Use of RGB images from unmanned aerial vehicle to estimate lettuce growth in root-knot nematode infested soil

• Autor(a) principal: Cavalcanti, Vytória Piscitelli
• Data de Publicação: 2023
• Outros Autores: dos Santos, Adão Felipe, Rodrigues, Filipe Almendagna, Terra, Willian César, Araújo, Ronilson Carlos, Ribeiro, Clerio Rodrigues, Campos, Vicente Paulo, Rigobelo, Everlon Cid [UNESP], Medeiros, Flávio Henrique Vasconcelos, Dória, Joyce
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1016/j.atech.2022.100100; http://hdl.handle.net/11449/246847
• topic: Bacillus subtilis; Biological control; Lactuca sativa; Meloidogyne incognita; Vegetation cover; Vegetation index

Lettuce (Lactuca sativa) is an important horticultural commodity all over the world, and its growth can be affected by root-knot nematodes (Meloidogyne spp.). To keep track of plant behaviors, growers are using new technologies. In this paper, aerial images were obtained using a low-cost unmanned aerial vehicle (UAV) to gather crop information in a short time giving acceptable accuracy for decision-making in the field. Evaluations were done to check the flight height interference in the image's quality for lettuce mapping, and select the best one to estimate the effect of root-knot nematode incidence on lettuce growth. In a field infested with M. incognita, lettuce seedlings were planted in plots treated with bionematicide and control plots. Aerial images were obtained using low-cost UAV in four flight heights performed for five weeks, along with field measurements. Images were processed and used to calculate vegetation indices (VI) and vegetation cover (VC). After lettuce harvesting, nematode eggs were extracted from plants' roots and quantified. Plots treated with bionematicide showed no difference from the control plots in eggs number and lettuce growth. Differences in VI values between the flight heights were not consistent, suggesting that VI values could be affected by the lack of luminosity calibration in each flight condition. VC values calculated from field data presented strong positive correlations with VI and VC values from UAV image data, indicating that RGB images obtained by UAV can be used in the detection of diseases that affect plant growth, as well as following up harvesting time.