A method for simulating personalized driving characteristics of vehicles based on video samples

A technology of driving characteristics and simulating vehicles, which is applied in the field of simulating personalized driving characteristics of vehicles based on video samples. It can solve the problems of large time and space overhead, limited vehicle behavior parameters and states, etc., and achieves a simple and novel method with great realistic guiding significance , the effect of solving the problem of lack of authenticity

Active Publication Date: 2016-09-14
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This reconstruction method requires considerable time and space overhead, and the vehicle behavior parameters and states that can be simulated are very limited

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 method for simulating personalized driving characteristics of vehicles based on video samples
  • A method for simulating personalized driving characteristics of vehicles based on video samples
  • A method for simulating personalized driving characteristics of vehicles based on video samples

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The technical solution of the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments, and the following embodiments do not constitute a limitation of the present invention.

[0044] In order to simulate the personalized driving characteristics of the vehicle, the present invention firstly inputs a section of real traffic video sample (that is, real traffic video), and obtains real vehicle trajectory data of each vehicle in the traffic video. Then these real vehicle trajectory data are input as training samples, and the adaptive genetic algorithm is used to find the optimal personalized parameters of the vehicle behavior control model that best conforms to the real trajectory data, which can be used for traffic flow reconstruction or simulation and real traffic video A virtual traffic flow with similar characteristics. Refer to the specific implementation method figure 1 , including the following steps: ...

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 method for simulating a vehicle personalized driving characteristic based on a video sample. The method comprises the followingsteps: acquiring real vehicle track data of each vehicle in real traffic video; simulating an optimal personalized parameter of a vehicle behavior control model according to the real vehicle track data; and performing traffic flow reconstruction and sample-based traffic simulation animation by using the optimal personalized parameter. The method is simple and novel; the problem of lack of authenticityin dummy traffic simulation is solved excellently; the method has great practical guiding significance;the adopted vehicle behavior control model is an IDMM (Intelligent Driver Model with Memory) model;and the adaptability of the vehicle to the current traffic environment can be embodied to a certain extent, so that a simulation result is closer to a real world traffic flow. In addition, an adaptive genetic algorithm is adopted, the integralperformance of the conventional genetic algorithm is improved, the convergence speed of the algorithm is quickened, and meanwhile, the method guarantees that the obtained optimal personalized parameter is the globally optimal solution rather than locally optimal solution.

Description

technical field [0001] The invention belongs to the field of virtual reality, in particular to a method for simulating personalized driving characteristics of a vehicle based on video samples. Background technique [0002] With the gradual popularization of motor vehicles and the sharp increase in transportation demand, road traffic has brought more and more negative impacts on people's lives --- traffic congestion, traffic accidents and environmental pollution. Traffic management has become a global problem with direct economic, environmental and energy impacts. On the other hand, with the continuous development of computer group simulation technology, traffic simulation has been widely used in computer animation, 3D games and virtual reality, and more and more 3D visualization software such as Google Maps and Virtual Earth The tools have been maturely applied, and the demand for adding 3D traffic animation simulation (such as car group animation) in the virtual 3D scene i...

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): G06F17/50G06N3/12
Inventor 粆倩文金小刚
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products