Abstract:
One of the most significant cereal crops in Uganda is maize. Smallholder farmers in particular depend on it as a source of food and income. Additionally, they raise it as a significant export crop. The overall amount of maize produced in Uganda has grown steadily throughout the years, rising from about 800,000 tons in 2000 to 2,575,000 tons in 2019. Its life cycles are short, around from 120 to 150 days. Approximately: 70–87% (carbohydrates), starch (amylose and amylopectin), 6–13% (protein), 4% (fat), 2-6% (oil), and 1-3% (sugar) are found in maize.
Because it contains antioxidants, fiber, protein, is gluten-free, and is a great option for vegetarians, corn is good for human health. Some of the most serious diseases that affect maize productivity in Uganda include gray leaf spot, common rust, and blight. They not only pose a risk to maize production in the commercial farming sector but also lower maize yields on small farms. By personally visiting the garden and assessing the condition of the maize based on visual characteristics, such as the way the leaves look, it is possible to manually monitor the diseases attacking maize in Uganda, including gray leaf spot, common rust, and blight. A lot of work goes into the visual examination, and the farmer, agronomist, or extension officer's experience is a requirement for the identification of these illnesses. Due to this, results are inconsistent, which may result in incorrect disease diagnoses. To overcome the drawbacks of manual approaches, technologies like remote sensing, drones, and IoT have been created to carry out these duties.
However, the currently available technologies also have drawbacks, such as the difficulty of data interpretation for remote sensing and the high cost of drones with more characteristics, necessitating the use of artificial intelligent based robot to monitor gray leaf spot, common rust and blight diseases in maize. The robot was designed, assembled, and had its performance assessed. It overcomes the mentioned issues with the monitoring techniques that are currently in use, such as remote sensing and drones. The robot is inexpensive and accessible to farmers, and data interpretation is simple. Due to the early discovery of these diseases that have major impacts on the harvests, the farmer can anticipate a decent yield output. The majority of farmers can afford the robot, and it is simple to use and maintain. The robot is made up of parts like the frame, the control box, which contains the circuit board, the web camera, which is used to take pictures in the field, an application for regulating motion, and an application that interacts with the farmer to provide him with the results. Mild steel angle bars and plates were used to construct it. A 26Ah battery powers the robot, while 12dc motors drive the wheels.
