Road congestion caused identification algorithm based on the image morphology and decision tree

With the advancement of urbanization in China, the demand for urban residents' traffic travel and the number of motor vehicles continue to grow, and the problem of traffic congestion is becoming increasingly serious. Rapid and accurate identification of urban road traffic congestion and the adoption of corresponding measures to alleviate traffic congestion are of great significance for improving the efficiency of urban road operation and reducing the economic losses caused by traffic congestion. This paper takes Shenzhen as an example, using image learning and decision tree machine learning algorithms, integrates floating car GPS data, meteorological data and other multi-source data to identify traffic congestion, correlate and analyze the causes of congestion, achieve the identification of congestion types such as recurrent congestion and non-recurrent congestion, or special event congestion, and support the rapid matching of governance measures based on the classification of congestion causes, which helps to improve the efficiency of traffic management.