高精度的货车内轮差危险区域测距方法研究  

Research on the High Precision Distance Measurement Method of Truck Interior Wheel Difference Dangerous Area

在线阅读下载全文

作  者:唐锡军 叶忠杰[2] TANG Xi-jun;YE Zhong-jie(Zhejiang Highway Technicians College,Hangzhou 310023,China;Zhejiang Institute of Communications,Hangzhou 311112,China)

机构地区:[1]浙江公路技师学院,杭州310023 [2]浙江交通职业技术学院,杭州311112

出  处:《浙江交通职业技术学院学报》2022年第4期12-17,共6页Journal of Zhejiang Institute of Communications

基  金:2019年浙江省基础公益研究计划项目(LGG19E050001);运输车辆运行安全技术交通运输行业重点实验室开放基金项目(KFKT2018-03)。

摘  要:针对货车内轮差危险区域检测场景下,通过目标检测算法获取到待检测物体位置信息,深度信息测量点选取不准确导致精度下降的问题,研究了对检测目标深度信息获取的方法,给出了货车内轮差危险区域检测系统方案,提出了一种基于YOLOV5目标检测和改进的深度图多点测量相结合的测距方法。实验结果表明,经改进后的深度信息获取方法可以有效降低目标框深度信息匹配错误的概率,且有效提高检测距离的精度。Aiming at the problem of accuracy decline caused by inaccurate selection of depth information measurement points after obtaining the position information of the object to be detected through the target detection algorithm in the detection scene of the dangerous area of the truck’s inner wheel difference, this paper mainly studies the method for obtaining the depth information of the detection target. The scheme of the detection system for the dangerous area of the truck’s inner wheel difference is given, and a ranging method based on YOLOV5 target detection and improved depth map multi-point measurement is proposed. The experimental results show that the improved depth information acquisition method can effectively reduce the probability of incorrect matching of the depth information of the target frame, and improve the accuracy of the detection distance.

关 键 词:内轮差 深度信息 YOLOV5 自适应 

分 类 号:TP391.41[自动化与计算机技术—计算机应用技术]

 

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