Integrating Computer Vision and Fusion Sensor for Object Dimensioning and Weight Measurement

Abstract

In the logistics industry, measuring the dimensions and weight of packages is crucial for optimizing cost expenditures, storage space, and inventory management. Traditional measurement methods often consume time and are prone to human errors. The objective of this research is to utilize load cell sensors, webcams, and image processing techniques to automatically and, in real-time, measure the three dimensions and weight of packages. The main contribution is to provide an effective solution for measuring package dimensions without the need for human intervention. The proposed solution includes the use of a 50kg half-bridge load cell sensor with HX711 for measuring package weight, HC-SR04 ultrasonic sensor for measuring the distance between the sensor and the package using Arduino Uno, and image processing using OpenCV to analyze the visual characteristics of the package. The system will be tested using various types of objects with varying sizes and shapes to determine the accuracy of the system in measuring package weight and dimensions. Measurement results indicate that the system can measure package dimensions, volume, and weight with a success rate of 92.45%. The system has a response time of around 1-2 seconds in its capacity to detect and measure objects. Conversely, when executed in simultaneously, it often has a duration of approximately 5 to 7 seconds