基于AOD-Net的雾天高速公路能见度动态检测方法  

Dynamic visibility detection method for foggy highways based on AOD Net

在线阅读下载全文

作  者:时兵[1] 唐昌华[1] 杨阳[2] 于超[1] Shi Bing;Tang Changhua;Yang Yang;Yu Chao(College of Humanities&Information,Changchun University of Technology,Changchun 130122,China;China Unicom Changchun Branch,Changchun 130000,China)

机构地区:[1]长春工业大学人文信息学院,长春130122 [2]中国联合网络通信有限公司长春市分公司,长春130000

出  处:《现代计算机》2024年第11期45-49,共5页Modern Computer

基  金:吉林省教育厅科学技术研究项目(JJKH20231440KJ、JJKH20231441KJ)。

摘  要:单纯以图像帧差特征为主的公路能见度动态检测方法,缺乏足够多样且具有代表性的真实数据集,使得能见度的智能检测精度下降,为此,利用生成对抗网络的博弈迭代计算优势,设计一种基于AOD-Net(An All-in-One Network)的雾天高速公路能见度动态检测。首先,采用生成对抗网络中的带雾图像生成算法,主要是判断生成的带雾图像的真实程度,旨在使判别器准确地区分真实图像和生成的图像。然后,捕获不同尺度下的特征,从而更准确地估计雾霾参数,利用AOD-Net完成雾霾动态识别与能见度检测。最后,构建团雾分级预警模型,以实现团雾智能预警。通过对比实验证明,所提检测方法可以实现对雾天高速公路能见度动态高精度检测,检测结果与实际能见度偏差不超过5m,具备较高的应用价值。The dynamic detection method of visibility of highway,which is mainly based on image frame difference characteristics,lacks enough diverse and representative real data sets,which makes the intelligent detection accuracy of visibility decrease.Therefore,therefore,using the advantage of game iterative calculation of generated against network,design a dynamic detection of fog-day visibility of highway based on AOD-Net(An All-in-One Network).Firstly,the foggy image generation algorithm in the ad-versarial generation network is adopted to judge the true degree of the generated foggy image,aiming to make the discriminator accurately distinguish the real image from the generated image.Then,the characteristics at different scales were captured to estimate the haze parameters more accurately,and the haze dynamic identification and visibility detection were completed using AOD-Net.Finally,the hierarchical early warning model of fog is constructed to realize the intelligent early warning of fog.Through comparative experiments,it is proved that the proposed detection method can realize the dynamic and high-precision detection of the visibility of the foggy expressway,and the deviation between the detection results and the actual visibility is not more than 5m,which has high application value.

关 键 词:AOD-Net 高速公路 动态检测 能见度 雾天 

分 类 号:U495[交通运输工程—交通运输规划与管理] TP391.41[交通运输工程—道路与铁道工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象