Lane line matching method and system based on deep learning
The invention discloses a lane line matching method based on deep learning. The method comprises the following steps: acquiring historical trajectory data of a target vehicle and historical trajectory data of an environmental vehicle; obtaining all historical lane line information corresponding to t...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention discloses a lane line matching method based on deep learning. The method comprises the following steps: acquiring historical trajectory data of a target vehicle and historical trajectory data of an environmental vehicle; obtaining all historical lane line information corresponding to the historical track data based on the historical track data of the target vehicle; the continuous historical lane line information and the historical track data of the vehicles are aligned through coding and then combined to obtain a sample vector; inputting the sample vector into a constructed deep learning network, and performing training and parameter adjustment on the deep learning network to enable the deep learning network to output a similarity calculation result of each piece of historical lane line information and historical track data of the target vehicle; when actual lane line matching is carried out, actual vectors are obtained after encoding is carried out based on the actual track data of the target |
---|