Vegetation Index Images Research Articles

Novel Feature-Extraction Methods for the Estimation of Above-Ground Biomass in Rice Crops.

Traditional methods to measure spatio-temporal variations in above-ground biomass dynamics (AGBD) predominantly rely on the extraction of several vegetation-index features highly associated with AGBD variations through the phenological crop cycle. This work presents a comprehensive comparison between two different approaches for feature extraction for non-destructive biomass estimation using aerial multispectral imagery. The first method is called GFKuts, an approach that optimally labels the plot canopy based on a Gaussian mixture model, a Montecarlo-based K-means, and a guided image filtering for the extraction of canopy vegetation indices associated with biomass yield. The second method is based on a Graph-Based Data Fusion (GBF) approach that does not depend on calculating vegetation-index image reflectances. Both methods are experimentally tested and compared through rice growth stages: vegetative, reproductive, and ripening. Biomass estimation correlations are calculated and compared against an assembled ground-truth biomass measurements taken by destructive sampling. The proposed GBF-Sm-Bs approach outperformed competing methods by obtaining biomass estimation correlation of with and g. This result increases the precision in the biomass estimation by around compared to previous works.

A Comparison of LUCC Detection Algorithms in a Mesoamerican Lowland Tropical Forest

Land use and land cover changes occur throughout the world, but none is more concerning than tropical deforestation, much of it for agricultural purposes. Rural-rural frontier migrant farmers such as those colonizing the Sierra del Lacandón National Park in Petén, Guatemala act as a primary direct agent in this land cover conversion. This paper seeks to compare three different algorithms for monitoring changes in forested land cover, making use of freely available remotely sensed Landsat images from two years, 1991 and 2000. In the intervening 9 years, some forested land was converted to cropped, pasture, or fallow land, while other areas experienced no change. This paper contains a detailed description of the methods employed for three different change detection techniques, producing a total of five land change maps: multidate principal components analysis (PCA), normalized difference vegetation index (NDVI ) image differencing, and brightness greenness wetness (BGW) image differencing. Of the five land change maps produced, the Greenness component of the BGW transformation had the highest overall accuracy, at 86%, and is conservative in detecting change. The amount of change detected by this algorithm represents approximately 300 km2 of forest loss, or 11.9% of the area examined.

Tracking small-scale tropical forest disturbances: Fusing the Landsat and Sentinel-2 data record

Information on forest disturbance is crucial for tropical forest management and global carbon cycle analysis. The long-term collection of data from the Landsat missions provides some of the most valuable information for understanding the processes of global tropical forest disturbance. However, there are substantial uncertainties in the estimation of non-mechanized, small-scale (i.e., small area) clearings in tropical forests with Landsat series images. Because the appearance of small-scale openings in a tropical tree canopy are often ephemeral due to fast-growing vegetation, and because clouds are frequent in tropical regions, it is challenging for Landsat images to capture the logging signal. Moreover, the spatial resolution of Landsat images is typically too coarse to represent spatial details about small-scale clearings. In this paper, by fusing all available Landsat and Sentinel-2 images, we proposed a method to improve the tracking of small-scale tropical forest disturbance history with both fine spatial and temporal resolutions. First, yearly composited Landsat and Sentinel-2 self-referenced normalized burn ratio (rNBR) vegetation index images were calculated from all available Landsat-7/8 and Sentinel-2 scenes during 2016–2019. Second, a deep-learning based downscaling method was used to predict fine resolution (10 m) rNBR images from the annual coarse resolution (30 m) Landsat rNBR images. Third, given the baseline Landsat forest map in 2015, the generated fine-resolution Landsat rNBR images and original Sentinel-2 rNBR images were fused to produce the 10 m forest disturbance map for the period 2016–2019. From data comparison and evaluation, it was demonstrated that the deep-learning based downscaling method can produce fine-resolution Landsat rNBR images and forest disturbance maps that contain substantial spatial detail. In addition, by fusing downscaled fine-resolution Landsat rNBR images and original Sentinel-2 rNBR images, it was possible to produce state-of-the-art forest disturbance maps with OA values more than 87% and 96% for the small and large study areas, and detected 11% to 21% more disturbed areas than either the Sentinel-2 or Landsat-7/8 time-series alone. We found that 1.42% of the disturbed areas indentified during 2016–2019 experienced multiple forest disturbances. The method has great potential to enhance work undertaken in relation to major policies such as the reducing emissions from deforestation and forest degradation (REDD+) programmes.

