Spanish scientists have designed a mechanism that by simulating human sight generates 3D maps of agricultural land, as well as a system that can apply herbicides only on those plots where they are needed.
Both innovations have been put forward by researchers from the UPV (Universidad Politécnica de Valencia) and the UCM (Universidad Complutense of Madrid), respectively, and are within the field of Precision Agriculture, a new discipline that tries to optimise farm management from an agronomic, economic and environmental point of view.
The methodology used to produce the three-dimensional maps, published recently in the Computers and Electronics in Agriculture journal, has been developed by Francisco Rovira Más from the department of Mechanisation and Agrarian Technology of the UPV, together with scientists from the University of Illinois (USA). Rovira explains to SINC that global maps are essential in Precision Agriculture, i.e. maps that use GNSS (Global Navigation Satellite Systems) techniques, with the traditional East and North co-ordinates. His team proposes to add a third dimension, altitude, and a level of detail “only attainable by means of local positioning systems that use cameras”.
In order to create these three-dimensional maps, a stereoscopic camera and sensors providing localisation and orientation data for the vehicle are installed by the researchers in a farm vehicle (a tractor or combine-harvester, for example). The images obtained by the camera are those that simulate human sight, as they enable at least two different simultaneous images to be obtained. When they are compared the distance at which the objects that appear within the field of vision of the camera can be estimated. “If the objects are very far away from the camera, they will occupy practically the same position in both images, but if they are near the camera, the differences will be greater”, explains Rovira Más.
With respect to the sensors, a GPS localisation sensor is used that allows the vehicle to be situated in real time within the system of co-ordinates, together with a sensor called “an inertial measurement unit”, to estimate their positions and speeds, as well as their gradient.
The scenes of the area captured by the camera are transformed into information that generates 3D point clouds. “The huge quantity of data these clouds involve, together with the lack of precision of the sensors, are the main challenges to overcome”, says the researcher. Moreover, he adds, the global maps give a plethora of information in real time for applications such as automatic guided vehicles, an improvement in safety measures, the monitoring of the increase in harvests or the planning of agricultural tasks according to local conditioning and climate factors (temperature, humidity, wind, quality of the soil, size and plant variety, historic yield data, etc.)
Herbicide only where it is needed
Moreover in Computers and Electronics in Agriculture, and other journals, such as Pattern Recognition, a new proposal has been published about Precision Agriculture focusing on the selective use of herbicides. Gonzalo Pajares, a lecturer in the Department of Software Engineering and Artificial Intelligence at the Faculty of Information Technology at the UCM, and one of the authors of the study, explains that this involves an intelligent system “based on the computerised vision to identify areas infested with weeds that require treatment with herbicides”.
The procedure is based on the analysis of the digital image sequences, captured by camera, of the field that is going to be treated. The method involves two stages: The division of the images into field parcels, and the decision about which of the parcels must be sprayed or not, and in what quantity. The choice is achieved by using Artificial Intelligence processes, that is to say “multi-attribute decision making”, a mathematical technique that enables a choice to be made between two finite alternatives. “This allows for doses of herbicides to be applied only in those fields where they are really needed", the researcher clarifies. At the moment, these phytosanitary products are applied indiscriminately to fields, regardless of whether they are needed or not.
The system thought up by the information technologists has been tried successfully in the cultivation of cereal and maize in the La Poveda research station in Arganda del Rey (Madrid), property of the CSIC (Consejo Superior de Investigaciones Científicas) (Spanish National Research Council). This government agency has promoted the development of the study through the Institutes known as the Instituto de Automática Industrial (Institute of Industrial Automation) and the |Instituto de Ciencias Medioambientales (Institute of Environmental Sciences). The results obtained represent a saving of over 80% in treatment with herbicides, which translates into a considerable reduction in costs. Pajares says, “and what is more important, there is also a reduction in pollution of the environment” without there being any repercussions on the productivity of the land.
The studies about Precision Agriculture, such as the two proposed by the Spanish researchers, enables farming tasks such as spraying with herbicides, sowing and the use of fertilisers, to be planned in a more efficient and sustainable way. These studies put forward the use of new technologies in order to optimise farm work, but do not forget the existence of the changeable nature of the land, something farmers have known about since time began.
Sinc Team | alfa
Trees and climate change: Faster growth, lighter wood
14.08.2018 | Technische Universität München
Animals and fungi enhance the performance of forests
01.08.2018 | Deutsches Zentrum für integrative Biodiversitätsforschung (iDiv) Halle-Jena-Leipzig
New design tool automatically creates nanostructure 3D-print templates for user-given colors
Scientists present work at prestigious SIGGRAPH conference
Most of the objects we see are colored by pigments, but using pigments has disadvantages: such colors can fade, industrial pigments are often toxic, and...
Scientists at the University of California, Los Angeles present new research on a curious cosmic phenomenon known as "whistlers" -- very low frequency packets...
Scientists develop first tool to use machine learning methods to compute flow around interactively designable 3D objects. Tool will be presented at this year’s prestigious SIGGRAPH conference.
When engineers or designers want to test the aerodynamic properties of the newly designed shape of a car, airplane, or other object, they would normally model...
Researchers from TU Graz and their industry partners have unveiled a world first: the prototype of a robot-controlled, high-speed combined charging system (CCS) for electric vehicles that enables series charging of cars in various parking positions.
Global demand for electric vehicles is forecast to rise sharply: by 2025, the number of new vehicle registrations is expected to reach 25 million per year....
Proteins must be folded correctly to fulfill their molecular functions in cells. Molecular assistants called chaperones help proteins exploit their inbuilt folding potential and reach the correct three-dimensional structure. Researchers at the Max Planck Institute of Biochemistry (MPIB) have demonstrated that actin, the most abundant protein in higher developed cells, does not have the inbuilt potential to fold and instead requires special assistance to fold into its active state. The chaperone TRiC uses a previously undescribed mechanism to perform actin folding. The study was recently published in the journal Cell.
Actin is the most abundant protein in highly developed cells and has diverse functions in processes like cell stabilization, cell division and muscle...
17.08.2018 | Event News
08.08.2018 | Event News
27.07.2018 | Event News
17.08.2018 | Physics and Astronomy
17.08.2018 | Information Technology
17.08.2018 | Life Sciences