Driver expressway lane changing intention prediction method, system and device

Abstract

The invention belongs to the technical field of intelligent driving, particularly relates to a driver expressway lane changing intention prediction method, system and device, and aims to solve the problem of low prediction accuracy of the lane changing intention of the driver. The driver expressway lane changing intention prediction method comprises the following steps: extracting feature data ofa driver head image, a driver limb image, a road scene image and vehicle speed information; carrying out feature data synchronization through interpolation; and calculating a left lane changing probability, a right lane changing probability and a lane keeping probability by adopting a lane changing prediction model, and taking the lane changing intention with the maximum probability value as a driver expressway lane changing prediction intention. According to the driver expressway lane changing intention prediction method, a multi-video stream image processing technology is adopted, and prediction model establishment and reckoning analysis are carried out in combination with all characteristic data, so that the prediction precision is high, and control divergence between a driver and an auxiliary system and interference of the auxiliary system on the driver are avoided, and a vehicle can start region-of-interest detection and early warning in advance, and traffic accidents are reduced.

Description

technical field [0001] The invention belongs to the technical field of intelligent driving, and in particular relates to a method, system and device for predicting a driver's intention to change lanes on a highway. Background technique [0002] With the development of smart cars and advanced driver assistance systems (ADAS, Advanced Driving Assistant System), more and more driver assistance systems are sharing vehicle control with the driver. Taking the lane keeping system as an example, the lane keeping system directly controls the steering system of the vehicle by detecting the current position of the vehicle in the lane, so that the vehicle can keep driving in a safe straight line and avoid unintentional lane changes. [0003] However, as the driver shares control of the vehicle with the driver assistance system, the issue of how to effectively manage the control authority between the two must be addressed to avoid control divergence and unnecessary disturbance to the dri...

AI Technical Summary

Problems solved by technology

[0009] In order to solve the above-mentioned problems in the prior art, that is, the problem of low prediction accuracy of the driver's lane-changing intention, the present invention provides a method for predicting the driver's lane-changing intention on a highway, the prediction method comprising:

Images