Optical Sensors for Precision Agriculture: An Outlook

Abstract

The growing human population added to the rural exodus has aggravated the pressure in the agricultural sector for greater production. Faced with this problem, research has developed optical sensors for more productive agriculture with the purpose of minimizing the effects of rural exodus, obtaining rapid information and promoting the rational use of natural resources. Optical sensors have a differential consisting of the ability to use the spectral signature of an attribute or part of it to gain information, often not obvious. This review provides recent advances in optical sensors as well as future challenges. The studies have shown the wide range of applicability of optical sensors in agriculture, from detection of weeds to identification of soil fertility, which favors management in different areas of agriculture. The main limitation to the use of optical sensors in agriculture in most parts of the world has been the cost of purchasing the devices, especially in poor countries. So one of the future challenges is the reduction of final prices paid by consumers.

Aplicações Da Termografia Na Agricultura

“…Isto leva ao aumento da temperatura em partes localizadas, tal como as folhas. Diante disto, imagens geradas por câmeras térmicas constituem uma forma de detectar presenças de infecção por patógeno ainda não visível a olho nu (VIANA et al, 2018;VIANA et al, 2019). Ruiz et al (2013), estudando uma nova abordagem de imagens aéreas de alta resolução para detecção da Huanglongbing (HLB) ou doença do greening dos citros, usando um veículo aéreo não tripulado (VANT) de sensor remoto de baixa altitude e multirotor de baixo custo, observaram que dentre os algoritmos de classificação testados, a máquina de vetores de suporte (SVM) com kernel resultou em melhor desempenho do que outros métodos como SVM (linear), análise discriminante linear e análise discriminante quadrática e concluíram que, o sensoriamento aéreo de alta resolução tem boas perspectivas para a detecção de árvores infectadas com HLB.…”

Spatial Modelling of Within-Field Weed Populations; a Review

“…Different real-time approaches are already feasible, but are not yet at the stage of widespread commercialization, and are continuously under development [8]. One common type of real-time approach involves optical sensors mounted on sprayers, with real-time image analysis and decision making as the machinery passes over the field e.g., [9][10][11]. Alternatively, cameras can be mounted on unmanned aerial vehicles for rapid mapping of whole fields, and machine learning techniques can be employed to rapidly produce spray maps for site-specific weed management [12,13].…”