| KEYWORD |
Microelectronics
Real-Time 3D Object Detection and Counting for Stock Monitoring in Warehouses using AI on Edge
Thesis in external company
keywords IMAGE ANALYSIS, MACHINE LEARNING
Reference persons LUCIANO LAVAGNO
External reference persons Marcello Babbi, Reply Torino
Research Groups Microelectronics
Thesis type APPLIED RESEARCH
Description Stock monitoring is a critical task in warehouses, and accurate counting and detection of objects can help
prevent stockouts and optimize inventory management. This thesis aims to develop an AI-based system for
real-time 3D object detection and counting in warehouses using edge devices.
The system will use 3D image processing and deep learning techniques to detect and count objects in realtime,
enabling warehouse managers to monitor stock levels and prevent stockouts. The use of edge devices
such as cameras and sensors will enable the system to operate in real-time without relying on cloud services,
enhancing reliability, speed and improving privacy.
Required skills Python programming, some knowledge of Machine Learning, image processing
Notes The student will be involved in:
❑ State-of-the-art literature review
❑ SW requirements definition for edge deployment
❑ Data pre-processing and feature engineering
❑ Developing and implementing a deep learning-based model for 3D point cloud analysis
❑ HW computational requirements trade-off
Deadline 11/10/2024
PROPONI LA TUA CANDIDATURA