CCTV METHOD AND APPARATUS FOR URBAN TRAFFIC NETWORK MODELING WITH MULTIPLE CCTV VIDEOS

• Main Authors: YEON HAN BYUL, SEO SEONG BUM, JANG YUN
• Format: Patent
• Language: English; Korean
• Published: 13.01.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; PICTORIAL COMMUNICATION, e.g. TELEVISION; SIGNALLING; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR; TRAFFIC CONTROL SYSTEMS

The present invention relates to a method for modeling an urban traffic network using a plurality of CCTV videos, which provides a real-time traffic flow analysis result and future traffic flow prediction result of a city, and an apparatus thereof. According to one embodiment of the present invention, the method comprises the following steps: (a) collecting videos from a plurality of CCTV networks and sampling the video by adjusting a sampling frequency according to a speed change of a vehicle; (b) generating vehicle flow data from the sampled video on the basis of a preset vehicle tracking algorithm; (c) combining the generated vehicle flow data and the plurality of CCTV networks including each CCTV location information to generate an incomplete traffic network in which observed data and non-observed data are identified; and (d) generating missing data for first non-observed data and second non-observed data through a missing data prediction model, and modeling a urban traffic network in which the observed data and the missing data are merged. 본 발명의 일 실시예에 따른 장치에 의해 수행되는 다중 CCTV 비디오를 이용한 도시 교통 네트워크 모델링 방법은 (a) 다중 CCTV 네트워크로부터 비디오를 수집하되, 차량의 속도 변화에 따른 샘플링 빈도를 조절하여 비디오를 샘플링하는 단계; (b) 기설정된 차량 추적 알고리즘에 기초하여 샘플링된 비디오로부터 차량 흐름 데이터를 생성하는 단계; (c) 생성된 차량 흐름 데이터와 각 CCTV 위치정보를 포함한 다중 CCTV 네트워크를 결합하여 관측 데이터와 비관측 데이터가 식별되는 불완전한 교통 네트워크를 생성하는 단계; 및 (d) 누락 데이터 예측 모델을 통해 제1비관측 데이터 및 제2비관측 데이터에 대한 누락 데이터를 생성한 후, 관측 데이터 및 누락 데이터가 병합된 도시 교통 네트워크를 모델링하는 단계;를 포함한다.