Automated Prototype VR Sprayer

 

Introduction

The variable rate technology (VRT) offers an opportunity to improve production efficiency by allowing input applications in amounts and locations where they are needed. The basic idea of VRT is to allocate agricultural inputs more efficiently by exploiting spatial variations in soil type, topographic features, fertility levels, and other field characteristics. Variable rate application includes GPS and GIS map-based, “on-the-go” sensor-based, or a combination of map and sensors. In the map based approach, disease detection, generation of application maps and variable-rate spraying are performed in consecutive, separate operations, if weather conditions are favourable, diseases can quickly spread over the whole field. In recent years, real-time technology has been introduced into the practice of spraying variable fungicides. The unique features of the wild blueberry cropping system emphasize the need for the development of cost-effective VR applicators for spot-applications to significantly reduce amount of agrochemicals usage. VR sprayer consists of sensors/cameras, computerized controllers, solenoid valves and custom image processing software capable of detecting weeds/plants/bare spots to spray herbicide/fungicide/insecticide in a specific section of the boom where the target was detected.

Objectives

The prototype, 20-foot sprayer equipped with ultrasonic sensor/digital color cameras on both sides of the boom, which are attached by USB cables to the computer in the all terrain vehicle (ATV) was developed in the Precision Agriculture Laboratory, Engineering Department, NSAC. Custom software processes the ultrasonic sensor data for tall weed (goldenrod) detection in real-time. In turn, this processed information was transmitted to the eight-channel computerized VR controller to target tall weeds. All the weeds are not tall in the wild blueberry cropping system; to target the small weeds; color contrast and/or textural feature based software was developed and connected with the VR controller. The prototype, 20-foot sprayer equipped with 2 digital color cameras on each side of the front boom, which are attached by USB cables to the computer. Custom software processes the images to detect weeds, bare spots and blueberry plants in real-time. In turn, these weed or plant triggering signals are transmitted to the eight-channel computerized VR controller. This device has user-programmable inputs such as a before-and-after buffer, time delay and ground speed corrections. The vision of the research was to substantially reduce crop protection usage, improve land stewardship and increase berry yields.

Researchers

Dr. Qamar Zaman, Associate Professor, Engineering Department, NSAC

Dr. Arnold Schumann, Associate Professor, Citrus Research and Education Centre, University of Florida, USA

Dr. Young Chang, Associate Professor, Department of Environmental Science, NSAC

Travis Esau (Graduate Student)

Aitazaz Farooque (Graduate Student) 

Partners

This research was funded by Oxford Frozen Foods, Nova Scotia Department of Agriculture, Wild blueberry Producers Association of Nova Scotia, CFI and Agri-Futures (ACAAF) Nova Scotia