Excess Green Index Research Articles

Estimation of Plant Height and Aboveground Biomass of Toona sinensis under Drought Stress Using RGB-D Imaging

Rapid and accurate plant growth and biomass estimation is essential for formulating and implementing targeted forest cultivation measures. In this study, RGB-D imaging technology was used to obtain the RGB and depth imaging data for a Toona sinensis seedling canopy to estimate plant growth and aboveground biomass (AGB). Three hundred T. sinensis seedlings from 20 varieties were planted under five different drought stress treatments. The U-Net model was applied first to achieve highly accurate segmentation of plants from complex backgrounds. Simple linear regression (SLR) was used for plant height prediction, and the other three models, including multivariate linear (ML), random forest (RF) and multilayer perceptron (MLP) regression, were applied to predict the AGB and compared for optimal model selection. The results showed that the SLR model yields promising and reliable results for the prediction of plant height, with R2 and RMSE values of 0.72 and 1.89 cm, respectively. All three regression methods perform well in the prediction of AGB estimation. MLP yields the highest accuracy in predicting dry and fresh aboveground biomass compared to the other two regression models, with R2 values of 0.77 and 0.83, respectively. The combination of Gray, Green minus red (GMR) and Excess green index (ExG) was identified as the key predictor by RReliefF for predicting dry AGB. GMR was the most important in predicting fresh AGB. This study demonstrated that the merits of RGB-D and machine learning models are effective phenotyping techniques for plant height and AGB prediction, and can be used to assist dynamic responses to drought stress for breeding selection.

A Semi-Automatic Workflow to Extract Irregularly Aligned Plots and Sub-Plots: A Case Study on Lentil Breeding Populations

Plant breeding experiments typically contain a large number of plots, and obtaining phenotypic data is an integral part of most studies. Image-based plot-level measurements may not always produce adequate precision and will require sub-plot measurements. To perform image analysis on individual sub-plots, they must be segmented from plots, other sub-plots, and surrounding soil or vegetation. This study aims to introduce a semi-automatic workflow to segment irregularly aligned plots and sub-plots in breeding populations. Imagery from a replicated lentil diversity panel phenotyping experiment with 324 populations was used for this study. Image-based techniques using a convolution filter on an excess green index (ExG) were used to enhance and highlight plot rows and, thus, locate the plot center. Multi-threshold and watershed segmentation were then combined to separate plants, ground, and sub-plot within plots. Algorithms of local maxima and pixel resizing with surface tension parameters were used to detect the centers of sub-plots. A total of 3489 reference data points was collected on 30 random plots for accuracy assessment. It was found that all plots and sub-plots were successfully extracted with an overall plot extraction accuracy of 92%. Our methodology addressed some common issues related to plot segmentation, such as plot alignment and overlapping canopies in the field experiments. The ability to segment and extract phenometric information at the sub-plot level provides opportunities to improve the precision of image-based phenotypic measurements at field-scale.

Investigating the Rainforest Canopy Phenology Variation and Productivity Responses to Drought by Using Digital Camera Images

