In-vehicle passenger recognition method and related apparatuses

Abstract

The application provides an in-vehicle passenger identification method and related equipment applied to a radar system, and the method comprises the following steps: detecting an in-vehicle environment and determining whether a moving object exists; if yes, acquiring first radar point cloud information of a horizontal region in the vehicle and confirming position information of the moving object; according to the position information, acquiring second radar point cloud information of a height region of the moving object, and identifying a passenger type to which the moving object belongs according to the first radar point cloud information and the second radar point cloud information; and when the vehicle is in a stationary and locked state, if a passenger of a specified type is identified, an alarm information is sent. In the initial stage, the in-vehicle environment is detected to exclude false alarms caused by non-biological objects. In addition, the characteristics of the moving object are analyzed from two dimensions of the horizontal region and the height region, and the passenger type to which the moving object belongs is finely identified through multi-feature calculation, so that false alarms or missed alarms are further excluded, and the accuracy of the alarm for the in-vehicle left passenger is improved.

Description

Technical Field

[0001] This invention relates to the field of automotive safety, and more particularly to a method for identifying in-vehicle passengers and related equipment. Background Technology

[0002] With the increasing number of vehicles owned by families in recent years, cases of children being left in cars are not uncommon. Installing millimeter-wave radar in vehicles can enable liveness detection. As intelligent vehicles develop, more and more vehicles have sunroofs. For vehicles with sunroofs, the radar cannot be installed in the center of the roof, as this would interfere with the use of the sunroof.

[0003] If an adult is in the car, they can make a phone call or call for help if needed, or they can rest in the car. In these situations, a vehicle alarm would disturb the driver's rest. Therefore, it's unnecessary for the vehicle alarm to sound when an adult is in the car. If the vehicle alarm still sounds when an adult is in the car, it wastes battery power and sends unnecessary alarm messages to the driver, affecting the user experience and ultimately the vehicle's reputation.

[0004] Patent CN116279265A describes a method of identifying whether a living person is left inside a vehicle by capturing video images of the interior using a camera. However, installing cameras inside vehicles can compromise customer privacy, and given the widespread concern for privacy in modern society, this solution has its limitations.

[0005] Therefore, improving the accuracy of alarms for passengers left behind in vehicles is an urgent problem to be solved. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide a method for identifying passengers inside a vehicle and related equipment, aiming to solve the technical problem of low accuracy of alarms for passengers left behind in vehicles in the prior art.

[0007] In a first aspect, the present invention provides an in-vehicle passenger identification method, applied to a radar system, comprising:

[0008] Detect the environment inside the vehicle to determine if there are moving objects;

[0009] If so, the first radar point cloud information of the horizontal area inside the vehicle is obtained to confirm the position information of the moving object. The horizontal area inside the vehicle includes the seat surface area and the floor mat area.

[0010] Based on the location information, the second radar point cloud information of the height area of ​​the moving object is obtained, and based on the first radar point cloud information and the second radar point cloud information, the passenger type of the moving object is identified. The height area includes the seat back area and the leg space, and the leg space is set perpendicular to the foot pad area.

[0011] When the car is stationary and locked, an alarm message will be issued if a passenger of a specified type is detected.

[0012] Preferably, if so, the step of acquiring first radar point cloud information of the horizontal area inside the vehicle and confirming the position information of the moving object includes:

[0013] The horizontal region is divided into several first regions, and the radar point cloud density of each first region is determined to be the first threshold.

[0014] If the radar point cloud density of the first region reaches the first threshold, the first region is determined to be the first effective region. Based on the distribution of all first effective regions, the position information of the moving object is confirmed.

[0015] Preferably, the step of acquiring second radar point cloud information of the height region of the moving object based on location information, and identifying the passenger type of the moving object based on the first and second radar point cloud information, includes:

[0016] The altitude region is divided into several second regions, and it is determined whether the radar point cloud density of each second region reaches the second threshold.

