Automatic driving scene classification and recognition system and method

Abstract

The invention discloses an automatic driving scene classification and recognition system and method. The system is provided with a scene data acquisition module, a driving scene recognition module, ascene fusion module and a scene fragment segmentation and storage module. The scene data acquisition module acquires scene key information; the driving scene recognition module performs parallel recognition on various driving scenes according to the scene key information; and the scene fusion module performs scene fusion on the recognized driving scene. The method comprises the following steps: 1)customizing a main scene and a sub-scene; 2) acquiring scene key information; 3) presetting parameter boundaries and extraction standards of all sub-scenes, and carrying out parallel recognition on all the sub-scenes based on scene key information; and 4) carrying out scene fusion on all the recognized sub-scenes based on the set scene fusion conditions and fusion principles to obtain multi-dimensional driving scenes. The system and the method can perform intelligent classification and recognition of the driving scenes.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a system and method for classifying and identifying automatic driving scenes. Background technique [0002] A self-driving car is an unmanned intelligent car realized by an automatic control system. In recent years, automobile intelligent technology has developed rapidly, assisted driving technology and some automatic driving technologies have entered the stage of industrialization; conditional automatic driving and highly automated driving technologies have entered the stage of testing and verification. Driving scene recognition technology is the key basic technology for intelligent driving assistance systems and unmanned vehicles to perceive the environment. Accurate recognition of driving scenes is conducive to safe and stable driving of self-driving cars. The identification of driving scenes depends on the classification of driving scenes in the early stage...

AI Technical Summary

Problems solved by technology

The identification of driving scenes depends on the classification of driving scenes in the early stage. The classification technology of driving scenes in the prior art is mainly based on the classification of numerous driving scene data. The fixed classification rules classify the driving scene data, but due to the complexity of the driving scene and the continuous development and changes of the social environment, it is sometimes difficult for the collected driving scene data to match the fixed classification rules, which leads to a messy classification system Disorder, not conducive to subsequent statistical analysis and optimization of automatic driving technology

Images