《计算机应用》唯一官方网站 ›› 0, Vol. ›› Issue (): 262-266.DOI: 10.11772/j.issn.1001-9081.2024010056

• 多媒体计算与计算机仿真 • 上一篇    下一篇

基于深度学习的无人机引导线识别模型

崔多(), 王秋生   

  1. 北京航空航天大学 自动化科学与电气工程学院,北京 100191
  • 收稿日期:2024-01-19 修回日期:2024-04-02 接受日期:2024-04-07 发布日期:2024-05-09 出版日期:2024-12-31
  • 通讯作者: 崔多
  • 作者简介:崔多(2000—),女,辽宁大连人,硕士研究生,主要研究方向:图像处理、机器视觉、机器学习、数据挖掘
    王秋生(1990—),男,北京人,副教授,博士,主要研究方向:图像处理、机器视觉、机器学习、模式识别、现代数字信号处理。
  • 基金资助:
    教育部高等学校产学研创新基金资助项目(2022XF027)

Drone guide line recognition model based on deep learning

Duo CUI(), Qiusheng WANG   

  1. School of Automation Science and Electrical Engineering,Beihang University,Beijing 100191,China
  • Received:2024-01-19 Revised:2024-04-02 Accepted:2024-04-07 Online:2024-05-09 Published:2024-12-31
  • Contact: Duo CUI

摘要:

无人机引导线识别是一种无人机基于地面引导线进行自动寻径的方法。针对地面引导线识别速度慢、识别准确率低等问题,提出一种多任务的基于U型网络(U-Net)的轻量化数据融合模型——Mobile-FuUnet。首先,在U-Net的结构上引入MobileNet-V3进行特征提取,并引入深度可分卷积(DSC)减少模型参数量,从而建立多任务轻量化模型;其次,引入前置图像的多项式特征矩阵,并基于注意力机制进行数据融合,从而解决引导线边缘部分大面积缺失所带来的计算问题,进而提高模型的识别准确率。在Tusimple数据集与无人机引导线数据集上展开多次对比验证,实验结果表明,在引导线数据集上,Mobile-FuUnet模型可以实现帧率为109 frame/s,平均交并比(MIoU)为98.71%,F1得分为99.64%,曲线模型R2评分95.03%的引导线识别任务,相较于U-Net、ENet、DeepLab v3等模型在运行速率与计算精度上均有提升。

关键词: 引导线识别, 深度学习, 语义分割, 注意力机制, 数据融合

Abstract:

Drone guide line recognition is an automatic path finding method based on ground guide lines. To address the issues of slow recognition speed and low recognition accuracy of ground guide lines, a multi-task lightweight model with data fusion called Mobile-FuUnet based on U-shaped Network (U-Net) was proposed. Firstly, on the structure of U-Net, MobileNet-V3 was introduced for feature extraction, and Depthwise Separable Convolution (DSC) was introduced to reduce the number of model parameters, so as to establish a multi-task lightweight model. Finally, based on attention mechanism for data fusion, the polynomial feature matrix of the pre-image was introduced to solve the computational problem caused by the large area missing at the edge of the guide line, in order to improve the operational accuracy of the model. Multiple comparisons were carried out on Tusimple dataset and the drone guide line dataset. Experimental results show that on the drone guide line dataset, Mobile-FuUnet model can achieve guide line recognition task with the frame rate of 109 frame/s, the Mean Intersection over Union (MIoU) of 98.71%, the F1 score of 99.64 %, and the curve model R2 score of 95.03%. Compared with models such as U-Net, ENet, and DeepLab v3, the proposed model improves both running speed and computational accuracy.

Key words: guide line recognition, deep learning, semantic segmentation, self-attention, data fusion

中图分类号: