CN118795454A - In-vehicle liveness detection method, device, equipment, storage medium and program product - Google Patents

Abstract

The disclosed embodiments provide a method, device, equipment, storage medium and program product for in-vehicle liveness detection. The method includes: obtaining a multi-frame radar signal within a currently set time length; downsampling the multi-frame radar signal within the currently set time length to obtain a multi-frame radar signal after downsampling; processing the multi-frame radar signal after downsampling to obtain a target radar signal; inputting the target radar signal into a set in-vehicle liveness detection model to output a target in-vehicle liveness detection result. The disclosed embodiments improve the accuracy and efficiency of in-vehicle liveness detection by downsampling the multi-frame radar signal within the currently set time length and processing the multi-frame radar signal after downsampling to obtain a target radar signal, and performing in-vehicle liveness detection on the target radar signal through a set in-vehicle liveness detection model.

Description

In-vehicle liveness detection method, device, equipment, storage medium and program product

Technical Field

The embodiments of the present disclosure relate to the technical field of in-vehicle liveness detection, and in particular to an in-vehicle liveness detection method, device, equipment, storage medium, and program product.

Background Art

With the continuous improvement of automobile intelligence and safety requirements, the technology of detecting live bodies in the vehicle after the vehicle is locked has become one of the important measures to ensure vehicle safety. At present, the method of detecting live bodies in the vehicle after the vehicle is locked is based on the radar signal of Ultra Wide Band (UWB) technology. Due to the limitations of the microcontroller unit (MCU) in storage, computing power, and running time, as well as the influence of the UWB radar signal itself, there are problems with low detection accuracy and detection efficiency, which leads to low vehicle safety.

Summary of the invention

The embodiments of the present disclosure provide a method, device, equipment, storage medium and program product for in-vehicle liveness detection, which can improve the accuracy and efficiency of in-vehicle liveness detection, thereby improving the safety of the vehicle.

In a first aspect, an embodiment of the present disclosure provides a method for in-vehicle liveness detection, comprising: acquiring a multi-frame radar signal within a currently set time length; downsampling the multi-frame radar signal within the currently set time length to obtain a multi-frame radar signal after downsampling; processing the multi-frame radar signal after downsampling to obtain a target radar signal; inputting the target radar signal into a set in-vehicle liveness detection model, and outputting a target in-vehicle liveness detection result.

In the second aspect, the embodiment of the present disclosure also provides an in-vehicle liveness detection device, including: a signal acquisition module, used to acquire a multi-frame radar signal within a currently set time length; a downsampling module, used to downsample the multi-frame radar signal within the currently set time length to obtain the downsampled multi-frame radar signal; a processing module, used to process the downsampled multi-frame radar signal to obtain a target radar signal; a detection module, used to input the target radar signal into a set in-vehicle liveness detection model, and output the target in-vehicle liveness detection result.

In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

one or more processors;

a storage device for storing one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement the in-vehicle living body detection method as described in the embodiment of the present disclosure.

In a fourth aspect, an embodiment of the present disclosure further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the in-vehicle living body detection method as described in the embodiment of the present disclosure.

In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, including a computer program, which, when executed by a processor, implements the in-vehicle living body detection method as described in the embodiment of the present disclosure.

The technical solution disclosed in this embodiment obtains a multi-frame radar signal within a currently set time length; downsamples the multi-frame radar signal within the currently set time length to obtain a multi-frame radar signal after downsampling; processes the multi-frame radar signal after downsampling to obtain a target radar signal; inputs the target radar signal into a set in-vehicle liveness detection model to output a target in-vehicle liveness detection result. The embodiment disclosed in this embodiment can improve the accuracy and efficiency of in-vehicle liveness detection by downsampling the multi-frame radar signal within the currently set time length and processing the multi-frame radar signal after downsampling to obtain a target radar signal, and performing in-vehicle liveness detection on the target radar signal through a set in-vehicle liveness detection model.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

FIG1 is a schematic flow chart of a method for detecting a living body in a vehicle provided by an embodiment of the present invention;

FIG2 is a flow chart of another in-vehicle living body detection method provided by an embodiment of the present invention;

FIG3 is a schematic diagram of the structure of a liveness detection device in a vehicle provided by an embodiment of the present disclosure;

FIG. 4 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure.

