Computer vision is increasingly used in farmers'fields and agricultural experiments to quantify important traits.Imaging setups with a sub-millimeter ground sampling distance enable the detection and tracking of p...Computer vision is increasingly used in farmers'fields and agricultural experiments to quantify important traits.Imaging setups with a sub-millimeter ground sampling distance enable the detection and tracking of plant features,including size,shape,and colour.Although today's AI-driven foundation models segment almost any object in an image,they still fail for complex plant canopies.To improve model performance,the global wheat dataset consortium assembled a diverse set of images from experiments around the globe.After the head detection dataset(GWHD),the new dataset targets a full semantic segmentation(GWFSS)of organs(leaves,stems and spikes)covering all developmental stages.Images were collected by 11 institutions using a wide range of imaging setups.Two datasets are provided:ⅰ)a set of 1096 diverse images in which all organs were labelled at the pixel level,and(ⅱ)a dataset of 52,078 images without annotations available for additional training.The labelled set was used to train segmentation models based on DeepLabV3Plus and Segformer.Our Segformer model performed slightly better than DeepLabV3Plus with a mIOU for leaves and spikes of ca.90%.However,the precision for stems with 54%was rather lower.The major advantages over published models are:ⅰ)the exclusion of weeds from the wheat canopy,ⅱ)the detection of all wheat features including necrotic and se-nescent tissues and its separation from crop residues.This facilitates further development in classifying healthy vs.unhealthy tissue to address the increasing need for accurate quantification of senescence and diseases in wheat canopies.展开更多
Pixel segmentation of high-resolution RGB images into chlorophyll-active or nonactive vegetation classes is a first step often required before estimating key traits of interest.We have developed the SegVeg approach fo...Pixel segmentation of high-resolution RGB images into chlorophyll-active or nonactive vegetation classes is a first step often required before estimating key traits of interest.We have developed the SegVeg approach for semantic segmentation of RGB images into three classes(background,green,and senescent vegetation).This is achieved in two steps:A U-net model is first trained on a very large dataset to separate whole vegetation from background.The green and senescent vegetation pixels are then separated using SVM,a shallow machine learning technique,trained over a selection of pixels extracted from images.The performances of the SegVeg approach is then compared to a 3-class U-net model trained using weak supervision over RGB images segmented with SegVeg as groundtruth masks.Results show that the SegVeg approach allows to segment accurately the three classes.However,some confusion is observed mainly between the background and senescent vegetation,particularly over the dark and bright regions of the images.The U-net model achieves similar performances,with slight degradation over the green vegetation:the SVM pixel-based approach provides more precise delineation of the green and senescent patches as compared to the convolutional nature of U-net.The use of the components of several color spaces allows to better classify the vegetation pixels into green and senescent.Finally,the models are used to predict the fraction of three classes over whole images or regularly spaced grid-pixels.Results show that green fraction is very well estimated(R^(2)=0.94)by the SegVeg model,while the senescent and background fractions show slightly degraded performances(R^(2)=0.70 and 0.73,respectively)with a mean 95%confidence error interval of 2.7%and 2.1%for the senescent vegetation and background,versus 1%for green vegetation.We have made SegVeg publicly available as a ready-to-use script and model,along with the entire annotated grid-pixels dataset.We thus hope to render segmentation accessible to a broad audience by requiring neither manual annotation nor knowledge or,at least,offering a pretrained model for more specific use.展开更多
