In-vehicle life body detection method and device, vehicle and readable storage medium

A multi-sensor approach using radar, cameras, and microphones in vehicles improves life form detection accuracy and safety by avoiding misjudgments and optimizing responses.

CN119176101APending Publication Date: 2024-12-24ZHEJIANG ZEEKR INTELLIGENT TECH CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411373936.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-29
Publication Date
2024-12-24

AI Technical Summary

Technical Problem

Existing vehicle detection systems face challenges in accurately identifying life forms within vehicles due to limitations in camera and millimeter-wave radar performance under varying lighting conditions and installation restrictions, leading to misjudgments and insufficient detection accuracy.

Method used

A method utilizing multiple detection methods, including vehicle-mounted radar systems, cameras, microphones, and rear door signals, to jointly determine the presence of life forms, with UWB radar for improved accuracy and cost-effectiveness.

Benefits of technology

Enhances detection accuracy by combining multiple sensors to avoid misjudgments and provides tailored alarm responses based on life form type, improving safety and energy efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119176101A_ABST
    Figure CN119176101A_ABST
Patent Text Reader

Abstract

The invention provides an in-vehicle life body detection method and device, a vehicle and a readable storage medium. The detection method comprises the steps that after a vehicle is shut down, whether the vehicle is in a whole vehicle locking state or not is monitored; in response to the fact that the vehicle is in the whole vehicle locking state, life body detection in the vehicle is conducted in multiple detection modes; according to the detection results corresponding to the multiple detection modes, determining whether a life body exists in the vehicle or not; and when it is detected that the life body exists in the vehicle, controlling the vehicle to execute at least one of the following alarm modes according to the type of the life body: mobile phone reminding, in-vehicle intervention and out-vehicle reminding. Whether the life body exists in the vehicle or not is determined through the detection results of the multiple detection modes, and the accuracy of detecting the life body in the vehicle can be improved. Meanwhile, when it is determined that the life body exists in the vehicle, the vehicle is controlled to execute corresponding alarm, and the safety of the life body in the vehicle can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle safety technology, and in particular to a method and device for detecting a life form in a vehicle, a vehicle, and a readable storage medium. Background Art

[0002] The vehicle in-cabin sensing track is currently in a high-prosperity cycle. Market demand is also gradually extending from early simple face recognition and driver fatigue warning to monitoring of larger areas in the cabin. Therefore, how to detect whether there is life in the car has become an urgent problem to be solved. Related technologies propose to detect life in the car through cameras. However, in poor lighting conditions, it is difficult for the camera to capture a clear image, resulting in misjudgment. Related technologies also propose to detect life in the car through millimeter-wave radar. However, due to restrictions such as installation position and vehicle body vibration, the detection accuracy of millimeter-wave radar in detecting life in the car is also insufficient. Summary of the invention

[0003] The embodiments of the present application provide a method, device, vehicle and readable storage medium for detecting a life form in a vehicle, so as to improve the accuracy of detecting a life form in the vehicle.

[0004] In a first aspect, a method for detecting life forms in a vehicle is provided, comprising: after the vehicle is turned off, monitoring whether the vehicle is in a fully locked state; in response to the vehicle being in a fully locked state, performing life form detection in the vehicle using a plurality of detection methods; determining whether there is a life form in the vehicle based on detection results corresponding to the plurality of detection methods; and in the event that a life form is detected in the vehicle, controlling the vehicle to execute at least one of the following alarm methods based on the type of the life form: mobile phone reminder, in-vehicle intervention, and outside-vehicle reminder.

[0005] In one possible implementation, the multiple detection methods include at least two of the following detection methods: an in-vehicle life form detection method based on a vehicle-mounted radar system; an in-vehicle life form detection method based on a vehicle-mounted camera; an in-vehicle life form detection method based on a vehicle-mounted microphone; an in-vehicle life form detection method based on an opening and closing signal of a rear door.

[0006] In one possible implementation, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system and an in-vehicle life form detection method based on a vehicle-mounted camera. The in-vehicle life form detection using multiple detection methods includes: using the vehicle-mounted radar system to perform in-vehicle life form detection to obtain a first detection result; in response to the first detection result indicating the presence of a life form in the vehicle, using the vehicle-mounted camera to perform in-vehicle life form detection.

[0007] In a possible implementation, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system and an in-vehicle life form detection method based on a vehicle-mounted microphone. The detection result corresponding to the in-vehicle life form detection method based on the vehicle-mounted radar system is a first detection result, and the detection result corresponding to the in-vehicle life form detection method based on the vehicle-mounted microphone is a second detection result. Determining whether there is a life form in the vehicle based on the detection results corresponding to the multiple detection methods includes: if both the first detection result and the second detection result indicate that there is a life form in the vehicle, determining that there is a life form in the vehicle.

[0008] In one possible implementation, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted camera, and the method also includes: generating relevant information of the life form based on image data collected by the vehicle-mounted camera, and the relevant information of the life form includes at least one of the following: the type of the life form; the age of the life form.

[0009] In a possible implementation, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system, and the method further includes: locating the life form according to the vehicle-mounted radar system.

[0010] In one possible implementation, the multiple detection methods include an in-vehicle life detection method based on opening and closing signals of rear doors, and the in-vehicle life detection using multiple detection methods includes: if the rear doors are always in a closed state during the process from unlocking the vehicle to locking the entire vehicle, it is determined that there is no life in the vehicle.

[0011] In a possible implementation, the radar system is an ultra-wideband (UWB) based radar system.

