A5040788606- Remote Sensing in Agriculture
- Smart Agriculture and AI
- Leaf Properties and Growth Measurement
- Remote Sensing and LiDAR Applications
- Plant Water Relations and Carbon Dynamics
- Remote Sensing and Land Use
- Greenhouse Technology and Climate Control
- Land Use and Ecosystem Services
- Spectroscopy and Chemometric Analyses
- Plant and Fungal Species Descriptions
- Forest, Soil, and Plant Ecology in China
- Environmental and Agricultural Sciences
- Crop Yield and Soil Fertility
- Irrigation Practices and Water Management
- Horticultural and Viticultural Research
- Simulation and Modeling Applications
- Phytochemistry and Biological Activities
- Species Distribution and Climate Change
- Plant Disease Management Techniques
- Natural product bioactivities and synthesis
- Urban Heat Island Mitigation
- Ziziphus Jujuba Studies and Applications
- Phytochemical Studies and Bioactivities
- Plant Ecology and Soil Science
- Plant Taxonomy and Phylogenetics
Nanjing Agricultural University
2020-2024
China Automotive Engineering Research Institute
2024
Center for Interdisciplinary Studies
2023
Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement
2016-2022
Université d'Avignon et des Pays de Vaucluse
2021-2022
Université de Montpellier
2019-2021
Institut Agro Montpellier
2019-2021
EMMAH - Environnement Méditerranéen et Modélisation des Agro-Hydrosystèmes
2015-2021
Laboratoire d'Écophysiologie Moléculaire des Plantes sous Stress Environnementaux
2019-2021
AgroParisTech
2021
The detection of wheat heads in plant images is an important task for estimating pertinent traits including head population density and characteristics such as health, size, maturity stage, the presence awns. Several studies have developed methods from high-resolution RGB imagery based on machine learning algorithms. However, these generally been calibrated validated limited datasets. High variability observational conditions, genotypic differences, development stages, orientation makes a...
The Global Wheat Head Detection (GWHD) dataset was created in 2020 and has assembled 193,634 labelled wheat heads from 4700 RGB images acquired various acquisition platforms 7 countries/institutions. With an associated competition hosted Kaggle, GWHD_2020 successfully attracted attention both the computer vision agricultural science communities. From this first experience, a few avenues for improvements have been identified regarding data size, head diversity, label reliability. To address...
Rapid, non-destructive and accurate detection of crop N status is beneficial for optimized fertilizer applications grain quality prediction in the context precision management. Previous research on remote estimation nutrition was mostly conducted with ground-based spectral data from nadir or oblique angles. Few studies investigated performance unmanned aerial vehicle (UAV) based multispectral imagery regular views such a purpose, not to mention feasibility multi-angular images improved...
Leaf chlorophyll content (LCC) is an indicator of leaf photosynthetic capacity. It crucial for improving the understanding plant physiological status. SPAD meters are routinely used to provide instantaneous estimation in situ LCC. However, calibration meter readings into absolute measures LCC difficult, and a generic approach this conversion remains elusive. This study presents evaluation approaches that commonly converting values. We compared these using three field datasets one synthetic...
Monitoring crops with high spatio-temporal resolution satellites provides valuable observations to ensure food security in the global change context. This study focuses on estimating Green Area Index (GAI) monitor wheat a spatial of 3 m and daily satellite from SuperDove constellation. With an easier access large training datasets ground GAI measurements, improvement realism radiative transfer model simulations, choice optimal approach (data-driven or model-driven) constitutes key question...
Crop density is a key agronomical trait used to manage wheat crops and estimate yield. Visual counting of plants in the field currently most common method used. However, it tedious time consuming. The main objective this work develop machine vision based automate survey at early stages. RGB images taken with high resolution camera are classified identify green pixels corresponding plants. rows extracted connected components (objects) identified. A neural network then trained number objects...
Accurate wall-to-wall estimation of forest crown cover is critical for a wide range ecological studies. Notwithstanding the increasing use UAVs in canopy mapping, ultrahigh-resolution UAV imagery requires an appropriate procedure to separate contribution understorey from overstorey vegetation, which complicated by spectral similarity between two components and illumination environment. In this study, we investigated integration deep learning combined data photogrammetric point clouds boreal...
The number of leaves at a given time is important to characterize plant growth and development. In this work, we developed high-throughput method count the by detecting leaf tips in RGB images. digital phenotyping platform was used simulate large diverse dataset images corresponding tip labels wheat plants seedling stages (150,000 with over 2 million labels). realism then improved using domain adaptation methods before training deep learning models. results demonstrate efficiency proposed...
The extraction of desirable heritable traits for crop improvement from high-throughput phenotyping (HTP) observations remains challenging. We developed a modeling workflow named "Digital Plant Phenotyping Platform" (D3P), to access architectural HTP observations. D3P couples the Architectural model DEvelopment based on L-systems (ADEL) wheat (
Abstract Canopy light interception determines the amount of energy captured by a crop, and is thus critical to modeling crop growth yield, may substantially contribute prediction uncertainty models (CGMs). We analyzed canopy 26 wheat (Triticum aestivum) CGMs used Agricultural Model Intercomparison Improvement Project (AgMIP). Twenty-one assume that extinction coefficient (K) constant, varying from 0.37 0.80 depending on model. The other take into account illumination conditions either all...
Deep learning has been widely used for plant disease recognition in smart agriculture and proven to be a powerful tool image classification pattern recognition. However, it limited interpretability deep features. With the transfer of expert knowledge, handcrafted features provide new way personalized diagnosis diseases. irrelevant redundant lead high dimensionality. In this study, we proposed swarm intelligence algorithm feature selection [salp (SSAFS)] image-based detection. SSAFS is...
The green fraction (GF), which is the of vegetation in a given viewing direction, closely related to light interception ability crop canopy. Monitoring dynamics GF therefore great interest for breeders identify genotypes with high radiation use efficiency. accuracy estimation depends heavily on quality segmentation dataset and image method. To enhance while reducing annotation costs, we developed self-supervised strategy deep learning semantic rice wheat field images very contrasting...