A target object detection method and device, a vehicle, and a medium

Abstract

The application discloses a target object detection method and device, a vehicle and a medium. The method is applied to a vehicle, a MIMO millimeter wave radar is installed on the vehicle, and the method comprises the following steps: obtaining echo signals of the MIMO millimeter wave radar, wherein the echo signals are distributed on three dimensions of distance, speed and channel; performing signal processing on the echo signals to obtain a processing result, wherein the processing result corresponds to two dimensions of distance and speed; determining a target signal-to-noise ratio of the echo signals in a preset distance range based on the processing result, and detecting whether a target object exists in the preset distance range of the vehicle according to the target signal-to-noise ratio. The method can quickly realize the detection of the target object on the basis of simplifying the detection method, and improves the real-time performance of the detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of millimeter wave radar signal processing, and particularly relates to a target object detection method and device, a vehicle and a medium. BACKGROUND

[0002] With the advent of the intelligent era, more and more new technologies are brought to the intelligentization of automobiles. In the process of pursuing the intelligentization of vehicles, users are also constantly pursuing the safety and use experience of vehicles. For example, vehicles have added the function of detecting target objects (such as children) left alone in the vehicle and sending an alarm to the vehicle owner or emergency department to avoid the death of children from heatstroke.

[0003] However, the existing target object detection method based on radar is relatively cumbersome and cannot quickly lock the target object in the scene, and the real-time performance is poor. SUMMARY

[0004] The present application provides a target object detection method, device, vehicle and medium to simplify the detection method and quickly realize the detection of target objects and improve the real-time performance of detection.

[0005] According to an aspect of the present application, a target object detection method is provided, which is applied to a vehicle, and a MIMO millimeter wave radar is installed on the vehicle. The method comprises:

[0006] Obtaining the echo signal of the MIMO millimeter wave radar, wherein the echo signal is distributed in three dimensions of distance, speed and channel;

[0007] Signal processing is performed on the echo signal to obtain a processing result, wherein the processing result corresponds to two dimensions of distance and speed;

[0008] Based on the processing result, a target signal-to-noise ratio of the echo signal in a preset distance range is determined, and whether there is a target object in the preset distance range of the vehicle is detected according to the target signal-to-noise ratio.

[0009] According to another aspect of the present application, a target object detection device is provided, which is configured in a vehicle and comprises:

[0010] An acquisition module is configured to acquire the echo signal of the MIMO millimeter wave radar, wherein the echo signal is distributed in three dimensions of distance, speed and channel;

[0011] A signal processing module is configured to perform signal processing on the echo signal to obtain a processing result, wherein the processing result corresponds to two dimensions of distance and speed;

[0012] The determining module is configured to determine a target signal-to-noise ratio of the echo signal within a preset distance range based on the processing result, and detect whether there is a target object within the preset distance range of the vehicle according to the target signal-to-noise ratio.

[0013] According to another aspect of the present application, there is provided a vehicle, comprising:

[0014] at least one processor; and

[0015] a memory connected to the at least one processor in communication; wherein,

[0016] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for detecting a target object according to any one of the embodiments of the present application.

[0017] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the method for detecting a target object according to any one of the embodiments of the present application when executed by the processor.

[0018] The embodiments of the present application provide a method and device for detecting a target object, a vehicle and a medium. The method is applied to a vehicle, and a MIMO millimeter wave radar is installed on the vehicle. The method comprises the following steps: obtaining an echo signal of the MIMO millimeter wave radar, wherein the echo signal is distributed in three dimensions of distance, speed and channel; performing signal processing on the echo signal to obtain a processing result, wherein the processing result corresponds to two dimensions of distance and speed; determining a target signal-to-noise ratio of the echo signal within a preset distance range based on the processing result, and detecting whether there is a target object within a preset distance range of the vehicle according to the target signal-to-noise ratio. By using the above technical solution, the processing result is obtained by performing signal processing on the echo signal, the target signal-to-noise ratio of the echo signal within the preset distance range is determined based on the processing result, and whether there is a target object within the preset distance range of the vehicle is detected according to the target signal-to-noise ratio. Therefore, the detection of the target object can be quickly realized on the basis of simplifying the detection method, and the real-time performance of the detection is improved.

