Computer Vision Algorithms on a Raspberry Pi 4 for Automated Depalletizing

The primary objective of a depalletizing system is to automate the process of detecting and locating specific variable-shaped objects on a pallet, allowing a robotic system to accurately unstack them. Although many solutions exist for the problem in industrial and manufacturing settings, the applica...

Full description

Saved in:
Bibliographic Details
Published in:Algorithms 2024-08, Vol.17 (8), p.363
Main Authors: Greco, Danilo, Fasihiany, Majid, Ranjbar, Ali Varasteh, Masulli, Francesco, Rovetta, Stefano, Cabri, Alberto
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial intelligence
Automation
Comparative analysis
Computer vision
Consumption
Deep learning
depalletizing systems
Edge computing
Embedded systems
Equipment and supplies
Feature selection
Industrial robots
Inventory
Inventory management
Localization
Machine learning
Machine vision
Materials handling
Mechanization
object detection
Pallets
Pattern matching
Performance evaluation
Productivity
Raspberry Pi 4
Robotics
single-board computer
Vending machines
Vision systems
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The primary objective of a depalletizing system is to automate the process of detecting and locating specific variable-shaped objects on a pallet, allowing a robotic system to accurately unstack them. Although many solutions exist for the problem in industrial and manufacturing settings, the application to small-scale scenarios such as retail vending machines and small warehouses has not received much attention so far. This paper presents a comparative analysis of four different computer vision algorithms for the depalletizing task, implemented on a Raspberry Pi 4, a very popular single-board computer with low computer power suitable for the IoT and edge computing. The algorithms evaluated include the following: pattern matching, scale-invariant feature transform, Oriented FAST and Rotated BRIEF, and Haar cascade classifier. Each technique is described and their implementations are outlined. Their evaluation is performed on the task of box detection and localization in the test images to assess their suitability in a depalletizing system. The performance of the algorithms is given in terms of accuracy, robustness to variability, computational speed, detection sensitivity, and resource consumption. The results reveal the strengths and limitations of each algorithm, providing valuable insights for selecting the most appropriate technique based on the specific requirements of a depalletizing system.
ISSN:1999-4893
1999-4893
DOI:10.3390/a17080363