Volume 7 Issue 1
Smart Sensor for Real-Time Quantification of Common Symptoms Present in Unhealthy Plants
Luis M. Contreras-Medina, Roque A. Osornio-Rios, Irineo Torres-Pacheco, Rene de J. Romero-Troncoso, Ramon G. Guevara-González and Jesus R. Millan-Almaraz
1HSPdigital-CA Mecatrónica, Facultad de Ingeniería, Universidad Autónoma de Querétaro, Campus San Juan del Rio, Rio Moctezuma 249, 76807 San Juan del Rio, Qro., México
2Ingeniería de Biosistemas CA, División de Estudios de Posgrado, Facultad de Ingeniería, Universidad Autónoma de Querétaro, Cerro de las Campanas S/N, 76010 Querétaro, Qro., México
3Facultad de Ciencias Físico-Matemáticas, Universidad Autónoma de Sinaloa, Av. De las Américas y Blvd., Universitarios, Cd. Universitaria, 80000 Culiacán, Sin., México
*
Author to whom correspondence should be addressed.
Abstract
Plant responses to physiological function disorders are called symptoms and they are caused principally by pathogens and nutritional deficiencies. Plant symptoms are commonly used as indicators of the health and nutrition status of plants. Nowadays, the most popular method to quantify plant symptoms is based on visual estimations, consisting on evaluations that raters give based on their observation of plant symptoms; however, this method is inaccurate and imprecise because of its obvious subjectivity. Computational Vision has been employed in plant symptom quantification because of its accuracy and precision. Nevertheless, the systems developed so far lack in-situ, real-time and multi-symptom analysis. There exist methods to obtain information about the health and nutritional status of plants based on reflectance and chlorophyll fluorescence, but they use expensive equipment and are frequently destructive. Therefore, systems able of quantifying plant symptoms overcoming the aforementioned disadvantages that can serve as indicators of health and nutrition in plants are desirable. This paper reports an FPGA-based smart sensor able to perform non-destructive, real-time and in-situ analysis of leaf images to quantify multiple symptoms presented by diseased and malnourished plants; this system can serve as indicator of the health and nutrition in plants. The effectiveness of the proposed smart-sensor was successfully tested by analyzing diseased and malnourished plants.Keywords:smart sensors; symptoms in plants; computer vision; image processing; plant diseases; FPGA