CN-122009076-A - Method, device, equipment and program product for monitoring vehicle safety in rest mode

CN122009076ACN 122009076 ACN122009076 ACN 122009076ACN-122009076-A

Abstract

The invention discloses a vehicle safety monitoring method, device, equipment and program product under a rest mode, which comprises the steps of when a target vehicle starts the rest mode, detecting that rest personnel exist in the target vehicle, acquiring temperature time sequence data and air component time sequence data in the target vehicle, acquiring face image time sequence data of the rest personnel, identifying cabin environment comfort level of the target vehicle according to the temperature time sequence data and the air component time sequence data, identifying physiological state health level of the rest personnel according to the face image time sequence data, judging whether the rest personnel has safety risk according to the cabin environment comfort level and the physiological state health level, and when the rest personnel has safety risk, carrying out early warning on the rest personnel and starting an emergency plan. The invention ensures the safety of rest staff in the vehicle in a rest mode, improves the safety of the vehicle, and can be applied to the technical field of vehicle monitoring.

Inventors

LU GUOPENG
Zou Ruixing
DONG HAOXUAN

Assignees

广汽本田汽车有限公司
广汽本田汽车研究开发有限公司

Dates

Publication Date: 20260512
Application Date: 20260401

Claims (10)

1. A method for vehicle safety monitoring in a rest mode, comprising the steps of: When a target vehicle starts a rest mode, detecting that rest staff exists in the target vehicle, acquiring temperature time sequence data and air component time sequence data in the target vehicle, and acquiring facial image time sequence data of the rest staff; identifying cabin environmental comfort of the target vehicle from the temperature timing data and the air composition timing data; Identifying the physiological state health degree of the rest personnel according to the facial image time sequence data; Judging whether the rest personnel have safety risks according to the cabin environment comfort level and the physiological state health level; and when the rest personnel have safety risks, early warning is carried out on the rest personnel and an emergency plan is started.
2. The method for monitoring vehicle safety in a rest mode according to claim 1, wherein the acquiring temperature time series data and air composition time series data in the target vehicle and acquiring facial image time series data of the rest person specifically comprises: acquiring the temperature time series data through a plurality of temperature sensors arranged at different positions in the target vehicle; acquiring the air composition time sequence data through a multi-gas sensor module arranged in the target vehicle; acquiring the facial image time series data through a vehicle-mounted camera arranged in the target vehicle; wherein when the rest mode is not interrupted, the temperature sensor, the multi-gas sensor module and the vehicle-mounted camera are kept in an intermittent acquisition mode, when the rest mode is interrupted, the temperature sensor, the multi-gas sensor module and the vehicle-mounted camera are switched to a real-time acquisition mode.
3. The method for monitoring vehicle safety in a rest mode according to claim 1, wherein the identifying the cabin environmental comfort of the target vehicle according to the temperature time series data and the air composition time series data specifically comprises: Predicting the temperature of a target cabin at the next moment according to the temperature time sequence data, and predicting the target air composition at the next moment according to the air composition time sequence data; Comparing the target cabin temperature with a preset comfortable temperature interval to obtain a temperature adaptation degree score; Comparing the target air component with a preset air component proportion to obtain an air adaptation degree score, And determining the cabin environment comfort level according to the temperature adaptation degree score and the air adaptation degree score.
4. The method for monitoring vehicle safety in a rest mode according to claim 1, wherein the step of identifying the physiological state health of the rest person according to the facial image time series data specifically comprises the steps of: Extracting regional image time sequence data of a forehead region and/or a cheek region according to the facial image time sequence data; respectively performing time domain sampling on the red channel pixel value, the green channel pixel value and the blue channel pixel value of the regional image time sequence data to obtain a multi-channel light intensity signal; inputting the multichannel light intensity signals into a pre-trained heart rate recognition model to obtain the real-time heart rate of the rest staff; Extracting micro-motion data of a plurality of facial key points according to the facial image time sequence data; performing time domain analysis on the micro-motion data to obtain a respiratory frequency band signal; Determining the real-time respiratory frequency of the rest personnel according to the respiratory frequency band signal; Comparing the real-time heart rate with a preset normal heart rate interval to obtain a heart rate health score; Comparing the real-time respiratory rate with a preset normal respiratory rate interval to obtain a respiratory rate health score; determining the physiological state health from the heart rate health score and the respiratory rate health score.
5. The method for monitoring vehicle safety in a rest mode according to claim 4, wherein the heart rate identification model is trained by the following steps: acquiring a facial image time sequence sample of a tester, and determining a corresponding heart rate label according to the actually measured heart rate of the tester; Extracting a regional image time sequence sample of a forehead region and/or a cheek region according to the facial image time sequence sample; respectively performing time domain sampling on the red channel pixel value, the green channel pixel value and the blue channel pixel value of the regional image time sequence sample to obtain a multichannel light intensity signal sample; inputting the multichannel light intensity signal sample into a pre-constructed multi-branch convolutional neural network to obtain a predicted heart rate; determining a loss value from the predicted heart rate and the heart rate label; and updating parameters of the multi-branch convolutional neural network through a back propagation algorithm according to the loss value to obtain the trained heart rate recognition model.
6. The method for monitoring vehicle safety in a rest mode according to claim 1, wherein the step of determining whether the rest person has a safety risk according to the cabin environment comfort level and the physiological state health level comprises the following steps: when the cabin environmental comfort level is greater than or equal to a preset first threshold value and the physiological state health level is greater than or equal to a preset second threshold value, judging that the rest personnel are not at safety risk; When the cabin environmental comfort level is smaller than the first threshold value and the physiological state health level is larger than or equal to the second threshold value, judging that the rest personnel have slight safety risks; when the cabin environmental comfort level is greater than or equal to the first threshold value and the physiological state health level is less than the second threshold value, judging that the rest personnel have moderate safety risks; And when the cabin environmental comfort level is smaller than the first threshold value and the physiological state health level is smaller than the second threshold value, judging that the rest personnel have serious safety risks.
7. The method for monitoring vehicle safety in a rest mode according to any one of claims 1 to 6, wherein the pre-warning of the rest person and the initiation of an emergency plan specifically comprises: matching corresponding voice reminding contents according to the security risk level, playing the voice reminding contents through a voice reminding module, and detecting whether the rest personnel perform response operation or not; and when the rest personnel do not respond to operation within a preset period of time, adjusting the air conditioner and/or the vehicle window of the target vehicle according to the comfort level of the cabin environment, and sending help seeking information to a cloud platform according to the health level of the physiological state.
8. A vehicle safety monitoring device in a rest mode, comprising: The data acquisition module is used for acquiring temperature time sequence data and air composition time sequence data in the target vehicle and acquiring facial image time sequence data of the rest staff when the target vehicle starts a rest mode and the rest staff in the target vehicle is detected; a cabin environment recognition module for recognizing cabin environment comfort of the target vehicle according to the temperature time series data and the air composition time series data; The physiological state identification module is used for identifying the physiological state health degree of the rest personnel according to the facial image time sequence data; the safety risk judging module is used for judging whether the rest personnel have safety risks according to the comfort level of the cabin environment and the health level of the physiological state; And the early warning module is used for carrying out early warning on the rest personnel and starting an emergency plan when the rest personnel have safety risks.
9. An electronic device, comprising: At least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor is caused to implement a method of vehicle safety monitoring in a nap mode as claimed in any one of claims 1 to 7.
10. A computer program product comprising a computer program which, when executed by a processor, implements a method of vehicle safety monitoring in a rest mode as claimed in any one of claims 1 to 7.