Among the natural disturbances, drought may cause significant change in forest ecosystems by shifting phenology and productivity. Digital cameras have been used in phenological observations for their high accuracy and the colour index values (digital-number of red, green and blue) derived from long-term continuous digital camera imagery are useful as proxies for investigating a forest canopy’s response to drought. Here, we examine the interaction between colour indices (the strength of red (Sred), the strength of green (Sgreen), green excess index (GEI)), productivity (gross primary productivity (GPP)) and drought (standardised precipitation evapotranspiration index (SPEI)) and climatic factors. We use forest canopy images derived from a digital camera and flux tower-based productivity from 2010 to 2016 to show the rainforest’s responses to drought in phenology and productivity. The SPEI indicated the occurrence of drought condition in 2014. The lowest values of the SPEI (-0.403 mmday-1), and total precipitation (1062 mmyr-1), and the highest values of average air temperature (21.3 C)”, need to be changed like that “the highest values of average air temperature (21.3°C)”, to put Degree symbol between the 21.3 and C, potential evapotranspiration (3.31 mmday-1) and rain use efficiency (2.26 gCL-1) were found in 2014. Leaf color variation period (CVP) become longer with an advance in foliage green-up after drought. The peak GEI values were found at the end of the CVPs. The GPP and the Sgreen had positive and the Sred had negative relationship with drought index. The GPP dropped during the drought and bounced back after the drought due to a longer leaf CVP. The Sgreen and GEI were significantly (p<0.05) related to GPP during the drought. During the CVP of the drought, the Sgreen and GEI were significantly correlated (p<0.05) with total P, PET and average Ta, meanwhile, there was only a significant relationship (p<0.05) between the GPP with PET and avg Ta. Among the variables, the GPP was more significant (p < 0.001) with avg Ta. There was also a relationship between the colour indices and GPP with climatic factors on a yearly time series. Our results indicate an understanding of the phenology and productivity response of rainforests to drought, which might be useful for ecologists when predicting the effects of future climatic change on rainforest phenology and productivity.

RGB Indices and Canopy Height Modelling for Mapping Tidal Marsh Biomass from a Small Unmanned Aerial System

Coastal tidal marshes are essential ecosystems for both economic and ecological reasons. They necessitate regular monitoring as the effects of climate change begin to be manifested in changes to marsh vegetation healthiness. Small unmanned aerial systems (sUAS) build upon previously established remote sensing techniques to monitor a variety of vegetation health metrics, including biomass, with improved flexibility and affordability of data acquisition. The goal of this study was to establish the use of RGB-based vegetation indices for mapping and monitoring tidal marsh vegetation (i.e., Spartina alterniflora) biomass. Flights over tidal marsh study sites were conducted using a multi-spectral camera on a quadcopter sUAS near vegetation peak growth. A number of RGB indices were extracted to build a non-linear biomass model. A canopy height model was developed using sUAS-derived digital surface models and LiDAR-derived digital terrain models to assess its contribution to the biomass model. Results found that the distance-based RGB indices outperformed the regular radio-based indices in coastal marshes. The best-performing biomass models used the triangular greenness index (TGI; R2 = 0.39) and excess green index (ExG; R2 = 0.376). The estimated biomass revealed high biomass predictions at the fertilized marsh plots in the Long-Term Research in Environmental Biology (LTREB) project at the study site. The sUAS-extracted canopy height was not statistically significant in biomass estimation but showed similar explanatory power to other studies. Due to the lack of biomass samples in the inner estuary, the proposed biomass model in low marsh does not perform as well as the high marsh that is close to shore and accessible for biomass sampling. Further research of low marsh is required to better understand the best conditions for S. alterniflora biomass estimation using sUAS as an on-demand, personal remote sensing tool.

Rolling pits of Hartmann's mountain zebra (Zebra equus hartmannae) increase vegetation diversity and landscape heterogeneity in the Pre-Namib.

Microsites created by soil‐disturbing animals are important landscape elements in arid environments. In the Pre‐Namib, dust‐bathing behavior of the near‐endemic Hartmann's mountain zebra creates unique rolling pits that persist in the landscape. However, the ecohydrological characteristics and the effects of those microsites on the vegetation and on organisms of higher trophic levels are still unknown. In our study, we characterized the soil grain size composition and infiltration properties of rolling pits and reference sites and recorded vegetation and arthropod assemblages during the rainy season of five consecutive years with different amounts of seasonal rainfall. We further used the excess green vegetation index derived from drone imagery to demonstrate the different green up and wilting of pits and references after a rainfall event. In contrast to the surrounding grassland, rolling pits had finer soil with higher nutrient content, collected runoff, showed a higher infiltration, and kept soil moisture longer. Vegetation in the rolling pits was denser, dominated by annual forbs and remained green for longer periods. The denser vegetation resulted in a slightly higher activity density of herbivorous arthropods, which in turn increased the activity density of omnivorous and predatory arthropods. In times of drought, the rolling pits could act as safe sites and refuges for forbs and arthropods. With their rolling pits, Hartmann's mountain zebras act as ecosystem engineers, contributing to the diversity of forb communities and heterogeneity of the landscape in the Pre‐Namib.

