Information Technology of Video Data Processing for Traffic Intensity Monitoring

Abstract

Traffic jams are a huge problem for all road users and are caused by increasing traffic intensity and poor quality of traffic management systems. The systems that control traffic flows and decide to change parameters must receive reliable and up-to-date data on traffic intensity. In order to accurately determine the traffic intensity, a system of automated video data processing from video surveillance cameras of the traffic lane is developed. The traffic intensity is determined by the method of obtaining the traffic congestion coefficient (TLCR) according to the data, gained by processing the video frame using the U-Net neural network, and the following transformation of TLCR time series into traffic intensity time series. The new in formation technology implements an image processing algorithm to detect the presence of vehicles in a certain section of road, a method of determining the congestion of the lane (TLCR) and a method of determining the intensity of successive values of congestion of the lane. The experimental results show that the proposed information technology is able to identify traffic intensity with an accuracy of99,35 percent.

Мета статті.Метою дослідження є підвищення точності визначення інтенсивності руху на основі аналізу відеоданих у режимі реального часу шляхом автоматизованої обробки відеоданих, отриманих від камер відеоспостереження у смузі.

Цель статьи. Целью исследования является повышение точности определения интенсивности движения на основе анализа видеоданных в режиме реального времени путем автоматизированной обработки видеоданных, полученных с камер видеонаблюдения полосы.