[0019] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiments description. Obviously, the drawings in the following description only some of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0021] Figure 1 is a flow chart of a target object detection method according to an embodiment of the present application;

[0022] Figure 2 is a flow chart of a target object detection method according to an embodiment of the present application;

[0023] Figure 3 is a flow chart of another target object detection method according to an embodiment of the present application;

[0024] Figure 4 is a schematic diagram of a transformed echo signal according to an embodiment of the present application;

[0025] Figure 5 is a schematic diagram of another transformed echo signal according to an embodiment of the present application;

[0026] Figure 6 is a schematic diagram of a preprocessed echo signal according to an embodiment of the present application;

[0027] Figure 7 is a schematic diagram of another preprocessed echo signal according to an embodiment of the present application;

[0028] Figure 8 is a schematic diagram of a target signal-to-noise ratio according to an embodiment of the present application;

[0029] Figure 9 is a schematic diagram of another target signal-to-noise ratio according to an embodiment of the present application;

[0030] Figure 10 is a structural schematic diagram of a target object detection device according to an embodiment of the present application;

[0031] Figure 11 is a structural schematic diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in combination with the accompanying drawings in the embodiments of the present application, so that those skilled in the art can better understand the technical solutions of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work should belong to the protection scope of the present application.

[0033] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment one

[0035] Figure 1 It is a flowchart of a target object detection method according to the embodiment one of the present application. The embodiment can be applied to the case of detecting a target object. The method can be executed by a target object detection device, which can be realized in the form of hardware and / or software, and can be configured in a vehicle.

[0036] It can be considered that radar, as an important intelligent perception sensor, is not only widely used to perceive the environment around the vehicle outside the vehicle body, but also used as an important sensor of the intelligent cabin to perceive the passengers in the vehicle.

[0037] At present, many research institutions at home and abroad carry out target object (such as living body) detection technology research based on radar. On the one hand, the prior art proposes a living body detection method, which can process vital sign information by detecting the phase of the radar received echo, avoiding the influence of high harmonic caused by amplitude estimation and the direct current bias caused by I / Q two signals. On the other hand, the prior art proposes a vehicle cabin human body detection method, which is different from the traditional non-contact vital sign detection technology that installs the radar in front of the living body. This method installs the radar on the car seat, measures the displacement of the human chest from the back, the loss factor of each part to the signal, and the loss factor of the type of clothes to the signal, to detect vital sign information. However, the above detection method cannot quickly lock the living body in the scene, and the effect is general. Secondly, the effect of eliminating false targets and other interference is not satisfactory, and the false alarm is high. For weak moving targets, such as slight breathing and weak reflection intensity targets, the detection effect of the above method is general, and the missed detection is more.

[0038] Based on this, the embodiment of the present application provides a target object detection method, which uses the difference of radar signal reflection intensity at the presence and absence of target to judge whether the target object exists or not, can quickly realize the detection of the target object, and improve the real-time and accuracy of the detection. As shown in the figure, the method comprises: Figure 1

[0039] S110, obtain the echo signal of the MIMO millimeter wave radar, the echo signal is distributed in three dimensions of distance, speed and channel.

[0040] Wherein, the MIMO millimeter wave radar can be considered as a millimeter wave radar device installed on a vehicle, this device works in a multiple-input multiple-output (Multiple-Input Multiple-Output, MIMO) way, the type and installation position of the specific millimeter wave radar device are not limited, and can be set according to actual needs.

[0041] ​In this embodiment, the MIMO millimeter wave radar can transmit millimeter wave radar signals in a MIMO manner and receive multi-channel returned signals, so this embodiment can collect the returned signals to obtain the echo signals of the MIMO millimeter wave radar, which are distributed in three dimensions of distance, speed and channel. The specific way of obtaining the echo signals is not limited. For example, the MIMO millimeter wave radar can transmit linear frequency modulation continuous wave (LFMCW) signals in a MIMO manner, and then the multi-channel returned signals can be obtained after mixing to obtain intermediate frequency signals. The acquisition board can collect the intermediate frequency signals according to the Nyquist sampling theorem to obtain ADC raw data, i.e., echo signals. It can be considered that the ADC raw data can contain information of the target object, and the relevant information of the target object can be obtained by processing the ADC data.

[0042] S120, signal processing is performed on the echo signal to obtain a processing result corresponding to two dimensions of distance and speed.

[0043] Specifically, the obtained echo signal can be processed to obtain a processing result corresponding to two dimensions of distance and speed. The specific signal processing process is not described here. For example, the echo signal can be preprocessed in the dimensions of distance, speed and / or channel, and then the preprocessed signal can be processed in the channel dimension to obtain the corresponding processing result. The specific processing method can be set according to the actual situation, and different processing methods can correspond to different processing results.

[0044] S130, determining a target signal-to-noise ratio of the echo signal in a preset distance range based on the processing result, and detecting whether there is a target object in the preset distance range of the vehicle according to the target signal-to-noise ratio.

[0045] The preset distance range can be considered as a pre-set distance range, and a target object can exist in the preset distance range. For example, the preset distance range can be understood as the distance of the target object from the millimeter wave radar, and the specific value can be determined by the configuration personnel according to the experience value. The target signal-to-noise ratio can refer to the signal-to-noise ratio of the echo signal in the preset distance range.

