A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Road disease detection method, system, equipment and medium
The invention provides a road disease detection method, system and device and a medium, and the method comprises the steps: obtaining road disease inspection images, and enabling the road disease inspection images to form a disease data set; inputting the disease data set into a detection model for training; the detection model comprises a convolutional neural network, a feature fusion network and a comparative learning module; the disease data set is sequentially subjected to feature extraction through the convolutional neural network, feature fusion through the feature fusion network and comparative learning through the comparative learning module; and inputting a to-be-detected road disease inspection image into the trained detection model to obtain a road disease detection result. According to the method, the contrast learning training process is optimized, and different road disease targets can be effectively detected and identified.
本发明提供了一种道路病害检测方法、系统、设备及介质，所述方法包括：获取道路病害巡检图像，并将所述道路病害巡检图像构成病害数据集；将所述病害数据集输入检测模型进行训练；所述检测模型包括卷积神经网络、特征融合网络和对比学习模块；所述病害数据集依次经由所述卷积神经网络进行特征提取、由所述特征融合网络进行特征融合，以及由所述对比学习模块进行对比学习；将待检测道路病害巡检图像输入训练后的检测模型，得到道路病害检测结果。本申请优化了对比学习训练过程，能够有效地检测识别不同的道路病害目标。
Road disease detection method, system, equipment and medium
The invention provides a road disease detection method, system and device and a medium, and the method comprises the steps: obtaining road disease inspection images, and enabling the road disease inspection images to form a disease data set; inputting the disease data set into a detection model for training; the detection model comprises a convolutional neural network, a feature fusion network and a comparative learning module; the disease data set is sequentially subjected to feature extraction through the convolutional neural network, feature fusion through the feature fusion network and comparative learning through the comparative learning module; and inputting a to-be-detected road disease inspection image into the trained detection model to obtain a road disease detection result. According to the method, the contrast learning training process is optimized, and different road disease targets can be effectively detected and identified.
本发明提供了一种道路病害检测方法、系统、设备及介质，所述方法包括：获取道路病害巡检图像，并将所述道路病害巡检图像构成病害数据集；将所述病害数据集输入检测模型进行训练；所述检测模型包括卷积神经网络、特征融合网络和对比学习模块；所述病害数据集依次经由所述卷积神经网络进行特征提取、由所述特征融合网络进行特征融合，以及由所述对比学习模块进行对比学习；将待检测道路病害巡检图像输入训练后的检测模型，得到道路病害检测结果。本申请优化了对比学习训练过程，能够有效地检测识别不同的道路病害目标。
Road disease detection method, system, equipment and medium
一种道路病害检测方法、系统、设备及介质
REN JIANGTAO (author) / ZHENG JUWU (author)
2023-08-22
Patent
Electronic Resource
Chinese
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
/
G06N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
,
Rechnersysteme, basierend auf spezifischen Rechenmodellen
Road disease detection method and device, computer equipment and readable storage medium
| European Patent Office | 2023
Road disease inspection method, device and system, electronic equipment and storage medium
| European Patent Office | 2023
ROAD DISEASE IDENTIFICATION METHOD AND SYSTEM AND MEDIUM
| European Patent Office | 2024