the stem density could be a good proxy of the ear density. The heritability/repeatability evaluated over 16 genotypes in one of the two experiments was slightly higher (80%) than that of the ear density (78%). The diameter of each stem was computed from the profile of gray values in the extracts of the stem cross section. Results show that the stem diameters follow a gamma distribution over each microplot with an average diameter close to 2.0 mm. Finally, the biovolume computed as the product of the average stem diameter, the stem density, and plant height is closely related to the above-ground biomass at harvest with a relative RMSE of 6%. Possible limitations of the findings and future applications are finally discussed.