A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
The invention discloses a road surface flatness detection method based on a motion camera, wherein the method comprises the steps: installing the motion camera to the top of an automobile and above the center of a rear axle of the automobile; adjusting the angle of the motion camera to enable the direction right ahead of the motion camera to be consistent with the direction of the head of the automobile, and setting the working mode of the motion camera to be a video recording mode; starting video recording at the starting point of a road to be detected and driving at a speed not higher than 80 km/H; stopping video recording at the end point of the road to be detected and obtaining video data; and constructing a deep learning model based on an international flatness index, inputting the video data for calculation processing, and outputting to obtain the pavement flatness of the road to be detected. According to the method for detecting the pavement flatness by using the video shot by the motion camera, the detection cost is reduced, and the detection process is simplified; and meanwhile, the application of the deep learning algorithm has the advantages of good robustness and high accuracy.
本发明公开了一种基于运动相机的路面平整度检测方法，包括，安装运动相机至汽车顶部且位于车辆后轴中心上方；调整所述运动相机角度，使其正前方与所述汽车车头方向一致，设置所述运动相机工作模式为视频录制模式；在待检道路的起点处开始视频录制并以不高于80km/H时速行驶；在所述待检道路的终点处停止视频录制并得到视频数据；基于国际平整度指数构建深度学习模型，输入所述视频数据进行计算处理，输出得到所述待检道路的路面平整度。本发明通过使用运动相机拍摄视频进行路面平整度检测的方法，使得检测成本得到降低，检测流程得以简化；同时，深度学习算法的运用，具备了鲁棒性好、准确度高的优点。
The invention discloses a road surface flatness detection method based on a motion camera, wherein the method comprises the steps: installing the motion camera to the top of an automobile and above the center of a rear axle of the automobile; adjusting the angle of the motion camera to enable the direction right ahead of the motion camera to be consistent with the direction of the head of the automobile, and setting the working mode of the motion camera to be a video recording mode; starting video recording at the starting point of a road to be detected and driving at a speed not higher than 80 km/H; stopping video recording at the end point of the road to be detected and obtaining video data; and constructing a deep learning model based on an international flatness index, inputting the video data for calculation processing, and outputting to obtain the pavement flatness of the road to be detected. According to the method for detecting the pavement flatness by using the video shot by the motion camera, the detection cost is reduced, and the detection process is simplified; and meanwhile, the application of the deep learning algorithm has the advantages of good robustness and high accuracy.
本发明公开了一种基于运动相机的路面平整度检测方法，包括，安装运动相机至汽车顶部且位于车辆后轴中心上方；调整所述运动相机角度，使其正前方与所述汽车车头方向一致，设置所述运动相机工作模式为视频录制模式；在待检道路的起点处开始视频录制并以不高于80km/H时速行驶；在所述待检道路的终点处停止视频录制并得到视频数据；基于国际平整度指数构建深度学习模型，输入所述视频数据进行计算处理，输出得到所述待检道路的路面平整度。本发明通过使用运动相机拍摄视频进行路面平整度检测的方法，使得检测成本得到降低，检测流程得以简化；同时，深度学习算法的运用，具备了鲁棒性好、准确度高的优点。
Road surface flatness detection method based on motion camera
一种基于运动相机的路面平整度检测方法
HUANG HE (author)
2021-07-30
Patent
Electronic Resource
Chinese
IPC:
G06K
Erkennen von Daten
,
RECOGNITION OF DATA
/
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 roller with road surface flatness detection function
| European Patent Office | 2021
Road surface flatness detection device for road construction
| European Patent Office | 2023