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

A driving intention recognition method based on improved hmm and svm double-layer algorithm

A driving intention and recognition method technology, applied in character and pattern recognition, computing, computer parts, etc., can solve the problems of not considering driver information, single learning model, and few classifications of driving intentions

Active Publication Date: 2021-02-12
江苏易齐物流有限公司
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can be seen that the existing driver's driving intention recognition system has fewer classifications of driving intentions, and only considers the motion state of the vehicle and the information of the road, without considering the information of the driver itself, and the classification learning model is relatively simple.

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
  • A driving intention recognition method based on improved hmm and svm double-layer algorithm
  • A driving intention recognition method based on improved hmm and svm double-layer algorithm
  • A driving intention recognition method based on improved hmm and svm double-layer algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The specific embodiments of the present invention will be described in conjunction with the accompanying drawings, so that future researchers can better understand the present invention.

[0030] figure 1 It is the flow chart of driver's driving intention recognition based on the improved HMM and SVM double-layer algorithm. Introduce the main idea of ​​the present invention as a whole, first collect and preprocess the data to obtain the training vector, then train the first-layer HMM classifier and the second-layer SVM classifier at the same time, and secondly eliminate the identifiable vector through the first-layer HMM classifier. The intention is to reduce the burden of the second layer SVM classifier. The training vector corresponding to the confusing intention in the first layer is imported into the second layer SVM classifier to complete the recognition of the driver's driving intention through the voting algorithm.

[0031] figure 2 Hidden Markov schematic. ...

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 discloses a driving intention recognition method based on an improved HMM and SVM double-layer algorithm. Step 1: Classify the driver's driving intention: classify the driver's driving intention into sudden left lane change, normal left lane change, lane keeping, Five categories of normal right lane change and emergency right lane change; Step 2: Experimental data collection and processing; Step 3: Offline training of the improved HMM and SVM two-layer algorithm; Step 4: Driver's driving intention recognition. The present invention completely considers the people-vehicle-road system, collects the information of the vehicle, the road and the driver, adopts the HMM and SVM double-layer learning model, and improves the accuracy and timeliness of the driver's lane-changing intention identification model.

Description

technical field [0001] The invention relates to the technical field of vehicle intelligent driving and active safety, in particular to a driving intention recognition method based on an improved HMM and SVM double-layer algorithm. Background technique [0002] Road accidents are usually caused by some non-standard driving behaviors of drivers, and road accidents caused by lane changing process account for about 23% of the total number of traffic accidents caused by improper driver operations. Therefore, it is of great significance to reduce the occurrence of road accidents and improve the safety level of motor vehicles to carry out the research on driver's driving intention recognition through the system's complete perception of the driver's operation behavior in the process of changing lanes. [0003] At present, some advanced driver intention recognition systems have been applied in real vehicles. The current common driver's driving intention recognition system is mainly ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62B60W40/09
CPCB60W40/09G06F18/2411G06F18/295
Inventor 刘志强吴雪刚倪捷汪澎
Owner 江苏易齐物流有限公司
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com