[0017] If the radar point cloud density of the second region reaches the second threshold, the second region is determined to be the second effective region. Based on all the second effective regions, the body size information of the moving object is calculated to identify the passenger type to which the moving object belongs.

[0018] Preferably, if the radar point cloud density of the second region reaches a second threshold, the second region is determined to be a second effective region. The step of calculating the body size information of the moving object based on all second effective regions to identify the passenger type of the moving object includes:

[0019] The seat back area is divided into a head area, a chest area, and a seat cushion area. Radar point cloud density information of the head area, foot area, and seat cushion area is obtained respectively to determine the head position and chest position of the moving object.

[0020] Obtain radar point cloud density information in the leg space to determine the foot position of a moving object;

[0021] Based on the radar point cloud density information of the seat back area and legroom, the body shape information of the moving object is calculated.

[0022] Head position, chest position, foot position, and body shape information are used as weighting factors to identify the passenger type of the moving object.

[0023] Preferably, the weighting factors also include respiratory rate, head position, chest position, foot position, and body shape information as weighting factors. The step of identifying the passenger type of a moving object includes:

[0024] Obtain the respiratory rates of passengers inside the vehicle and calculate the similarity between the respiratory rates and reference rates;

[0025] If the similarity reaches the third threshold, then the breathing frequency will be used as a new weighting factor to participate in the identification of moving objects.

[0026] Preferably, the step of identifying the passenger type of a moving object, using head position, chest position, foot position, and body shape information as weighting factors, includes:

[0027] Obtain the vehicle type, adjust the weighting factors according to the type, and identify the passenger type.

[0028] Preferably, the step of issuing an alarm message if a specified type of passenger is detected when the vehicle is stationary and locked includes:

[0029] An alarm will be triggered when a child is identified as a passenger.

[0030] Secondly, embodiments of the present invention also provide an in-vehicle passenger identification device, comprising:

[0031] The initial inspection module is used to detect the environment inside the vehicle and determine whether there are moving objects.

[0032] The position confirmation module is used to obtain the first radar point cloud information of the horizontal area inside the vehicle if the position is confirmed, and to confirm the position information of the moving object. The horizontal area inside the vehicle includes the seat surface area and the floor mat area.

[0033] The identification module is used to obtain the second radar point cloud information of the height area of ​​the moving object based on the location information, and to identify the passenger type of the moving object based on the first radar point cloud information and the second radar point cloud information. The height area includes the seat back area and the leg space, and the leg space is set perpendicular to the foot pad area.

[0034] The alarm module is used to issue an alarm message if a specified type of passenger is detected when the car is stationary and locked.

[0035] Thirdly, embodiments of the present invention also provide a storage medium storing computer program instructions thereon, which implement the above-described method when executed by a processor.

[0036] Fourthly, embodiments of the present invention also provide an electronic device, including: at least one processor, at least one memory, and computer program instructions stored in the memory, which implement the method described above when executed by the processor.

[0037] In summary, the beneficial effects of the present invention are as follows:

[0038] This invention detects the in-vehicle environment from the initial stage, eliminating false alarms caused by non-biological objects. Furthermore, this invention breaks down multiple features of moving objects from both horizontal and vertical dimensions. Through multi-feature calculations, it performs refined identification of the passenger type to which the moving object belongs, further eliminating false alarms or missed alarms and significantly improving the accuracy of alarms for passengers left behind in the vehicle. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments of the present invention will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, and these are all within the protection scope of the present invention.

[0040] Figure 1 This is a flowchart illustrating a method for identifying passengers inside a vehicle according to an embodiment of the present invention.

[0041] Figure 2 This is a schematic diagram of the horizontal area of ​​a car seat according to an embodiment of the present invention.

[0042] Figure 3 This is a schematic diagram of the height region of a car seat according to an embodiment of the present invention.

[0043] Figure 4 This is a schematic diagram of the structure of the in-vehicle passenger identification device according to an embodiment of the present invention.

[0044] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0045] The features and exemplary embodiments of various aspects of the present invention will now be described in detail. To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the invention.