DETAILED DESCRIPTION

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and/or in parallel. In addition, the method embodiments may include additional steps and/or omit the steps shown. The scope of the present disclosure is not limited in this respect.

The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

FIG1 is a flow chart of a method for detecting a live body in a vehicle provided by an embodiment of the present invention. This embodiment is applicable to the case where a live body detection is performed in a vehicle by using a radar signal in the vehicle after the vehicle is locked. The method can be performed by an in-vehicle live body detection device and specifically includes the following steps:

It should be noted that the radar in the present invention can be any type of radar, for example, it can be a UWB radar. There can be multiple radars, which can be installed at any position in the car. For example, there are two radars, which can be used to detect whether there are living things in the front and back rows of the car. Living things can include animals, people, etc. The program corresponding to this solution can run on low-computing power and low-storage devices. This solution can be applied to scenarios such as anti-theft reminders and reminders for forgotten children or pets. For example, if the liveness detection result in the target car is that there is a live thing, a corresponding safety reminder can be made, thereby realizing safety monitoring of the vehicle and improving the safety of the vehicle.

S110, obtaining multiple frames of radar signals within a currently set time length.

In this embodiment, the current set duration may be any duration, for example, 6 seconds, 7 seconds, 8 seconds, etc. One frame may correspond to any millisecond, preferably, one frame may correspond to 40 milliseconds. The multiple frames of radar signals within the current set duration are continuous in time, that is, the multiple frames of radar signals include a time sequence feature.

The last radar signal frame within the currently set time period is the current radar signal frame. The radar signal may include living body data, such as human breathing rate data.

In this embodiment, in-vehicle liveness detection can be performed in real time, that is, in-vehicle liveness detection can be performed on each frame of radar signal. However, each time in-vehicle liveness detection is performed, multiple frames of radar signals within a set duration are required (multiple frames of radar signals within a set duration can more clearly show whether there is a live body). Multiple frames of radar signals within the current set duration can be used to perform in-vehicle liveness detection on the current frame of radar signal. In this embodiment, each time in-vehicle liveness detection is performed, in-vehicle liveness detection is performed using multiple frames of radar signals within a set duration, which can improve the accuracy of detection relative to a single-frame prediction method.

For example, the current set time length is 8 seconds, and each frame corresponds to 40 milliseconds. Multiple frames of radar signals within the current set time length can represent 200 frames of radar signals. When performing in-vehicle living body detection on the current frame radar signal, the input data required to be obtained is the current frame radar signal and the radar signals of the previous 199 frames.

Optionally, the radar signal is a signal within a set distance range. The distance range is composed of a plurality of continuous distance sub-ranges; and the distance sub-range corresponds to a distance of a set length.

In this embodiment, taking UWB radar as an example, in actual application, for UWB radar in-vehicle live body detection, UWB radar can correspond to multiple distance sub-ranges. In this embodiment, there is no restriction on the specific number of multiple distance sub-ranges, and there is no restriction on the specific distance of the set length. Exemplarily, the distance sub-range is represented by "tap", and the UWB radar can correspond to 64 taps, tap0-tap13 can be regarded as noise, that is, each tap in tap0-tap13 can correspond to 0 meters, and each tap from tap14 to tap63 corresponds to 15cm. In this embodiment, the set distance range can be expressed as tap18 to tap26, tap18 to tap26 corresponds to 0.75 meters to 1.95 meters, and the set distance range can meet the detection of the in-vehicle space (limited in-vehicle space). Multiple continuous distance sub-ranges are tap18 to tap26. The set length is 15cm. In this embodiment, selecting the signal within the set distance range in the radar signal can solve the problem of limited in-vehicle space.

Among them, the radar signal corresponding to each distance sub-range is a complex signal, that is, it includes a real part and an imaginary part. In this embodiment, the radar signal is the data after modulo taking. For example, after modulo taking the radar signal corresponding to the tap18 distance sub-range, it can be 418.9367494.

S120: down-sample the multiple frames of radar signals within the currently set time length to obtain the down-sampled multiple frames of radar signals.