The utilisation of sentinel-2A images and google earth engine for monitoring tropical Savannah grassland

A fast, precise and efficient method of savannah grassland mapping and monitoring is essential to support sustainable livestock feed management. This study aims to utilise Sentinel-2A Level-1C imagery to map and monitor tropical savannah grasslands on Sabu Island, Indonesia. Normalized Difference Vegetation Index (NDVI) images were generated to identify vegetation objects from 50 image scenes covering each month from 2016 to 2020 through the Google Earth Engine (GEE). Principal Component Analysis (PCA) was applied to the 50 NDVI data to produce monthly images (12 months). The grassland objects were classified from Sentinel-2A images using the parallelepiped algorithm and resulted in an overall accuracy of 82.86%. Results showed a range of the average monthly NDVI between 0.127 and 0.449, which falls within the grassland class. NDVI combined with GEE can quickly and accurately identify grasslands, creating highly recommended tools for monitoring tropical savannah grasslands.

Assessment of Aerodynamic Roughness Length Using Remotely Sensed Land Cover Features and MODIS

Wind speed profile has a significant role in environmental transport phenomena whereby Roughness length is a governing factor that determines wind speed profile. Normally, relatively crude estimates of roughness length are used in global climate models based on constant values for each specific land cover category. However, a significant variation may exist within any one of these land cover categories. For this reason, it is necessary to derive detailed roughness length distribution over areas under consideration. Satellite observations can be used to assess the details of roughness length distribution. The aim of the present study was to develop method for roughness length assessment based on remotely sensed Normalized Difference Vegetation Index (NDVI) and landscape images for the entire Iraq area. The NDVI was generated using MODIS data (MOD13Q1) at 250 m resolution acquired on 23th April 2015 for whole Iraq. And the landscape images were classified based on land use and land cover (LU/LC) that relates general classes of LU/LC and values of roughness length coefficient. Taking into consideration a specific range of NDVI values of each landscape category, a correlation analysis was used to determine the aerodynamic roughness between the values of (NDVI) and the aerodynamic roughness based on the European Wind Atlas classification and the Royal Netherlands Meteorological Institute. A quantitative relationship was set up to retrieve the aerodynamic roughness length from MODIS data (MOD13Q1) where R2 = 0.96. Experiments prove that the proposed methodology can provide accurate roughness length estimations for the spatial and temporal analysis of land surface. The findings of this study will enhance sustainability in Iraq and many other regions of the world, thus, supporting the Sustainable Development Goals (SDGs) through the establishment of wind farms especially in countries with coastal areas that can serve as a major source of the national electricity.

Vegetation Indices Data Clustering for Dynamic Monitoring and Classification of Wheat Yield Crop Traits

Monitoring the spatial and temporal variability of yield crop traits using remote sensing techniques is the basis for the correct adoption of precision farming. Vegetation index images are mainly associated with yield and yield-related physiological traits, although quick and sound strategies for the classification of the areas with plants with homogeneous agronomic crop traits are still to be explored. A classification technique based on remote sensing spectral information analysis was performed to discriminate between wheat cultivars. The study analyzes the ability of the cluster method applied to the data of three vegetation indices (VIs) collected by high-resolution UAV at three different crop stages (seedling, tillering, and flowering), to detect the yield and yield component dynamics of seven durum wheat cultivars. Ground truth data were grouped according to the identified clusters for VI cluster validation. The yield crop variability recorded in the field at harvest showed values ranging from 2.55 to 7.90 t. The ability of the VI clusters to identify areas with similar agronomic characteristics for the parameters collected and analyzed a posteriori revealed an already important ability to detect areas with different yield potential at seedling (5.88 t ha−1 for the first cluster, 4.22 t ha−1 for the fourth). At tillering, an enormous difficulty in differentiating the less productive areas in particular was recorded (5.66 t ha−1 for cluster 1 and 4.74, 4.31, and 4.66 t ha−1 for clusters 2, 3, and 4, respectively). An excellent ability to group areas with the same yield production at flowering was recorded for the cluster 1 (6.44 t ha−1), followed by cluster 2 (5.6 t ha−1), cluster 3 (4.31 t ha−1), and cluster 4 (3.85 t ha−1). Agronomic crop traits, cultivars, and environmental variability were analyzed. The multiple uses of VIs have improved the sensitivity of k-means clustering for a new image segmentation strategy. The cluster method can be considered an effective and simple tool for the dynamic monitoring and assessment of agronomic traits in open field wheat crops.

