Skip to main content

An Internet of Things assisted Unmanned Aerial Vehicle based artificial intelligence model for rice pest detection

Authors: 

Sourav Kumar Bhoi, Kalyan KumarJena, Sanjaya Kumar Panda, Hoang Viet Long, Raghvendra Kumar, P. Subbulakshmi, Haifa Bin Jebreen

Source title: 
Microprocessors and Microsystems, 80: 103607, 2021 (ISI)
Academic year of acceptance: 
2020-2021
Abstract: 

Rice is a very essential food for the survival of human society. Most of the people focus on production of rice for their financial gain as well as their survival in the society. Rice production means a lot, not only for the farmers, but also for the entire human society However, it is very difficult to protect the rice during and after the production due to several reasons, such as natural calamities, heavy rain fall, flood, earthquakes, damage of rice due to pests, etc. Damage of rice can occur during production and after the production due to several pests. So, it is very much essential to identify the pests in the rice so that preventive measures can be taken for its protection. In this paper, an Internet of Things (IoT) assisted Unmanned Aerial Vehicle (UAV) based rice pest detection model using Imagga cloud is proposed to identify the pests in the rice during its production in the field. The IoT assisted UAV focuses on artificial intelligence (AI) mechanism and Python programming paradigm for sending the rice pest images to the Imagga cloud and providing the pest information. The Imagga cloud detects the pest by finding the confidence values with the tags. The tag represents the object in that image. The tag with maximum confidence value and beyond threshold is selected as the target tag to identify the pest. If pest is detected then the information is sent to the owner for further actions. The proposed method can able to identify any kind of the pest that affects the rice during production. Alternatively, this paper attempts to minimize the wastage of rice during its production by monitoring the pests at regular intervals.