In this embodiment, any downsampling method can be used to downsample the multi-frame radar signal within the set time length, so that the number of frames of the downsampled multi-frame radar signal is less than the number of frames of the multi-frame radar signal within the current set time length. For example, the downsampling method can be: uniform sampling (such as sampling according to a fixed sampling interval), random downsampling (such as random sampling), channel strength-based downsampling (such as selecting frames with signal strength greater than a set signal strength threshold), etc.

Optionally, downsampling is performed on the multi-frame radar signal within the currently set time length to obtain the downsampled multi-frame radar signal, including: downsampling is performed on the multi-frame radar signal within the currently set time length according to a set sampling interval to obtain the downsampled multi-frame radar signal; the number of frames of the downsampled multi-frame radar signal is less than the number of frames of the multi-frame radar signal within the currently set time length.

In this embodiment, under the premise of meeting the acquisition speed and human breathing frequency, the multi-frame radar signal within the current set time length can be downsampled by uniform downsampling, while retaining the breathing-related feature data, which can solve the problem of too large input features and limited equipment resources in the prior art, and improve the accuracy and speed of detection. Exemplary: Taking 200 frames of radar signals as an example of the multi-frame radar signal within the current set time length, the sampling interval can be set to extract one frame every a certain number of frames (such as 10 frames), that is, from the 200 frames of radar signals, one frame can be extracted every 10 frames, and 20 frames of radar signals can be obtained. The 20 frames of radar signals still maintain the time continuity of the 200 frames of radar signals, that is, the multi-frame radar signals after downsampling still have timing characteristics, which can further increase the accuracy of detection.

S130: Process the downsampled multiple frames of radar signals to obtain target radar signals.

The target radar signal may be one-dimensional data. In this embodiment, the downsampled multi-frame radar signal may be processed in any manner so that the downsampled multi-frame radar signal becomes one-dimensional data. For example, the downsampled multi-frame radar signal may be superimposed or averaged, flattened, and merged.

Optionally, the downsampled multi-frame radar signals are processed to obtain a target radar signal, including: flattening and merging the downsampled multi-frame radar signals corresponding to the set distance range in sequence to obtain a target radar signal.

In this embodiment, the downsampled multi-frame radar signals corresponding to the set distance range can be flattened to obtain a flat time-series radar signal corresponding to each distance sub-range, and then the flat time-series radar signals corresponding to multiple distance sub-ranges can be merged to obtain the target radar signal. The flat time-series radar signal can be understood as a flat radar signal with time-series features, that is, one-dimensional data with time-series features.

S140: Input the target radar signal into a set in-vehicle living body detection model, and output a target in-vehicle living body detection result.

Among them, the in-vehicle liveness detection model can be a machine learning type model or a deep learning type model, and this embodiment does not limit this. Preferably, the set in-vehicle liveness detection model can be a decision tree algorithm with low computing power and fast time in machine learning, which can meet the requirements of running on low computing power and low storage devices. In this embodiment, the set in-vehicle liveness detection model can be obtained by training based on a training set, and the training set can be composed of multiple frames of radar signals within a plurality of historical set time periods, and the labels corresponding to the multiple frames of radar signals within each historical set time period are the presence of a live body or the absence of a live body.

The target vehicle in-vehicle live body detection result may include a first detection result and a second detection result. The first detection result may be the presence of a live body, and the second detection result may be the absence of a live body.

In this embodiment, the in-vehicle liveness detection is performed on the target radar signal through the set in-vehicle liveness detection model, and the target in-vehicle liveness detection result can be quickly output, and the time consumption for a single prediction can be 0.4 milliseconds.

The technical solution disclosed in this embodiment obtains a multi-frame radar signal within a currently set time length; downsamples the multi-frame radar signal within the currently set time length to obtain a multi-frame radar signal after downsampling; processes the multi-frame radar signal after downsampling to obtain a target radar signal; inputs the target radar signal into a set in-vehicle liveness detection model to output a target in-vehicle liveness detection result. The disclosed embodiment of the present invention improves the accuracy and efficiency of in-vehicle liveness detection by downsampling the multi-frame radar signal within the currently set time length and processing the multi-frame radar signal after downsampling to obtain a target radar signal, and performs in-vehicle liveness detection on the target radar signal through a set in-vehicle liveness detection model, thereby improving the safety of the vehicle.