Ecological Monitoring with Spy Satellite Images—The Case of Red Wood Ants in Romania

Dynamics of habitat conditions drive important changes in distribution and abundance of animal species making monitoring an important but also a challenging task when data from the past are scarce. We compared the distribution of ant mounds in the 1960s with recent inventories (2018), looking at changes in canopy cover over time, in a managed forest. Both historical and recent sources of information were used. Habitat suitability at present was determined using a Normalized Difference Vegetation Index (NDVI) image as a proxy for stand canopy cover. The NDVI product was obtained using Google Earth Engine and Sentinel 2 repository. For past conditions (no spectral information available), presence of edges and more open canopies was assessed on a Corona spy-satellite image and based on information from old forest management plans. A threshold distance of 30 m was used to assess location of ant nests compared to favorable habitats. Both old and new information sources showed that ants prefer intermediate canopy cover conditions in their vicinity. Nests remained clustered because of the heterogeneous habitat conditions, but spatial distribution has changed due to canopy alteration along time. The analysis on the NDVI was effective for 82% of cases (i.e., nests occurred within 30 m from favorable habitats). For all the remaining nests (18%), the Google Earth high resolution satellite image revealed in their vicinity the presence of small canopy gaps (undetected by the NDVI). These results show that historical satellite images are very useful for explaining the long-term dynamics of ant colonies. In addition, the use of modern remote sensing techniques provides a reliable and expedite method in determining the presence of favorable small-scale habitat, offering a very useful tool for ecological monitoring across large landscapes and in very different areas, especially in the context of ecosystem dynamics driven and exacerbated by climate change.

Automatically selecting hot and cold pixels for satellite actual evapotranspiration estimation under different topographic and climatic conditions

The persistent monitoring of evapotranspiration (ET) over the regions suffering from water scarcity is critical for sustainable agricultural water management. Remote sensing provides time- and cost-effective capability to investigate daily ET rates at large scales. Satellite-based actual evapotranspiration (ETa) algorithms typically rely on specifying the upper and lower boundaries of ETa rate over agricultural and pasture fields, commonly known as hot (dry) and cold (wet) pixels selection. These boundaries are to be recognized by an expert through a subjective and labor-intensive task. In this study, a method has been introduced to automatically select appropriate anchor pixels (i.e., hot and cold pixels) independent from land use/cover maps with the simplest possible way, quickly applied even by an inexperienced operator. Subsequently, ETa was calculated using Mapping EvapoTranspiration at high Resolution with Internalized Calibration (METRIC), Surface Energy Balance Algorithm for Land (SEBAL), and Surface Energy Balance System (SEBS) algorithms and evaluated against measured data. In this method, the mountains and foothills were removed using the Shuttle Radar Topography Mission Digital Elevation Model (SRTM DEM) and the subsequent product was a slope mask. Then, filters were applied based on the Normalized Difference Vegetation Index (NDVI), Albedo, and Land Surface Temperature (LST) images to identify potential candidate pixels for hot and cold pixels. In the end, the best-conditioned pixel being closest to the meteorological station was selected. The method was assessed in five different regions with different topographic and climatic conditions. The selected pixels were first visually validated in Landsat images, and then the fluctuations and values were discussed in time series of anchor pixels and LST histograms. The visual interpretation was indicative of selecting the anchor pixels in fallow (hot pixel) and densely vegetated (cold pixel) surfaces. Also, the hot and cold pixels were suitably situated in the upper and lower quartiles of the LST histogram, respectively. The range of cold pixels variations throughout the study periods was lower compared with the hot pixels (44.2, 55.3, 35.5, 66.5, and 25.2 K for hot pixels against 34.2, 45.7, 25.6, 52.2, and 17 K for cold pixels) as expected, which emanated from the lower fluctuations of temperature over vegetation against the soil. The results were indicative of the better performance of METRIC compared with SEBAL and SEBS with greater values of R2 in all the regions. Therefore, using the introduced method, the expert subjective interference was eliminated and processing time reduced significantly from about 1 h per image to a few minutes.

