Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Deep learning pavement segregation identification method based on ground penetrating radar
The invention discloses a deep learning pavement segregation identification method based on a ground penetrating radar, and belongs to the field of intelligent traffic. The problem that an existing pavement segregation identification method based on a deep learning network is poor in identification effect is solved. The method comprises the following steps: 1, acquiring ground penetrating radar waveform data of a pavement with a known segregation condition, and then calculating radar wave amplitude, radar wave phase and phase gradient; 2, calculating a segregation area attention score of the obtained ground penetrating radar waveform data; 3, splicing the obtained radar wave amplitude, radar wave phase and phase gradient to serve as the input of the constructed deep learning network, and training the constructed deep learning network by fusing the attention score of the segregation region; 4, acquiring radar wave amplitude, radar wave phase, phase gradient and segregation area attention score of the ground penetrating radar waveform data of the road surface to be detected; and inputting a trained deep learning network to obtain a segregation identification result. The method can be applied to the field of intelligent transportation.
一种基于探地雷达的深度学习路面离析识别方法，它属于智能交通领域。本发明解决了现有基于深度学习网络的路面离析识别方法的识别效果差的问题。本发明方法为：1、获取已知离析情况的路面的探地雷达波形数据，再计算雷达波振幅、雷达波相位和相位梯度；2、计算获取的探地雷达波形数据的离析区域注意力分数；3、将获得的雷达波振幅、雷达波相位和相位梯度进行拼接后作为构建的深度学习网络的输入，并融合离析区域注意力分数对构建的深度学习网络进行训练；4、获取待检测路面的探地雷达波形数据的雷达波振幅、雷达波相位、相位梯度以及离析区域注意力分数；再输入训练好的深度学习网络得到离析识别结果。本发明可以应用于智能交通领域。
Deep learning pavement segregation identification method based on ground penetrating radar
The invention discloses a deep learning pavement segregation identification method based on a ground penetrating radar, and belongs to the field of intelligent traffic. The problem that an existing pavement segregation identification method based on a deep learning network is poor in identification effect is solved. The method comprises the following steps: 1, acquiring ground penetrating radar waveform data of a pavement with a known segregation condition, and then calculating radar wave amplitude, radar wave phase and phase gradient; 2, calculating a segregation area attention score of the obtained ground penetrating radar waveform data; 3, splicing the obtained radar wave amplitude, radar wave phase and phase gradient to serve as the input of the constructed deep learning network, and training the constructed deep learning network by fusing the attention score of the segregation region; 4, acquiring radar wave amplitude, radar wave phase, phase gradient and segregation area attention score of the ground penetrating radar waveform data of the road surface to be detected; and inputting a trained deep learning network to obtain a segregation identification result. The method can be applied to the field of intelligent transportation.
一种基于探地雷达的深度学习路面离析识别方法，它属于智能交通领域。本发明解决了现有基于深度学习网络的路面离析识别方法的识别效果差的问题。本发明方法为：1、获取已知离析情况的路面的探地雷达波形数据，再计算雷达波振幅、雷达波相位和相位梯度；2、计算获取的探地雷达波形数据的离析区域注意力分数；3、将获得的雷达波振幅、雷达波相位和相位梯度进行拼接后作为构建的深度学习网络的输入，并融合离析区域注意力分数对构建的深度学习网络进行训练；4、获取待检测路面的探地雷达波形数据的雷达波振幅、雷达波相位、相位梯度以及离析区域注意力分数；再输入训练好的深度学习网络得到离析识别结果。本发明可以应用于智能交通领域。
Deep learning pavement segregation identification method based on ground penetrating radar
一种基于探地雷达的深度学习路面离析识别方法
MA YONGJIAN (Autor:in) / SONG XIANMIN (Autor:in) / LI ZHIHUI (Autor:in) / LI HAITAO (Autor:in) / CAO QIAN (Autor:in) / ZHANG YUNXIANG (Autor:in) / TAO PENGFEI (Autor:in)
29.08.2023
Patent
Elektronische Ressource
Chinesisch
IPC:
G01S
RADIO DIRECTION-FINDING
,
Funkpeilung
/
E01C
Bau von Straßen, Sportplätzen oder dgl., Decken dafür
,
CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE
/
G06F
ELECTRIC DIGITAL DATA PROCESSING
,
Elektrische digitale Datenverarbeitung
/
G06N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
,
Rechnersysteme, basierend auf spezifischen Rechenmodellen
Pavement Evaluation Using Ground Penetrating Radar
| ASCE | 2014
Pavement Evaluation Using Ground Penetrating Radar
| British Library Conference Proceedings | 2014
Interpreting Ground Penetrating Radar Pavement Data
| British Library Conference Proceedings | 1997
Ground Penetrating Radar (GPR) for Pavement Evaluation
| NTIS | 2012