Research on acceleration and optimization of image recognition based on FPGA
Currently, Convolutional Neural Network (CNN) has been widely applied in key fields such as autonomous driving, security monitoring, and medical image diagnosis due to its powerful feature extraction ability. However, the large parameter volume and complex computational process of CNN models pose se...
| Published in: | Инноватика-2025 : сборник материалов XXI Международной школы-конференции студентов, аспирантов и молодых ученых, 28-30 апреля 2025 г., г. Томск, Россия С. 242-250 |
|---|---|
| Main Author: | |
| Format: | Book Chapter |
| Language: | English |
| Subjects: | |
| Online Access: | https://vital.lib.tsu.ru/vital/access/manager/Repository/koha:001272902 Перейти в каталог НБ ТГУ |
| Summary: | Currently, Convolutional Neural Network (CNN) has been widely applied in key fields such as autonomous driving, security monitoring, and medical image diagnosis due to its powerful feature extraction ability. However, the large parameter volume and complex computational process of CNN models pose severe challenges in their practical deployment. Although GPUs are often used to accelerate CNN computations, their high-power consumption, high cost, and insufficient flexibility make them unable to meet the low power consumption and real-time requirements of edge devices. Based on this, this paper delves into the acceleration and optimization technologies of CNN image recognition based on FPGA, relying on the Vivado development tool provided by Xilinx FPGA platform. |
|---|---|
| Bibliography: | Библиогр.: 3 назв. |
| ISBN: | 9785936297311 |