FIG2 is a flow chart of another in-vehicle liveness detection method provided by an embodiment of the present invention. The embodiment of the present invention is a specific implementation of the above-mentioned embodiment of the invention. Referring to FIG2 , the method provided by the embodiment of the present invention specifically includes the following steps:

S210: Acquire multiple frames of radar signals within a currently set time period.

The radar signal is a signal within a set distance range, and the distance range is composed of a plurality of continuous distance sub-ranges.

S220: down-sample the multiple frames of radar signals within the currently set time length to obtain the down-sampled multiple frames of radar signals.

S230: Flatten the down-sampled multi-frame radar signals corresponding to each distance sub-range to obtain a flat time-series radar signal corresponding to each distance sub-range.

Exemplarily, the set distance range is still taken as tap18 to tap26, that is, the number of distance sub-ranges includes 9, and the multi-frame radar signal after downsampling is still taken as 20 frames. The 20 frames of radar signals corresponding to each distance sub-range in tap18 to tap26 are flattened, and the flattened time series radar signal corresponding to each distance sub-range can be a one-dimensional data of 1*20.

S240 , horizontally splicing the flat time-series radar signals corresponding to each distance sub-range according to a set order to obtain a target radar signal.

The setting order may be the order of multiple distance sub-ranges within the set distance range, such as the arrangement order corresponding to tap18 to tap26. Exemplarily, the set distance range is still taken as tap18 to tap26. After obtaining the flat time-series radar signals corresponding to tap18 to tap26, the flat time-series radar signals corresponding to tap18 to tap26 are sequentially horizontally spliced in accordance with the setting order corresponding to tap18 to tap26 to obtain the target radar signal, that is, the target radar signal may be 1*180 one-dimensional data (obtained by splicing 9 1*20 one-dimensional data).

S250: Input the target radar signal into a set in-vehicle living body detection model, and output a target in-vehicle living body detection result.

Optionally, the target radar signal is input into a set in-vehicle liveness detection model, and the target in-vehicle liveness detection result is output, including: inputting the target radar signal into a set in-vehicle liveness detection model, and outputting an initial in-vehicle liveness detection result; if the probability value of the initial in-vehicle liveness detection result is less than a set probability threshold, then determining the historical set time lengths corresponding to the previous set number of historical frame radar signals corresponding to the current frame radar signal; wherein the last frame radar signal within each historical set time length is the corresponding historical frame radar signal; determining the target in-vehicle liveness detection result based on multiple initial detection results corresponding to multiple historical set time lengths and the initial detection result corresponding to the current set time length; if the probability value of the initial in-vehicle liveness detection result is equal to or greater than the set probability threshold, then using the initial in-vehicle liveness detection result as the target in-vehicle liveness detection result.

In this embodiment, when the initial detection result is output by the set in-vehicle liveness detection model, there are certain fluctuations (there are certain similarities in the breathing rate data of a person sitting still in the car and standing near the car window), but the process from the presence of a living body in the car to the absence of a living body is a temporal process. The initial detection result output by the set in-vehicle liveness detection model can be corrected by combining the previously set number of historical frame radar signals and the current frame radar signal.

In this embodiment, there is no restriction on the specific setting probability threshold, which may be 50% for example. In this embodiment, there is no restriction on the specific number of the setting quantity, which may be 4 for example.

Exemplarily, the target radar signal is input into a set in-vehicle liveness detection model, and an initial in-vehicle liveness detection result is output; if the probability value of the initial in-vehicle liveness detection result is equal to or greater than a set probability threshold, the initial in-vehicle liveness detection result is directly used as the target in-vehicle liveness detection result.