[0046] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0047] Please see Figures 1 to 3 This invention provides a method for identifying passengers inside a vehicle, the method comprising:

[0048] S1: Detects the environment inside the vehicle to determine if there are moving objects;

[0049] S2: If so, obtain the first radar point cloud information of the horizontal area inside the vehicle to confirm the position information of the moving object. The horizontal area inside the vehicle includes the seat surface area and the floor mat area.

[0050] S2: Based on the location information, obtain the second radar point cloud information of the height area of ​​the moving object, and based on the first radar point cloud information and the second radar point cloud information, identify the passenger type to which the moving object belongs. The height area includes the seat back area and the leg space, and the leg space is set perpendicular to the foot pad area.

[0051] S3: When the car is stationary and locked, if a specified type of passenger is detected, an alarm message will be issued.

[0052] In this embodiment of the invention, reference is made to Figure 2 The radar is installed on the side of the vehicle, either left or right. It covers the seats and floor mats without obstruction, ensuring the radar is fixed to the vehicle and remains relatively stationary, preventing displacement due to vehicle movement. Figure 2As shown, areas A to C represent the rear seats, areas D to F represent the rear floor mats, area G represents the driver's seat, area I represents the driver's floor mat, area H represents the passenger seat, and area J represents the passenger's floor mat. The radar system detects the in-vehicle environment to determine if any moving objects are present. The specific principle is as follows: Millimeter-wave radar receives reflected information from objects. Due to the human body's natural breathing and heartbeat, a person cannot be completely still inside a vehicle; therefore, only moving or slightly moving targets need to be detected. The specific detection method involves judging the consistency of multiple frames of data within the same time period. If there is no living person inside the vehicle, the multiple frames of data at the same distance are basically consistent, with a small energy difference between them. If there is a living person inside the vehicle, the movement of the living person will cause differences in the multiple frames of data at the same distance, leading to an increase in the energy difference between them. When the energy difference is greater than a threshold, it is considered that there is a slightly moving target (i.e., a living person) inside the vehicle; otherwise, it is considered that there is no slightly moving target (i.e., a living person). If there is no slightly moving target inside the vehicle, it is considered that there are no moving objects inside the vehicle. When a moving object is present inside the vehicle, the first radar point cloud information of the horizontal area inside the vehicle is acquired to confirm the location of the moving object. For example, refer to Figure 2 When the radar point cloud density of regions H and J meets the threshold, the moving object is considered to exist in the co-pilot's position. (Refer to...) Figure 3 After confirming the location of the moving object, the second radar point cloud information of the object's height region is acquired. Combined with the first and second radar point cloud information, multiple feature information of the moving object is calculated, including height, density, and volume, to identify the passenger type to which the moving object belongs. Because regulations require children to use child safety seats, which increase height, making a child's height in a safety seat similar to that of a small to medium-sized adult, this solution decomposes multiple features of the moving object from both horizontal and vertical dimensions. Through multi-feature calculation, the passenger type to which the moving object belongs is precisely identified. When the car is stationary and locked, an alarm is triggered if a specific type of passenger (such as a child) is identified; otherwise, no alarm is triggered to avoid false alarms or missed alarms. In addition, this solution detects the in-vehicle environment in the initial stage to eliminate false alarms caused by non-biological objects. In summary, this solution detects the in-vehicle environment in the initial stage, eliminating false alarms caused by non-biological objects. Moreover, this solution breaks down multiple features of moving objects from two dimensions: horizontal and vertical regions. Through the calculation of multiple features, it can accurately identify the passenger type to which the moving object belongs, further eliminating false alarms or missed alarms, and significantly improving the accuracy of alarms for passengers left in the vehicle.

[0053] Reference Figure 2 If so, the step S2, which involves acquiring the first radar point cloud information of the horizontal area inside the vehicle and confirming the position information of the moving object, includes:

[0054] S21: Divide the horizontal region into several first regions, and determine whether the radar point cloud density of each first region reaches the first threshold.