Seed rain potential in late-season weed escapes can be estimated using remote sensing

AbstractThe presence of a soil seedbank facilitates the persistence of annual weed species in arable fields. Soil weed seedbank is replenished by many sources, but the largest one is the seeds produced by uncontrolled late-season weed escapes. The estimation of weed seed production potential from late-season escapes may allow farmers to make appropriate management decisions to minimize seedbank replenishment. The objective of this research was to evaluate the feasibility of using unmanned aerial vehicle–based RGB and multispectral imagery for estimating seed rain potential in late-season weed escapes in crop fields. Three case studies were used to capture images of weed escapes before crop harvest: common waterhemp [Amaranthus tuberculatus (Moq.) Sauer] in soybean [Glycine max (L.) Merr.], Palmer amaranth [Amaranthus palmeri (S.) Watson] in cotton (Gossypium hirsutum L.), and johnsongrass [Sorghum halepense (L.) Pers.] in soybean. Randomly selected quadrats with different density gradients of weed escapes were sampled at the time of crop maturity. High-resolution RGB and multispectral images of the experimental area were collected using drones immediately before ground sample collection. Normalized difference vegetation index (NDVI), excess green index (ExG), and canopy volume estimates derived from canopy height models were used to obtain weed biological measurements (biomass and seed production). Among the indices investigated, NDVI and ExG had very strong correlations (0.71 to 0.97) with weed biomass. No specific remote sensing variable was ideal across the three cases examined here, suggesting that a generalized remote sensing approach may not offer robust estimations and case-specific applications are imperative. Nonetheless, drone imagery is a powerful tool for estimating seed production from uncontrolled weed escapes and assisting with management decision making.

Recognition and counting of pitaya trees in karst mountain environment based on unmanned aerial vehicle RGB images

The counting of crop plants is an important basis for the estimation of pitaya yield. Traditional crop monitoring methods are time-consuming and laborious. The pitaya tree, one of the characteristic economic crops in the complex mountain environment, was selected as the research object. Considering the comprehensive factors such as different seasons, cloud shadow shading, crop interplanting, steep terrain, different breeds, and ages of pitaya trees, the quad-rotor unmanned aerial vehicles (UAVs) were used to collect the visible light images of the planting base of pitaya trees in the test area in karst plateau canyon region and the verification area in a complex environment. First, the characteristics of the RGB values of the eight main ground objects in the test areas are analyzed according to the color index, geometric size, and texture characteristics, which show that pitaya plants, weeds, and shrubs have certain interference with each other. Then the excess green index (ExG) of the images is calculated to enhance the vegetation characteristics and separate vegetation and non-vegetation. Gaussian high-pass filter (GHPF) is used to retain the high-frequency information of pitaya plants on the ExG images. After GHPF processing, the DN values of shrub and weeds are reduced, the edges of the area target are enhanced, and the influences of weeds and cloud shadows on plant identification are eliminated. Finally, through field measurement of pitaya plant data and OTSU, grayscale segmentation was performed on the images processed by GHPF and the pitaya plant information was extracted. Combined with the projection area of single pitaya tree, the number of pitaya trees was obtained by area screening method. The target detection percentage of test area A, test area B, and the verification area in complex environment is, respectively, 96.99%, 94.66%, and 94.30%; the quality percentage of them is, respectively, 92.46%, 90.41% and 91.50%; the branching factor of them is, respectively, 0.05, 0.05, and 0.03, proving that the RGB images collected by UAV can be used in the recognition and counting of pitaya trees in complex mountain environments. Our study can provide a reference for the application of low-cost, high-efficiency UAV visible light remote sensing to precision agriculture in complex mountain environment.