[0012] In one possible implementation, the in-vehicle intervention includes performing at least two of the following operations in sequence: controlling the vehicle to send a reminder message to the vehicle owner's terminal device to remind the vehicle owner to turn on the in-vehicle air-conditioning system; controlling the vehicle to automatically turn on the in-vehicle air-conditioning system; turning off the in-vehicle air-conditioning system and controlling the vehicle to open the windows.

[0013] In a second aspect, a device for detecting life forms in a vehicle is provided, comprising: a monitoring module for monitoring whether the vehicle is in a fully locked state after the vehicle is turned off; a life form detection module for performing in-vehicle life form detection using a plurality of detection methods in response to the vehicle being in a fully locked state; a determination module for determining whether there is a life form in the vehicle based on detection results corresponding to the plurality of detection methods; and a control module for controlling the vehicle to execute at least one of the following alarm methods based on the type of the life form when the presence of a life form in the vehicle is detected: a mobile phone reminder, in-vehicle intervention, and an outside-vehicle reminder.

[0014] In one possible implementation, the multiple detection methods include at least two of the following detection methods: an in-vehicle life form detection method based on a vehicle-mounted radar system; an in-vehicle life form detection method based on a vehicle-mounted camera; an in-vehicle life form detection method based on a vehicle-mounted microphone; an in-vehicle life form detection method based on an opening and closing signal of a rear door.

[0015] In one possible implementation, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system and an in-vehicle life form detection method based on a vehicle-mounted camera. The in-vehicle life form detection using multiple detection methods includes: using the vehicle-mounted radar system to perform in-vehicle life form detection to obtain a first detection result; in response to the first detection result indicating the presence of a life form in the vehicle, using the vehicle-mounted camera to perform in-vehicle life form detection.

[0016] In a possible implementation, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system and an in-vehicle life form detection method based on a vehicle-mounted microphone. The detection result corresponding to the in-vehicle life form detection method based on the vehicle-mounted radar system is a first detection result, and the detection result corresponding to the in-vehicle life form detection method based on the vehicle-mounted microphone is a second detection result. Determining whether there is a life form in the vehicle based on the detection results corresponding to the multiple detection methods includes: if both the first detection result and the second detection result indicate that there is a life form in the vehicle, determining that there is a life form in the vehicle.

[0017] In one possible implementation, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted camera, and the device also includes: a generation module, used to generate relevant information of the life form based on image data collected by the vehicle-mounted camera, and the relevant information of the life form includes at least one of the following: the type of the life form; the age of the life form.

[0018] In a possible implementation, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system, and the device further includes: a positioning module, configured to locate the life form according to the vehicle-mounted radar system.

[0019] In one possible implementation, the multiple detection methods include an in-vehicle life detection method based on opening and closing signals of rear doors, and the in-vehicle life detection using multiple detection methods includes: if the rear doors are always in a closed state during the process from unlocking the vehicle to locking the entire vehicle, it is determined that there is no life in the vehicle.

[0020] In a possible implementation manner, the radar system is a UWB-based radar system.

[0021] In one possible implementation, the in-vehicle intervention includes executing at least two of the following operations in sequence: controlling the vehicle to send a reminder message to the vehicle owner's terminal device to remind the vehicle owner to turn on the in-vehicle air-conditioning system; controlling the vehicle to automatically turn on the in-vehicle air-conditioning system; turning off the in-vehicle air-conditioning system and controlling the vehicle to open the windows.

[0022] In a third aspect, a vehicle is provided, comprising: a memory; and a processor for executing a program stored in the memory to execute the method described in the first aspect or any possible implementation of the first aspect.

[0023] According to a fourth aspect, a computer-readable storage medium is provided, on which a code is stored, wherein the code is used to execute the method described in the first aspect or any possible implementation of the first aspect.

[0024] The related art uses a single detection method when detecting life forms in the car. However, a single detection method may lead to misjudgment. Different from the related art, when detecting life forms in the car, the embodiment of the present application determines whether there is a life form in the car through the detection results of multiple detection methods, which can avoid the misjudgment of a single detection method, and thus improve the accuracy of life form detection in the car. At the same time, after determining that there is a life form in the car, the vehicle is controlled to perform different alarm methods according to the type of life form, which can improve the safety of the life form in the car. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a flow chart of a method for in-vehicle life detection provided in an embodiment of the present application.

[0026] Figure 2 This is an example diagram of performing in-vehicle life detection using multiple detection methods provided in an embodiment of the present application.

[0027] Figure 3It is a schematic diagram of the principle of in-vehicle life detection based on radar provided in an embodiment of the present application.

[0028] Figure 4 This is an example diagram of the hardware structure for performing radar-based in-vehicle life detection according to an embodiment of the present application.

[0029] Figure 5a-5c This is an example diagram of the location arrangement of the in-vehicle UWB radar anchor points provided in an embodiment of the present application.

[0030] Figure 6 This is an example diagram of the alarm operation scheme provided in the embodiment of the present application.

[0031] Figure 7 It is a flowchart of in-vehicle life detection based on UWB radar and passenger monitoring system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The in-cabin sensing track is currently in a high-prosperity cycle. In-cabin sensing generally refers to the ability to monitor and understand the environment and passenger status inside the vehicle using sensors and related technologies. Market demand is also gradually extending from simple facial recognition and driver fatigue warning in the early days to monitoring of larger areas in the cabin. In the Chinese market, according to relevant vehicle research, many models already provide in-cabin vital sign sensing functions. Vital body detection has also been introduced into the scoring criteria for new car ratings in Europe. Therefore, how to detect whether there are living things in the car has become an urgent problem to be solved.