[0055] S22: If the radar point cloud density of the first region reaches the first threshold, the first region is determined to be the first effective region, and the position information of the moving object is confirmed according to the distribution of all first effective regions.

[0056] In this embodiment of the invention, reference is made to Figure 2 The horizontal area is divided into regions A to J. Regions A to C represent the rear seats, regions D to F represent the rear floor mats, region G represents the driver's seat, region I represents the driver's floor mat, region H represents the passenger seat, and region J represents the passenger's floor mat. The radar system can detect multiple moving objects inside the vehicle. First, the radar system acquires the distribution of radar point clouds in different regions (i.e., the first region). Then, the radar system determines whether the radar point cloud density in each of the first regions meets a first threshold requirement. If a first region contains only a few scattered radar points and its density does not meet the first threshold requirement, it is considered that there are no moving objects in that region. If the radar point cloud density in a first region meets the first threshold requirement, it is considered that there are moving objects in that region. If the radar point cloud density in all first regions is less than the first threshold, the radar system considers the detected micro-motion information to be due to the shaking of objects inside the vehicle or interference caused by multipath reflection from objects inside the vehicle, and there are actually no moving objects inside the vehicle. Through the above measures, interference caused by objects can be effectively identified, avoiding false alarms caused by vehicle shaking or interference from objects inside the vehicle.

[0057] Reference Figure 3 Step S3, which involves acquiring second radar point cloud information of the height region of a moving object based on location information, and identifying the passenger type of the moving object based on the first and second radar point cloud information, includes:

[0058] S31: Divide the altitude region into several second regions and determine whether the radar point cloud density of each second region reaches the second threshold.

[0059] S32: If the radar point cloud density of the second region reaches the second threshold, the second region is determined to be the second effective region. Based on all the second effective regions, the body size information of the moving object is calculated to identify the passenger type to which the moving object belongs.

[0060] In this embodiment of the invention, reference is made to Figure 3The height region of a seat is divided into six regions: a first height region 1, a second height region 2, a third height region 3, a fourth height region 4, a fifth height region 5, and a sixth height region 6. Regions 1, 2, and 3 are included in the seat back area, while regions 4, 5, and 6 are included in the legroom. The radar point cloud density within each height region (i.e., the second region) is calculated. If the radar point cloud density within a height region is below a second threshold, that region is considered to be devoid of objects. Conversely, if the radar point cloud density within a height region is above the second threshold, an object is confirmed to exist within that region, making it a valid second region. The radar point cloud density is determined by calculating the average distance between each radar point and the nearest radar point. When the radar point cloud density is below the threshold, it is considered that the interference caused by signal refraction within the first or second region is due to signal refraction and does not represent a real target; therefore, the radar point cloud information for that region is deleted.

[0061] In this embodiment of the invention, the first height region 1 corresponds to the head region, the second height region 2 corresponds to the chest region, the third height region 3 corresponds to the seat cushion region, the fourth height region 4 corresponds to the thigh region, the fifth height region 5 corresponds to the calf region, and the sixth height region 6 corresponds to the foot region. The radar system calculates the body shape information of the moving object based on the radar point cloud information of the six height regions, and identifies the passenger type of the moving object based on the body shape information. For example, if the radar point cloud density of the first height region 1 to the fourth height region 4 all meet the standard, three height regions are used. The radar point calculation features each radar point corresponds to X, Y, and Z coordinates in space. In the first height region 1, the average height of the N points with the highest height inside the vehicle is calculated as the head height of the moving object. The average height is calculated using the average height of the N points in the middle of the second height region 2, and the average height of the N points with the lowest height in the third height region 3. If there are fewer than N points in a region, all points are used. In the fourth height region 4, the average height of the N points is used. After selecting the specified radar points, the radar system calculates the height and volume of the moving object based on the coordinate values ​​(x, y, z) of each radar point. Specifically, the calculation process involves calculating the height of the moving object using the Z-axis coordinate values, calculating the area using the X and Y axis coordinate values, and then obtaining the volume of the moving object by calculating the area and height, thus obtaining the body information of the moving object. Based on this body information, the passenger type of the moving object is determined. For example, when the moving object is an infant, radar point cloud information meeting the requirements exists in the first height region 1 to the fourth height region 4, but radar point cloud information meeting the requirements does not exist in the fifth height region 5 and the sixth height region 6. Therefore, the body shape information of a moving object can be calculated from the radar point cloud information of the first altitude region 1 to the fourth altitude region 4. The body shape information includes height information, volume information and body length information.