[0046] Specifically, after obtaining the processing result through the above steps, the target signal-to-noise ratio of the echo signal in the preset distance range of the vehicle can be determined based on the obtained processing result, and whether there is a target object in the preset distance range of the vehicle can be detected according to the determined target signal-to-noise ratio. The determination of the target signal-to-noise ratio is not limited, for example, the target signal-to-noise ratio can be obtained directly based on the processing result, or the processing result can be calculated to determine the target signal-to-noise ratio. Here, the calculation method is not further expanded, as long as the target signal-to-noise ratio can be obtained.

[0047] Further, after obtaining the target signal-to-noise ratio, whether there is a target object in the preset distance range of the vehicle can be detected according to the determined target signal-to-noise ratio, for example, whether there is a target object in the preset distance range of the vehicle can be determined according to the specific size of the target signal-to-noise ratio, so as to realize the detection of the target object.

[0048] In one embodiment, the detection of whether there is a target object in the preset distance range of the vehicle according to the target signal-to-noise ratio comprises:

[0049] Detecting whether the target signal-to-noise ratio is greater than a preset signal-to-noise ratio to obtain a detection result.

[0050] Determining whether there is a target object in the preset distance range of the vehicle based on the detection result.

[0051] The preset signal-to-noise ratio can be a preset signal-to-noise ratio used to determine the detection result. The value of the preset signal-to-noise ratio can be an empirical value. Optionally, the preset signal-to-noise ratio can be 1.

[0052] In one embodiment, the obtained target signal-to-noise ratio can be detected whether it is greater than a preset signal-to-noise ratio to obtain a detection result, and then whether there is a target object in the preset distance range of the vehicle can be determined based on the obtained detection result. For example, when the calculated target signal-to-noise ratio is 0.8, it can be compared with the preset signal-to-noise ratio 1 to detect whether the target signal-to-noise ratio is greater than the preset signal-to-noise ratio. At this time, the detection result is that the target signal-to-noise ratio is less than the preset signal-to-noise ratio, so it can be considered that there is no target object in the preset distance range of the vehicle according to the detection result.

[0053] The embodiment one of the present application provides a target object detection method, obtains a MIMO millimeter wave radar echo signal, the echo signal is distributed in distance, speed and channel three dimensions; the echo signal is subjected to signal processing, and a processing result is obtained, the processing result corresponds to two dimensions of distance and speed; target signal-to-noise ratio of the echo signal in a preset distance range is determined based on the processing result, and whether a target object exists in the preset distance range of the vehicle is detected according to the target signal-to-noise ratio. By using the method, the processing result is obtained by signal processing on the echo signal, the target signal-to-noise ratio of the echo signal in the preset distance range is determined based on the processing result, and whether a target object exists in the preset distance range of the vehicle is detected according to the target signal-to-noise ratio, so that the detection of the target object can be realized quickly on the basis of simplifying the detection method, and the real-time performance of detection is improved.

[0054] In one embodiment, the target signal-to-noise ratio of the echo signal in the preset distance range is determined based on the processing result, comprising:

[0055] The first signal strength of the echo signal in the complete distance range is determined based on the processing result;

[0056] The second signal strength of the echo signal in the preset distance range is determined based on the processing result;

[0057] The target signal-to-noise ratio of the echo signal in the preset distance range is calculated according to the first signal strength and the second signal strength.

[0058] The complete distance range can be considered as the range of the echo signal in the distance dimension, and the complete distance range contains all amplitude values of the echo signal in the distance dimension. The preset distance range can be a part of the complete distance range, for example, the preset distance range can be understood as the part of the complete distance range that is concerned in the embodiment. The first signal strength can refer to the signal amplitude corresponding to the complete distance range at each speed dimension, and the second signal strength can refer to the signal amplitude corresponding to the preset distance range at each speed dimension.

[0059] Specifically, the embodiment can determine the first signal strength of the echo signal in the complete distance range based on the processing result, and determine the second signal strength of the echo signal in the preset distance range based on the processing result, and then calculate the target signal-to-noise ratio of the echo signal in the preset distance range according to the obtained first signal strength and second signal strength. For example, the first signal strength and the second signal strength of the echo signal at each speed dimension can be obtained based on the processing result, and then the target signal-to-noise ratio of the echo signal in the preset distance range is determined according to the obtained first signal strength and second signal strength.

[0060] In one embodiment, determining the first signal strength of the echo signal over the entire distance range based on the processing result includes:

[0061] The processing result is processed in the distance dimension within the complete distance range to obtain the first signal strength of the echo signal within the complete distance range.

[0062] In one implementation, the processing result can be processed along the distance dimension over the entire distance range to obtain the first signal strength of the echo signal over the entire distance range, such as obtaining the first signal strength of the echo signal in each velocity dimension. For example, the first signal strength in the velocity dimension can be expressed as... Where X(k,v) represents the processing result corresponding to the two dimensions of distance and velocity, and R N This represents the number of sampling points for a single chirp in the distance dimension.

