본 발명은 입력영상으로부터 객체를 감지하기 위한 딥-러닝(Deep learning) 알고리즘의 모델을 도로 환경에 적합하도록 최적화시킴과 동시에 카메라의 촬영에 의해 영상 획득 시, 딥-러닝을 이용하여 영상을 분석하여 객체(차량 및 보행자)를 검출한 후, 검출된 객체정보를 기반으로 신호체계를 수립함으로써 영상분석을 통한 객체 감지 및 트래킹의 정확성을 현저히 높임에 따라 신호 제어의 신뢰도를 높일 수 있을 뿐만 아니라 교차로의 차량 대기시간이 현저히 절감되며, 현장에서 실시간 영상처리가 가능한 객체 감응형 차량 흐름 제어 방법에 관한 것이다.
The present invention relates to an object-responsive vehicle flow control method in which a model of the deep learning algorithm for detecting an object from an input image is optimized to be suitable for a road environment, and at the same time, when the image is captured and acquired by a camera, the image is analyzed using deep-learning to analyze the object (vehicle and pedestrians), it is possible to increase the reliability of signal control by significantly increasing the accuracy of object detection and tracking through image analysis by establishing a signal system based on the detected object information, as well as increasing vehicle waiting time at intersections, and thus real-time image processing is possible in the field.
Traffic flow controlling method for controlling traffic signal with sensing vehicle
신호 제어를 위한 객체 감응형 차량 흐름 제어 방법
2023-07-31
Patent
Electronic Resource
Korean
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / H04N PICTORIAL COMMUNICATION, e.g. TELEVISION , Bildübertragung, z.B. Fernsehen |
Traffic flow controlling method for controlling traffic signal with sensing vehicle
European Patent Office | 2022
|TRAFFIC SIGNAL CONTROLLER AND TRAFFIC SIGNAL CONTROLLING METHOD
European Patent Office | 2016
|Traffic signal lamp capable of controlling signal time according to traffic flow
European Patent Office | 2021
|