Driver misoperation risk early warning method and system

A technology for risk warning and driving personnel, applied in neural learning methods, predictions, alarms, etc., can solve the problems of impossible driving operation, lack of scientific and effective proof, and distinction, so as to improve accuracy and increase risk The effect of predictive power

Pending Publication Date: 2021-07-30
合肥中聚源智能科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The defective that above-mentioned prior art exists is: original technical limitation is:
[0012] (1) The original technology did not distinguish the two concepts of cognitive load and misoperation. From the perspective of cognitive neuroscience and ergonomics, high cognitive load does not mean that misoperation must occur. Influencing factors also include negative emotions, attentional bias, and other factors. Therefore, when designing and developing early warning equipment for misoperation, other factors that affect misoperation should be further included in the early warning predictor variables when considering cognitive load detection;
[0013] (2) Many technologies in the original technology have not been considered applicable to the driving environment and driving scene. Place large sensing and computing devices inside;
[0014] (3) Many technologies in the original technology have not been tested in real driving scenes or simulation scenes specially oriented to driving characteristics, and experimental data have been obtained, and early warning models have been designed based on these experimental data, which lacks scientific and effective proof

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 misoperation risk early warning method and system
  • Driver misoperation risk early warning method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to further illustrate the features of the present invention, please refer to the following detailed description and accompanying drawings of the present invention. The accompanying drawings are for reference and description only, and are not intended to limit the protection scope of the present invention.

[0055] Such as figure 1 As shown, this embodiment discloses a method for early warning of driver's misoperation risk, which includes the following steps:

[0056] S1. Obtain the real-time driving video of the driver to be tested as the data to be tested;

[0057] S2. Analyze the data to be tested to obtain predictor variables, and convert the predictor variables into corresponding predictor vectors;

[0058] The specifics are: segment the data video to be tested according to time series, divide it into a video unit every 10 seconds, and extract 50 pictures per second from a video unit. For the extracted 500 pictures per unit video, establish 8 points to d...

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 driver misoperation risk early warning method and system, and belongs to the technical field of intelligent driving; the method comprises the steps: obtaining a real-time driving video of a to-be-detected driver as to-be-detected data; analyzing the to-be-measured data to obtain a prediction variable, and converting the prediction variable into a corresponding prediction vector; and taking the prediction vector as an input of a pre-trained risk early warning model to obtain a risk early warning result of the to-be-tested driver. According to the method, the influence of cognitive load on misoperation is considered, the action of action coordination degree and negative emotion variables is also added, risk factors of the misoperation are considered more completely, and the risk prediction capability and prediction accuracy of the misoperation are greatly improved.

Description

technical field [0001] The invention relates to the technical field of intelligent driving, in particular to a risk warning method and system for a driver's misoperation. Background technique [0002] At present, the driver's driving state is generally judged by the driver's performance during the driving process. The cognitive load detection methods in the existing technology mainly include the following types: [0003] (1) Subjective measurement method: the subjects are required to state their own cognitive load and make a self-evaluation report on their own experience state; [0004] (2) Task performance measurement method: through the task performance, behavior records, and test scores obtained by the subjects under different cognitive load conditions, the degree of cognitive load can be inferred from the level of performance and performance; [0005] (3) Physiological correlation test method: By establishing the correlation between physiological signals and cognitive l...

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): G06K9/00G06N3/04G06N3/08G06Q10/04G06Q10/06G06Q50/30G08B31/00
CPCG06N3/04G06N3/08G06Q10/04G06Q10/0635G08B31/00G06V40/161G06V40/174G06V40/18G06V20/597G06Q50/40
Inventor 孙晓汪萌
Owner 合肥中聚源智能科技有限公司
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