The applications or use of drones (more technically, UAV – Unmanned Aerial Vehicle) in agriculture have shown a strong growth trend. This trend could accelerate even further when considering the countless potential applications that are still under development.
It is important to note that when we talk about "drones", we are using a generic term that includes several components and systems, each used in one phase of the information generation pipeline (Figure 1).
One of these components is the UAV itself, which can be a mini-helicopter type with a vertical-axis rotor or multi-rotors with 4, 6, or 8 rotors, as well as fixed-wing drones, called “hard-wing drones” (Figure 2). Each type and model has its advantages and disadvantages. Multi-rotor UAVs generally fly at lower speeds and altitudes than fixed-wing types and are more stable and safe in stronger wind conditions. Another important feature that differentiates UAVs is the payload capacity (the maximum weight they can carry), ranging from less than 200 grams to several tens of kilograms. Additionally, there are UAVs equipped with an inertial system, GPS, uni- or multi-directional obstacle sensors, assisted landing sensors, among others.
Another component is the Control and Communication System (CCS), also called “ground stations” (Figure 3), which includes communication between the base device and the UAV, flight planning and autopilot software, as well as a wide range of safety and energy consumption settings. There are dozens of ground station solutions available, but it is recommended to use the one developed and provided by your UAV manufacturer.
Undoubtedly, the payload component has received the most market attention, as it is here — along with image processing — that various applications are customized. What can be onboard a UAV? The possibilities are almost limitless. From digital cameras to sprayers, active sensors (microwaves), passive sensors (visible and invisible light, including infrared regions), environmental variable sensors, seeders, and more.
When using digital cameras or sensors onboard a UAV to collect images or videos, the use of Image Processing Systems (IPS) is mandatory (Figure 3). There is a wide variety of solutions available in the market. This system component allows the user to combine hundreds or thousands of digital images into a single image of a field or experimental plot, usually called an orthorectified mosaic. Each image captured by a UAV camera or sensor is affected by axis rotation caused by wind or thermal flows during flight, as well as variations in sunlight intensity throughout the mission. IPS algorithms correct these distortions and generate a unified image of the target area.
Perhaps the pioneering application of drones in agriculture was visual monitoring through images (still or video) captured by UAV-mounted digital cameras. Undoubtedly, the speed and quality of UAV monitoring surpasses that performed on foot or with ground vehicles.
A significant advance occurred with the use of images captured in wavelengths invisible to the human eye. Cameras capturing infrared images allowed the generation of orthomosaics showing the spatial-temporal variation of a vegetation index across a field (Figure 4). This correlates with some soil elements, as well as plant health, enabling inferences about disease occurrence and location. This information can be used, for example, to generate spraying recommendation maps, directing UAV-mounted sprayers to apply only where needed.
The next market step was the use of multispectral sensors that capture visible light and two or three bands in the near and mid-infrared regions. This allows monitoring vegetation indices related to water stress and improves information on biotic stresses. There are dozens of vegetation indices that can be calculated from multispectral images, with some better suited to specific plant species or growth stages.
Additional applications include plant height measurement (Figure 5), plant counting, and population estimation (Figure 6).
Hyperspectral sensors will play an increasingly important role in agronomic research and plant breeding. They capture images across the visible spectrum, near and mid-infrared bands, and can even reach far-infrared and microwave ranges. To draw an analogy: the evolution from early infrared images to hyperspectral imaging is similar to the evolution from X-rays to 3D color magnetic resonance imaging.
These sensors will soon enable high-throughput phenotyping for genetic improvement programs worldwide (Figure 7), at costs thousands of times lower than current solutions.
Before flying a UAV, it is important to comply with relevant regulations. Recently, ANAC published a normative instruction. Key restrictions include, but are not limited to: register your UAV with ANAC; never fly above 120 meters above ground level; flights over crowds must be at least 30 meters high and with written authorization from the people present; UAVs with payloads over 25 kg require a pilot license equivalent to airplane pilots, after a course at the Civil Aviation Department.
Learn more about the use of drones in agriculture in our technical bulletin.
Restricted Area