Non-destructive method of biomass and nitrogen (N) level estimation in Stevia rebaudiana using various multispectral indices

Unmanned Aerial Vehicle (UAV) based remote sensing is one of the modern techniques for crop management, which has been used in this study for biomass and Nitrogen (N) level estimations for Stevia rebaudiana, a medicinal crop used as an alternative to sugar as a natural sweetener. Different levels of nitrogen treatments were given to S. rebaudiana and the crops were harvested for biomass estimation. Mica sense Altum multispectral sensor on board was used for acquiring the image data of the crop. The linear regression model was used to examine the best vegetation index using K-fold cross validation approach. Excess Green Index (ExG) was identified as best vegetation index for biomass estimation (R2 = 0.7; RMSE = 23.77 g/m2; nRMSE = 29.14%), whereas Enhanced Normalized Difference Vegetation Index (ENDVI) was found as best predictor for Nitrogen (N) level estimation (R2 = 0.9; RMSE = 1.75 g/m2; nRMSE = 14.59%).

The importance of spectral correction of UAV-based phenotyping with RGB cameras

Spectral correction of colour (RGB) cameras mounted on unmanned aerial vehicles (UAV) is considered important to produce accurate data for quantitative studies in agricultural field research and breeding nurseries. This study investigated the extent to which a simplified spectral correction improves the precision and accuracy of early vigour assessments in winter wheat and winter barley genotypes based on the excess green vegetation Index (nExG) from a pairwise comparison of colour-corrected orthomosaics produced with two different RGB cameras. Two methods of spectral correction were compared, the empirical line method (ELM) and the spectral correction performed in a commercial photogrammetry software package (Pix4D Mapper). Both methods improved the accuracy, with the ELM spectral correction performing better than the Pix4D Mapper spectral correction. Despite high precision and improved accuracy after spectral correction, there were still statistically significant camera effects on vigour assessments because of the minute differences in nExG between genotypes. However, camera effects were evaluated as marginal and with little practical and agronomical relevance under field conditions and in breeding nurseries, as the minute differences between genotypes is overall difficult to reproduce in outdoor field experiments.

3D Change Detection of Buildings Based on Multi-level Segmentation of Dense Matching Point Clouds from UAV Images

Objectives Buildings are one of the main bodies of the city. Change information of buildings is of great significance to the investigation and treatment of illegal buildings, urban planning management and the real-time incremental updating of geographic databases. Rapid, accurate and low-cost methods of 3D change detection have received more and more attention. Methods This paper proposes a method of building change detection base on dense matching point clouds from unmanned aerial vehicle (UAV) images. First, we meshed point clouds, and analyzed the space features including normalized digital surface model (nDSM) and differential digital surface model (dDSM) and the spectral features including normalized excessive green index (nEGI) and brightness in grids. Then point clouds are segmented based on region growth, and the state of the segmentation object (changing/unchanged/uncertain) is judged. The segmentation criterion will become more and more strict for the segmented object with uncertain state until the changing state of all points is judged(taller/lower/uncertain). Finally, spatial and spectral features are integrated to identify building targets from changed objects. Results The dense matching point clouds from UAV images in two phases of Wuhan University are used to verify the experimental results of this method. The experimental results show that the integrity, accuracy and detection quality of the proposed change detection method can all reach more than 90%. Conclusions The proposed method can achieve object-level, high-precision 3D change detection of buildings based on multi-level segmentation and voting strategy.

