Real-Time Robotic Vision Application for Health Monitoring of Paddy Plants

This paper proposes real-time inspection of the paddy field using robotic vision technology. Chlorophyll content in the plant is the measure of sufficient or deficit amount of nutrients in the field as well as the health condition of the plant. The proposed work estimates the chlorophyll content of the plant while navigating the robotic vehicle in the field. An image acquisition arrangement has been mounted facing the ground on the robotic vehicle which captures on-field images. Color information from these images is compared with the digitized reference leaf color chart. Mahalanobis distance has been calculated from the extracted color with all colors in the reference color chart. Using the minimum Mahalanobis distance the best match with the reference chart has been decided. The robotic vehicle has the provision of spraying fertilizer if the matched color is the last two colors (e.g. having a light green shade) from the reference color chart. The result of this chlorophyll estimation approach is encouraging and the accuracy is to the tune of 92%.