[0063] In one embodiment, determining the second signal strength of the echo signal within a preset distance range based on the processing result includes:

[0064] The processing result is processed in the distance dimension within a preset distance range to obtain the second signal strength of the echo signal within the preset distance range.

[0065] In one implementation, the processing result can be processed along the distance dimension within a preset distance range to obtain a second signal intensity of the echo signal within the preset distance range, such as obtaining the second signal intensity of the echo signal in each velocity dimension. For example, the second signal intensity in the velocity dimension can be expressed as... Where X(k,v) represents the processing result corresponding to the two dimensions of distance and velocity, and r2 and r1 represent the maximum and minimum values ​​of the distance unit corresponding to the preset distance range, respectively.

[0066] Example 2

[0067] Figure 2 This is a flowchart of a target object detection method according to Embodiment 2 of the present invention, which is an optimization based on the above embodiments. In this embodiment, the signal processing of the echo signal to obtain the processing result is further specified as follows: the echo signal is preprocessed to obtain a preprocessed echo signal; the preprocessed echo signal is coherently accumulated in the channel dimension to obtain the processing result.

[0068] For details not covered in this embodiment, please refer to Embodiment 1.

[0069] like Figure 2 As shown, the method includes:

[0070] S210, obtain echo signals of the MIMO millimeter wave radar, the echo signals being distributed in three dimensions of distance, velocity and channel.

[0071] S220, pre-process the echo signals to obtain pre-processed echo signals.

[0072] In the embodiment, before the processing result is calculated, the echo signals can be pre-processed to better calculate the subsequent processing result. For example, the echo signals can be pre-processed in one or more of the dimensions of distance, velocity and channel to obtain pre-processed echo signals. Further, the specific pre-processing method can be different according to the dimensions.

[0073] In one embodiment, the pre-processing of the echo signals to obtain the pre-processed echo signals comprises:

[0074] performing Fourier transform on the echo signals in the distance dimension to obtain transformed echo signals;

[0075] performing clutter processing on the transformed echo signals to obtain the pre-processed echo signals.

[0076] Specifically, the echo signals can be Fourier transformed in the distance dimension to obtain transformed echo signals. The frequency spectrum is positively correlated with the distance, and the frequency can be converted into the target distance according to the relationship, so as to obtain the distribution of the signals in the distance image. Then, the transformed echo signals can be processed to obtain the pre-processed echo signals. For example, the clutter corresponding to the fixed target in the scene can be removed by clutter processing. The clutter processing method is not limited. For example, the clutter processing can be performed by mean cancellation operation in the velocity dimension.

[0077] S230, perform coherent accumulation processing on the pre-processed echo signals in the channel dimension to obtain a processing result.

[0078] After the pre-processed echo signals are obtained, coherent accumulation processing can be performed on the pre-processed echo signals in the channel dimension to obtain a processing result. For example, the data in the same distance unit and velocity unit can be accumulated in the channel to obtain the processing result corresponding to the distance and velocity dimensions.

[0079] S240, determine a target signal-to-noise ratio of the echo signals in a preset distance range based on the processing result, and detect whether there is a target object in the preset distance range of the vehicle according to the target signal-to-noise ratio.

[0080] The embodiment two of the present application provides a target object detection method, obtains a MIMO millimeter wave radar echo signal, the echo signal is distributed in distance, speed and channel three dimensions, pre-processes the echo signal to obtain a pre-processed echo signal, coherently accumulates the pre-processed echo signal in the channel dimension to obtain a processing result, determines a target signal-to-noise ratio of the echo signal in a preset distance range based on the processing result, and detects whether there is a target object in the preset distance range of the vehicle according to the target signal-to-noise ratio. By using the method, the pre-processed echo signal is obtained by pre-processing the echo signal, the pre-processed echo signal is coherently accumulated in the channel dimension, the processing result is obtained, the accuracy of the processing result can be improved, and the real-time performance of detection can be improved.

[0081] In one embodiment, before the echo signal is Fourier transformed in the distance dimension to obtain a transformed echo signal, the method further comprises:

[0082] The echo signal is windowed in the distance dimension to obtain a windowed echo signal.

[0083] The echo signal is Fourier transformed in the distance dimension to obtain a transformed echo signal, comprising:

[0084] The windowed echo signal is Fourier transformed in the distance dimension to obtain a transformed echo signal.

[0085] It can be considered that before the echo signal is Fourier transformed in the distance dimension, the echo signal can be windowed in the distance dimension to obtain a windowed echo signal, and then the windowed echo signal is Fourier transformed in the distance dimension to obtain a transformed echo signal. On this basis, the sidelobe of the amplitude-frequency curve in the subsequent Fourier transform can be suppressed. The method of windowing is not limited, for example, the echo signal can be multiplied by a window function sequence along the distance dimension to realize windowing of the echo signal, wherein the window function sequence includes but is not limited to a rectangular window, a hamming window and the like.

