CN-121987003-A - Helmet wearing intelligent detection method and device and electronic equipment

CN121987003ACN 121987003 ACN121987003 ACN 121987003ACN-121987003-A

Abstract

The invention provides a helmet wearing intelligent detection method, device and electronic equipment, wherein the method comprises the steps of obtaining a first acceleration signal of a vehicle and a second acceleration signal of the helmet, selecting the same frequency band from frequency domain signals of the first acceleration signal and frequency domain signals of the second acceleration signal based on a preset frequency band selection strategy to obtain a first frequency band signal and a second frequency band signal, wherein the first frequency band signal and the second frequency band signal are frequency bands with the energy ratio of active motion components of the head of a human body lower than a preset threshold value, determining characteristic parameters of a neck transfer function based on the first frequency band signal and the second frequency band signal, determining coherence coefficient characteristics of the first acceleration signal and the second acceleration signal based on components of the first acceleration signal and the second acceleration signal in the same frequency band, and determining whether the helmet is in a wearing state based on the characteristic parameters of the neck transfer function, the coherence coefficient characteristics and a pre-trained classifier. By implementing the invention, the wearing detection accuracy of the helmet can be improved.

Inventors

WU LICHENG

Assignees

北京快松果科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260326

Claims (10)

1. The intelligent detection method for helmet wearing is characterized by comprising the following steps: Acquiring a first acceleration signal of a vehicle and a second acceleration signal of a helmet in the running process of the vehicle; Based on a preset frequency band selection strategy, selecting the same frequency band from the frequency domain signal of the first acceleration signal and the frequency domain signal of the second acceleration signal to obtain a first frequency band signal and a second frequency band signal, wherein the first frequency band signal and the second frequency band signal are frequency bands with the energy ratio of the active motion component of the human head lower than a preset threshold; determining characteristic parameters of the neck transfer function based on the first frequency band signal and the second frequency band signal; based on the components of the first acceleration signal and the second acceleration signal in the same frequency band, determining the coherence coefficient characteristics of the first acceleration signal and the second acceleration signal; Based on the characteristic parameters of the neck transfer function, the coherence coefficient characteristics and the pre-trained classifier, whether the helmet is in a wearing state or not is determined.
2. The method for intelligently detecting the wearing of the helmet according to claim 1, wherein the step of selecting the same frequency band from the frequency domain signal of the first acceleration signal and the frequency domain signal of the second acceleration signal based on a preset frequency band selection strategy to obtain a first frequency band signal and a second frequency band signal comprises the steps of: Acquiring a target frequency band based on the current position of the vehicle, wherein the target frequency band is predetermined based on the road surface characteristics of the current position when the target frequency band is the last target road section, and the last target road section is the road section which the vehicle passes in a target time period before the current position; And selecting a target frequency band from the frequency domain signal of the first acceleration signal and the frequency domain signal of the second acceleration signal to obtain a first frequency band signal and a second frequency band signal.
3. The headgear-worn intelligent detection method according to claim 1, wherein determining the coherence coefficient characteristic of the first acceleration signal and the second acceleration signal based on the components of the two signals within the same frequency band comprises: performing frequency band screening and inverse transformation on the first acceleration signal and the second acceleration signal to obtain a first frequency band time domain signal and a second frequency band time domain signal; Carrying out framing treatment on the first frequency band time domain signal and the second frequency band time domain signal to obtain a plurality of first acceleration time frames and a plurality of second acceleration time frames; transforming the first frequency band time domain signal and the second frequency band time domain signal in each time frame to a frequency domain to obtain a first frequency domain frame signal and a second frequency domain frame signal; determining a first power spectral density according to the first frequency domain frame signal, and determining a second power spectral density according to the second frequency domain frame signal; Determining cross power spectral density according to the first frequency domain frame signal and the second frequency domain frame signal; calculating a coherence function according to the first power spectral density, the second power spectral density and the cross power spectral density; Based on the coherence function, coherence coefficient features are extracted.
4. The headgear wear intelligent detection method of claim 1, further comprising: Continuously acquiring a preset number of groups of first acceleration signals and second acceleration signals when the vehicle is in an unworn state; based on a plurality of groups of first acceleration signals and second acceleration signals, a plurality of corresponding groups of coherence coefficient characteristics and neck transfer function characteristics are calculated respectively; Obtaining a plurality of groups of wearing state results based on a plurality of groups of coherence coefficient features, neck transfer function features and pre-trained classifiers; when the multiple groups of wearing state results meet the unworn condition, triggering the sound and light alarm of the helmet and the speed limiting prompt of the vehicle; when the wearing state results of the multiple groups do not meet the unworn condition, the instantaneous signal is judged to be abnormal, and the alarm is not triggered.
5. The headgear wear intelligent detection method of claim 4, wherein the determining of the preset number of sets of first acceleration signals and second acceleration signals comprises: Determining a signal fluctuation amplitude based on the first frequency band signal and the second frequency band signal; And determining the magnitude of the preset quantity based on the signal fluctuation amplitude, wherein the larger the signal fluctuation amplitude is, the larger the preset quantity is.
6. The headgear wear intelligent detection method according to claim 2, wherein the determining of the frequency band adjustment parameter includes: In the last target road section, determining the road surface condition of the current position through a map and a road condition database; classifying the roads according to road surface conditions to obtain road surface classification of the current position; Based on the road surface grading of the current position, correspondingly matching a preset frequency band adjustment reference value; Acquiring the average running speed of the last target road section; And calibrating the frequency band adjustment reference value based on the average running speed of the last target road section to obtain the final frequency band adjustment parameter.
7. The intelligent detection method for helmet wearing according to any one of claims 1 to 6, wherein the pre-trained classifier is a CNN-LSTM fusion classifier, and the training sample set includes neck transfer function characteristic parameters and coherence coefficient characteristics corresponding to helmet wearing and non-wearing states under different road surface grades and different running speeds.
8. Intelligent detection device is worn to helmet, a serial communication port includes: The signal acquisition module is used for acquiring a first acceleration signal of the vehicle and a second acceleration signal of the helmet in the running process of the vehicle; The frequency band selection module is used for selecting the same frequency band from the frequency domain signal of the first acceleration signal and the frequency domain signal of the second acceleration signal based on a preset frequency band selection strategy to obtain a first frequency band signal and a second frequency band signal, wherein the first frequency band signal and the second frequency band signal are frequency bands with the energy ratio of the active motion component of the head of the human body lower than a preset threshold value; the characteristic parameter determining module is used for determining characteristic parameters of the neck transfer function based on the first frequency band signal and the second frequency band signal; The coherence coefficient determining module is used for determining the coherence coefficient characteristics of the first acceleration signal and the second acceleration signal based on the components of the first acceleration signal and the second acceleration signal in the same frequency band; the wearing judgment module is used for determining whether the helmet is in a wearing state or not based on the characteristic parameters of the neck transfer function, the coherence coefficient characteristics and the classifier trained in advance.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor performs the steps of a helmet-wear smart detection method according to any one of the preceding claims 1-7.
10. A computer storage medium having stored thereon computer instructions which, when executed by a processor, perform the steps of a headgear wear intelligent detection method according to any of claims 1-7.

