Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Driver lane changing intention recognition method based on Gaussian mixture hidden Markov model

A Gaussian mixture, driving intent technology, applied in character and pattern recognition, computational models, machine learning, etc., can solve the driver's nervous attention, distraction and other problems

Active Publication Date: 2020-02-28
JILIN UNIV
View PDF7 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Ignoring driving intentions so that the system may issue warnings or actions that are contrary to the driver's intentions, causing the driver to become nervous or distracted

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Driver lane changing intention recognition method based on Gaussian mixture hidden Markov model
  • Driver lane changing intention recognition method based on Gaussian mixture hidden Markov model
  • Driver lane changing intention recognition method based on Gaussian mixture hidden Markov model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0104] A driver's lane-changing intention recognition method based on a Gaussian mixture hidden Markov model includes the following steps:

[0105] Step 1, determine the frame where the face area is located and the coordinates corresponding to the horizontal direction of the left and right borders of the frame, and extract the driver's face area based on the YCbCr color space for skin color extraction, to obtain a rough positioning map of the face;

[0106] Step 2. Human eye positioning based on the ASEF (Average of Synthetic Exact Filters) filter. First, the filter needs to be trained using pictures, and the driver video data obtained through the driving recorder is disassembled into a sequence of pictures as training samples. Manually specify the center position of the left eye and right eye for each picture as the output, so that each sequence picture and output are a pair of training pairs, and the training pair is input into the ASEF filter for training, and the human eye ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of driver intention mode recognition and machine learning, and particularly relates to a driver lane changing intention recognition method based on a Gaussian mixture hidden Markov model. The lane changing driving intention recognition method based on the actual measurement data of the vehicle-mounted sensor comprises the steps that whether a driver hasa lane changing intention or not is judged by observing the action of a rearview mirror and the state of controlling a steering wheel of the driver, and meanwhile whether a lane changing requirementexists or not currently is judged by monitoring the current road condition state. According to the method, the driving intention most likely to be generated by the current driver is speculated based on the Gaussian mixture hidden Markov model, the burden of the driver can be relieved on the premise that safety is guaranteed, the comfort degree of the driver is improved, and if a dangerous situation occurs, handling can be conducted earlier to avoid accidents.

Description

technical field [0001] The invention belongs to the technical field of driver intention pattern recognition and machine learning, and in particular relates to a driver lane-changing intention recognition method based on a Gaussian mixture hidden Markov model. Background technique [0002] In recent years, the level of automobile intelligence has been continuously improved. In the process of intelligence, the joint driving of the car by the driver and the intelligent control system is still a hot spot in current research. As the relatively most unstable main factor in the human-vehicle-road closed-loop system, the driver often exhibits different driving characteristics during the driving process. At present, when the automotive active safety assistance system represented by the advanced driver assistance system evaluates the traffic safety situation, it often perceives the surrounding environment information and the state of the vehicle through radar or vision, ignoring the d...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/00G06N20/00
CPCG06N20/00G06V40/161G06V40/171G06V20/597
Inventor 曲婷王一男曲文奇于树友
Owner JILIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products