Ground-truthing of UAV-based remote sensing data of citrus plants
21 May 2018-Vol. 10664, pp 1066403
TL;DR: In this article, a ground-truthing of remote sensing data of citrus plants collected from UAVs is presented, which helps detect crop stresses throughout the crop season and provides information on the health of the plant.
Abstract: This paper presents the ground-truthing of remote sensing data of citrus plants collected from unmanned aerial vehicles (UAVs). The main advantage of the UAV-based remote sensing is the reduced cost and immediate availability of high resolution data. This helps detect crop stresses throughout the crop season. Near infrared (NIR) images obtained using remote sensing techniques help determine the crop performances and stresses of a large area in a short amount of time for precision agriculture, which aims to optimize the amount of water, fertilizers, and pesticides using site-specific management of crops. However, to be useful for the real-world applications, the accuracy of remote sensing data must be validated using the proven ground-based methods. UAVs equipped with multispectral sensors were flown over the citrus orchard at Cal Poly Pomona’s Spadra Farm. The multispectral/hyperspectral images are used in the determination of vegetation indices that provide information on the health of the plant. Handheld spectroradiometer, water potential meter, and chlorophyll meter were used to collect ground-truth data. Correlations between the vegetation indices calculated using airborne data and proximal sensor data are shown.
Citations
More filters
01 Jun 2018
TL;DR: In this article, the authors present the lessons learned from the ongoing investigation at Cal Poly Pomona on the effectiveness of UAV-based remote sensing technology in detecting plant stresses due to water and nutrients.
Abstract: This paper presents the lessons learned from the ongoing investigation at Cal Poly Pomona on the effectiveness of UAV-based remote sensing technology in detecting plant stresses due to water and nutrients UAVs equipped with multispectral/hyperspectral sensors and RGB cameras were flown over lettuce and citrus plants at Cal Poly Pomona’s Spadra farm The spectral sensor data were used in the determination of various vegetation indices that provide information on the water and nitrogen stresses of the plants Proximal sensors that were used for the verification of remote sensing data included water potential meter, chlorophyll meter, and handheld spectroradiometer The paper shows the relationship between the remote sensing and proximal sensor data The paper also discusses the flight test procedures, data collection methods, and lessons learned so far
11 citations
Cites background or methods from "Ground-truthing of UAV-based remote..."
...Cal Poly Pomona is currently engaged in several research projects that use UAV-based remote sensing technology and machine learning techniques for the assessment of crop health [17-22]....
[...]
...However, for the proximal sensor data, only a sample of leaves was selected from each plot or subplot [17, 19]....
[...]
...It can provide valuable information on leaf nitrogen content [17, 19]....
[...]
...Proximal sensors that we are using include handheld spectroradiometer, chlorophyll content meter, and leaf water potential meter [17, 25, 26]....
[...]
...The remote sensing data from the UAV was used in the calculation of various other vegetation indices [17, 19]....
[...]
14 May 2019
TL;DR: In this paper, a comparison between multispectral and hyperspectral data collected from UAVs in detecting citrus nitrogen and water stresses is presented, which are used in the determination of normalized differential vegetation index (NDVI), water band index (WBI), and other vegetation indices.
Abstract: This paper shows the comparison between multispectral and hyperspectral data collected from UAVs in detecting citrus nitrogen and water stresses. UAVs equipped with multispectral and hyperspectral sensors were flown over Citrus trees at Cal Poly Pomona’s Spadra Farm. The multispectral and/or hyperspectral data are used in the determination of normalized differential vegetation index (NDVI), water band index (WBI), and other vegetation indices. These indices are compared with the proximal sensor data that include handheld spectroradiometer, water potential meter, and chlorophyll meter. Correlations of multispectral and hyperspectral data with the proximal sensor data are shown.
7 citations
14 May 2019
TL;DR: The goal of the machine learning algorithms is to provide precise detection of nitrogen and water stresses on a plant level basis using just the digital images collected from UAVs, which will help reduce the cost associated with precision agriculture.
Abstract: This paper presents the development and validation of machine learning models for the prediction of water and nitrogen stresses in lettuce. Linear regression and deep learning neural networks, mainly convolutional neural networks (CNNs), are used to train the machine learning models. The data used for the training include both airborne and proximal sensor data. The airborne data used are digital images collected from unmanned aerial vehicles (UAVs) and the normalized difference vegetation index (NDVI) obtained from airborne multispectral images. Chlorophyll meter, water potential meter, and spectroradiometer are the proximal sensors used. Also used for the training are agronomic measurements such as leaf count and plant height. For the validation of the developed models, two sets of tests were performed. The first test used a set of data similar to the training data, but different from the training data. The second test used aerial images of various random lettuce plots at farms obtained from Google Maps. The second test evaluates the models’ portability and performance in an unknown environment using the data that was not collected from the experimental plot. The goal of the machine learning algorithms is to provide precise detection of nitrogen and water stresses on a plant level basis using just the digital images collected from UAVs. This will help reduce the cost associated with precision agriculture.