[0086] In one embodiment, the pre-processed echo signal is obtained by processing the transformed echo signal, comprising:

[0087] The mean value of the transformed echo signal in the speed dimension is calculated.

[0088] The pre-processed echo signal is determined based on the transformed echo signal and the mean value.

[0089] In an embodiment, the process of clutter processing on the transformed echo signal can be, for example, that the mean value of the transformed echo signal in the velocity dimension is calculated first, such as the mean value of each velocity unit under the same distance unit and the same channel, and then the pre-processed echo signal is determined based on the transformed echo signal and the mean value. For example, the pre-processed echo signal can be obtained by subtracting the mean value from the transformed echo signal, or the pre-processed echo signal can be obtained by calculating the average value of the transformed echo signal and the mean value again.

[0090] Figure 3 is a flow chart of another method for detecting a target object according to Embodiment Two of the present application, as shown in Figure 3 the ADC data of multiple channels is obtained first (i.e., the echo signal of the MIMO millimeter wave radar is obtained, and the echo signal is distributed in three dimensions of distance, velocity and channel), the fast Fourier transform is performed in the distance dimension (the Fourier transform is performed on the echo signal in the distance dimension to obtain a transformed echo signal), and the mean value of the multiple channel data after FFT is cancelled to eliminate the clutter introduced by the stationary target in the scene (i.e., the transformed echo signal is processed to obtain a pre-processed echo signal), then coherent accumulation is performed, and the accumulated data is distributed in the distance dimension and the Doppler dimension (i.e., the pre-processed echo signal is processed by coherent accumulation in the channel dimension to obtain a processing result); the signal intensity S in the interested distance range [a, b] is taken out (i.e., the processing result is processed in the distance dimension in the preset distance range to obtain the second signal intensity of the echo signal in the preset distance range), and the mean value N of the signal intensity in the entire ranging range of the radar can be obtained, and the ratio SNR of the signal in the interested distance range to the mean value of the signal intensity in the entire detection range can be obtained in each Doppler unit, the mean value of SNR in the interested distance range is calculated (i.e., the processing result is processed in the distance dimension in the preset distance range to obtain the second signal intensity of the echo signal in the preset distance range); finally, whether there is a living moving target in the interested distance range [a, b] is determined by comparing SNR with a set threshold (i.e., whether the signal-to-noise ratio of the target is greater than a preset signal-to-noise ratio is detected to obtain a detection result; whether there is a target object in the preset distance range of the vehicle is determined based on the detection result). The specific processing scheme can be as follows:

[0091] Step One: Distance Dimension FFT. The ADC data can be considered as a data matrix distributed in three dimensions of distance, velocity and channel, and the ADC data of the i-th frame can be represented as X1 i (R N ,V N ,C N ), wherein R NV represents the number of sampling points in a single chirp in the distance dimension. N C represents the number of chirps in a single frame of data. N This represents the number of virtual channels. The raw ADC data contains target distance information. By performing an FFT on the raw ADC data in the range dimension, the resulting spectrum is positively correlated with the distance. Based on this relationship, the frequency can be converted into target distance, thus obtaining the target's distribution in the range image. The data after the first FFT is denoted as X2. i (R r V N C N ), where R r ≥R N .

[0092] Furthermore, X2 i The elements in the FFT are usually complex numbers with real and imaginary parts. In order to reduce the sidelobes of the amplitude-frequency curve in the FFT, the ADC data can be windowed in the distance dimension before the distance dimension FFT (i.e., the echo signal is windowed in the distance dimension to obtain the windowed echo signal).

[0093] Figure 4 This is a schematic diagram of a transformed echo signal provided according to Embodiment 2 of the present invention, as shown below. Figure 4 As shown, the 1DFFT spectrum of the scene contains a living target. It can be seen that the strong reflectors in the scene are mainly distributed between 0.5 and 2m.

[0094] Figure 5 This is a schematic diagram of another transformed echo signal provided according to Embodiment 2 of the present invention, as shown below. Figure 5 The image shown is a 1DFFT spectrum of a live target in the scene.