Estimating winter wheat straw amount and spatial distribution in Qihe County, China, using GF-1 satellite images

Crop straw is considered an important renewable energy source. China produces approximately one billion tons of crop straw annually, but 35% of this yield is not used effectively. In this study, a novel method for estimating the regional winter wheat straw yield was developed to promote straw resource recovery. Medium resolution (16 m) GF-1 satellite images of Qihe County were obtained. A weighted normalized difference vegetation index (WNDVI) image of winter wheat based on time-series normalized difference vegetation index values was generated by weighting samples to distinguish winter wheat from other land cover types, such as woodland, bare land, water, settlement, and other cultivated land. Four kernel functions of support vector machines (SVMs) were used for image classification. The linear kernel function with the highest accuracy was selected to construct the extraction model of the winter wheat plantation area in the Qihe County, Shandong Province, China, and the estimation method for total theoretical resources and spatial distribution of winter wheat straw in the region was established. The results show that the winter wheat straw in the Qihe County was mainly concentrated in the central and southern regions followed by the northern region; the central urban districts in the central-north region had the lowest straw concentration. The theoretical total quantity of straw resources of winter wheat in the county was 690 497 t; and the theoretical recoverable resource quantity was 504 063 t. The error between the estimated data and statistical data was only 1.27%, indicating that SVM and WNDVI can accurately identify winter wheat and estimate the spatial distribution of winter wheat straw in Qihe County.

Využitie UAV snímok na poloautomatickú detekciu výpadkov viniča vo vinohradoch Jelenca a Topoľčianok (Slovensko)

The use of UAV (Unmanned Aerial Vehicles) in precision viticulture leads to a more flexible and efficient approach to vineyard management. Images from UAV help determine the condition of the vineyard. Identification of the missing roots of the vineyard in a row by semi-automatic image classification and its comparison with manual classification is a goal of the paper. This study presents a new methodology for the segmentation of vine and row gaps. RGB (Red-Green-Blue) images, multispectral images, Near-Infrared (NIR) images, and Normalized Differential Vegetation Index (NDVI) images were tested and compared with manual classification. The percentage of row gap and the accuracy of individual images were determined. Object-oriented classification of the vine and row gaps in the buffer zone of the vineyard is a core of our method. Using geostatistical methods, such as zonal and logistic regression statistics, the accuracy of individual data in buffer zones was evaluated. Areas of interest were parts of vineyards in Jelenec and Topoľčianky. Success of the method detectomg outage (compared to manual classification) was achieved by images in the RGB spectrum: 96.45% for the Jelenec vineyard and 82.61% for the Topoľčianky vineyard. By this method, we quickly determine row gaps/vine which can be used to optimize or reduce the application of fertilizers to be used only on the vine. The method can be also used by inspection authorities to reveal the actual condition of the vineyard.

Impact of meteorological drought on vegetation in non-irrigated lands

Drought is a natural phenomenon that causes a lot of damages annually in various sectors, including agriculture and natural resources. The aim of this study is to evaluate the influence of meteorological drought index on vegetation index. For this purpose, the standard precipitation index (SPI) as a meteorological drought index is calculated using the precipitation data of 28 meteorological stations located on the area of Lorestane province, Iran, during the years 1987–2017. Then, the vegetation condition index (VCI) is computed using normalized difference vegetation index (NDVI) images that obtained from MODIS images of Terra satellite during 2000–2017. Dry, normal, and wet years were obtained based on the SPI results for 2008, 2013, and 2016, respectively. SPI and VCI were correlated using Pearson's correlation method. The results of the relationship between VCI and SPI showed that the highest Pearson correlation coefficient related to 9-month SPI in November was equal to 0.64. Multivariate linear regression was also performed between SPI and VCI, and the results showed that SPI was significantly correlated with VCI at 5% level over a period of 9 and 12 months. Finally, a confusion matrix was used to evaluate the compliance of the SPI and VCI drought classes. Results showed that the VCI had the highest compliance in the moderate drought class with SPI.

Using UAV images for semiautomatic detection of row-gaps in vineyards in Jelenec and Topoľčianky (Slovakia)

The use of UAV (Unmanned Aerial Vehicles) in precision viticulture leads to a more flexible and efficient approach to vineyard management. Images from UAV help determine the condition of the vineyard. Identification of the missing roots of the vineyard in a row by semi-automatic image classification and its comparison with manual classification is a goal of the paper. This study presents a new methodology for the segmentation of vine and row gaps. RGB (Red-Green-Blue) images, multispectral images, Near-Infrared (NIR) images, and Normalized Differential Vegetation Index (NDVI) images were tested and compared with manual classification. The percentage of row gap and the accuracy of individual images were determined. Object-oriented classification of the vine and row gaps in the buffer zone of the vineyard is a core of our method. Using geostatistical methods, such as zonal and logistic regression statistics, the accuracy of individual data in buffer zones was evaluated. Areas of interest were parts of vineyards in Jelenec and Topoľčianky. Success of the method detectomg outage (compared to manual classification) was achieved by images in the RGB spectrum: 96.45% for the Jelenec vineyard and 82.61% for the Topoľčianky vineyard. By this method, we quickly determine row gaps/vine which can be used to optimize or reduce the application of fertilizers to be used only on the vine. The method can be also used by inspection authorities to reveal the actual condition of the vineyard.