[0062] To further improve the accuracy of body size calculation, the radar system can acquire radar point cloud information from the first height region 1 to the sixth height region 6 to calculate the body size information of the moving object. Specifically, if the radar point cloud density of the first height region 1 to the sixth height region 6 all reach the second threshold, it proves that the current moving object is not an infant. If there is radar point cloud information that meets the requirements in the first height region 1 to the fifth height region 5, and there is no radar point cloud information that meets the requirements in the sixth height region 6, it proves that the current moving object is a child. To further determine whether the child is an infant or a toddler, we also need to obtain the coordinate values ​​of the radar points in the first height region 1 to the fifth height region 5 to calculate the height and volume data of the moving object in order to identify the passenger type to which the moving object belongs.

[0063] Reference Figure 3 If the radar point cloud density of the second region reaches a second threshold, then the second region is determined to be a second effective region. Step S32, which calculates the body size information of the moving object based on all second effective regions to identify the passenger type of the moving object, includes:

[0064] S321: Divide the seat back area into the head area, chest area and seat cushion area, and obtain the radar point cloud density information of the head area, foot area and seat cushion area respectively to determine the head position and chest position of the moving object.

[0065] S322: Acquire radar point cloud density information of the leg space to determine the foot position of the moving object;

[0066] S323: Calculate the body shape information of the moving object based on the radar point cloud density information of the seat back area and legroom.

[0067] S324: Head position, chest position, foot position, and body shape information are used as weighting factors to identify the passenger type of a moving object.

[0068] In this embodiment of the invention, the radar system calculates the coordinates of radar points to obtain feature values ​​such as the head position, chest position, foot position, and body shape information of a moving object, assigning different weights to each feature. The radar system calculates the final total score of the moving object based on the feature value and its corresponding weight. The radar system compares the total score with a threshold to determine whether the moving object is a child or an adult. When a child is identified, an alarm is triggered to the vehicle owner. In summary, by comprehensively judging multiple feature values, the accuracy of passenger identification is higher compared to judging based on a single dimension.

[0069] Furthermore, the weighting factors also include respiratory rate, head position, chest position, foot position, and body shape information as weighting factors. Step S324, which identifies the passenger type of the moving object, includes:

[0070] S324A: Obtain the respiratory rate of passengers inside the vehicle and calculate the similarity between the respiratory rate and the reference rate;

[0071] S324B: If the similarity reaches the third threshold, then the breathing frequency will be used as a new weighting factor to participate in the identification of moving objects.

[0072] In this embodiment of the invention, respiratory rate can be obtained simultaneously with chest position calculation at different height regions. Obstruction of the respiratory rate by a person inside a vehicle or by a child safety seat can lead to inaccurate respiratory rate calculation; therefore, it is necessary to determine the reliability of respiratory rate as a feature value. For calm, undisturbed breathing, the signal characteristic is in the form of a sine wave. The respiratory rate f1 is calculated based on the signal, generating a sine wave with frequency f1. The similarity between the respiratory signal and the sine wave is compared. If the similarity is greater than a threshold, the current respiratory rate is considered accurate and can be used for passenger identification. Different weight values ​​are assigned based on the similarity; the higher the similarity, the higher the weight value. If the similarity is lower than the threshold, it is considered that there is movement or obstruction of the living body, leading to inaccurate respiratory rate calculation, and the respiratory rate cannot be used as a weighting factor. Due to differences in lung capacity, children's respiratory rate is faster than adults; therefore, using respiratory rate as a feature value can further improve the accuracy of passenger identification.

