| 徐晓光,李 海.多尺度特征在 YOLO 算法中的应用研究[J].电子测量与仪器学报,2021,35(6):96-101 |
| 多尺度特征在 YOLO 算法中的应用研究 |
| Application research of multi-scale features in YOLO slgorithm |
| |
| DOI： |
| 中文关键词: 目标检测 YOLO 算法 多尺寸特征 定位精度 |
| 英文关键词:target detection YOLO algorithm multi-scale features location accuracy |
| 基金项目:芜湖市科技计划（2020cg12）、安徽工程大学校级科研项目（xjky02201909）资助 |
|
|
|
|
| 摘要点击次数: 421 |
| 全文下载次数: 3 |
| 中文摘要: |
| 针对 YOLO 算法在下采样过程中丢失了部分大尺寸特征图的有效信息,从而导致在检测任务中因目标定位不够精准而
影响模型整体检测精度的问题。 提出利用多尺度特征融合的方法来解决 YOLO 定位不精准的问题,首先,对 YOLO 算法的网络
模型进行修改,利用 YOLO 网络模型中不同尺寸特征图具有不同特征属性的特点,融合不同尺寸特征图来提高检测网络对目标
的定位精度;其次在预训练模型的基础上对修改后的网络模型进行重新训练;最后在计算机中对训练好的模型进行检测试验。
实验结果表明,基于多尺度特征的 YOLO 目标检测算法在精确率上相对于 YOLO 目标检测算法提高了 3. 02%,mAP 提高
了 1. 53%。 |
| 英文摘要: |
| YOLO algorithm loses part of the effective information of large-size feature maps in the downsampling process, which leads to
the problem of insufficient target location in the detection task, which affects the overall detection accuracy of the model. This paper
proposes the use of multi-scale feature fusion to solve the problem of inaccurate location of YOLO; First, modify the network model of
YOLO algorithm, use different size feature maps in the YOLO network model with different feature attributes, and merge different size
feature maps to improve the location accuracy of the detection network to the target; second, based on the pre-training model Re-train the
modified network model on the last; finally, test the trained model in the computer. Experimental results show that the YOLO target
detection algorithm based on multi-scale features improves the Accuracy rate by 3. 02% and improves mAP by 1. 53% compared with
YOLO target detection algorithm. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