Extraction method for single Zanthoxylum bungeanum in karst mountain area based on unmanned aerial vehicle visible-light images

The efficient and rapid extraction of information about the growth period of the Zanthoxylum bungeanum maxim is one of the prerequisites for analyzing and mastering its growth trend. The 5-cm high-resolution visible-light red, green, blue (RGB) image of the Zanthoxylum bungeanum growing period is obtained based on the low-altitude aerial photography of a quad-rotor unmanned aerial vehicle (UAV) platform. The color space of the R-, G-, and B-channels is converted into the H-, S-, L-, and V-components, and the sensitivity of seven feature vectors to target features is analyzed. The combination of the R-band, H-component, and S-component (which distinguish ground objects very differently) is obtained as the identification feature. Motivated by this, the color space index (CSI) is built by three sensitive component features, which are segmented by the maximum class variance method (OTSU), filtered by majority filtering analysis, and processed by clump to obtain spots containing only the plants. The number of single plants completely separated was calculated by ArcGIS10.2 software, and the average area of a single plant was obtained. The number of conjoined plants was obtained by dividing the cluster by the average area of a single plant. The number of separated complete plants and cluster divisions is counted to get the final total amount of plants and compared with the excess green mainstream index (EXG), visible-light band difference vegetation index (VDVI), and normalized green red difference index (NGRDI). The results indicate the following: (1) the reflectance overlapping phenomenon between ground objects is usually encountered during the construction of the index using only the RGB channel features of the visible-light band. However, the H-, S-, L-, and V-components are merged when the original image features are changed by the color space, in which the images containing only the RGB band are enriched and more conducive to finding sensitive features to distinguish between features; (2) in the CSI extraction results of three experimental research areas and one test verification area, the overall accuracy exceeded 90% (kappa index over 0.90), the false extraction rate and leakage extraction rate were <10 % , and the results showed that the CSI had an effect on the identification and extraction of Zanthoxylum bungeanum; and (3) when the growth environment of Zanthoxylum bungeanum is disturbed by weeds, the CSI has more advantages than the EXG and VDVI.

The mean value of gaussian distribution of excess green index: A new crop water stress indicator

The study proposed a new crop water stress indicator - the mean value of Gaussian distribution of excess green index for maize canopy (MGDEXG) within an RGB image. A series of RGB images were collected in a maize field under varying levels of deficit irrigation during 2013, 2015 and 2016 growth seasons in northern Colorado. To evaluate the sensitivity of MGDEXG to maize water status, canopy temperature, canopy-to-air temperature difference, crop water stress index (CWSI), leaf water potential, and sap flow were used as water status references. The results show that MGDEXG distinguished different levels of deficit irrigation treatments well and responded to the release and reimposition of deficit irrigation. The MGDEXG showed a significant correlation (p < 0.01) to different water stress references. Especially, the coefficient of determination (R2) with CWSI was 0.63 (n = 59) for 2013, 0.80 (n = 90) for 2015, and 0.80 (n = 50) for 2016. In addition, among the three Tc-based water stress indicators, the relationship between MGDEXG and CWSI was the most robust with the least annual changes of slope and intercept. The robust relationship between MGDEXG and CWSI could also show that MGDEXG was resistant to the micro-meteorological conditions within the field. Significant correlations (p < 0.01) were found between MGDEXG and leaf water potential with R2 of 0.85 and 0.87 for 2013 and 2015, and between MGDEXG and sap flow in 2015 (R2 = 0.62). MGDEXG relies only on the distribution of crop pixels within an RGB image and could be calculated easily, so it could be cheaper or easier to popularize than other crop water stress indicators in practice. Overall, our results show that MGDEXG could be successfully used as a maize water stress indicator. In the future, more field experiments are needed to further explore the changes of MGDEXG with different scale and spatial resolution of RGB images, and to evaluate MGDEXG for specific climate and crop varieties.

Assessing the Effect of Drought on Winter Wheat Growth Using Unmanned Aerial System (UAS)-Based Phenotyping