Multispectral observations from unmanned aerial vehicles(UAVs)are currently used for precision agriculture and crop phenotyping applications to monitor a series of traits allowing the characterization of the vegetatio...Multispectral observations from unmanned aerial vehicles(UAVs)are currently used for precision agriculture and crop phenotyping applications to monitor a series of traits allowing the characterization of the vegetation status.However,the limited autonomy of UAVs makes the completion of flights difficult when sampling large areas.Increasing the throughput of data acquisition while not degrading the ground sample distance(GSD)is,therefore,a critical issue to be solved.We propose here a new image acquisition configuration based on the combination of two focal length(f)optics:an optics with f=4:2 mm is added to the standard f=8 mm(SS:single swath)of the multispectral camera(DS:double swath,double of the standard one).Two flights were completed consecutively in 2018 over a maize field using the AIRPHEN multispectral camera at 52 m altitude.The DS flight plan was designed to get 80%overlap with the 4.2 mm optics,while the SS one was designed to get 80%overlap with the 8 mm optics.As a result,the time required to cover the same area is halved for the DS as compared to the SS.The georeferencing accuracy was improved for the DS configuration,particularly for the Z dimension due to the larger view angles available with the small focal length optics.Application to plant height estimates demonstrates that the DS configuration provides similar results as the SS one.However,for both the DS and SS configurations,degrading the quality level used to generate the 3D point cloud significantly decreases the plant height estimates.展开更多
The MODIS LAI/FPAR products have been widely used in various fields since their first public release in 2000.This review intends to summarize the history,development trends,scientific collaborations,disciplines involv...The MODIS LAI/FPAR products have been widely used in various fields since their first public release in 2000.This review intends to summarize the history,development trends,scientific collaborations,disciplines involved,and research hotspots of these products.Its aim is to intrigue researchers and stimulate new research direction.Based on literature data from the Web of Science(WOS)and associated funding information,we conducted a bibliometric visualization review of the MODIS LAI/FPAR products from 1995 to 2020 using bibliometric and social network analysis(SNA)methods.We drew the following conclusions:(1)research based on the MODIS LAI/FPAR shows an upward trend with a multiyear average growth rate of 24.9%in the number of publications.(2)Researchers from China and the USA are the backbone of this research area,among which the Chinese Academy of Sciences(CAS)is the core research institution.(3)Research based on the MODIS LAI/FPAR covers a wide range of disciplines but mainly focus on environmental science and ecology.(4)Ecology,crop production estimation,algorithm improvement,and validation are the hotspots of these studies.(5)Broadening the research field,improving the algorithms,and overcoming existing difficulties in heterogeneous surface,scale effects,and complex terrains will be the trend of future research.Our work provides a clear view of the development of the MODIS LAI/FPAR products and valuable information for scholars to broaden their research fields.展开更多
基金Global wheat was directly supported by Analytics for the Australian Grains Industry(AAGI).
文摘Computer vision is increasingly used in farmers'fields and agricultural experiments to quantify important traits.Imaging setups with a sub-millimeter ground sampling distance enable the detection and tracking of plant features,including size,shape,and colour.Although today's AI-driven foundation models segment almost any object in an image,they still fail for complex plant canopies.To improve model performance,the global wheat dataset consortium assembled a diverse set of images from experiments around the globe.After the head detection dataset(GWHD),the new dataset targets a full semantic segmentation(GWFSS)of organs(leaves,stems and spikes)covering all developmental stages.Images were collected by 11 institutions using a wide range of imaging setups.Two datasets are provided:ⅰ)a set of 1096 diverse images in which all organs were labelled at the pixel level,and(ⅱ)a dataset of 52,078 images without annotations available for additional training.The labelled set was used to train segmentation models based on DeepLabV3Plus and Segformer.Our Segformer model performed slightly better than DeepLabV3Plus with a mIOU for leaves and spikes of ca.90%.However,the precision for stems with 54%was rather lower.The major advantages over published models are:ⅰ)the exclusion of weeds from the wheat canopy,ⅱ)the detection of all wheat features including necrotic and se-nescent tissues and its separation from crop residues.This facilitates further development in classifying healthy vs.unhealthy tissue to address the increasing need for accurate quantification of senescence and diseases in wheat canopies.
基金The study was partly supported by several projects including ANR PHENOME(Programme d’investissement d’avenir),Digitag(PIA Institut Convergences Agriculture Numérique ANR-16-CONV-0004),CASDAR LITERAL,and P2S2 funded by CNES.