[0033] In response to the above problems, related technologies propose to use cameras to detect life forms in the car. The camera can collect images inside the car, analyze the images, and detect whether there are life forms in the car. However, there are some disadvantages in using a camera to collect images inside the car to detect whether there are life forms in the car. For example, when the lighting conditions in the car are poor, such as on cloudy days or at night, the camera may find it difficult to capture a clear image, resulting in a misjudgment. In addition, life forms in the car may be obscured by coverings such as blankets, and the images captured by the camera are difficult to accurately show whether there are life forms in the car. For another example, the camera may also identify a doll as a life form, which will also affect the accuracy of life form detection in the car.

[0034] Related technologies also propose the use of millimeter-wave radar to detect whether there are life forms in the car. Millimeter-wave radar can operate effectively under all lighting conditions, including penetrating blankets and other obstructions covering children and passengers. In addition, millimeter-wave radar can detect whether there are life forms in the car by monitoring the chest rise and fall or tiny vibrations caused by breathing or heartbeat of the target. Although the use of millimeter-wave radar to detect life forms in the car overcomes some of the shortcomings of camera detection of life forms, misjudgments still occur due to restrictions on conditions such as installation location and vehicle body vibration. This leads to insufficient accuracy in life form detection based on millimeter-wave radar.

[0035] In view of the problem that a single detection method is prone to inaccurate detection results when detecting life forms in the car, the embodiments of the present application propose to use the detection results detected by multiple detection methods to jointly determine whether there is a life form in the car. In the case of detecting the presence of a life form in the car, the vehicle is controlled to execute at least one of the following alarm methods according to the type of the life form: mobile phone reminder, in-car intervention, and outside-car reminder. Since the use of multiple detection methods for in-car life form detection can avoid misjudgment caused by a single detection method, the accuracy of the detection can be improved. At the same time, after determining the presence of a life form in the car, controlling the vehicle to execute relevant alarms according to the type of the life form in the car can improve the safety of the life form in the car.

[0036] Combine the following Figure 1 , a more detailed introduction is given to the method for detecting life forms in a vehicle proposed in an embodiment of the present application.

[0037] In step S110, after the vehicle is turned off, it is monitored whether the vehicle is in a fully locked state. The fully locked state of the vehicle may refer to the doors and windows being locked. There are multiple ways to monitor the fully locked state of the vehicle. For example, it is possible to determine whether the vehicle is in a fully locked state by monitoring whether the doors and windows are both locked. For another example, it is possible to detect whether an external vehicle locking signal is received. Once an external vehicle locking signal is received, it is determined that the vehicle is in a fully locked state.

[0038] In step S120, when the vehicle is in a locked state, a variety of detection methods are used to detect life forms in the vehicle. There may be a variety of detection methods for detecting life forms in the vehicle, for example, the detection method may be based on a vehicle-mounted radar system, a vehicle-mounted camera, a vehicle-mounted microphone, or an opening and closing signal of a rear door.

[0039] Regarding the above-mentioned detection methods of life forms in a vehicle, different detection methods are now described with examples separately.

[0040] Detection method 1: In-vehicle life detection based on the vehicle-mounted radar system.

[0041] The vehicle-mounted radar system is a system installed on the vehicle that uses radio waves to determine the location of objects. There are many types of vehicle-mounted radar systems, such as millimeter wave radar, UWB radar, etc. The transmitting antenna of the vehicle-mounted radar system transmits radar signals. When the radar signal encounters a living organism or other object, part of the signal will be reflected back. The receiving antenna of the radar system captures the reflected signal. The radar system analyzes the characteristics of the reflected signal (such as the rise and fall of the chest or tiny vibrations caused by breathing or heartbeat) to identify whether there is a living organism in the car. Based on this method, life detection is not affected by light conditions and is not easily misjudged due to obstructions.

[0042] The vehicle-mounted radar system can not only detect whether there is a living being in the car, but also locate the living being. For example, it can locate the specific azimuth or specific position of the living being in the car. By locating the position of the living being, different alarm operations can be performed according to the location of the living being. For example: when turning on the air conditioner, the air conditioner in the area close to the location of the living being can be turned on. When it is detected that the living being is sitting in the back row, only the air conditioner in the back row area is turned on. When it is detected that the living being is sitting in the front row, only the air conditioner in the front row area is turned on. This can reduce the energy consumption of the car. The alarm operation will be introduced in detail later, so I will not repeat it here.

[0043] Detection method 2: In-vehicle life detection based on vehicle-mounted cameras.

[0044] A vehicle camera is a device installed in a vehicle for collecting images. There are many types of vehicle cameras, for example, a vehicle camera can be an occupant monitoring system (OMS), an interior monitoring system (IMS), etc. The vehicle camera collects images inside the vehicle and uses algorithms to identify whether there are living things in the images. The image recognition function can also improve the accuracy of image recognition through the training of a large model in the later stage.

[0045] The on-board camera can not only detect whether there is a life form in the car based on the image data, but also generate relevant information about the life form, such as the type of life form, the age of the life form, etc. The relevant information about the life form may include at least one of the type of life form and the age of the life form. The type of life form may include: human or animal. The age of the life form may include: children and adults according to age groups. By detecting the relevant information about the life form, different alarm operations can be formulated for different life forms. For example, if it is a child or an animal, the car window cannot be opened, and the air conditioner is mainly turned on. If it is an adult, the car window can be opened.