If the probability value of the initial in-vehicle liveness detection result is less than the set probability threshold, the historical set durations corresponding to the first four historical frame radar signals corresponding to the current frame radar signal are determined respectively; the first four historical frame radar signals can be recorded as the first historical frame radar signal, the second historical frame radar signal, the third historical frame radar signal and the fourth historical frame radar signal in chronological order. The historical set durations corresponding to the first four historical frame radar signals can also be recorded as the first historical set duration, the second historical set duration, the third historical set duration and the fourth historical set duration in chronological order, and the set duration after the fourth historical set duration is the current set duration. Among them, the last frame radar signal within each historical set duration is the corresponding historical frame radar signal.

If the first historical setting time length takes the 200 frames of radar signals from the 1st frame to the 200th frame (all are historical frame radar signals) as an example, and the last frame of radar signal of the first historical setting time length is the first historical frame radar signal, then the second historical setting time length can be the 200 frames of radar signals from the 2nd frame to the 201st frame (all are historical frame radar signals), and the last frame of radar signal of the second historical setting time length is the second historical frame radar signal, the third historical setting time length can be the 200 frames of radar signals from the 3rd frame to the 202nd frame (all are historical frame radar signals), and the last frame of radar signal of the third historical setting time length is the third historical frame radar signal, the fourth historical setting time length can be the 200 frames of radar signals from the 4th frame to the 203rd frame (all are historical frame radar signals), and the last frame of radar signal of the fourth historical setting time length is the fourth historical frame radar signal, and the current setting time length can be the 200 frames of radar signals from the 5th frame to the 204th frame (all are historical frame radar signals), and the last frame of radar signal of the current setting time length is the current frame radar signal.

The target liveness result is determined according to the initial detection results corresponding to the first historical setting time, the second historical setting time, the third historical setting time, the fourth historical setting time and the current setting time.

Optionally, the initial in-vehicle liveness detection result includes a first detection result and a second detection result; determining the target in-vehicle liveness detection result based on multiple initial detection results corresponding to multiple historical set time lengths and the initial detection result corresponding to the current set time length includes: counting the number of occurrences of the first detection result and the number of occurrences of the second detection result in the multiple initial detection results corresponding to the multiple historical set time lengths and the initial detection result corresponding to the current set time length; if the number of occurrences of the first detection result is greater than the number of occurrences of the second detection result, taking the first detection result as the target in-vehicle liveness detection result; if the number of occurrences of the second detection result is greater than the number of occurrences of the first detection result, taking the second detection result as the target in-vehicle liveness detection result.

Among them, the first detection result is the presence of a living body, and the second detection result is the absence of a living body. Exemplarily, if the initial detection result corresponding to the first historical setting time is the absence of a living body, the initial detection result corresponding to the second historical setting time is the absence of a living body, the initial detection result corresponding to the third historical setting time is the presence of a living body, the initial detection result corresponding to the fourth historical setting time is the presence of a living body, the initial detection result corresponding to the current setting time is the presence of a living body, the first detection result appears 3 times, and the second detection result appears 2 times, then the detection result of the living body in the target vehicle may be the presence of a living body.

If the initial detection result corresponding to the first historical setting time is the presence of a living body, the initial detection result corresponding to the second historical setting time is the presence of a living body, the initial detection result corresponding to the third historical setting time is the absence of a living body, the initial detection result corresponding to the fourth historical setting time is the absence of a living body, and the initial detection result corresponding to the current setting time is the absence of a living body, the first detection result appears 2 times, and the second detection result appears 3 times, then the live body detection result in the target vehicle may be the absence of a living body.

The technical solution provided in this embodiment downsamples the multi-frame radar signals within the currently set time length, flattens the downsampled multi-frame radar signals corresponding to each distance sub-range, obtains the flattened time-series radar signal corresponding to each distance sub-range, horizontally splices the flattened time-series radar signals corresponding to each distance sub-range in a set order, obtains the target radar signal, inputs the target radar signal into the set in-vehicle liveness detection model, and outputs the target in-vehicle liveness detection result, which can further improve the accuracy and efficiency of in-vehicle liveness detection.

FIG3 is a schematic diagram of the structure of a vehicle-based liveness detection device provided by an embodiment of the present disclosure. As shown in FIG3 , the device includes: a signal acquisition module 310, a downsampling module 320, a processing module 330, and a detection module 340;

The signal acquisition module 310 is used to acquire multiple frames of radar signals within a currently set time period;

A downsampling module 320 is used to perform downsampling processing on the multi-frame radar signal within the currently set time length to obtain the downsampled multi-frame radar signal;

A processing module 330 is used to process the downsampled multi-frame radar signal to obtain a target radar signal;

The detection module 340 is used to input the target radar signal into a set in-vehicle living body detection model and output a target in-vehicle living body detection result.

