لطفا منتظر بمانید ...
0% Complete
صفحه اصلی
/
سی و سومین کنفرانس بین المللی مهندسی برق
Design and Implementation of a Flexible CNN Accelerator for Fast Real-Time Object Detection on FPGA
نویسندگان :
Emadodin Sakhaee
1
Mahdi Kalbasi
2
1- دانشگاه اصفهان
2- دانشگاه اصفهان
کلمات کلیدی :
Energy efficiency،real-time image processing،convolutional neural networks،hardware accelerator
چکیده :
In edge computing systems with limited resources, such as mobile devices and the Internet of Things, the use of Convolutional Neural Network (CNN) accelerators on FPGA has increasingly expanded. Ultrascale ZYNQ FPGAs offer scalability and flexibility for implementing deep learning-based object detection applications. However, this technology has low performance and limitations in achieving real-time processing. This paper addresses the optimization of the accelerator at the Register Transfer Level (RTL) to increase processing speed using low-power techniques in FPGA implementation. Therefore, a configurable accelerator design for a CNN-based object detection system at the RTL level on FPGA is proposed. We also present RTL optimization techniques that include techniques for disabling unnecessary clock cycles to reduce energy consumption and the use of the Posit number system format to increase calculation accuracy. The proposed system was tested with ResNet-20 and trained with the CIFAR-10 dataset. The weight data used for this test was provided by Tensil. Experimental results show that the proposed design process improves energy consumption, hardware utilization, and computational accuracy by 11%, up to 25%, and 4%, respectively.
لیست مقالات
لیست مقالات بایگانی شده
Object Detection enhancement based on Super-Resolution Mapping
Danial Abyazi - Dadfar Abyazi - Mehran Yazdi
MRI Data Quality: Do You Check Before You Trust?
Mostafa Fakhri - Narjes Soltani Dehaghani
بازسازی تصویر با معکوس کردن شبکه GAN
علی مجلسی کوپائی - سعید باقری شورکی - احمد شعبانی
Modeling and Analysis of Segmental Translator Permanent Magnet Linear Switched Reluctance Motor
Milad Golzarzadeh - Hashem Oraee - Babak Ganji
A 2.4 GHz Low Phase Noise Voltage Controlled Oscillator With Low Supply Voltage and Robust Start-Up for WLAN Standard in 0.13µm CMOS Technology
Farzad Ramezani Sani - Mortaza Mojarad
The Theory of A Novel Circuit Design For An Identification Processor Using 0.35µm CMOS Technology
Rouhollah Mohammadinasr - Kheirollah Hadidi - Farhad Piri
Python-Based Optimization of Inverse Taper Structures for Enhanced Fiber-to-Chip Coupling Efficiency Using FDTD Simulations
Soroush Rostami - Sarmad Rostami - Ali Poureslami - Davood Ranjbar Rafi
Data-Driven Simultaneous Estimation of Power System Inertia and Damping under Measurement Noise
Saeed Aslani amin abad - Turaj Amraee - Moein Abedini
Type-2 fuzzy expert system for management of smart home with combining renewable resources
Ali Beheshtikhoo - Mahdi Pourgholi - Iman Khazaee
Combination of a Convolutional Neural Network and a Vision Transformer for Segmenting Internal Organs in CT Scans
Mohammad Amin Nooraei Yeganeh - Hamid Soltanian-Zadeh
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 44.7.2