[0046] Detection method three: In-vehicle life detection method based on vehicle-mounted microphone.

[0047] The car microphone can collect audio data in the car. By analyzing the audio data, it is possible to detect whether there is life in the car. Audio can include various types of sounds, such as talking, crying, breathing, movement in the car, knocking and other sounds inside the car, and can also include some sounds from outside the car, such as the horns of other vehicles, environmental noise, etc. The analysis of audio data can be achieved through algorithms. The recognition function of audio data can also improve the accuracy of detection through the training of large models in the later stage.

[0048] Detection method 4: In-vehicle life detection method based on the opening and closing signals of the rear doors.

[0049] Generally speaking, the purpose of in-vehicle life detection is to detect whether there are life forms in the back seats after the vehicle is locked. Therefore, it is possible to consider using the rear door signal for detection. For example, the door signal from the vehicle unlocking to the vehicle locking process can be monitored. If the rear seats are always in a closed state during the process from unlocking to locking, it can be determined that there are no life forms in the vehicle. This method of detecting whether there are life forms in the back seats of the vehicle is simple and direct, and can reduce the vehicle's power consumption.

[0050] The above text describes different detection methods in detail. Multiple detection methods can be formed by combining the above detection methods. Multiple detection methods can include at least two of the above detection methods. Figure 2 An example of using multiple detection methods to detect life forms in a vehicle is given. For example, the multiple detection methods may include a detection method based on a vehicle-mounted camera and a detection method based on a vehicle-mounted microphone. Take the vehicle-mounted camera OMS as an example. After the vehicle is turned off, monitor whether the vehicle is in a fully locked state. If the vehicle is in a normally locked state, the OMS collects image data, and the microphone collects audio data at the same time. The OMS analyzes the collected images through an algorithm to determine whether there are life forms in the vehicle. The microphone also analyzes the collected audio through an algorithm to determine whether there are life forms in the vehicle. Then, based on the detection results of the OMS and the detection results of the microphone, determine whether there are life forms in the vehicle. If the detection results of the OMS and the microphone both determine that there are life forms in the vehicle, it is confirmed that there are life forms in the vehicle. The defects of a single detection method can be avoided by using a detection method based on the OMS and a detection method based on the vehicle-mounted microphone, thereby improving the accuracy of the detection.

[0051] In step S130, it is determined whether there is a life form in the car based on the detection results corresponding to the multiple detection methods. Each of the multiple detection methods will have a corresponding detection result after detecting a life form in the car. The embodiment of the present application does not specifically limit how to determine whether there is a life form in the car through multiple detection results. For example, only when the detection results of each of the multiple detection methods detect the presence of a life form in the car can it be determined that there is a life form in the car. For another example, a weight can be assigned to each of the multiple detection methods. The weights are combined to determine the final detection result. The following example illustrates how to determine whether there is a life form in the car through multiple detection results.

[0052] Example 1: Assign weights to the detection results of various detection methods respectively, and fuse them according to the weights to determine the final detection result.

[0053] The multiple detection methods include vehicle-mounted radar system-based and vehicle-mounted camera-based in-vehicle life form detection methods as examples. For the final detection results, different weights can be assigned to the detection results based on the vehicle-mounted radar system and the detection results based on the vehicle-mounted camera. For example, more weights can be assigned to the detection results of the radar system. The vehicle-mounted radar system with a large weight is used to first detect the life form in the vehicle and obtain the detection results. For the sake of convenience in description, the detection result of the life form in the vehicle based on the radar system is called the first detection result. When the first detection result shows that there is a life form in the car, the vehicle-mounted camera is used for further detection, which can not only improve the accuracy of detecting the life form in the car, but also determine the type of life form in the car, providing a reference for the selection of subsequent alarm operations. If the first detection result is that there is no life form in the car, the vehicle-mounted camera will no longer perform detection, and the first detection result will be used as the final detection result, which can reduce the energy consumption of the car.

[0054] Example 2: The presence of a living being in the vehicle is determined only when the test results of multiple detection methods all show that a living being exists in the vehicle.

[0055] The multiple detection methods include in-vehicle life detection methods based on a vehicle-mounted radar system and based on a vehicle-mounted microphone as examples. For the sake of ease of description, the detection result corresponding to the in-vehicle life body detection based on the vehicle-mounted radar system is called the first detection result, and the detection result corresponding to the in-vehicle life body detection based on the vehicle-mounted microphone is called the second detection result. If the first detection result and the second detection result are different, it is determined that there is no life in the car. If the first detection result and the second detection result both show that there is no life in the car, it is determined that there is no life in the car. If the first detection result and the second detection result both show that there is a life in the car, it is determined that there is a life in the car. By jointly determining whether there is a life in the car through the first detection result and the second detection result, the accuracy of the detection can be improved.

[0056] As mentioned above, the radar system can be a millimeter wave radar. However, the millimeter wave radar needs to be installed on the vehicle, which will increase the cost of the vehicle. In order to reduce costs, the radar system can be a UWB-based radar system, because the UWB radar can reuse the hardware anchor point of the digital key to detect life in the car. The hardware anchor point refers to a hardware device or component.

[0057] The process of using UWB radar for in-vehicle detection can be referred to Figure 3 . To realize in-cabin life detection based on UWB, only two UWB anchor points (placed in the car) are needed, one is the transmitting end anchor point and the other is the receiving end anchor point. The UWB anchor point sends and receives UWB radar signals through antennas. The antenna of the UWB radar transmitting end anchor point is used to transmit UWB radar signals. The antenna of the UWB radar receiving end anchor point is used to receive the signal reflected after the radar signal hits the target. The antenna of the receiving end anchor point can analyze the reflected signal to determine whether there is life in the car.