[0095] Step 2: Static Clutter Removal. The 1DFFT data obtained in Step 1 is multiplied by 2. i (R r V N C N Afterwards, mean cancellation can be used to remove fixed target clutter from the scene. Specifically, this could involve multiplying the 1DFFT data of the i-th frame by 2. i (R r V N C N ) Calculate the mean value for each distance unit in the velocity dimension, such as the nth (1≤k≤C) N ) channel k (1≤k≤R) r The mean value of the distance cells in the velocity dimension is m i (k,n) can be calculated as follows:

[0096]

[0097] The result of mean cancellation is X3 i (R r ,V N ,C N ), the cancellation result corresponding to the kth distance unit, the qth chirp and the nth channel can be expressed as follows:

[0098] X3 i (k,q,n)=X2 i (k,q,n)-m i (k,n)。

[0099] In order to eliminate the stationary clutter in the scene, the transformed echo signal can be subjected to mean cancellation operation, and the following Figure 6 and Figure 7 It can be seen that the mean cancellation operation can achieve the effect of removing the stationary clutter in the scene.

[0100] Figure 6 is a schematic diagram of a preprocessed echo signal according to the second embodiment of the present application, as Figure 6 indicated, is a signal after clutter processing on the preprocessed echo signal generated in Figure 4 . Figure 7 is another schematic diagram of a preprocessed echo signal according to the second embodiment of the present application, as Figure 7 indicated, is a signal after clutter processing on the preprocessed echo signal generated in Figure 5 .

[0101] Step three: coherent accumulation. After obtaining the mean cancellation data matrix X3 i (R r ,V N ,C N ) in step two, the data can be accumulated in the virtual channel dimension, that is, the data in the same distance unit and velocity unit is accumulated in C N channel, and the coherent accumulation data is recorded as X4 i (R r ,V N ). The specific operation is as follows:

[0102]

[0103] Wherein, k represents the kth distance unit, q represents the qth velocity unit, and X4 i (k,q) represents the coherent accumulation result of the kth distance unit and the qth velocity unit.

[0104] Step four: calculate signal and noise.

[0105] In step three, the coherent accumulation result X4 is obtained i (R r ,V N ), assuming that the distance range of interest is R1 to R2, the distance resolution unit of the radar is ΔR, and the distance unit indexes corresponding to the distance of interest are r1 to r2, the calculation of r1 and r2 is as follows:

[0106]

[0107] The integer part of the above calculation result is taken to obtain the distance unit range [r1, r2] of interest, and the mean X5 of the signal amplitudes of all distance units under each velocity dimension is calculated i (1,V N ), and the mean X6 of the signal amplitudes of the distance unit range [r1, r2] of interest under each velocity dimension is calculated i (1,V N ), and the calculation method can be as follows:

[0108]

[0109]

[0110] In the above formula, abs(…) represents taking the absolute value of the number in the parentheses, and if the number in the parentheses is a complex number, it represents the corresponding amplitude value.

[0111] Step five: calculating the signal-to-noise ratio and making a decision. The signal-to-noise ratio X7 in the distance range is calculated according to the results obtained above i , which can be:

[0112] After X7 i is obtained, the following decision can be made:

[0113] If X7 i >1, it indicates that there is a living body moving target in the distance [R1, R2] range at the i-th moment; if X7 i ≤1, it indicates that there is no living body moving target in the distance [R1, R2] range at the i-th moment.

[0114] For example, in order to detect whether there is a target object in the distance range [0.8, 1.1] (unit: m) of interest, the signal strength mean of the [0.8, 1.1] region is calculated, and the signal strength mean of the entire detection region is calculated, and the ratio is calculated to obtain the signal-to-noise ratio Figure 8 and Figure 9 .

[0115] Figure 8 is a schematic diagram of a target signal-to-noise ratio according to Embodiment Two of the present application, asFigure 8 As shown in the figure, the signal-to-noise ratio of each frame of the radar in the scene where the target object exists can be seen, and the signal-to-noise ratio in the figure is greater than 1.

[0116] Figure 9 Another schematic diagram of a target signal-to-noise ratio is provided according to Embodiment Two of the present application, as shown in the figure. Figure 9 As shown in the figure, the signal-to-noise ratio of each frame of the radar in the scene where the target object exists can be seen, and the signal-to-noise ratio in the figure is greater than 1.

[0117] Therefore, it can be determined whether the target object exists at the specified distance in the scene.

[0118] It can be found that the current millimeter wave radar-based living body detection algorithm generally has the problems of large calculation amount and poor real-time performance, needs to consume more hardware resources, and is difficult to quickly detect the real living body in the scene. At the same time, there are a large number of methods for detecting life characteristic signals in fixed scenes, which cannot effectively eliminate false targets introduced by complex vehicle cabin environment and life motion diversity, and generally have the problems of high false alarm rate and high miss rate.

[0119] In addition, the vehicle cabin living body detection method based on vision easily invades the privacy of passengers in the vehicle, and cannot detect targets in the blind area of the camera.

[0120] The detection method provided by the embodiments of the present application can use fewer signal processing steps to determine whether a living body motion target exists from a single frame of data, quickly and highly real-time detect motion living bodies in a scene, save computing power and storage resources, and reduce hardware costs. In addition, the embodiments of the present application have the obvious advantage of not invading privacy.

