Yinka-Banjo and Ajayi (2019)Yinka-Banjo C, Ajayi O (2019) Sky-farmers: Applications of unmanned aerial vehicle (UAV) in agriculture. In: Dekoulis G, editor. Autonomous vehicles. London: IntechOpen. https://doi.org/10.5772/intechopen.89488 https://doi.org/10.5772/intechopen.89488...
|
Crop monitoring |
The development of a framework to analyse unmanned aerial vehicle images and create mosaic images that can be matched with maps for GIS integration is centred on establishing a framework to analyse unmanned aerial vehicle photos and create mosaic images that can eventually be matched with maps for GIS integration. |
Digital; Hyperspectral cameras; Multispectral cameras; GPS Receiver; Wireless temperature and humidity sensors |
Lancaster 5; AgBot. |
Advances in computer intelligence, particularly in navigation, automated sensing, and actuation. Techniques for data gathering, data mulling, and, most crucially, transforming these data into valuable information must be developed. The flying time of an unmanned aerial vehicle is mostly determined by its battery capacity. Most unmanned aerial vehicles are unable to carry a large amount of cargo at once due to their small size. |
Radoglou-Grammatikis et al. (2020)Radoglou-Grammatikis P, Sarigiannidis P, Lagkas T, Moscholios I (2020) A compilation of UAV applications for precision agriculture. Comput Netw 172:107148. https://doi.org/10.1016/j.comnet.2020.107148 https://doi.org/10.1016/j.comnet.2020.10...
|
Precision agriculture |
The vegetation indices are calculated using unmanned aerial vehicle photos, allowing farmers to track crop variability and other unusual situations. The normalized difference vegetation index (NDVI) helps extract information on biomass levels, which can then be used to get essential insights on crop diseases, pest infestations, nutrient deficits, and other factors that affect productivity. |
RGB cameras; Hyperspectral cameras; Multispectral cameras; Thermal cameras; GPS receiver; Wireless temperature and humidity sensors. |
Sentera PHX; AgEagle RX-60. |
Designing a decision support system (DSS) capable of handling both a FANET and a ground-based WSN for crop monitoring and spraying. |
Cancela et al. (2019)Cancela JJ, González XP, Vilanova M, Mirás-Avalos JM (2019) Water management using drones and satellites in agriculture. Water 11(5):874. https://doi.org/10.3390/w11050874 https://doi.org/10.3390/w11050874...
|
Irrigation management |
Using proximal and remote sensing to determine crop water requirements and monitor crop water status to improve irrigation efficiency. Exploring novel approaches to better irrigation management and a more accurate estimate of crop water requirements. |
Digital cameras; Micro hyperspectral cameras; Multispectral cameras; GPS receiver; Wireless temperature and humidity sensors. |
eBee SQ; HoneyComb; DJI Matrice 210. |
Improving model predictions at larger scales aims to address information gaps and obtain consistent hydraulic space-temporal input data to be used in artificial intelligence networks. Unmanned aerial vehicles allow researchers and water managers to collect large amounts of data in a safe, cost-effective, and more accessible way than previous techniques. As unmanned aerial vehicle and sensing technology evolve, new processing tools and algorithms will be developed. |
Yaxley et al. (2021)Yaxley KJ, Joiner KF, Abbass H (2021) Drone approach parameters leading to lower stress sheep flocking and movement: Sky shepherding. Sci Rep 11:7803. https://doi.org/10.1038/s41598-021-87453-y https://doi.org/10.1038/s41598-021-87453...
|
Aerial livestock mustering |
It combines a deep learning algorithm for imprecise animal location with pixel modification to boost animal contrast. |
RGB cameras; Hyperspectral cameras; Multispectral cameras; Thermal cameras GPS receiver; Wireless temperature and humidity sensors. |
AgEagle; DJI Matrice 600 Pro; Lancaster 5. |
It is not optimal to consider several features of the same animal; new techniques will be explored for animal tracking. New approaches to collect photographs with the purpose of increasing the useful space in each image. |
Chen and Li (2019)Chen Y, Li Y (2019) Intelligent autonomous pollination for future farming: A micro air vehicle conceptual framework with artificial intelligence and human-in-the-loop. IEEE Access 7:119706-119717. https://doi.org/10.1109/ACCESS.2019.2937171 https://doi.org/10.1109/ACCESS.2019.2937...
|
Artificial pollination |
It includes flower recognition using computer vision techniques and a robotic MPR system, as well as an unmanned aerial vehicle pollinating system. A six-configuration MPr architecture has indeed been presented for autonomous artificial pollination. |
OpenMV Camera |
QWinOut DIY F450 |
Experimental verification and validation of unmanned aerial vehicle pollination, Create a CIAD framework for intelligent unmanned aerial vehicle pollination. New artificial intelligence algorithms are being developed, such as the heredity algorithm (HA). |
Iost Filho et al. (2019)Iost Filho FH, Heldens WB, Kong Z, Lange E (2019) Drones: Innovative technology for use in precision pest management. J Econ Entomol 113(1):1-25. https://doi.org/10.1093/jee/toz268 https://doi.org/10.1093/jee/toz268...
|
Biological control |
Changes in leaf reflectance are caused by physiological defence responses that are triggered by arthropod pests that damage plants and cause biotic stress. Advanced imaging technologies allow noninvasive crop monitoring by detecting changes such as these. |
Temperature sensor; Humidity sensor; Light intensity sensor; CO2 sensor; Water level sensor; EC and pH sensor. |
eBee SQ; Sentera PHX; AgBot. |
To employ drones for precision agriculture, you will face financial issues, such as the expenses of drones and associated sensors and material, a restricted flight time and payload, and rules that will constantly be changing. There will be an increased demand for multidisciplinary research partnerships among agronomists, ecologists, software developers, and engineers as a result of this new trend. |