[0058] The above article introduces how UWB radar determines whether there is a living being in the car by analyzing the reflected signal. Figure 4 This paper introduces the process of UWB radar detecting life forms inside the car from the perspective of hardware.

[0059] After the car is locked, the body control module (BCM) or the domain control unit (DCU) can construct a controller area network (CAN) data frame. The CAN data frame can include information about the locking of the doors and windows. The BCM can send the constructed data frame to the CAN bus. The CAN transceiver provides an interface for the microcontroller unit (MCU) to communicate with the CAN bus. The MCU receives the CAN data frame through the CAN transceiver, a communication interface, and communicates with the UWB radar through the serial peripheral interface (SPI) interface. The MCU controls the transmitting antenna of the UWB radar to transmit the signal. The receiving antenna of the UWB radar receives the reflected signal and transmits the signal to the MCU. The MCU processes the received UWB radar reflected signal and analyzes the signal to determine whether there is a life form in the car. If there is a life form in the car, the MCU sends this information to the CAN bus in the form of a CAN data frame through the CAN transceiver. The CAN bus transmits the information to the BCM or DCU. After receiving the information sent by MCU, BCM or DCU can perform corresponding alarm operations according to the preset logic, such as controlling the vehicle to adjust the air conditioner, windows, honk, turn on the double flash, etc. The alarm operation will be introduced in detail later, so it will not be repeated here.

[0060] The radar system uses UWB radar to not only save costs, but also some of the characteristics of UWB itself make it perform better in detecting life forms in the car. For example, the characteristics of UWB can include: sending short pulse signals, high signal-to-noise ratio, high bandwidth, high energy efficiency, etc. The following is a detailed introduction to the role of UWB characteristics in detecting life forms in the car.

[0061] UWB radar sends short pulse signals. Short pulse signals usually have good penetration ability and can pass through obstacles such as seats and interior decoration in the car to detect obscured life forms. Therefore, UWB radar can improve the accuracy of detecting life forms in the car.

[0062] UWB radar signals have a high signal-to-noise ratio. The high signal-to-noise ratio of UWB radar signals can help the radar system effectively distinguish between weak life-signal signals (such as breathing or heartbeat) and environmental noise. Therefore, it can reduce misjudgments caused by environmental noise, thereby improving the accuracy of detecting life in the car.

[0063] UWB radar has a high bandwidth. For example, the bandwidth of UWB radar is greater than 500HZ. The bandwidth of general millimeter-wave radar is smaller than that of UWB radar. Since the distance resolution is proportional to the bandwidth of the radar signal, a wider bandwidth means that the radar can distinguish more subtle distance changes. Therefore, compared with millimeter-wave radar, UWB radar can accurately locate the specific position of life forms in the car. For example, it can not only detect the azimuth of life forms in the car, but also accurately distinguish whether the life forms are in the front and rear rows of the car, as well as the left, right or middle position of the back row.

[0064] UWB radar has a high energy efficiency ratio. For example, the frequency power density of UWB radar is relatively small. The frequency power density of UWB radar can be less than -41.3DBm / Mhz. At low power density, UWB radar signals have better penetration and can penetrate obstructions such as blankets and clothing in the car. Therefore, the accuracy of UWB radar in identifying living things in the car can be improved. In addition, UWB radar with low power density can reduce energy consumption while maintaining detection performance, thus helping to improve the energy efficiency of the vehicle.

[0065] As mentioned above, UWB radar needs two anchor points to detect life forms in a car. The two anchor points of the UWB radar can be arranged in many ways. For example, Figure 5a As shown in the figure, the point where the number 1 is located represents the anchor point of the UWB radar transmitter, and the point where the number 2 is located represents the anchor point of the UWB radar receiver. The anchor point of the UWB radar transmitter can be installed in the middle of the upper edge of the front windshield (the specific location is as follows Figure 5b The receiving end anchor point of the UWB radar can be installed on the roof position corresponding to the backrest of the rear seat (the specific position is as shown in Figure 5c By arranging the anchor points in this way, it is possible to ensure that the location of the life form inside the vehicle is within the coverage of the UWB radar signal, thereby improving the accuracy of the life form detection inside the vehicle.

[0066] Optionally, in some embodiments, the anchor point of the UWB radar is 50 mm or more away from the conductor / semiconductor when installed. Due to the conductivity of conductor and semiconductor materials, the electromagnetic waves emitted by the UWB radar may be absorbed or reflected, thereby interfering with the transmission and reception of radar signals. Maintaining a certain distance can reduce this interference and ensure that the radar system can accurately detect life forms in the car.

[0067] Optionally, in some embodiments, the anchor point of the UWB radar can be installed on the central axis of the vehicle body. Even if the UWB radar anchor point cannot be installed on the central axis of the vehicle body, the distance from the central axis of the vehicle body should not be too large. For example, the distance from the central axis of the vehicle body can be within 5 cm. Deviation from the central axis may cause asymmetry in the propagation path of the radar signal and increase the risk of multipath effects, thereby affecting the propagation and reception of the signal and causing detection errors. Therefore, setting the anchor point on or close to the central axis can improve the accuracy of detecting life forms in the vehicle.

