Sack Object Counter on a Conveyor Belt Based on Segmentation Using the Thresholding Technique

Abstract

Automation technology provides better outcomes from the perspective of time efficiency, material usage, and reducing error rates in a process. Sensors and visual sensing are components or methods frequently used in industrial automation systems. Visual sensing methods can replace simple tasks typically performed by an operator's vision in the industry, such as counting specific objects. Object counting algorithms are adapted to the type of object being counted; for example, counting fish objects and counting sack objects on a conveyor belt require different algorithms. Operators who are tired or unfocused can cause errors in counting objects like sacks on a conveyor belt, leading to financial losses. The main component used in this automatic counting system is a webcam. Each image frame is captured and processed in a computer to obtain parameters used as the basis for counting sack objects. The counting results are displayed on a monitor to facilitate the operator's view of the output. The method used is segmentation with a thresholding technique, which allows the separation of sack objects from the conveyor. The application of the segmentation method produces accurate counts; a total of 21 sack objects on the conveyor belt were counted without errors using this method. The use of filters did not affect the counting results, while the area size did. An area size of 50x50 provided the most accurate counting results and the best FPS (Frames Per Second) compared to other area sizes. This technique can ensure that the calculation process does not cause errors that result in losses.