The technical solution disclosed in this embodiment is to obtain a multi-frame radar signal within a currently set time length through a signal acquisition module; to perform downsampling processing on the multi-frame radar signal within the currently set time length through a downsampling module to obtain a multi-frame radar signal after downsampling; to process the multi-frame radar signal after downsampling through a processing module to obtain a target radar signal; and to input the target radar signal into a set in-vehicle liveness detection model through a detection module to output a target in-vehicle liveness detection result. The embodiment disclosed in this embodiment can improve the accuracy and efficiency of in-vehicle liveness detection by downsampling the multi-frame radar signal within the currently set time length and processing the multi-frame radar signal after downsampling to obtain a target radar signal, and perform in-vehicle liveness detection on the target radar signal through a set in-vehicle liveness detection model, thereby improving the safety of the vehicle.

The radar signal is a signal within a set distance range.

Optionally, the downsampling module is specifically used to: downsample the multi-frame radar signal within the current set time length according to a set sampling interval to obtain the downsampled multi-frame radar signal; the number of frames of the downsampled multi-frame radar signal is less than the number of frames of the multi-frame radar signal within the current set time length.

Optionally, the processing module is specifically used to: sequentially flatten and merge the down-sampled multiple frames of radar signals corresponding to the set distance range to obtain a target radar signal.

Wherein, the distance range is composed of multiple continuous distance sub-ranges; the distance sub-range corresponds to a distance of a set length; optionally, the processing module is also used to flatten the down-sampled multi-frame radar signals corresponding to each distance sub-range to obtain a flat time-series radar signal corresponding to each distance sub-range; and horizontally splice the flat time-series radar signals corresponding to each distance sub-range in a set order to obtain a target radar signal.

Among them, the last frame radar signal within the current set time length is the current frame radar signal; optionally, the detection module is specifically used to: input the target radar signal into the set in-vehicle liveness detection model, and output the initial in-vehicle liveness detection result; if the probability value of the initial in-vehicle liveness detection result is less than the set probability threshold, then determine the historical set time lengths corresponding to the previous set number of historical frame radar signals corresponding to the current frame radar signal; wherein the last frame radar signal within each historical set time length is the corresponding historical frame radar signal; determine the target in-vehicle liveness detection result based on multiple initial detection results corresponding to multiple historical set time lengths and the initial detection result corresponding to the current set time length; if the probability value of the initial in-vehicle liveness detection result is equal to or greater than the set probability threshold, then use the initial in-vehicle liveness detection result as the target in-vehicle liveness detection result.

The initial in-vehicle liveness detection result includes a first detection result and a second detection result; optionally, the detection module is also used to: respectively count the number of occurrences of the first detection result and the number of occurrences of the second detection result in multiple initial detection results corresponding to multiple historical set time lengths and the initial detection result corresponding to the current set time length; if the number of occurrences of the first detection result is greater than the number of occurrences of the second detection result, use the first detection result as the target in-vehicle liveness detection result; if the number of occurrences of the second detection result is greater than the number of occurrences of the first detection result, use the second detection result as the target in-vehicle liveness detection result.

The in-vehicle liveness detection device provided in the embodiments of the present disclosure can execute the in-vehicle liveness detection method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

FIG3 shows a block diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and/or required herein.

As shown in FIG3 , the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11 in communication, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.

A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for in-vehicle liveness detection.

In some embodiments, the method for in-vehicle liveness detection can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and/or installed on the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for in-vehicle liveness detection described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for in-vehicle liveness detection in any other appropriate manner (for example, by means of firmware).

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and/or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions/operations specified in the flow chart and/or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the in-vehicle living body detection method provided in any embodiment of the present application.