Drought significantly limits wheat productivity across the temporal and spatial domains. Unmanned Aerial Systems (UAS) has become an indispensable tool to collect refined spatial and high temporal resolution imagery data. A 2-year field study was conducted in 2018 and 2019 to determine the temporal effects of drought on canopy growth of winter wheat. Weekly UAS data were collected using red, green, and blue (RGB) and multispectral (MS) sensors over a yield trial consisting of 22 winter wheat cultivars in both irrigated and dryland environments. Raw-images were processed to compute canopy features such as canopy cover (CC) and canopy height (CH), and vegetation indices (VIs) such as Normalized Difference Vegetation Index (NDVI), Excess Green Index (ExG), and Normalized Difference Red-edge Index (NDRE). The drought was more severe in 2018 than in 2019 and the effects of growth differences across years and irrigation levels were visible in the UAS measurements. CC, CH, and VIs, measured during grain filling, were positively correlated with grain yield (r = 0.4–0.7, p &lt; 0.05) in the dryland in both years. Yield was positively correlated with VIs in 2018 (r = 0.45–0.55, p &lt; 0.05) in the irrigated environment, but the correlations were non-significant in 2019 (r = 0.1 to −0.4), except for CH. The study shows that high-throughput UAS data can be used to monitor the drought effects on wheat growth and productivity across the temporal and spatial domains.

A Fixed-Threshold Method for Estimating Fractional Vegetation Cover of Maize under Different Levels of Water Stress

Accurate estimation of fractional vegetation cover (FVC) from digital images taken by commercially available cameras is of great significance in order to monitor the vegetation growth status, especially when plants are under water stress. Two classic threshold-based methods, namely, the intersection method (T1 method) and the equal misclassification probability method (T2 method), have been widely applied to Red-Green-Blue (RGB) images. However, the high coverage and severe water stress of crops in the field make it difficult to extract FVC stably and accurately. To solve this problem, this paper proposes a fixed-threshold method based on the statistical analysis of thresholds obtained from the two classic threshold approaches. Firstly, a Gaussian mixture model (GMM), including the distributions of green vegetation and backgrounds, was fitted on four color features: excessive green index, H channel of the Hue-Saturation-Value (HSV) color space, a* channel of the CIE L*a*b* color space, and the brightness-enhanced a* channel (denoted as a*_I). Secondly, thresholds were calculated by applying the T1 and T2 methods to the GMM of each color feature. Thirdly, based on the statistical analysis of the thresholds with better performance between T1 and T2, the fixed-threshold method was proposed. Finally, the fixed-threshold method was applied to the optimal color feature a*_I to estimate FVC, and was compared with the two classic approaches. Results showed that, for some images with high reference FVC, FVC was seriously underestimated by 0.128 and 0.141 when using the T1 and T2 methods, respectively, but this problem was eliminated by the proposed fixed-threshold method. Compared with the T1 and T2 methods, for images taken in plots under severe water stress, the mean absolute error of FVC obtained by the fixed-threshold method was decreased by 0.043 and 0.193, respectively. Overall, the FVC estimation using the proposed fixed-threshold method has the advantages of robustness, accuracy, and high efficiency, with a coefficient of determination (R2) of 0.99 and root mean squared error (RMSE) of 0.02.

Estimation of SPAD value in waterlogged winter wheat based on characteristic indices of hyperspectral and digital image.

To explore the optimal monitoring method for soil and plant analyzer development (SPAD) of winter wheat under waterlogging stress based on hyperspectral and digital image techno-logy, the correlations between SPAD of the waterlogged winter wheat and fifteen indices of hyperspectral characteristic and fourteen indices of digital image feature were analyzed under a micro-plot which could be irrigated and drainage separately. Then, the BP neural network models for SPAD estimation were constructed based on the optimal monitoring feature indices. Compared with the normal winter wheat, SPAD and the value of hyperspectral reflectance did not change under short-term waterlogging (less than 7 d), whereas the SPAD was significantly decreased after more than 12 d waterlogging treatment with the value being close to zero at the late stage of growth. The estimation accuracy based on the digital image characteristics of green minus red, excess red index, norma-lized redness index and excess green index showed similar results compared to that using the BP network model based on the characteristics of the corresponding hyperspectral band. The highest R2 between the measured value and the predicted value was 0.86, while the root mean square error (RMSE) was 3.98. Compared with the BP network models built with the digital image feathers, the accuracy of the models based on the four hyperspectral characteristic indices (carotenoid reflex index, yellow edge amplitude, normalized difference vegetation index and structure insensitive pigment index) for SPAD was significantly improved, with the highest R2 of 0.97 and the lowest RMSE of 1.95. Our results suggest that both hyperspectral and digital image technology could be used to estimate SPAD value of waterlogged winter wheat and that the BP network model based on hyperspectral characteristic indices performed better in the estimation accuracy.

