Urban traffic situation identification method based on directed graph convolutional neural network

Abstract

The invention discloses an urban traffic situation identification method based on a directed graph convolutional neural network. The method comprises the steps: carrying out the traffic situation classification of historical traffic flow information, converting an urban road network into a directed graph according to a point-edge conversion rule, and extracting a corresponding sub-graph; then, calculating the weight of a directed edge and the weight between non-directly connected nodes, standardizing the number of nodes of the subgraph, and calculating a traffic information matrix and a feature matrix of the subgraph; finally, designing a traffic directed graph convolutional neural network model, performing training and testing, using the model for classifying real-time traffic flow information to identify the real-time traffic situation of all road sections. According to the method, the incidence relation between directed road sections of different levels and different grades under the hybrid road network is fully considered, a unified standardized model input and traffic situation recognition model is designed, and good universality is achieved; moreover, the method has the characteristics of simple process, easiness in calculation, easiness in programming realization and the like, and can be suitable for complex urban road networks.

Description

technical field [0001] The invention relates to an urban traffic situation recognition method for intelligent traffic. The urban traffic situation recognition can not only facilitate vehicle drivers to implement route rules, but also can be used for urban traffic management, providing a basis for formulating and implementing traffic management measures. Background technique [0002] Data-driven intelligent transportation systems are beginning to gradually integrate into people's daily lives. Intelligent transportation systems generate and use a large amount of data every day, which can better analyze urban traffic conditions and provide great help to traffic control. According to the traffic analysis report of major cities in China in 2018, the mileage ratio of congestion during peak hours in medium and large cities mostly exceeds 5%, that is, 50 meters of roads per kilometer are congested. In this case, traffic situation recognition can detect the congestion state of the r...

AI Technical Summary

Problems solved by technology

In addition, there are some methods to establish a neural network model under the static road network structure based on the topological structure of the road, which can completely capture the traffic information of the local road network, but the model is limited by the model structure that has been constructed. When the road network When the topology changes, the model needs to be redefined and retrained

[0004] At present, the existing urban traffic situation recognition methods have the following main problems: 1) Most neural network methods use structured input, and such methods do not consider the large number of one-way lanes, tidal lanes, inner city viaducts and underground tunnels that exist in the urban road network. Various structures cannot fully grasp the traffic road network information around the target road segment; 2) Other methods use static road network modeling methods. It needs to consume a lot of computing resources and cannot be applied to all road sections, because each road section needs to train a model, which consumes a lot of software and hardware resources; 3) The design process and calculation process of many traffic situation recognition methods are very complicated and cannot be applied to actual traffic environment

Images