| 张立国,孟子杰,金梅.针对嵌入式设备的YOLO目标检测算法改进方法[J].高技术通讯(中文),2024,34(4):356~365 |
| 针对嵌入式设备的YOLO目标检测算法改进方法 |
| Improvement methods for YOLO object detection algorithm targeting embedded devices |
| |
| DOI：10. 3772 / j. issn. 1002-0470. 2024. 04. 003 |
| 中文关键词: 目标检测； YOLOv4-Tiny； 轻量化设计； 嵌入式实现； 加速器 |
| 英文关键词: object detection, YOLOv4-Tiny, lightweight design, embedded implementation, accelerator |
| 基金项目: |
| 作者 | 单位 | | 张立国 | (燕山大学电气工程学院秦皇岛 066000) | | 孟子杰 | | | 金梅 | |
|
| 摘要点击次数: 715 |
| 全文下载次数: 525 |
| 中文摘要: |
| 针对算法在资源有限的嵌入式设备实现困难的问题，本文基于YOLO系列算法提出适应嵌入式设备实现的轻量化改进方法。方法具体包括：基于YOLOv4-Tiny算法结构，引入GhostNet思想改进其网络主干，大量降低网络参数量和计算量；通过加强颈部网络特征融合效果，减少模型压缩导致的精度损失；采用训练中量化的方式将网络模型参数从32位浮点型数据转换为适合嵌入式设备计算的8位定点型参数。实验结果表明，改进后的网络在检测精度满足应用要求的情况下，模型尺寸相对原算法降低57%，在嵌入式设备上实现功耗仅3.795W。 |
| 英文摘要: |
| To address the problem of implementing algorithms on resource-limited embedded devices, a lightweight improvement is proposed based on the YOLO series of algorithms to adapt to embedded device implementation, specifically including: improving the network backbone by introducing GhostNet ideas based on the YOLOv4-Tiny algorithm structure to significantly reduce network parameters and computational complexity; strengthening the fusion effect of neck network features to reduce accuracy loss caused by model compression; and using quantization during training to convert network model parameters from 32-bit floating-point data to 8-bit fixed-point parameters suitable for embedded device computation. Experimental results show that after the improvement in this paper, the network’s model size relative to the original algorithm is reduced by 57% when the detection accuracy meets application requirements, and the power consumption for embedded device implementation is only 3.795W. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