[0121] Embodiment Three

[0122] Figure 10 A structure schematic diagram of a target object detection device is provided according to Embodiment Three of the present application, as shown in the figure. Figure 10 As shown in the figure, the device comprises:

[0123] The acquisition module 310 is configured to acquire the echo signal of the MIMO millimeter wave radar, and the echo signal is distributed in three dimensions of distance, speed and channel.

[0124] The signal processing module 320 is configured to perform signal processing on the echo signal to obtain a processing result, and the processing result corresponds to two dimensions of distance and speed.

[0125] The determination module 330 is configured to determine a target signal-to-noise ratio of the echo signal in a preset distance range based on the processing result, and detect whether a target object exists in the preset distance range of the vehicle according to the target signal-to-noise ratio.

[0126] The embodiment three of the present application provides a target object detection device. A MIMO millimeter wave radar echo signal is obtained by an acquisition module. The echo signal is distributed in three dimensions of distance, speed and channel. A signal processing module is used for signal processing of the echo signal to obtain a processing result. The processing result corresponds to two dimensions of distance and speed. A determination module is used for determining a target signal-to-noise ratio of the echo signal in a preset distance range based on the processing result, and detecting whether there is a target object in the preset distance range of the vehicle according to the target signal-to-noise ratio. By using the device, the processing result is obtained by signal processing of the echo signal, the target signal-to-noise ratio of the echo signal in the preset distance range is determined based on the processing result, and whether there is a target object in the preset distance range of the vehicle is detected according to the target signal-to-noise ratio. The detection of the target object can be quickly realized on the basis of simplifying the detection method, and the real-time performance of the detection is improved.

[0127] Optionally, the signal processing module 320 comprises:

[0128] a preprocessing unit, configured to perform preprocessing on the echo signal to obtain a preprocessed echo signal;

[0129] a processing unit, configured to perform coherent accumulation processing on the preprocessed echo signal in the channel dimension to obtain a processing result.

[0130] Optionally, the preprocessing unit comprises:

[0131] a transformation subunit, configured to perform Fourier transform on the echo signal in the distance dimension to obtain a transformed echo signal;

[0132] a clutter processing subunit, configured to perform clutter processing on the transformed echo signal to obtain the preprocessed echo signal.

[0133] Optionally, the preprocessing unit further comprises:

[0134] a windowing processing subunit, configured to perform windowing processing on the echo signal in the distance dimension before the Fourier transform on the echo signal in the distance dimension to obtain the transformed echo signal, to obtain a windowed echo signal;

[0135] The transformation subunit is specifically configured to:

[0136] perform Fourier transform on the windowed echo signal in the distance dimension to obtain the transformed echo signal.

[0137] Optionally, the clutter processing subunit is specifically configured to:

[0138] calculate a mean value of the transformed echo signal in the speed dimension.

[0139] determine a pre-processed echo signal based on the transformed echo signal and the mean value.

[0140] Optionally, the determining module 330 includes:

[0141] a first determining unit, configured to determine a first signal intensity of the echo signal in a full distance range based on the processing result;

[0142] a second determining unit, configured to determine a second signal intensity of the echo signal in a preset distance range based on the processing result;

[0143] a calculating unit, configured to calculate a target signal-to-noise ratio of the echo signal in the preset distance range according to the first signal intensity and the second signal intensity.

[0144] Optionally, the first determining unit is specifically configured to:

[0145] perform processing on the processing result in the distance dimension in the full distance range to obtain the first signal intensity of the echo signal in the full distance range.

[0146] Optionally, the second determining unit is specifically configured to:

[0147] perform processing on the processing result in the distance dimension in the preset distance range to obtain the second signal intensity of the echo signal in the preset distance range.

[0148] Optionally, the determining module 330 is specifically configured to:

[0149] detect whether the target signal-to-noise ratio is greater than a preset signal-to-noise ratio to obtain a detection result;

[0150] determine whether there is a target object in the preset distance range of the vehicle based on the detection result.

[0151] The target object detection device provided in the embodiments of the present application can execute the target object detection method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0152] Embodiment Four

[0153] Figure 11is a structural diagram of a vehicle provided according to Embodiment Four of the present application. The vehicle is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The vehicle can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0154] As shown in Figure 11 Vehicle 10 includes at least one processor 11, and memory, such as read-only memory (ROM) 12, random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor 11, which can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the vehicle 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0155] Various components in the vehicle 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 magnetic 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 vehicle 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunications networks.

[0156] The processor 11 can be various general and / or special-purpose 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-purpose 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 performs various methods and processes described above, such as the detection method of the target object.

[0157] In some embodiments, the method of detecting a target object can be implemented as a computer program tangibly embodied in a computer readable storage medium, e.g., storage unit 18. In some embodiments, portions or all of the computer program can be loaded and / or installed onto vehicle 10 via ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the method of detecting a target object described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the method of detecting a target object by other means, e.g., with the aid of firmware.

