Call for Post-Doc Position in Digital Twin for Asset Tracking System 2023
The Office of International Affairs and Overseas Students at Persian Gulf University announces a call for hiring a joint dual certificate post doc researcher for a project on Distributed Edge-AI Vision-based Asset Positioning and Tracking System in collaboration between Persian Gulf University and Polytechnic university of Viana do Castelo (Portugal). The details of the call can be found as follows:
Title:
Enabling Digital Twin Through a Distributed Visual Based Asset Positioning and Tracking System via Edge-AI
Supervisors:
Dr. Ahmad Keshavarz, PGU
Dr. Sérgio Ivan Lopes , IPVC
External Collaborator:
Dr. Azin Moradbeikie, CiTin – Centro de Interface Tecnológico Industrial
Funding and Duration
Duration: 1 to 2 years partially remote
Funding: Monthly salary of an Assistant Professor at Persian Gulf University in IRR for each post-doc position plus research grant.
Completion
Two Scopus indexed publications (one of which in JCR IF Journal) are required to complete the projects, and dual completion certificates will be issued from both side.
Who can apply?
PhD's holders in Computer Engineering and Electrical Engineering familiar with deep learning can apply.
Qualifications
Image analysis (ML and Deep learning algorithms), Localization, Edge-AI, Industry 5.0
How to apply?
The applicants can apply via email and send the required documents to (ICT@pgu.ac.ir) before the deadline. Please write ApplicantName_PostDoc(ICT5) as the subject of email.
The strict closing date of the call is October 22, 2023 (Mehr 30, 1402).
Required documents
- Motivation Letter (one page; including the title and code of the post-doc position)
- Recommendations from Supervisor(s)
- CV
- PhD and Master Transcripts
- Competencies Certificates (Recommended)
- Language proficiency proof (Recommended)
More Description
Enabling Digital Twin Through A Distributed Visual Based Asset Positioning and Tracking System via Edge-AI
The next generation of industry is shifting towards collaborative, autonomous systems that operate safely and efficiently in dynamic and unstructured environments. Key enablers for the implementation of Industry 5.0 include applications such as smart logistics, human-in-the-loop, digital twin, and real-time decision-making. Accurate localization and tracking of assets are becoming essential components for all of these enablers. For instance, a digital twin technology that creates virtual representations of physical assets must be continuously monitored and updated in real-time based on the corresponding asset's location and status to achieve optimal performance and support decision-making.
Although Global Positioning Systems (GPS) have been widely used as a positioning technology in many application domains, its high cost and reduced accuracy in indoor environments have become significant limitations. To address these limitations, many researchers have justified the use of visual-based localization systems as a more cost-effective and accurate technology.
Visual-based localization systems can offer higher accuracy than GPS, as they can utilize advanced image processing techniques to identify and track objects in real-time. With the increasing availability of high-resolution cameras and advancements in edge-AI technology, visual-based localization systems are becoming an increasingly attractive solution for indoor applications, including asset and operator identification and tracking. By utilizing edge computing, the system minimizes network load and latency, while distributed implementation enables seamless monitoring of multiple assets across different locations.
This study is going to propose a distributed vision-based localization system that utilizes the power of edge-AI. As factories often have large areas, this system should provide real-time localization and tracking of assets using multiple cameras distributed throughout the area. The system is designed to identify objects and track their movements in real-time, while also minimizing network load and delay by processing data at the edge. The final goal of this study is to provide a secure and accurate localization system within a large-scale factory environment, while minimizing network load and latency.
