首页|基于双特征提取网络的复杂环境车道线精准检测

基于双特征提取网络的复杂环境车道线精准检测

扫码查看
原文链接
  • 万方数据
  • 维普
为解决现有方法在复杂环境中检测精度低的问题，提出了一种基于双特征提取网络的复杂环境车道线精准检测算法。首先，搭建双特征提取网络，获取不同尺度的特征图，提取更有效的特征，提高模型在复杂环境下的特征提取能力。然后，构建跨通道联合注意力模块，提高模型对车道线细节的关注度，抑制无用信息。最后，结合改进的空洞空间金字塔池化模块扩大图像感受野，提高模型对上下文信息的利用率，以强化算法的检测能力。经实验验证，本文算法在CULane数据集上的F1-measure达到了 72。43%，相比于基线模型提升了 4。03%，在复杂的场景中对车道线进行检测时效果提升明显。
Accurate lane detection of complex environment based on double feature extraction network
The existing lane detection methods have the problem of low detection accuracy due to fuzzy details in a complex environment.Therefore,this paper proposes an accurate lane detection algorithm based on a double feature extraction network in a complex environment.Firstly,a double feature extraction network is built to obtain feature maps of different scales,extract more effective features,and improve the feature extraction ability of the model in complex environments.Besides,a cross-channel joint attention module is constructed to improve the attention of the model to lane details and suppress useless information.Finally,combined with the improved void space pyramid pooling module,the receptive field is enlarged to improve the utilization of context information of the model,to strengthen the detection ability.The experimental results show that the F1-measure of the proposed algorithm on CULane dataset reaches 72.43%,which is 4.03%higher than that of the mainstream UFSD algorithm.When detecting lane lines in complex scenes,the detection effect of the proposed method is significantly improved,which has been proven to be able to meet the needs of practical applications.

computer applicationlane detectiondouble feature extractionmulti-scalecombined attention mechanism

张云佐、郑宇鑫、武存宇、张天

展开 >

石家庄铁道大学 信息科学与技术学院,石家庄 050043

石家庄铁道大学 河北省电磁环境效应与信息处理重点实验室,石家庄 050043

计算机应用 车道线检测 双特征提取 多尺度 跨通道联合注意力

国家自然科学基金项目国家自然科学基金项目河北省自然科学基金项目河北省自然科学基金项目河北省高等学校科学技术研究项目中央引导地方科技发展资金项目

6170234762027801F2022210007F2017210161ZD2022100226Z0501G

2024

10.13229/j.cnki.jdxbgxb.20221129

吉林大学学报(工学版)
吉林大学

吉林大学学报(工学版)

CSTPCD北大核心
影响因子：0.792
ISSN：1671-5497
年,卷(期)：2024.54(7)
  • 6