A Systematic Driving Behavior Recognition Method Based on Clustering Thought

A recognition method and behavior technology, applied in the field of driving behavior recognition, can solve problems such as gaps in practical applications, and achieve the effects of good universality and efficiency, low calculation amount, and strong theoretical basis.

CN108229304BInactive Publication Date: 2021-04-16SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
6 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2021-04-16
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a systematic driving behavior recognition method based on the idea of ​​clustering. The driving behavior recognition method includes the following steps: establishing a statistical feature model; using an inertial sensor to collect driving behavior data; using a Kalman filter to Filtering the data; using an adaptive window function method to extract effective driving behavior data on the filtered data, and further extracting the statistical features of the effective data; screening to obtain the optimal statistical features; classifying the statistical features of the driving behavior data , to identify the corresponding driving behavior. Based on the idea of ​​clustering, the present invention provides a systematic driving behavior recognition method with very few features, very low calculation amount and high precision, which has broad application prospects in the fields of social security, auto insurance, fleet management and the like.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] Based on the idea of ​​clustering, the present invention proposes a systematic driving behavior recognition method, which belongs to the fields of signal processing, pattern recognition and machine learning. Background technique

[0002] According to data from the Traffic Management Bureau of the Ministry of Public Security, as of the end of June 2017, the number of motor vehicles in the country reached 304 million, including 205 million cars. While the popularity of automobiles brings convenience to people's lives, it also brings potential safety hazards that cannot be ignored. According to data from the National Bureau of Statistics, there were 187,781 traffic accidents across the country in 2015, including 170,130 motor vehicle traffic accidents, and a total of 58,022 deaths in traffic accidents, posing a great threat to life safety. However, frequent traffic accidents are mainly due to people's dangerous driving. According to statistical analysis...

Examples

Embodiment Construction

[0030] The objects and functions of the present invention and methods for achieving the objects and functions will be clarified by referring to the exemplary embodiments. However, the present invention is not limited to the exemplary embodiments disclosed below; it can be implemented in various forms. The essence of the description is only to help those skilled in the relevant art comprehensively understand the specific details of the present invention.

[0031] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0032] figure 1 Shown is the flowchart of the systematic method for driving behavior recognition of the present invention, as figure 1 As shown, a systematic clustering-based driving behavior recognition method includes the following steps:

[0033] S1: Based on the idea of ​​clustering,...