Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Road rut upheaval subsidence size and severity calculation method and system based on machine learning
The invention relates to a road rut upheaval subsidence size and severity calculation method and system based on machine learning, and the method comprises the following steps: 1, installing a high-definition camera, a central industrial control computer and line laser transmitter equipment on an inspection vehicle, and enabling the high-definition camera to collect an image according to the instruction of the central industrial control computer; and step 2, performing neural network algorithm identification deployed in the central industrial personal computer, fitting coordinate points [u, v] of the laser rays in the image, identifying a road datum line by using a road datum line algorithm deployed in the central industrial personal computer based on machine learning, performing post-processing calculation on the identified laser rays and the road datum line, and obtaining a road datum line. Obtaining a three-dimensional disease size and severity; step 3, performing disease length calculation according to a relationship among a plurality of continuous pictures; and step 4, finally, storing an identification result locally, and returning the identification result to the cloud through the mobile network. According to the method, the detection accuracy of the depth, the width and the like of deformation diseases such as road rut upheaval subsidence is improved.
本发明涉及一种基于机器学习的道路车辙拥包沉陷尺寸及严重程度计算方法及系统，其方法包括以下步骤：步骤1、在巡检车上安装高清相机、中央工控机、线激光发射器设备，高清相机根据中央工控机的指令采集图像；步骤2、部署在中央工控机的神经网络算法识别、拟合图像中激光线的坐标点[u,v]，利用部署在中央工控机中的基于机器学习的道路基准线算法识别道路基准线，将上述识别得到的激光线和道路基准线进行后处理计算，得到三维病害尺寸及严重程度；步骤3、再通过多张连续图片之间的关系，进行病害长度计算；步骤4、最后将识别的结果保存在本地，并通过移动网络回传至云端。此方法提高了道路车辙拥包沉陷等变形类病害的深度和宽度等检测的准确度。
Road rut upheaval subsidence size and severity calculation method and system based on machine learning
The invention relates to a road rut upheaval subsidence size and severity calculation method and system based on machine learning, and the method comprises the following steps: 1, installing a high-definition camera, a central industrial control computer and line laser transmitter equipment on an inspection vehicle, and enabling the high-definition camera to collect an image according to the instruction of the central industrial control computer; and step 2, performing neural network algorithm identification deployed in the central industrial personal computer, fitting coordinate points [u, v] of the laser rays in the image, identifying a road datum line by using a road datum line algorithm deployed in the central industrial personal computer based on machine learning, performing post-processing calculation on the identified laser rays and the road datum line, and obtaining a road datum line. Obtaining a three-dimensional disease size and severity; step 3, performing disease length calculation according to a relationship among a plurality of continuous pictures; and step 4, finally, storing an identification result locally, and returning the identification result to the cloud through the mobile network. According to the method, the detection accuracy of the depth, the width and the like of deformation diseases such as road rut upheaval subsidence is improved.
本发明涉及一种基于机器学习的道路车辙拥包沉陷尺寸及严重程度计算方法及系统，其方法包括以下步骤：步骤1、在巡检车上安装高清相机、中央工控机、线激光发射器设备，高清相机根据中央工控机的指令采集图像；步骤2、部署在中央工控机的神经网络算法识别、拟合图像中激光线的坐标点[u,v]，利用部署在中央工控机中的基于机器学习的道路基准线算法识别道路基准线，将上述识别得到的激光线和道路基准线进行后处理计算，得到三维病害尺寸及严重程度；步骤3、再通过多张连续图片之间的关系，进行病害长度计算；步骤4、最后将识别的结果保存在本地，并通过移动网络回传至云端。此方法提高了道路车辙拥包沉陷等变形类病害的深度和宽度等检测的准确度。
Road rut upheaval subsidence size and severity calculation method and system based on machine learning
一种基于机器学习的道路车辙拥包沉陷尺寸及严重程度计算方法及系统
ZHANG XIAOMING (Autor:in) / YANG QIANG (Autor:in) / YAN JINGQI (Autor:in) / SHAO XI (Autor:in) / CAO GUANGWEI (Autor:in)
04.06.2024
Patent
Elektronische Ressource
Chinesisch
IPC:
G06T
Bilddatenverarbeitung oder Bilddatenerzeugung allgemein
,
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
/
E01C
Bau von Straßen, Sportplätzen oder dgl., Decken dafür
,
CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE
/
G01B
MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS
,
Messen der Länge, der Dicke oder ähnlicher linearer Abmessungen
/
G01C
Messen von Entfernungen, Höhen, Neigungen oder Richtungen
,
MEASURING DISTANCES, LEVELS OR BEARINGS
/
G06N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
,
Rechnersysteme, basierend auf spezifischen Rechenmodellen
/
G06V
Quantitative detection method for rut subsidence upheaval based on road line laser
| Europäisches Patentamt | 2023
| Europäisches Patentamt | 2018
| British Library Conference Proceedings | 2018