[0068] Optionally, in some embodiments, the anchor point of the UWB radar can be arranged horizontally. The horizontal setting of the anchor point helps to optimize the propagation path of the radar signal in the car and reduce the attenuation and radiation of the radar signal in the complex car environment. Therefore, the accuracy of detecting life forms in the car can be improved.

[0069] Optionally, in some embodiments, the antenna of the UWB radar anchor point can be set to face the cabin area inside the vehicle, which can increase the strength of the radar signal in the cabin area, reduce radar signal attenuation, and improve the sensitivity and accuracy of detecting life forms.

[0070] Continue to refer to Figure 1 In step S140, when a life form is detected in the vehicle, the vehicle is controlled to execute at least one of the following alarm modes according to the type of the life form: mobile phone reminder, in-vehicle intervention, and outside-vehicle reminder. When a life form is detected in the vehicle, a subsequent alarm is also required to notify the owner to provide help to the life form in the vehicle, avoid dangerous situations, and improve the safety of the life form in the vehicle. The subsequent alarm mode may include multiple types, for example: it may be a mobile phone reminder, it may be an in-vehicle intervention, it may be an outside-vehicle reminder, etc. The alarm mode may include at least one of these alarm modes. The following is a detailed example of different alarm modes.

[0071] Alarm method 1: Mobile phone reminder

[0072] The mobile phone reminder may include calling or sending a message to the owner. The message may be, for example, a reminder message sent by a mobile phone APP to the owner, or a text message sent by a mobile phone to the owner, which is not limited in the present embodiment of the application. In order to avoid the reminder message being sent to the owner without attracting the owner's attention, the vehicle digital instrument meter (DIM) may also be controlled to make an emergency call to the owner. The phone call facilitates timely contact with the owner, which can improve the efficiency of rescuing the life in the car.

[0073] Alarm method 2: In-car intervention

[0074] In-car intervention can include a variety of methods. For example, it can be to control the vehicle to send a reminder message to the owner's terminal device to remind the owner to turn on the air conditioning system in the car; it can also be to control the vehicle to automatically turn on the air conditioning system in the car; it can also be to turn off the air conditioning in the car and control the vehicle to open the windows. When it is determined that there is a life form in the car, the vehicle can be controlled to perform at least two of the above operations in sequence. In many cases, life forms left in the car are prone to danger due to high temperatures in summer, so it is preferred to control the vehicle to turn on the air conditioning in the car. This can provide a more comfortable environment for the life forms in the car and prevent the life forms in the car from feeling uncomfortable in a high temperature environment. In addition, when it is detected that there are children or animals in the car, for the safety of the life forms in the car and to prevent the children or animals from being taken away by strangers, the operation of controlling the vehicle to open the windows may not be performed. The following is combined with Figure 6 An example of controlling the vehicle to perform the above three in-car intervention operations in sequence is given. These three alarm operations can correspond to different levels of alarms. When the previous alarm operation is not released by the owner, the next level of alarm will be performed. For example, within 30 seconds after the vehicle is locked, a message can be sent to the owner's mobile phone application (application, APP) to remind the owner to turn on the air conditioner. When the owner does not release this alarm operation after 30 seconds, the next level of alarm operation is started, that is, the vehicle is controlled to automatically turn on the air conditioner in the car. After the vehicle is controlled to automatically turn on the air conditioner in the car for a period of time, for example, if the owner still does not actively release this operation within 5 minutes, the next level of alarm operation will continue to be started, that is, the air conditioner in the car is turned off and the vehicle is controlled to open the window.

[0075] Alarm method three: reminder outside the car

[0076] After detecting the existence of a life form in the car, an alarm may be performed outside the car to draw the attention of the car owner or people around the car. This facilitates helping or rescuing the life form in the car as soon as possible. The outside car reminder may include an alarm operation in terms of vision outside the car and an alarm operation in terms of hearing outside the car. For example, the alarm operation in terms of hearing outside the car may be to control the vehicle to honk. For example, the alarm operation in terms of vision outside the car may be to turn on the double flash.

[0077] Optionally, in some embodiments, the horn operation can extend the horn time or increase the number of horn honks according to the time when the life form in the car is detected. If the corresponding alarm operation is not actively released after a short horn honks, the horn time can be extended or the number of horns can be increased to attract the attention of the owner or people around the vehicle so that the life form in the car can be rescued in time. For example, Figure 6As shown, when a life form is detected in the car, the horn can be sounded for 5 seconds within 30 seconds of locking the car. If the owner does not cancel this alarm operation, the next level of alarm operation will be activated, such as honking for 15 seconds, 1 minute once, and lasting for 5 minutes. If this level of alarm operation is still not canceled by the owner, the next level of alarm operation will be activated, such as honking for 15 seconds, 1 minute once, and lasting for 30 minutes.

[0078] Optionally, in some embodiments, the double flash operation can extend the double flash time or increase the number of double flashes according to the time when the life form in the car is detected. If the corresponding alarm operation is not actively released by the car owner after a short period of double flash, the double flash time can be extended or the number of double flashes can be increased to attract the attention of the car owner or people around the vehicle, so that the life form in the car can be rescued in time. For example, Figure 6 As shown, when a life form is detected in the car, the car can be flashed for 5 seconds within 30 seconds of locking the car. If the owner does not cancel this alarm operation, the next level of alarm operation will be activated, such as flashing for 15 seconds, 1 minute cycle, and lasting for 5 minutes. If this level of alarm operation is still not canceled by the owner, the next level of alarm operation will be activated, such as flashing for 15 seconds, 1 minute cycle, and lasting for 30 minutes.