3 citations
TL;DR: In this paper , a multispectral camera may be used to calibrate satellite images for detecting phenology and disturbances in trees, and the correlation of the changes in a signal of top and lateral imaging proved that the contribution of the whole canopy is reflected in satellite images.
Abstract: Remote sensing of phenology is adopted as the practice in greenery monitoring. Now research is turned towards the fusion of data from various sensors to fill in the gap in time series and allow monitoring of pests and disturbances. Poplar species were monitored for the determination of the best approach for detecting phenology and disturbances. With the adjustments that include a choice of indices, wavelengths, and a setup, a multispectral camera may be used to calibrate satellite images. The image processing pipeline included different denoising and interpolation methods. The correlation of the changes in a signal of top and lateral imaging proved that the contribution of the whole canopy is reflected in satellite images. Normalized difference vegetation index (NDVI) and normalized difference red edge index (NDRE) successfully distinguished among phenophases and detected leaf miner presence, unlike enhanced vegetation index (EVI). Changes in the indices were registered before, during, and after the development of the disease. NDRE is the most sensitive as it distinguished among the different intensities of damage caused by pests but it was not able to forecast its occurrence. An efficient and accurate system for detection and monitoring of phenology enables the improvement of the phenological models’ quality and creates the basis for a forecast that allows planning in various disciplines.
1 citations
04 Jun 2022
TL;DR: This paper presents an approach towards the autonomous collaboration between unmanned aerial vehicle (UAV) and an unmanned ground vehicle (UGV) for weed classification and detection and outlines the development of an infrastructure for continued work towards a sustainable solution.
Abstract: This paper presents an approach towards the autonomous collaboration between unmanned aerial vehicle (UAV) and an unmanned ground vehicle (UGV) for weed classification and detection. The paper outlines the development of an infrastructure for continued work towards a sustainable solution. RGB and multispectral data of a strawberry crop field infested with weeds were collected from UAVs. Fully convolutional neural network (U-Net v2) was employed in an effort to create a real-time capable onsite segmentation engine. Using a combination of images collected from UAVs and highly accurate location information, target species were identified and isolated to efficiently generate a large dataset of images, which were then used to train a robust and state-of- the-art classifier. A highly sanitized dataset was used to effectively extract and augment a large amount of data without the need for manually labeling or outsourcing. The trained bounding box classifier were hosted onsite for real-time inferencing capabilities. In the proposed solution, a UAV surveys the areas of interest and transmits the images to the computing unit to detect and determine the presence of invasive weeds using the trained classifier. Positively identified locations by the UAV is stored for further investigation by the UGV. The UGV is equipped with high a precision IMU/GPS for the autonomous routing to the target location. After arriving at the target location, the UGV utilizes the onboard camera to confirm the presence of the invasive weed species. The UGV is equipped with a highly maneuverable robotic manipulator.
References
More filters
TL;DR: The low cost and very-high spatial resolution associated with the camera-UAV system may provide important information for site-specific agriculture.
Abstract: Payload size and weight are critical factors for small Unmanned Aerial Vehicles (UAVs). Digital color-infrared photographs were acquired from a single 12-megapixel camera that did not have an internal hot-mirror filter and had a red-light-blocking filter in front of the lens, resulting in near-infrared (NIR), green and blue images. We tested the UAV-camera system over two variably-fertilized fields of winter wheat and found a good correlation between leaf area index and the green normalized difference vegetation index (GNDVI). The low cost and very-high spatial resolution associated with the camera-UAV system may provide important information for site-specific agriculture.
419 citations
"Ground-truthing of UAV-based remote..." refers background in this paper
...Near infrared (NIR) images have been found to be of significant importance in determining the crop performances and stresses [4, 5]....
[...]
TL;DR: In this article, a model aircraft was used to acquire high-resolution digital images of corn, alfalfa, and soybeans from a consumer-oriented digital camera, where colored tarpaulins were used to calibrate the images and a Normalized Green-Red Difference Index (NGRDI) was used.
