딥러닝 기반 교통 흐름 분석 방법 및 시스템이 제공된다. 본 발명의 실시예에 따른 교통 흐름 분석 방법은, 도로 영상을 획득하고, 획득된 도로 영상에서 딥러닝 모델을 이용하여 객체를 검출하고 추적하고, 획득된 도로 영상에서 딥러닝 모델을 이용하여 교통 정보를 인식하며, 검출하고 추적하는 객체와 인식한 교통 정보를 이용하여 교통 이벤트를 생성한다. 이에 의해, 교통 흐름의 분석과 교통 이벤트 생성을 보다 정확하게 수행할 수 있게 된다.
A deep learning based traffic flow analysis method and system are provided. A traffic flow analysis method according to an embodiment of the present invention comprises the following steps: obtaining a road image; detecting and tracking an object using a deep learning model in the obtained road image; recognizing traffic information by using the deep learning model in the obtained road image; and creating a traffic event by using the object to be detected and tracked and the recognized traffic information. Accordingly, it is possible to more accurately analyze traffic flow and generate the traffic event.
Deep Learning based Traffic Flow Analysis Method and System
딥러닝 기반 교통 흐름 분석 방법 및 시스템
2022-10-12
Patent
Electronic Resource
Korean
Deep Learning based Traffic Flow Analysis Method and System
European Patent Office | 2021
|Traffic flow prediction method based on hybrid deep learning
European Patent Office | 2023
|A Deep Learning Based Traffic State Estimation Method for Mixed Traffic Flow Environment
DOAJ | 2022
|Graph neural network traffic flow prediction method based on deep learning
European Patent Office | 2023
|