Description

Helmet wearing intelligent detection method and device and electronic equipment Technical Field The invention belongs to the technical field of safe driving of vehicles, and particularly relates to a helmet wearing intelligent detection method and device and electronic equipment. Background With the popularization of two-wheeled vehicles (such as motorcycles and electric vehicles) and engineering work vehicles, riding safety and work safety are increasingly paid attention to. Helmets are a key equipment for protecting the safety of the head, and the wearing condition of the helmets is directly related to the life safety of personnel. However, in practical applications, the phenomenon that the helmet is not worn or is not worn regularly is often restricted, which results in frequent safety accidents. In the related art, the motion state of the helmet is judged by an acceleration sensor arranged in the helmet. However, when the vehicle runs on a bumpy road, the helmet is highly coupled with the motion of the vehicle, and it is difficult to distinguish whether the helmet is worn on the head or placed on the vehicle, resulting in a high false positive rate. Disclosure of Invention Therefore, the invention aims to provide a helmet wearing intelligent detection method, a helmet wearing intelligent detection device and electronic equipment, so as to meet the requirement of improving the helmet wearing detection precision. In order to achieve the above purpose, the present invention provides the following technical solutions: According to a first aspect, the invention provides an intelligent helmet wearing detection method, which comprises the steps of obtaining a first acceleration signal of a vehicle and a second acceleration signal of the helmet in the running process of the vehicle, selecting the same frequency band from a frequency domain signal of the first acceleration signal and a frequency domain signal of the second acceleration signal based on a preset frequency band selection strategy to obtain a first frequency band signal and a second frequency band signal, wherein the first frequency band signal and the second frequency band signal are frequency bands with the energy ratio of active motion components of the head of a human body lower than a preset threshold value, determining characteristic parameters of a neck transfer function based on the first frequency band signal and the second frequency band signal, determining the characteristics of coherence coefficients of the first acceleration signal and the second acceleration signal based on the components of the first acceleration signal and the second acceleration signal in the same frequency band, and determining whether the helmet is in a wearing state based on the characteristic parameters of the neck transfer function, the coherence coefficient characteristics and a pre-trained classifier. Optionally, the same frequency band is selected from the frequency domain signal of the first acceleration signal and the frequency domain signal of the second acceleration signal based on a preset frequency band selection strategy to obtain a first frequency band signal and a second frequency band signal, wherein the method comprises the steps of acquiring a target frequency band based on the current position of a vehicle, when the target frequency band is a last target road section, determining the last target road section as a road section passed by the vehicle in a target time period before the current position based on the road surface characteristic of the current position, and selecting the target frequency band from the frequency domain signal of the first acceleration signal and the frequency domain signal of the second acceleration signal to obtain the first frequency band signal and the second frequency band signal. The method comprises the steps of selecting a first acceleration signal and a second acceleration signal according to a frequency band, carrying out inverse transformation on the first acceleration signal and the second acceleration signal to obtain a first frequency band time domain signal and a second frequency band time domain signal, carrying out framing processing on the first frequency band time domain signal and the second frequency band time domain signal to obtain a plurality of first acceleration time frames and a plurality of second acceleration time frames, transforming the first frequency band time domain signal and the second frequency band time domain signal in each time frame to a frequency domain to obtain a first frequency domain frame signal and a second frequency domain frame signal, determining a first power spectrum density according to the first frequency domain frame signal and the second frequency domain frame signal, determining a second power spectrum density according to the first frequency domain frame signal and the second frequency domain frame signal, calculating a coherence function according to the first p