文摘Pixel segmentation of high-resolution RGB images into chlorophyll-active or nonactive vegetation classes is a first step often required before estimating key traits of interest.We have developed the SegVeg approach for semantic segmentation of RGB images into three classes(background,green,and senescent vegetation).This is achieved in two steps:A U-net model is first trained on a very large dataset to separate whole vegetation from background.The green and senescent vegetation pixels are then separated using SVM,a shallow machine learning technique,trained over a selection of pixels extracted from images.The performances of the SegVeg approach is then compared to a 3-class U-net model trained using weak supervision over RGB images segmented with SegVeg as groundtruth masks.Results show that the SegVeg approach allows to segment accurately the three classes.However,some confusion is observed mainly between the background and senescent vegetation,particularly over the dark and bright regions of the images.The U-net model achieves similar performances,with slight degradation over the green vegetation:the SVM pixel-based approach provides more precise delineation of the green and senescent patches as compared to the convolutional nature of U-net.The use of the components of several color spaces allows to better classify the vegetation pixels into green and senescent.Finally,the models are used to predict the fraction of three classes over whole images or regularly spaced grid-pixels.Results show that green fraction is very well estimated(R^(2)=0.94)by the SegVeg model,while the senescent and background fractions show slightly degraded performances(R^(2)=0.70 and 0.73,respectively)with a mean 95%confidence error interval of 2.7%and 2.1%for the senescent vegetation and background,versus 1%for green vegetation.We have made SegVeg publicly available as a ready-to-use script and model,along with the entire annotated grid-pixels dataset.We thus hope to render segmentation accessible to a broad audience by requiring neither manual annotation nor knowledge or,at least,offering a pretrained model for more specific use.
文摘Multispectral observations from unmanned aerial vehicles(UAVs)are currently used for precision agriculture and crop phenotyping applications to monitor a series of traits allowing the characterization of the vegetation status.However,the limited autonomy of UAVs makes the completion of flights difficult when sampling large areas.Increasing the throughput of data acquisition while not degrading the ground sample distance(GSD)is,therefore,a critical issue to be solved.We propose here a new image acquisition configuration based on the combination of two focal length(f)optics:an optics with f=4:2 mm is added to the standard f=8 mm(SS:single swath)of the multispectral camera(DS:double swath,double of the standard one).Two flights were completed consecutively in 2018 over a maize field using the AIRPHEN multispectral camera at 52 m altitude.The DS flight plan was designed to get 80%overlap with the 4.2 mm optics,while the SS one was designed to get 80%overlap with the 8 mm optics.As a result,the time required to cover the same area is halved for the DS as compared to the SS.The georeferencing accuracy was improved for the DS configuration,particularly for the Z dimension due to the larger view angles available with the small focal length optics.Application to plant height estimates demonstrates that the DS configuration provides similar results as the SS one.However,for both the DS and SS configurations,degrading the quality level used to generate the 3D point cloud significantly decreases the plant height estimates.
基金supported by the National Natural Science Foundation of China[grant number 41901298]the Open Fund of State Key Laboratory of Remote Sensing Science[grant number OFSLRSS201924]+1 种基金the Open Research Fund of Key Laboratory of Digital Earth Science,Institute of Remote Sensing and Digital Earth,Chinese Academy of Sciences[grant number 2018LDE002]the Fundamental Research Funds for the Central Universities[grant number 2652018031].
文摘The MODIS LAI/FPAR products have been widely used in various fields since their first public release in 2000.This review intends to summarize the history,development trends,scientific collaborations,disciplines involved,and research hotspots of these products.Its aim is to intrigue researchers and stimulate new research direction.Based on literature data from the Web of Science(WOS)and associated funding information,we conducted a bibliometric visualization review of the MODIS LAI/FPAR products from 1995 to 2020 using bibliometric and social network analysis(SNA)methods.We drew the following conclusions:(1)research based on the MODIS LAI/FPAR shows an upward trend with a multiyear average growth rate of 24.9%in the number of publications.(2)Researchers from China and the USA are the backbone of this research area,among which the Chinese Academy of Sciences(CAS)is the core research institution.(3)Research based on the MODIS LAI/FPAR covers a wide range of disciplines but mainly focus on environmental science and ecology.(4)Ecology,crop production estimation,algorithm improvement,and validation are the hotspots of these studies.(5)Broadening the research field,improving the algorithms,and overcoming existing difficulties in heterogeneous surface,scale effects,and complex terrains will be the trend of future research.Our work provides a clear view of the development of the MODIS LAI/FPAR products and valuable information for scholars to broaden their research fields.