[0158] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0159] Computer programs used to implement the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the computer program, when executed by the processor of the machine, implements the functions / acts specified in the flowcharts and / or block diagrams. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0160] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide for interaction with a user, the systems and techniques described here can be implemented on a vehicle 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 a trackball) by which the user can provide input to the vehicle. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0162] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can 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.

[0163] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can 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 large management difficulty and weak business scalability in traditional physical host and VPS service.

[0164] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, each step described in the present application can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0165] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of detecting a target object, characterized by, The method is applied to a vehicle on which a MIMO millimeter wave radar is installed, and the method comprises: acquiring echo signals of the MIMO millimeter wave radar, the echo signals being distributed in three dimensions of distance, speed and channel; performing signal processing on the echo signals to obtain a processing result, the processing result corresponding to two dimensions of distance and speed; determining a target signal-to-noise ratio of the echo signals in a preset distance range based on the processing result, and detecting whether a target object exists in the preset distance range of the vehicle according to the target signal-to-noise ratio; the processing result is obtained by performing signal processing on the echo signals, comprising: preprocessing the echo signals to obtain preprocessed echo signals; performing coherent accumulation processing on the preprocessed echo signals in the channel dimension to obtain the processing result; the preprocessed echo signals are obtained by preprocessing the echo signals, comprising: performing Fourier transform on the echo signals in the distance dimension to obtain transformed echo signals; performing clutter processing on the transformed echo signals to obtain preprocessed echo signals; the preprocessed echo signals are obtained by performing clutter processing on the transformed echo signals, comprising: calculating the mean value of the transformed echo signals in the speed dimension; determining the preprocessed echo signals based on the transformed echo signals and the mean value.

2. The method of claim 1, wherein, Before the Fourier transform is performed on the echo signals in the distance dimension to obtain the transformed echo signals, it further comprises: performing windowing processing on the echo signals in the distance dimension to obtain windowed echo signals; the Fourier transform is performed on the windowed echo signals in the distance dimension to obtain the transformed echo signals. the target signal-to-noise ratio of the echo signals in the preset distance range is determined based on the processing result, comprising:

3. The method of claim 1, wherein, determining a first signal strength of the echo signals in a complete distance range based on the processing result; determining a second signal strength of the echo signals in the preset distance range based on the processing result; calculating the target signal-to-noise ratio of the echo signals in the preset distance range according to the first signal strength and the second signal strength. the first signal strength of the echo signals in the complete distance range is determined based on the processing result, comprising:

4. The method of claim 3, wherein, processing the processing result in the distance dimension in the complete distance range to obtain the first signal strength of the echo signals in the complete distance range. the second signal strength of the echo signals in the preset distance range is determined based on the processing result, comprising:

5. The method of claim 3, wherein, processing the processing result in the distance dimension in the preset distance range to obtain the second signal strength of the echo signals in the preset distance range. whether a target object exists in the preset distance range of the vehicle is detected according to the target signal-to-noise ratio, comprising:

6. The method of claim 1, wherein, detecting whether the target signal-to-noise ratio is greater than a preset signal-to-noise ratio to obtain a detection result; determining whether a target object exists in the preset distance range of the vehicle based on the detection result. ​ 7. A device for detecting a target object, characterized by comprising: The device is configured in a vehicle, comprising: An acquisition module configured to acquire echo signals of a MIMO millimeter wave radar, the echo signals being distributed in three dimensions of distance, speed and channel; A signal processing module configured to perform signal processing on the echo signals to obtain a processing result, the processing result corresponding to two dimensions of distance and speed; A determination module configured to determine a target signal-to-noise ratio of the echo signals in a preset distance range based on the processing result, and detect whether a target object exists in the preset distance range of the vehicle according to the target signal-to-noise ratio; The signal processing module comprises: A preprocessing unit configured to perform preprocessing on the echo signals to obtain preprocessed echo signals; A processing unit configured to perform coherent accumulation processing on the preprocessed echo signals in the channel dimension to obtain a processing result; The preprocessing unit comprises: A transformation subunit configured to perform Fourier transform on the echo signals in the distance dimension to obtain transformed echo signals; A clutter processing subunit configured to perform clutter processing on the transformed echo signals to obtain preprocessed echo signals; The clutter processing subunit is specifically configured to: Calculate the mean value of the transformed echo signals in the speed dimension; Determine preprocessed echo signals based on the transformed echo signals and the mean value.

8. A vehicle characterized by comprising: The vehicle comprises: At least one processor; and A memory connected in communication with the at least one processor; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the target object detection method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for enabling the processor to execute the target object detection method of any one of claims 1-6 when executed.

Images