Automobile running speed detection method based on smart phone audio perception

A technology of driving speed and smart phones, applied in the direction of neural learning methods, measuring devices, computer components, etc., can solve the problems of high cost and weak anti-interference, and achieve low cost, strong anti-interference, and not easy to interfere Effect

Pending Publication Date: 2021-01-15
BEIJING INSTITUTE OF TECHNOLOGYGY
0 Cites 2 Cited by

AI-Extracted Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the current technical problem of high cost or low anti-interference in monitoring vehic...
View more

Abstract

The invention discloses an automobile running speed detection method based on smart phone audio perception. According to the method, a microphone of a smart phone is used for collecting sound signalsgenerated when an automobile runs, and the speed interval to which the automobile speed belongs is determined by analyzing the characteristics of the sound signals; meanwhile, a simple sonar system isformed by a loudspeaker and a microphone of the smart phone, and the speed of moving objects around pedestrians is obtained by analyzing high-frequency sound signals which are collected by the microphone, emitted by the loudspeaker and reflected by the moving objects. Finally, the speed of the automobile passing through the user is detected by combining the two results. According to the invention, high-frequency sound which cannot be perceived by human ears is emitted only by means of the loudspeaker in the smart phone, the microphone receives sound signals, the deployment cost is low, the anti-interference performance is strong, the privacy leakage problem does not exist, and the method is especially suitable for detection environments where vehicles sequentially pass and vehicles and pedestrians are close to each other, and has very high accuracy.

Application Domain

Character and pattern recognitionNeural architectures +2

Technology Topic

Automotive engineeringLoudspeaker +8

Image

  • Automobile running speed detection method based on smart phone audio perception
  • Automobile running speed detection method based on smart phone audio perception
  • Automobile running speed detection method based on smart phone audio perception

Examples

  • Experimental program(1)

Example Embodiment

[0054]Example
[0055]In order to test the performance of this method, this method was written as an Android application and deployed in different models of Android phones. And recruited 6 volunteers, 3 as drivers driving different vehicles, 3 as pedestrians carrying mobile phones for testing. In order to ensure safety, an open and empty road is chosen as the experimental site.
[0056]First, test the overall error of this method in various situations.figure 2 Shows the cumulative distribution function of the speed detection error of electric vehicles, gasoline vehicles and the whole. It can be seen from the figure that 90% of electric vehicles have a speed detection error of less than 2.9km/h; 90% of gasoline vehicles have a speed detection error of less than 2.4km/h; 90% of the overall detection error is less than 2.7km/h, which fully explains This method has smaller errors and higher accuracy.
[0057]Then, test the accuracy of the electric vehicle speed range classifier.image 3 Shows the confusion matrix of electric vehicle speed range detection. It can be seen from the figure that the recognition accuracy of each speed range is above 91.2%, and the average recognition accuracy is 97.3%. A very small amount of data is divided into adjacent speed intervals because a small amount of speed is on the boundary of the interval, and there is a certain probability that it will be misclassified into other intervals. The gasoline vehicle speed range classifier has similar performance, which reflects the high accuracy of the present invention.
[0058]Finally, test the detection accuracy of this method in different scenarios.Figure 4Shows the average detection error on campuses, residential areas, edge streets and rural roads. It can be seen from the figure that campuses and residential areas are generally quieter, so the detection errors in these two areas are lower; small streets have more noise , Rural roads are not smooth and easily cause vehicle bumps, so the detection error in these two areas is slightly higher. However, the speed detection error in all scenarios does not exceed 3.3 km/h, which reflects the high universality of the present invention.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.

Similar technology patents

Material including graphene and an inorganic material and method of manufacturing the material

ActiveUS20110129675A1reduce defectlow cost
Owner:SAMSUNG ELECTRONICS CO LTD +1

Haptic trackball device

InactiveUS7710399B2simple actuatorlow cost
Owner:IMMERSION CORPORATION

Mobile authentication for network access

ActiveUS20060069916A1low cost
Owner:ALCATEL LUCENT SAS

Classification and recommendation of technical efficacy words

  • low cost
  • Strong anti-interference

System and method for transmitting wireless digital service signals via power transmission lines

ActiveUS7929940B1reduce bandwidth requirementlow cost
Owner:NEXTEL COMMUNICATIONS

System and method for determination of position

InactiveUS20090149202A1low costreduce requirement
Owner:STEELE CHRISTIAN

Adaptive antenna optimization network

InactiveUS6961368B2low costminimal space
Owner:ERICSSON INC

Antenna device and method for attaching the same

ActiveUS20150138022A1low costimproved strength characteristic
Owner:NEC CORP

Urban road obstacle recognition system

InactiveCN103914688AStrong anti-interferenceRaise the level of research and application
Owner:UNIV OF SCI & TECH BEIJING
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