[0073] Further, step S324, which uses head position, chest position, foot position, and body shape information as weighting factors to identify the passenger type of a moving object, includes:

[0074] S324a: Obtain the type of the vehicle, adjust the values ​​of each weight factor according to the type, and identify the passenger type.

[0075] In this embodiment of the invention, weighting factors include, but are not limited to, the head position, chest position, foot position, and body shape information of the moving object. Due to differences in vehicle types, adjusting the values ​​of each weighting factor based on different vehicle models can further improve the accuracy of passenger type recognition. For example, for small private cars, the roof is low, and due to radar measurement errors, the height difference between a 1.2-meter child and a 1.5-meter adult in their seats is not significant. Therefore, the weights for height, head position, and chest position are relatively small, while the weights for foot position and body length are relatively high. For SUVs, the roof is high, and there is a height difference between children and adults. Therefore, the weights for height, head position, and chest position are relatively large, while the weights for foot position and body length are relatively low. Therefore, flexibly adjusting the corresponding values ​​of the weighting factors according to the vehicle type further improves the accuracy of recognition.

[0076] Reference Figure 4 The present invention also provides an in-vehicle passenger identification device, comprising:

[0077] The initial inspection module 1A is used to detect the environment inside the vehicle and determine whether there are moving objects.

[0078] The position confirmation module 1B is used to acquire first radar point cloud information of the horizontal area inside the vehicle if the position is yes, and to confirm the position information of the moving object, wherein the horizontal area inside the vehicle includes the seat surface area and the floor mat area.

[0079] The identification module 1C is used to obtain second radar point cloud information of the height region of the moving object based on the location information, and to identify the passenger type of the moving object based on the first radar point cloud information and the second radar point cloud information, wherein the height region includes a seat back area and a leg space, and the leg space is set perpendicular to the foot pad area;

[0080] The alarm module 1D is used to issue an alarm message when a specified type of passenger is detected when the car is stationary and locked.

[0081] In this embodiment of the invention, reference is made to Figure 2 The radar is installed on the side of the vehicle, either left or right. It covers the seats and floor mats without obstruction, ensuring the radar is fixed to the vehicle and remains relatively stationary, preventing displacement due to vehicle movement. Figure 2 As shown, areas A to C represent the rear seats, areas D to F represent the rear floor mats, area G represents the driver's seat, area I represents the driver's floor mat, area H represents the passenger seat, and area J represents the passenger's floor mat. The radar system detects the in-vehicle environment to determine if any moving objects are present. The specific principle is as follows: Millimeter-wave radar receives reflected information from objects. Due to the human body's natural breathing and heartbeat, a person cannot be completely still inside a vehicle; therefore, only moving or slightly moving targets need to be detected. The specific detection method involves judging the consistency of multiple frames of data within the same time period. If there is no living person inside the vehicle, the multiple frames of data at the same distance are basically consistent, with a small energy difference between them. If there is a living person inside the vehicle, the movement of the living person will cause differences in the multiple frames of data at the same distance, leading to an increase in the energy difference between them. When the energy difference is greater than a threshold, it is considered that there is a slightly moving target (i.e., a living person) inside the vehicle; otherwise, it is considered that there is no slightly moving target (i.e., a living person). If there is no slightly moving target inside the vehicle, it is considered that there are no moving objects inside the vehicle. When a moving object is present inside the vehicle, the first radar point cloud information of the horizontal area inside the vehicle is acquired to confirm the location of the moving object. For example, refer to Figure 2 When the radar point cloud density of regions H and J meets the threshold, the moving object is considered to exist in the co-pilot's position. (Refer to...) Figure 3After confirming the location of the moving object, the second radar point cloud information of the object's height region is acquired. Combined with the first and second radar point cloud information, multiple feature information of the moving object is calculated, including height, density, and volume, to identify the passenger type to which the moving object belongs. Because regulations require children to use child safety seats, which increase height, making a child's height in a safety seat similar to that of a small to medium-sized adult, this solution decomposes multiple features of the moving object from both horizontal and vertical dimensions. Through multi-feature calculation, the passenger type to which the moving object belongs is precisely identified. When the car is stationary and locked, an alarm is triggered if a specific type of passenger (such as a child) is identified; otherwise, no alarm is triggered to avoid false alarms or missed alarms. In addition, this solution detects the in-vehicle environment in the initial stage to eliminate false alarms caused by non-biological objects. In summary, this solution detects the in-vehicle environment in the initial stage, eliminating false alarms caused by non-biological objects. Moreover, this solution breaks down multiple features of moving objects from two dimensions: horizontal and vertical regions. Through the calculation of multiple features, it can accurately identify the passenger type to which the moving object belongs, further eliminating false alarms or missed alarms, and significantly improving the accuracy of alarms for passengers left in the vehicle.