[0079] The above describes different alarm methods in detail. When a life form is detected in the vehicle, at least one of the above alarm methods can be executed according to the type of the life form. For example, when it is determined that there is a life form in the vehicle and the type of the life form in the vehicle can be determined to be an adult, one or more of the above alarm methods can be executed. However, when it is determined that there is a life form in the vehicle and the type of the life form in the vehicle can be determined to be an animal, in order to avoid the harsh sound of the horn and the shaking of the lights in the double flash from disturbing the animal in the vehicle, one or more alarm methods other than intervention outside the vehicle can be executed.

[0080] The alarm operation described above can be canceled when the user performs any of the following operations, for example, unlocking the vehicle, opening any door, turning off the air conditioner, opening a window, honking the horn, turning on the hazard lights, etc. If the alarm is canceled in time with user intervention, the energy consumption of the vehicle can be reduced.

[0081] When the alarm operation described in the previous text continues for a period of time without any active cancellation operation intervention, the vehicle can automatically cancel the alarm and keep the air conditioner on. The alarm operation has not been canceled for a period of time. In this case, the time when the life in the car is rescued is uncertain. At this time, automatically canceling the alarm can reduce the energy consumption of the vehicle. The energy saved is the duration of the air conditioning in the car, which can increase the survival time of the life in the car. The duration here can be any set time, such as 30 minutes, 40 minutes, etc., and this application is not limited here.

[0082] Combine the following Figure 7 The embodiments of the present application are described in more detail. In the example below, a plurality of detection methods adopt a detection method based on UWB radar and a detection method based on OMS, and the determination of the detection results of the plurality of detection methods is based on the weight of the comprehensive detection results occupied by different detection methods. It should be noted that this example is only to help those skilled in the art understand the embodiments of the present application, and is not intended to limit the embodiments of the present application to the specific types or scenarios illustrated. Those skilled in the art can obviously make various equivalent modifications or changes based on the examples given below, and such modifications or changes also fall within the scope of the embodiments of the present application.

[0083] After the vehicle is turned off, monitor whether the vehicle is in a locked state. If the vehicle is in a locked state, determine whether the function of detecting life forms in the vehicle is turned on. If the function of detecting life forms in the vehicle is turned on, the UWB radar will perform detection first. When the presence of life forms in the vehicle is detected, the OMS will perform further detection and confirmation. The UWB radar confirms the location of the life forms in the vehicle while confirming whether there are life forms in the vehicle. The OMS confirms the type and age of the life forms in the vehicle while confirming whether there are life forms in the vehicle. After confirming the presence of life forms in the vehicle, the corresponding appropriate alarm operation is initiated. These alarm operations can be completely lifted when the user performs some unlocking of the vehicle or any of the previously performed alarm operations are lifted. For example, the alarm lifting operation can be any door opening, air conditioning off, window opening, horn honking, double flash, etc. If there is still no active lifting operation intervention after the alarm operation is performed for a period of time, the vehicle automatically lifts the alarm and keeps the air conditioning on.

[0084] Combination of the above Figures 1 to 7 The method embodiment of the present application is described in detail, and the device embodiment of the present application is described in detail below. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment, so the part not described in detail can refer to the previous method embodiment.

[0085] The embodiment of the present application also provides a device for detecting life forms in a vehicle, comprising: a monitoring module, a life form detection module, a determination module and a control module. The monitoring module is used to monitor whether the vehicle is in a fully locked state after the vehicle is turned off. The life form detection module is used to perform life form detection in the vehicle using a variety of detection methods in response to the vehicle being in a fully locked state. The determination module is used to determine whether there is a life form in the vehicle based on the detection results corresponding to the multiple detection methods. The control module is used to control the vehicle to execute at least one of the following alarm methods according to the type of the life form when the presence of a life form in the vehicle is detected: mobile phone reminder, in-vehicle intervention, and outside-vehicle reminder.

[0086] Optionally, in some embodiments, the multiple detection methods include at least two of the following detection methods: an in-vehicle life form detection method based on a vehicle-mounted radar system; an in-vehicle life form detection method based on a vehicle-mounted camera; an in-vehicle life form detection method based on a vehicle-mounted microphone; an in-vehicle life form detection method based on an opening and closing signal of a rear door.

[0087] Optionally, in some embodiments, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system and an in-vehicle life form detection method based on a vehicle-mounted camera, and the in-vehicle life form detection using multiple detection methods includes: using the vehicle-mounted radar system to perform in-vehicle life form detection to obtain a first detection result; in response to the first detection result indicating the presence of a life form in the vehicle, using the vehicle-mounted camera to perform in-vehicle life form detection.

[0088] Optionally, in some embodiments, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system and an in-vehicle life form detection method based on a vehicle-mounted microphone, the detection result corresponding to the in-vehicle life form detection method based on the vehicle-mounted radar system is a first detection result, and the detection result corresponding to the in-vehicle life form detection method based on the vehicle-mounted microphone is a second detection result, and determining whether there is a life form in the vehicle based on the detection results corresponding to the multiple detection methods includes: if both the first detection result and the second detection result indicate that there is a life form in the vehicle, then determining that there is a life form in the vehicle.

[0089] Optionally, in some embodiments, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted camera, and the device also includes: a generation module, used to generate relevant information of the life form based on image data collected by the vehicle-mounted camera, and the relevant information of the life form includes at least one of the following: the type of the life form; the age of the life form.