Abstract: Remote sensing is a key technology for precision agriculture to assess actual crop conditions. Commercial, high-spatial-resolution imagery from aircraft and satellites are expensive so the costs may outweigh the benefits of the information. Hobbyists have been acquiring aerial photography from radio-controlled model aircraft; we evaluated these very-low-cost, very high-resolution digital photography for use in estimating nutrient status of corn and crop biomass of corn, alfalfa, and soybeans. Based on conclusions from previous work, we optimized an aerobatic model aircraft for acquiring pictures using a consumer-oriented digital camera. Colored tarpaulins were used to calibrate the images; there were large differences in digital number (DN) for the same reflectance because of differences in the exposure settings selected by the digital camera. To account for differences in exposure a Normalized Green–Red Difference Index [(NGRDI = (Green DN − Red DN)/(Green DN + Red DN)] was used; this index was linearly related to the normalized difference of the green and red reflectances, respectively. For soybeans, alfalfa and corn, dry biomass from zero to 120 g m−2 was linearly correlated to NGRDI, but for biomass greater than 150 g m−2 in corn and soybean, NGRDI did not increase further. In a fertilization experiment with corn, NGRDI did not show differences in nitrogen status, even though areas of low nitrogen status were clearly visible on late-season digital photographs. Simulations from the SAIL (Scattering of Arbitrarily Inclined Leaves) canopy radiative transfer model verified that NGRDI would be sensitive to biomass before canopy closure and that variations in leaf chlorophyll concentration would not be detectable. There are many advantages of model aircraft platforms for precision agriculture; currently, the imagery is best visually interpreted. Automated analysis of within-field variability requires more work on sensors that can be used with model aircraft platforms.
412 citations
"Ground-truthing of UAV-based remote..." refers background in this paper
...The agriculture sector has seen increased use of UAVs for precision agriculture [8-11]....
[...]
TL;DR: The mission demonstrated the capability of a slow-flying UAV, equipped with downsized imaging systems and line-of-sight telemetry, to monitor a localized agricultural region for an extended time period and suggested that evolving long-duration UAVs stand to make a valuable future contribution to regional agricultural resource monitoring.
366 citations
"Ground-truthing of UAV-based remote..." refers background in this paper
...The agriculture sector has seen increased use of UAVs for precision agriculture [8-11]....
[...]
TL;DR: In this paper, a radio-controlled unmanned helicopter-based low-altitude remote sensing (LARS) platform was used to acquire quality images of high spatial and temporal resolution in order to estimate yield and total biomass of a rice crop (Oriza sativa L.).
Abstract: A radio-controlled unmanned helicopter-based low-altitude remote sensing (LARS) platform was used to acquire quality images of high spatial and temporal resolution in order to estimate yield and total biomass of a rice crop (Oriza sativa L.). Fifteen rice field plots with five N treatments (0, 33, 66, 99, and 132 kg ha-1) having three replicates each were arranged in a randomized complete block design for estimating yield and biomass as a function of applied N. Images were obtained by image acquisition sensors mounted on the LARS platform operating at the height of 20 m over experimental plots. The rice yield and total biomass for the five N treatments were found to be significantly different at the 0.05 and 0.1 levels of significance, respectively, and normalized difference vegetation index (NDVI) values at panicle initiation stage were highly correlated with yield and total biomass with regression coefficients (r2) of 0.728 (RMSE = 0.458 ton ha-1) and 0.760 (RMSE = 0.598 ton ha-1), respectively. The study demonstrated the suitability of using LARS images as a substitute for satellite images for estimating leaf chlorophyll content in terms of NDVI values (r2 = 0.897, RMSE = 0.012). The LARS system described has potential to evaluate areas that require additional nutrients at critical growth stages to improve final yield in rice cropping.
180 citations
"Ground-truthing of UAV-based remote..." refers background in this paper
...UAVs can be deployed immediately, repeatedly and they can fly at even lower altitudes than manned aircraft [12-14] for high resolution data....
[...]
TL;DR: In this article, the authors propose la technologie a taux variable (VRT) for agriculture de precision, i.e., the use of virtual reality to reduce the intrants tout en optimisant les extrants, ces deux aspects being importants for le producteur agricole.
Abstract: RESUMEL'agriculture de precision est basee sur l'integration de nouvelles technologies telles que les systemes d'information geographique (SIG), les systemes de positionnement global (GPS) et la teledetection pour permettre aux producteurs agricoles de gerer la variabilite a l'interieur d'un mente champ par opposition a l'approche traditionnelle basee sur l'analyse du champ dans son entier et ce, dans l'optique de maximiser son rapport cout-benefice. La technologie a taux variable (VRT) proposee dans la panoplie d'equipements agricoles tels que les applicateurs de fertilisants ou de pesticides et les moniteurs de rendement, a evolue rapidement et a favorise la croissance de l'agriculture de precision. La gestion basee sur un site specifique permet de reduire les intrants tout en optimisant les extrants, ces deux aspects etant importants pour le producteur agricole. Parallelement, en reduisant les intrants, on reduit le ruissellement des fertilisants et des pesticides, ameliorant ainsi la condition environ...
139 citations
"Ground-truthing of UAV-based remote..." refers background in this paper
...INTRODUCTION Remote sensing plays a key role in precision agriculture, which aims to optimize the amount of water, fertilizers, and pesticides [1, 2]....
[...]