[0082] In addition, combined Figure 5 The in-vehicle passenger identification method described in this embodiment of the invention can be implemented by an electronic device. Figure 5 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention is shown.

[0083] Electronic devices may include processors and memory storing computer program instructions.

[0084] Specifically, the processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement embodiments of the present invention.

[0085] The memory may include a large-capacity storage device for data or instructions. For example, and not limitingly, the memory may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory may include removable or non-removable (or fixed) media. Where appropriate, the memory may be internal or external to a data processing device. In a particular embodiment, the memory is a non-volatile solid-state memory. In a particular embodiment, the memory includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0086] The processor reads and executes computer program instructions stored in the memory to implement any of the automatic layout methods for cut images in the above embodiments.

[0087] In one example, the electronic device may also include a communication interface and a bus. For example, Figure 5 As shown, the processor, memory, and communication interface are connected via a bus and communicate with each other.

[0088] The communication interface is mainly used to enable communication between various modules, devices, units and / or equipment in the embodiments of the present invention.

[0089] A bus, including hardware, software, or both, couples components of an electronic device together. For example, and not limitingly, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, a bus may include one or more buses. While specific buses are described and illustrated in embodiments of the invention, the invention contemplates any suitable bus or interconnect.

[0090] Furthermore, in conjunction with the in-vehicle passenger identification method in the above embodiments, this invention can be implemented using a computer-readable storage medium. This computer-readable storage medium stores computer program instructions; when executed by a processor, these computer program instructions implement any of the in-vehicle passenger identification methods described in the above embodiments.

[0091] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0092] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0093] It should also be noted that the exemplary embodiments mentioned in this invention describe methods or systems based on a series of steps or apparatus. However, this invention is not limited to the order of the steps described above; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0094] The above description is merely a specific embodiment of the present invention. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the protection scope of the present invention.

Claims

1. A method for identifying passengers inside a vehicle, applied to a radar system, characterized in that, include: Detect the environment inside the vehicle to determine if there are moving objects; If so, the first radar point cloud information of the horizontal area inside the vehicle is obtained to confirm the position information of the moving object, wherein the horizontal area inside the vehicle includes the seat surface area and the floor mat area; Based on the location information, the second radar point cloud information of the height region of the moving object is obtained, and based on the first radar point cloud information and the second radar point cloud information, the passenger type of the moving object is identified. The height region includes a seat back area and a leg space, and the leg space is set perpendicular to the footrest area. When the car is stationary and locked, an alarm message will be issued if a passenger of a specified type is detected. The step of obtaining second radar point cloud information of the height region of the moving object based on the location information, and identifying the passenger type of the moving object based on the first radar point cloud information and the second radar point cloud information, includes: The height region is divided into several second regions, and it is determined whether the radar point cloud density of each second region reaches a second threshold. If the radar point cloud density of the second region reaches the second threshold, the second region is determined to be the second effective region. Based on all the second effective regions, the body size information of the moving object is calculated to identify the passenger type to which the moving object belongs. The step of determining the second region as a second effective region if the radar point cloud density of the second region reaches the second threshold, and calculating the body size information of the moving object based on all second effective regions to identify the passenger type of the moving object, includes: The seat back area is divided into a head area, a chest area, and a seat cushion area. Radar point cloud density information of the head area, the chest area, and the seat cushion area are obtained respectively to determine the head position and chest position of the moving object. The radar point cloud density information of the leg space is obtained to determine the foot position of the moving object; Based on the radar point cloud density information of the seat back area and the legroom, the body shape information of the moving object is calculated. The head position, chest position, foot position, and body shape information are used as weighting factors to identify the passenger type of the moving object.