[0090] Optionally, in some embodiments, the multiple detection methods include an in-vehicle life form detection method based on a vehicle-mounted radar system, and the device further includes: a positioning module, used to locate the life form according to the vehicle-mounted radar system.

[0091] Optionally, in some embodiments, the multiple detection methods include an in-vehicle life detection method based on opening and closing signals of rear doors, and the in-vehicle life detection using multiple detection methods includes: if the rear doors are always in a closed state during the process from unlocking the vehicle to locking the entire vehicle, it is determined that there is no life in the vehicle.

[0092] Optionally, in some embodiments, the radar system is a UWB-based radar system.

[0093] Optionally, in some embodiments, the in-vehicle intervention includes performing at least two of the following operations in sequence: controlling the vehicle to send a reminder message to the owner's terminal device to remind the owner to turn on the in-vehicle air-conditioning system; controlling the vehicle to automatically turn on the in-vehicle air-conditioning system; turning off the in-vehicle air-conditioning system and controlling the vehicle to open the windows.

[0094] The embodiment of the present application further provides a vehicle, comprising: a memory and a processor. The processor is used to execute a program stored in the memory to execute the method for detecting a living being in a vehicle in any of the above embodiments.

[0095] An embodiment of the present application also provides a computer-readable storage medium, on which a code is stored, and the code is used to execute the method for detecting a living being in a vehicle in any of the above embodiments.

[0096] It should be understood that in the embodiment of the present application, "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0097] It should be understood that the term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0098] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0099] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0100] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0102] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0103] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for detecting a living being in a vehicle, characterized in that: include: After the vehicle is turned off, monitor whether the vehicle is in a fully locked state; In response to the vehicle being in a fully locked state, performing in-vehicle life detection using a variety of detection methods; Determining whether there is a living being in the vehicle according to the detection results corresponding to the multiple detection methods; When a life form is detected in the vehicle, the vehicle is controlled to execute at least one of the following alarm modes according to the type of the life form: mobile phone reminder, in-vehicle intervention, and outside-vehicle reminder.

2. The method according to claim 1, characterized in that The multiple detection methods include at least two of the following detection methods: In-vehicle life detection method based on vehicle-mounted radar system; In-vehicle life detection method based on vehicle-mounted cameras; In-vehicle life detection method based on vehicle microphone; A method for detecting life inside a vehicle based on the opening and closing signals of rear doors.

3. The method according to claim 2, characterized in that The multiple detection methods include an in-vehicle life body detection method based on an in-vehicle radar system and an in-vehicle life body detection method based on an in-vehicle camera. The in-vehicle life detection is performed using a variety of detection methods, including: Detecting a living being in the vehicle using the vehicle-mounted radar system to obtain a first detection result; In response to the first detection result indicating that there is a living being in the vehicle, the vehicle-mounted camera is used to perform life detection in the vehicle.

4. The method according to claim 2, characterized in that: The multiple detection methods include an in-vehicle life form detection method based on an on-board radar system and an in-vehicle life form detection method based on an on-board microphone, the detection result corresponding to the in-vehicle life form detection method based on the on-board radar system is a first detection result, and the detection result corresponding to the in-vehicle life form detection method based on the on-board microphone is a second detection result, The determining whether there is a living being in the vehicle according to the detection results corresponding to the multiple detection methods includes: If both the first detection result and the second detection result indicate that a living being exists in the vehicle, it is determined that a living being exists in the vehicle.

5. The method according to claim 2, characterized in that: The multiple detection methods include a method of detecting a life form in a vehicle based on a vehicle-mounted camera, and the method further includes: Generate relevant information of the living organism based on the image data collected by the vehicle-mounted camera, where the relevant information of the living organism includes at least one of the following: the type of life form; The age of the being.

6. The method according to claim 2, characterized in that The multiple detection methods include a vehicle-based life form detection method based on a vehicle-mounted radar system, and the method further includes: The living being is positioned according to the vehicle-mounted radar system.

7. The method according to claim 2, characterized in that The multiple detection methods include an in-vehicle life body detection method based on the opening and closing signals of the rear doors. The in-vehicle life body detection using multiple detection methods includes: If the rear door is always in a closed state during the process from unlocking the vehicle to locking the entire vehicle, it is determined that there is no living being in the vehicle.

8. The method according to claim 2, characterized in that: The radar system is an ultra-wideband based radar system.

9. The method according to any one of claims 1 to 8, characterized in that The in-vehicle intervention includes at least two of the following operations in sequence: Controlling the vehicle to send a reminder message to the vehicle owner's terminal device to remind the vehicle owner to turn on the vehicle air conditioning system; Controlling the vehicle to automatically turn on the air conditioning system in the vehicle; The air conditioning system in the vehicle is turned off and the vehicle windows are controlled to open.

10. A device for detecting life forms in a vehicle, characterized in that: include: A monitoring module is used to monitor whether the vehicle is in a fully locked state after the vehicle is turned off; A life detection module, configured to detect life in the vehicle using a variety of detection methods in response to the vehicle being in a fully locked state; A determination module, used to determine whether there is a living being in the vehicle according to the detection results corresponding to the multiple detection methods; The control module is used to control the vehicle to execute at least one of the following alarm modes according to the type of the life form when a life form is detected in the vehicle: mobile phone reminder, in-vehicle intervention, and outside-vehicle reminder.

11. A vehicle, characterized in that: include: Memory; A processor, configured to execute the program stored in the memory to perform the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores codes for executing the method according to any one of claims 1 to 9.

Citation Information

Cited By

  • Speaker localization system

    TWI938036B