Description

Method, device, equipment and program product for monitoring vehicle safety in rest mode Technical Field The invention relates to the technical field of vehicle monitoring, in particular to a vehicle safety monitoring method, device, equipment and program product under a rest mode. Background With the continuous richness of automobile functions, more and more vehicles are equipped with a rest mode in order to meet the requirements of users for short rest in the automobile. The mode generally adjusts the angle of the vehicle seat, closes part of unnecessary electric equipment, opens an air conditioner to keep comfortable temperature in the vehicle, and provides a comfortable rest environment for users. However, the existing vehicle has obvious potential safety hazard that when the rest mode is automatically interrupted for a preset time or the air conditioning system is abnormally stopped due to faults, insufficient electric quantity and the like, the system can simply terminate the related functions of the rest and can not send any alarm prompt to rest staff in the vehicle. At this time, the interior of the vehicle is in a relatively airtight environment, and along with the breathing of rest staff, the oxygen concentration in the vehicle can gradually decrease, and meanwhile, if the external temperature is higher, the temperature in the vehicle can rapidly rise. Because the rest staff is in a sleeping or light sleeping state, the environment change is difficult to detect, the rest staff is extremely easy to fall into dangers such as hypoxia, heatstroke and the like, and even the life safety of the rest staff is endangered in serious cases. The above problems need to be solved. Disclosure of Invention The present invention aims to solve at least one of the technical problems existing in the prior art to a certain extent. Therefore, an object of the embodiments of the present invention is to provide a vehicle safety monitoring method in a rest mode, which ensures safety of rest personnel in a vehicle in the rest mode and improves safety of the vehicle. It is another object of an embodiment of the present invention to provide a vehicle safety monitoring device in a rest mode. In order to achieve the technical purpose, the technical scheme adopted by the embodiment of the invention comprises the following steps: in one aspect, an embodiment of the present invention provides a method for monitoring vehicle safety in a rest mode, including the following steps: When a target vehicle starts a rest mode, detecting that rest staff exists in the target vehicle, acquiring temperature time sequence data and air component time sequence data in the target vehicle, and acquiring facial image time sequence data of the rest staff; identifying cabin environmental comfort of the target vehicle from the temperature timing data and the air composition timing data; Identifying the physiological state health degree of the rest personnel according to the facial image time sequence data; Judging whether the rest personnel have safety risks according to the cabin environment comfort level and the physiological state health level; and when the rest personnel have safety risks, early warning is carried out on the rest personnel and an emergency plan is started. Further, in one embodiment of the present invention, the acquiring temperature time series data and air composition time series data in the target vehicle, and acquiring facial image time series data of the rest person, specifically includes: acquiring the temperature time series data through a plurality of temperature sensors arranged at different positions in the target vehicle; acquiring the air composition time sequence data through a multi-gas sensor module arranged in the target vehicle; acquiring the facial image time series data through a vehicle-mounted camera arranged in the target vehicle; wherein when the rest mode is not interrupted, the temperature sensor, the multi-gas sensor module and the vehicle-mounted camera are kept in an intermittent acquisition mode, when the rest mode is interrupted, the temperature sensor, the multi-gas sensor module and the vehicle-mounted camera are switched to a real-time acquisition mode. Further, in one embodiment of the present invention, the identifying cabin environment comfort level of the target vehicle according to the temperature time series data and the air composition time series data specifically includes: Predicting the temperature of a target cabin at the next moment according to the temperature time sequence data, and predicting the target air composition at the next moment according to the air composition time sequence data; Comparing the target cabin temperature with a preset comfortable temperature interval to obtain a temperature adaptation degree score; Comparing the target air component with a preset air component proportion to obtain an air adaptation degree score, And determining the cabin environment comfort le