2. The in-vehicle passenger identification method according to claim 1, characterized in that, If so, the step of acquiring first radar point cloud information of the horizontal area inside the vehicle and confirming the position information of the moving object includes: The horizontal region is divided into several first regions, and it is determined whether the radar point cloud density of each first region reaches a first threshold. If the radar point cloud density of the first region reaches the first threshold, the first region is determined to be a first effective region, and the position information of the moving object is confirmed based on the distribution of all the first effective regions.

3. The in-vehicle passenger identification method according to claim 1, characterized in that, The weighting factors also include respiratory rate, head position, chest position, foot position, and body shape information as weighting factors. The step of identifying the passenger type of the moving object includes: The respiratory rates of the passengers inside the vehicle are obtained, and the similarity between the respiratory rates and reference rates is calculated. If the similarity reaches the third threshold, the breathing frequency will be used as a new weighting factor to participate in the identification of the moving object.

4. The in-vehicle passenger identification method according to claim 1 or 3, characterized in that, The step of identifying the passenger type of the moving object using the head position, chest position, foot position, and body shape information as weighting factors includes: Obtain the vehicle type, adjust the values ​​of each weight factor according to the type, and identify the passenger type.

5. The in-vehicle passenger identification method according to claim 1, characterized in that, The step of issuing an alarm message if a specified type of passenger is detected when the vehicle is stationary and locked includes: An alarm will be triggered when a child is identified as a passenger.

6. A vehicle passenger identification device, characterized in that, include: The initial inspection module is used to detect the environment inside the vehicle and determine whether there are moving objects. The position confirmation module is used to acquire first radar point cloud information of the horizontal area inside the vehicle if the position is yes, and to confirm the position information of the moving object, wherein the horizontal area inside the vehicle includes the seat surface area and the floor mat area. The identification module is used to obtain second radar point cloud information of the height region of the moving object based on the location information, and to identify the passenger type of the moving object based on the first radar point cloud information and the second radar point cloud information, wherein the height region includes a seat back area and a leg space, and the leg space is set perpendicular to the footrest area; The alarm module is used to issue an alarm message if a specified type of passenger is detected when the car is stationary and locked. The step of obtaining second radar point cloud information of the height region of the moving object based on the location information, and identifying the passenger type of the moving object based on the first radar point cloud information and the second radar point cloud information, includes: The height region is divided into several second regions, and it is determined whether the radar point cloud density of each second region reaches a second threshold. If the radar point cloud density of the second region reaches the second threshold, the second region is determined to be the second effective region. Based on all the second effective regions, the body size information of the moving object is calculated to identify the passenger type to which the moving object belongs. The step of determining the second region as a second effective region if the radar point cloud density of the second region reaches the second threshold, and calculating the body size information of the moving object based on all second effective regions to identify the passenger type of the moving object, includes: The seat back area is divided into a head area, a chest area, and a seat cushion area. Radar point cloud density information of the head area, the chest area, and the seat cushion area are obtained respectively to determine the head position and chest position of the moving object. The radar point cloud density information of the leg space is obtained to determine the foot position of the moving object; Based on the radar point cloud density information of the seat back area and the legroom, the body shape information of the moving object is calculated. The head position, chest position, foot position, and body shape information are used as weighting factors to identify the passenger type of the moving object.

7. A storage medium storing computer program instructions thereon, characterized in that, The method as described in any one of claims 1 to 5 is implemented when the computer program instructions are executed by the processor.

8. An electronic device, characterized in that, include: At least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method as described in any one of claims 1 to 5.

Images