Disentangling the effects of hydro-climatic factors and land use intensification on wetland vegetation dynamics in the Lower Delta of the Paraná River

The non-insular portion of the Lower Delta of the Paraná River is part of the largest mosaic of wetlands in Argentina. However, it is being altered by intensification of cattle grazing and the increasingly rapid implementation of water management infrastructure. In this context, studying the relationship between hydro-climatic variables and vegetation growth is urgent to ensure sound management and conservation. To overcome the limitation of high cloud cover in the area which has hampered the construction of regularly spaced high-resolution time series, we implemented the recently developed spatio-temporal vegetation index image fusion model (STVIFM). In order to understand the relationship between vegetation growth and hydro-climatic factors, we performed pixel-wise correlation analyses between the newly synthesized monthly (30m) NDVI time series and hydro-climatic variables. Then, we tested whether water control infrastructure alters these relationships. Based on the accurate performance of STVIFM, we provide quantitative and spatially accurate evidence on the positive, complementary and heterogeneous relationships between vegetation growth, temperature, rainfall and the flood pulse. Our results show that water management infrastructure decouples certain areas from its natural hydrological regime, decreasing water availability and altering vegetation growth dynamics. In this context, urgent action is needed aimed towards implementing land planning measures that consider the natural variability and hydrologic regime of the system while balancing production and conservation.

Development of a Stereo NDVI Imaging System Using Raspberry Pi

Multispectral imagery for sensing applications are very pricey and sometimes not available. Thispaper shows the development of an imaging system that captures near infrared light and visible lightto produce a Normalized Difference Vegetation Index (NDVI) image. It utilizes the Raspberry Pimicrocomputer which was capable of performing different image processing techniques to processimages captured by the multi-spectral band digital cameras. The system applied image rectification,and stereo correspondence prior to calculation of the NDVI. Images produced were validated and are70 percent comparable to an existing system.

Weed Pixel Level Classification Based on Evolving Feature Selection on Local Binary Pattern With Shallow Network Classifier

This paper proposes an evolving feature selection on a rotation-invariant Local Binary Pattern (LBP) with genetic algorithm (GA) and a non-linear classifier to perform pixel-wise classification on biomass pixels. Early true leaf growth of carrots and weeds consists of 60 images provided by a public benchmark Crop/Weed Field Image Dataset (CWFID) [1] was used. The GA encodes LBP feature parameters generated from normalized difference vegetation index (NDVI) image slices as genome consisting of number of neighbours, radius, size of image slice, number of LBP combinations. LBP is a lightweight rotation invariant texture feature descriptor which encodes discriminative local texture information between crops and weeds. The study evaluated multiple ensemble models evolved by GA, where GA evolves the LBP feature parameter selection, and the number of LBP features as input variables used. The classifier can handle crop and weed overlaps, which are often present in commercial fields. Weeds often grow in close proximity and overlap crops and are similar in size, which adds complexity in discriminating them. Our experiments have shown that combinations with a back-propagation neural network with a symmetrical two hidden-layer network achieved the best classification accuracy when compared to other non-linear classifiers. By utilizing a single type of feature (LBP texture feature), our resulting Artificial Neural Network (ANN) ensemble classifier is able to achieve a classification accuracy of 83.5 %.

