The lack of updated maps on large scale representations has encouraged the use of remotely piloted aircraft systems (RPAS) to generate maps for a wide range of professionals. However, some questions arise: do the orthomosaics generated by these systems have the cartographic precision required to use them? Which problems can be identified in stitching orthophotos to generate orthomosaics? To answer these questions, an aerophotogrammetric survey was conducted in an environmental conservation unit in the city of Goiânia. The flight plan was set up using the E-motion software, provided by Sensefly—a Swiss manufacturer of the RPAS Swinglet CAM used in this work. The camera installed in the RPAS was the Canon IXUS 220 HS, with the number of pixels in the sensor array of 12.1 megapixel, complementary metal oxide semiconductor 1 ∶ 2.3 ? (4000 × 3000 pixel), horizontal and vertical pixel sizes of 1.54 μm. Using the orthophotos, four orthomosaics were generated in the Pix4D mapper software. The first orthomosaic was generated without using the control points. The other three mosaics were generated using 4, 8, and 16 premarked ground control points. To check the precision and accuracy of the orthomosaics, 46 premarked targets were uniformly distributed in the block. The three-dimensional (3-D) coordinates of the premarked targets were read on the orthomosaic and compared with the coordinates obtained by the geodetic survey real-time kinematic positioning method using the global navigation satellite system receiver signals. The cartographic accuracy standard was evaluated by discrepancies between these coordinates. The bias was analyzed by the Student’s t test and the accuracy by the chi-square probability considering the orthomosaic on a scale of 1 ∶ 250, in which 90% of the points tested must have a planimetric error of <0.13 m with a standard deviation of 0.08 m and altimetric errors of <0.30 m with a standard deviation of 0.20 m. It was observed that some buildings in the orthomosaics were not properly orthorectified. The orthomosaics generated with 8 or more points reached the scale of 1 ∶ 250, whereas without control points the scale was 10-fold smaller (1 ∶ 3000).
This paper presents a system developed by an application of a neural network Multilayer Perceptron for drone acquired agricultural image segmentation. This application allows a supervised user training the classes that will posteriorly be interpreted by neural network. These classes will be generated manually with pre-selected attributes in the application. After the attribute selection a segmentation process is made to allow the relevant information extraction for different types of images, RGB or Hyperspectral. The application allows extracting the geographical coordinates from the image metadata, geo referencing all pixels on the image. In spite of excessive memory consume on hyperspectral images regions of interest, is possible to perform segmentation, using bands chosen by user that can be combined in different ways to obtain different results.
Precision agriculture (PA) has offered a multitude of benefits to farmers, such as cost reduction, accuracy and speed in decision making. Among the tools that work with PA, the aerial image mosaics have key role in accurate mapping of diseases and pests in crops. A mosaic is the combination of multiple images, creating a new image that covers the property or plots accurately. One of the important analysis for farmers is based on the properties of the reflectance in each range of the electromagnetic spectrum of vegetation. Performing mathematical combinations of the different spectral bands has a better understanding of the spectral response of the vegetation. These combinations are called vegetation index (VI) and are useful for the control of the biomass, water content in leaf, chlorophyll content and others. It is usually calculated VI after the construction of the mosaic, as well the farmer has an accurate analysis of its vegetation. However, building a mosaic of images, it has a high computational cost, taking hours to complete and then apply the VI and to have the first test results. In order to reduce the computational cost of this process, this work aims to present a mosaic of images constructed from images with the VI already pre-calculated providing faster analysis to the farmer, given the fact that applying VI on the image came a this reduction in density image and thus have the gain in computational cost to build the mosaic.
The Interest in Unmanned Aerial Vehicles (UAVs) has grown around the world and several efforts are underway to integrate UAV operations routinely and safely into remote sensing applications, specially applied in precision agriculture. Reviewing the use of UAV in agriculture it shows limitations and opportunities. So the challenges of UAV platforms for remote sensing and precision agriculture were identified during a real case studied at a citrus area to monitor the HLB (Huanglongbing) infestation. Recommended actions for moving forward were identified and showed that is possible to use UAVs for detection of crop diseases with high precision.
The objective of this study was the spatial identification of the NDVI index and cotton yield distributions through different crop phenological stages using geostatistical methods in Goiás state, Brazil. The experiment was carried out in a commercial field with 47.4 ha, in 80x80m georeferenced grid with 74 plots. Yield monitor data and multispectral satellite images at 56 m spatial resolution were collected in a rainfed cotton field in two dates to monitor the plant vigor. Satellite images of AWiFS sensor were acquired on 08/02/2011 and 01/04/2011, during the first flowering and fruiting cotton stages, respectively, corresponding to 70 and 120DAE (days after emergence). Measures of canopy reflectance, plant height and leaf nitrogen content were determined and cotton yield was obtained by mechanical harvest in August, 2011. Data were analyzed using descriptive statistics, correlation and geostatistical analyses by building and setting semivariograms and kriging interpolation. Best correlation was found between NDVI and cotton yield at 120DAE. At first flowering, the NDVI and cotton yield showed strong spatial dependence, while for 120DAE there was no dependence, probably due to the enlargement of vegetated coverage. There were similarities in the bottom left of the study area with high values of NDVI, as well as the highest values of cotton yield due to excellent plant vigor in the cotton flowering stage. Identifications of spatial differences were possible using geostatistical methods with remote sensing data obtained from medium resolution satellite images, allowing to identify distinct stages of plant growth and also to predict the cotton yield.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.