Artificial Intelligence in Agriculture (Jan 2020)
Image processing based real-time variable-rate chemical spraying system for disease control in paddy crop
Abstract
The agrochemical application with conventional sprayers results in wastage of applied chemicals, which not only increases the economic losses but also pollutes the environment. In order to overcome these drawbacks, an image processing based real-time variable-rate chemical spraying system was developed for the precise application of agrochemicals in diseased paddy crop based on crop disease severity information. The developed system comprised of web cameras for image acquisition, laptop for image processing, microcontroller for controlling the system functioning, and solenoid valve assisted spraying nozzles. The chromatic aberration (CA) based image segmentation method was used to detect the diseased region of paddy plants. The system further calculated the disease severity level of paddy plants, based on which the solenoid valves remained on for a specific time duration so that the required amount of agrochemical could be sprayed on the diseased paddy plants. Field performance of developed sprayer prototype was evaluated in the variable-rate application (VRA) and constant-rate application (CRA) modes. The field testing results showed a minimum 33.88% reduction in applied chemical while operating in the VRA mode as compared with the CRA mode. Hence, the developed system appears promising and could be used extensively to reduce the cost of pest management as well as to control environmental pollution due to such agrochemicals.