Greenness identification using visible spectral colour indices for site specific weed management

In the present study an attempt has been made to identify the green vegetation based on colour using visible spectral colour indices such as excess green index (ExG), excess red index (ExR) and excess green minus excess red index (ExGR). At first stage, the performance of colour indices were tested at four illumination intensities using the standard colour patches. The results indicated a clear separation between the ExG, ExR and ExGR values of green colour patches (foliage, yellow green & green) and soil colour patches (dark skin, moderate red & magenta) at illumination intensity of 89.04 ± 8.12 lux than 188.8 ± 6.36, 259.25 ± 12.73 and 359.28 ± 10.10 lux illumination intensities. This observation suggested that the colour indices might perform better at low lighting condition. In the second stage, the images of original plants and soil were captured at an illumination intensity of 89.04 ± 8.12 lux and classification rate at different threshold were studied. The average correct classification rate of ExGR and ExG colour indices were found to be 93.03% and 86.03% at threshold values 0 and 10, respectively. This indicates that the colour index ExGR could be successfully employed for image based classification of plant and non-plant material.

A Field Weed Density Evaluation Method Based on UAV Imaging and Modified U-Net

Weeds are one of the main factors affecting the yield and quality of agricultural products. Accurate evaluation of weed density is of great significance for field management, especially precision weeding. In this paper, a weed density calculating and mapping method in the field is proposed. An unmanned aerial vehicle (UAV) was used to capture field images. The excess green minus excess red index, combined with the minimum error threshold segmentation method, was used to segment green plants and bare land. A modified U-net was used to segment crops from images. After removing the bare land and crops from the field, images of weeds were obtained. The weed density was evaluated by the ratio of weed area to total area on the segmented image. The accuracy of the green plant segmentation was 93.5%. In terms of crop segmentation, the intersection over union (IoU) was 93.40%, and the segmentation time of a single image was 35.90 ms. Finally, the determination coefficient of the UAV evaluated weed density and the manually observed weed density was 0.94, and the root mean square error was 0.03. With the proposed method, the weed density of a field can be effectively evaluated from UAV images, hence providing critical information for precision weeding.

Using automated vegetation cover estimation from close-range photogrammetric point clouds to compare vegetation location properties in mountain terrain

ABSTRACT In this paper we present a low-cost approach to mapping vegetation cover by means of high-resolution close-range terrestrial photogrammetry. A total of 249 clusters of nine 1 m2 plots each, arranged in a 3 × 3 grid, were set up on 18 summits in Mediterranean mountain regions and in the Alps to capture images for photogrammetric processing and in-situ vegetation cover estimates. This was done with a hand-held pole-mounted digital single-lens reflex (DSLR) camera. Low-growing vegetation was automatically segmented using high-resolution point clouds. For classifying vegetation we used a two-step semi-supervised Random Forest approach. First, we applied an expert-based rule set using the Excess Green index (ExG) to predefine non-vegetation and vegetation points. Second, we applied a Random Forest classifier to further enhance the classification of vegetation points using selected topographic parameters (elevation, slope, aspect, roughness, potential solar irradiation) and additional vegetation indices (Excess Green Minus Excess Red (ExGR) and the vegetation index VEG). For ground cover estimation the photogrammetric point clouds were meshed using Screened Poisson Reconstruction. The relative influence of the topographic parameters on the vegetation cover was determined with linear mixed-effects models (LMMs). Analysis of the LMMs revealed a high impact of elevation, aspect, solar irradiation, and standard deviation of slope. The presented approach goes beyond vegetation cover values based on conventional orthoimages and in-situ vegetation cover estimates from field surveys in that it is able to differentiate complete 3D surface areas, including overhangs, and can distinguish between vegetation-covered and other surfaces in an automated manner. The results of the Random Forest classification confirmed it as suitable for vegetation classification, but the relative feature importance values indicate that the classifier did not leverage the potential of the included topographic parameters. In contrast, our application of LMMs utilized the topographic parameters and was able to reveal dependencies in the two biomes, such as elevation and aspect, which were able to explain between 87% and 92.5% of variance.