The Use of LSTM-Based RNN and SVM Models to Detect Ludian Coseismic Landslides in Time Series Images

With the increase of temporal frequency of satellite images, time series analysis based on Artificial Neural Network has become a tendency to detect land cover changes in images. We briefly introduces a case study that uses Long-Short Term Memory (LSTM), a specific Recurrent Neural Network (RNN) for time series modelling and forecasting, and Support Vector Machine (SVM) to detect landslides triggered by Ms.6.5 earthquake in Ludian, China in 2014. The study uses 72 available images with 16/30m spatial resolution from Landsat-7/8, GaoFen-1 and HJ-1A/1B satellites. Firstly, per-pixel LSTM models are trained by Normalized Difference Vegetation Index (NDVI) images before the earthquake. Secondly, the trained LSTM models are used to predict NDVI images after the earthquake. Then, anomalies or changes are detected by comparing predicted and observed NDVI images. Finally, anomalies related to landslides are separated from other changes with a SVM model which was trained by multi-spectral images in the study area. Experiment demonstrates that the recall rate and precision rate of landslides detection are 82.09% and 76.21%, respectively. The study shows a potential that the combination of LSTM and SVM models can be used to detect landslides in Landsat-like time series images with 30m resolution.

Remote Sensing-Informed Zonation for Understanding Snow, Plant and Soil Moisture Dynamics within a Mountain Ecosystem

In the headwater catchments of the Rocky Mountains, plant productivity and its dynamics are largely dependent upon water availability, which is influenced by changing snowmelt dynamics associated with climate change. Understanding and quantifying the interactions between snow, plants and soil moisture is challenging, since these interactions are highly heterogeneous in mountainous terrain, particularly as they are influenced by microtopography within a hillslope. Recent advances in satellite remote sensing have created an opportunity for monitoring snow and plant dynamics at high spatiotemporal resolutions that can capture microtopographic effects. In this study, we investigate the relationships among topography, snowmelt, soil moisture and plant dynamics in the East River watershed, Crested Butte, Colorado, based on a time series of 3-meter resolution PlanetScope normalized difference vegetation index (NDVI) images. To make use of a large volume of high-resolution time-lapse images (17 images total), we use unsupervised machine learning methods to reduce the dimensionality of the time lapse images by identifying spatial zones that have characteristic NDVI time series. We hypothesize that each zone represents a set of similar snowmelt and plant dynamics that differ from other identified zones and that these zones are associated with key topographic features, plant species and soil moisture. We compare different distance measures (Ward and complete linkage) to understand the effects of their influence on the zonation map. Results show that the identified zones are associated with particular microtopographic features; highly productive zones are associated with low slopes and high topographic wetness index, in contrast with zones of low productivity, which are associated with high slopes and low topographic wetness index. The zones also correspond to particular plant species distributions; higher forb coverage is associated with zones characterized by higher peak productivity combined with rapid senescence in low moisture conditions, while higher sagebrush coverage is associated with low productivity and similar senescence patterns between high and low moisture conditions. In addition, soil moisture probe and sensor data confirm that each zone has a unique soil moisture distribution. This cluster-based analysis can tractably analyze high-resolution time-lapse images to examine plant-soil-snow interactions, guide sampling and sensor placements and identify areas likely vulnerable to ecological change in the future.

Delineation of Crop Field Areas and Boundaries from UAS Imagery Using PBIA and GEOBIA with Random Forest Classification

Unmanned aircraft systems (UAS) have been proven cost- and time-effective remote-sensing platforms for precision agriculture applications. This study presents a method for automatic delineation of field areas and boundaries that uses UAS multispectral orthomosaics acquired over 7 vegetated fields having a variety of crops in Prince Edward Island (PEI). This information is needed by crop insurance agencies and growers for an accurate determination of crop insurance premiums. The field areas and boundaries were delineated by applying both a pixel-based and an object-based supervised random forest (RF) classifier applied to reflectance and vegetation index images, followed by a vectorization pipeline. Both methodologies performed exceptionally well, resulting in a mean area goodness of fit (AGoF) for the field areas greater than 98% and a mean boundary mean positional error (BMPE) lower than 0.8 m for the seven surveyed fields.

DETECTING AND COUNTING ORCHARD TREES ON UNMANNED AERIAL VEHICLE (UAV)-BASED IMAGES USING ENTROPY AND NDVI FEATURES

Abstract. Multispectral images were acquired by a camera on board an Unmanned Aerial Vehicle (UAV) over two apple orchards in Prince Edward Island in summer 2016. A method was developed to automatically detect rows of planted trees and trees in each row using the normalized difference vegetation index (NDVI) image and its related entropy and variance images. The image-based tree position was then compared to the actual tree location measured in the field. We achieved an accuracy of 93% between the estimated and measured number of trees in both orchards.

Improvement of Vegetation Index Image Simulations by Applying Accumulated Temperature

Improvement of Vegetation Index Image Simulations by Applying Accumulated Temperature