In the process of implementation, the computer program product can be written in one or more programming languages or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims (11)

1. An in-vehicle living body detection method, characterized by comprising:

acquiring multi-frame radar signals within a current set time length;

performing downsampling processing on the multi-frame radar signals in the current set duration to obtain downsampled multi-frame radar signals;

Processing the downsampled multi-frame radar signals to obtain target radar signals;

and inputting the target radar signal into a set in-vehicle living body detection model, and outputting a target in-vehicle living body detection result.

2. The method of claim 1, wherein the radar signal is a signal within a set range of distances.

3. The method of claim 1, wherein downsampling the multi-frame radar signal for the current set duration to obtain downsampled multi-frame radar signals, comprising:

downsampling the multi-frame radar signals in the current set time length according to a set sampling interval to obtain downsampled multi-frame radar signals; the frame number of the multi-frame radar signals after downsampling is smaller than that of the multi-frame radar signals in the current set duration.

4. The method of claim 2, wherein processing the downsampled multi-frame radar signal to obtain a target radar signal comprises:

and flattening and merging the downsampled multi-frame radar signals corresponding to the set distance range in sequence to obtain target radar signals.

5. The method of claim 4, wherein the distance range consists of a plurality of consecutive distance sub-ranges; flattening and merging the downsampled multi-frame radar signals corresponding to the set distance range in sequence to obtain target radar signals, wherein the flattening and merging processes comprise the following steps:

Flattening the downsampled multi-frame radar signals corresponding to each distance sub-range to obtain flat time sequence radar signals corresponding to each distance sub-range;

And transversely splicing the flat time sequence radar signals corresponding to each distance sub-range according to a set sequence to obtain target radar signals.

6. The method of claim 1, wherein the last frame of radar signal in the current set time period is a current frame of radar signal; inputting the target radar signal into a set in-vehicle living body detection model, and outputting a target in-vehicle living body detection result, wherein the method comprises the following steps:

Inputting the target radar signal into a set in-vehicle living body detection model, and outputting an initial in-vehicle living body detection result;

If the probability value of the initial in-vehicle living body detection result is smaller than a set probability threshold value, respectively determining the historical set time length corresponding to the previous set number of historical frame radar signals corresponding to the current frame radar signals; the last frame of radar signal in each history set time length is a corresponding history frame radar signal;

determining a living body detection result in the target vehicle based on a plurality of initial detection results corresponding to a plurality of historical set time lengths and an initial detection result corresponding to a current set time length;

and if the probability value of the initial in-vehicle living body detection result is equal to or greater than a set probability threshold value, taking the initial in-vehicle living body detection result as a target in-vehicle living body detection result.

7. The method of claim 6, wherein the initial in-vehicle living body detection result comprises a first detection result and a second detection result; determining a target in-vehicle living body detection result based on a plurality of initial detection results corresponding to a plurality of historical set time periods and an initial detection result corresponding to a current set time period, including:

counting the occurrence times of the first detection result and the occurrence times of the second detection result respectively in a plurality of initial detection results corresponding to a plurality of historical set time periods and initial detection results corresponding to the current set time periods;

If the number of times of occurrence of the first detection result is larger than that of occurrence of the second detection result, the first detection result is used as a target in-vehicle living body detection result;

And if the number of times of occurrence of the second detection result is larger than that of occurrence of the first detection result, taking the second detection result as a target in-vehicle living body detection result.

8. An in-vehicle living body detection apparatus, characterized by comprising:

The signal acquisition module is used for acquiring multi-frame radar signals within the current set duration;

The downsampling module is used for downsampling the multi-frame radar signals in the current set time length to obtain downsampled multi-frame radar signals;

The processing module is used for processing the downsampled multi-frame radar signals to obtain target radar signals;

And the detection module is used for inputting the target radar signal into a set in-vehicle living body detection model and outputting a target in-vehicle living body detection result.

9. An electronic device, the electronic device comprising:

One or more processors;

Storage means for storing one or more programs,

When executed by the one or more processors, causes the one or more processors to implement the in-vehicle living body detection method as recited in any one of claims 1-7.

10. A storage medium containing computer executable instructions for performing the in-vehicle biopsy method of any one of claims 1-7 when executed by a computer processor.

11. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the in-vehicle living detection method according to any of claims 1-7.