Design of an IoT ultrasonic-vision based system for automatic fruit sorting utilizing size and color

Abstract

While integrating mechanical conveyor chains and object sorting automation with an Internet of Things (IoT) system can present exciting and challenging opportunities, the potential benefits of increased efficiency, real-time tracking, and predictive maintenance make it valuable. Machine learning techniques, precise computer vision, and ultrasonic technology have proven to be powerful tools for accurately detecting and differentiating fruits based on color and size. In light of this, a proposed solution is developing an automatic IoT system comprising a mechanical conveyor chain, wooden sorting trays, ultrasonic sensors, a fisheye camera, Raspberry Pi, and other necessary components. This system can detect and sort fruits such as apples, oranges, lemons, tangerines, bananas, and avocados into four customizable trays, with a sorting accuracy of 90%. Moreover, the system can be easily adapted and expanded to support more sorting trays and a more comprehensive range of agricultural products.