Avaz Naghipour

University of Tabriz, Computer Science, Faculty Member

University of Tabriz, Electrical and Computer Engineering, Faculty Member

Followers

Following

Public Views

AVAZ-NAGHIPOUR received Ph.D. degree in Applied Mathematics (Quantum Computing) from University of Tabriz, Tabriz, Iran in 2015. Now he is an Assistant Professor, Department of Computer Engineering, University College of Nabi Akram, Tabriz, Iran.
Dr. Naghipour has published over 20 technical papers and is the author of the book Algebraic Construction of Binary Quantum Stabilizer Codes (LAMBERT Academic Publishing Co., 2016). His research interests include image processing, pattern recognition, artificial intelligence, medical information processing, fuzzy logic, genetic algorithms, neural networks, optimization, quantum computing, and quantum information.
Dr. Naghipour is a Member of the American Mathematical Society, and a Member of the Mathematical Society of Iran.
Dr. Naghipour is also a Member of the Mendeley Advisor Community and a Reviewer of IEEE Communications Letters.
Supervisors: Prof. Dr. M. A. Jafarizadeh and Prof. Dr. B. Mehri

less

Osman GÜLDEMİR

Anadolu University

David Seamon

Kansas State University

Thomas K Gugler

Goethe-Universität Frankfurt am Main

Therese Martin

CSIC (Consejo Superior de Investigaciones Científicas-Spanish National Research Council)

João Pedro Gomes

Escola Superior de Educação de Coimbra

Nahyan Fancy

University of Exeter

Viacheslav Kuleshov

Stockholm University

Mahmoud Zaki

Georgetown University

rudolph bauer

Washington Center for Consciousness Studies

Jeremy Johns

University of Oxford

Interests

Uploads

Papers by Avaz Naghipour

Efficient Vision Transformer for Accurate Traffic Sign Detection

arXiv (Cornell University), Nov 1, 2023

This research paper addresses the challenges associated with traffic sign detection in selfdrivin... more This research paper addresses the challenges associated with traffic sign detection in selfdriving vehicles and driver assistance systems. The development of reliable and highly accurate algorithms is crucial for the widespread adoption of traffic sign recognition and detection (TSRD) in diverse real-life scenarios. However, this task is complicated by suboptimal traffic images affected by factors such as camera movement, adverse weather conditions, and inadequate lighting. This study specifically focuses on traffic sign detection methods and introduces the application of the Transformer model, particularly the Vision Transformer variants, to tackle this task. The Transformer's attention mechanism, originally designed for natural language processing, offers improved parallel efficiency. Vision Transformers have demonstrated success in various domains, including autonomous driving, object detection, healthcare, and defense-related applications. To enhance the efficiency of the Transformer model, the research proposes a novel strategy that integrates a locality inductive bias and a transformer module. This includes the introduction of the Efficient Convolution Block and the Local Transformer Block, which effectively capture short-term and long-term dependency information, thereby improving both detection speed and accuracy. Experimental evaluations demonstrate the significant advancements achieved by this approach, particularly when applied to the GTSDB dataset.

Avaz Naghipour

Related Authors

Uploads

Papers by Avaz Naghipour

Log In