Seasonal behavior of vegetation determined by sensor on an unmanned aerial vehicle.

Geographic information systems make it possible to obtain fine scale maps for environmental monitoring from airborne sensors on aerial platforms, such as unmanned aerial vehicles (UAVs), which offer products with low costs and high space-time resolution. The present study assessed the performance of an UAV in the evaluation of the seasonal behavior of five vegetation coverages: Coffea spp., Eucalyptus spp., Pinus spp. and two forest remnants. For this, vegetation indices (Excess Green and Excess Red minus Green), meteorological data and moisture of surface soils were used. In addition, Sentinel-2 satellite images were used to validate these results. The highest correlations with soil moisture were found in coffee and Forest Remnant 1. The Coffea spp. had the indices with the highest correlation to the studied soil properties. However, the UAV images also provided relevant results for understanding the dynamics of forest remnants. The Excess Green index (p = 0.96) had the highest correlation coefficients for Coffea spp., while the Excess Red minus Green index was the best index for forest remnants (p = 0.75). The results confirmed that low-cost UAVs have the potential to be used as a support tool for phenological studies and can also validate satellite-derived data.

ESTIMACIÓN DE LA FRACCIÓN DE COBERTURA DE LA VEGETACIÓN EN MAÍZ (Zea mays) MEDIANTE IMÁGENES DIGITALES TOMADAS POR UN VEHÍCULO AÉREO NO TRIPULADO (UAV)

La fracción de cobertura de la vegetación es una variable importante en el monitoreo de cultivos que se relaciona con características biofísicas como la densidad, la fenología, el índice de área foliar, la germinación, la capacidad fotosintética del follaje, la evapotranspiración, la productividad y el rendimiento de los cultivos. El objetivo de este estudio fue estimar la fracción de cobertura vegetal durante el desarrollo del cultivo de maíz a partir de imágenes tomadas por un sensor que captura información en el espectro del rojo, verde y azul (RGB) montado en un vehículo aéreo no tripulado, con índices de vegetación y métodos de umbralización. Se realizaron seis vuelos, lo que generó seis ortomosaicos durante el desarrollo del cultivo. La captura de la imagen fue a 30 m de altura sobre el nivel del suelo, con resoluciones de 0.75 a 0.80 cm/pixel. Para la extracción de la vegetación y transformación de los ortomosaicos a escala de grises se emplearon cuatro índices de vegetación (IV): índice de verdor triangular (TGI), índice exceso de verde (EXG), índice de resistencia atmosférica visible (VARI) e índice de diferencia normalizado verde-rojo (NGRDI). La umbralización se realizó con los algoritmos Otsu, IsoData, Fuzzy y conservación de momentos a cada imagen en escala de grises generada con los IV para separar y clasificar los pixeles de las imágenes en dos clases, suelo y vegetación. Los índices utilizados para extraer la vegetación mostraron alta precisión en las primeras etapas de desarrollo, por lo que es posible utilizarlos para conocer la germinación, densidad y vigor inicial del cultivo. Se encontró que el índice EXG presentó errores de 2.2 a 17.8 % en la estimación de la fracción de cobertura de la vegetación durante el desarrollo del cultivo; errores menores al 5 % se obtuvieron mediante el umbral calculado con el método Fuzzy hasta los 58 días después de siembra. El uso de las imágenes digitales de alta resolución desde el vehículo aéreo no tripulado (UAV) permitió estimar la cobertura vegetal con errores menores al 5 % en las primeras etapas de desarrollo del cultivo del maíz.