[6-1015-D] Other Categories (3)

[6-1015-D-03] Development of a Smart Spraying System For Weeds On Rice Fields

*Thanh Tinh Nguyen¹, Ricardo Ospina², Noboru Noguchi² (1. Hokkaido University, Graduate School of Agriculture(Japan), 2. Hokkaido University, Research Faculty of Agriculture(Japan))

Keywords:Precision agriculture, Weeds, Rice field, Image processing, Real time detection

In recent years, precision agriculture has become an important aspect of sustainable agriculture and environment protection. The problem of how to reduce the amount of chemicals used on the fields while ensuring productivity has become a challenge. In this study, we developed a smart spraying system prototype which uses a machine vision system capable of performing real time detection of two kinds of weeds in the paddy fields of the Vietnamese Mekong Delta (VMD). The prototype of the smart spraying system was tested to perform real time precision spraying of herbicide on weed location. The input images were recorded by using an RGB camera. The discrimination between rice and weeds was obtained by processing the images based on well-known image segmentation methods and analysis of the bounding rectangle of blob. This method is simple but effective, allowing to detect narrow leaf weeds and broadleaf weeds on the post-emergence stage of weeds with reasonable accuracy. Accuracy of spraying was also evaluated, spray volume and rate application were adapted and tuned for real work conditions on the field. Results suggest this system is more precise and reliable in comparison to current methods used in Vietnam.