Target object detection method and device, and computer device

Abstract

The application relates to a target object detection method and device and a computer device. The method comprises the following steps: controlling an ultrasonic wave module to send ultrasonic waves, the ultrasonic wave module being used for sending ultrasonic waves to the activity space of a target object; receiving ultrasonic echoes, the ultrasonic echoes being echoes reflected by objects in the activity space; determining the correlation coefficient of the ultrasonic echoes of a to-be-detected frame according to the ultrasonic echoes of the to-be-detected frame and the ultrasonic echoes of a previous frame of the to-be-detected frame; and determining whether the target object is in the activity space within the time corresponding to the ultrasonic echoes of the to-be-detected frame according to the comparison result of the correlation coefficient of the ultrasonic echoes of the to-be-detected frame and the corresponding reference threshold value, wherein the reference threshold value refers to a numerical judgment condition for judging whether the target object exists. The method can improve the detection accuracy of the target object, thereby avoiding misjudgment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of detection, in particular to a target object detection method and device and computer equipment. BACKGROUND

[0002] With the development of ultrasonic technology, more and more ultrasonic technology is applied to distance measurement and object state recognition. The time of ultrasonic wave reflected by obstacles after being emitted is measured, and the actual distance from the emission point to the obstacles is calculated according to the time difference between emission and reception, so as to complete the measurement according to the change of distance.

[0003] However, when the above technology is applied to target object detection in a closed space, the detection accuracy is limited, which is easy to cause misjudgment. SUMMARY

[0004] Therefore, it is necessary to provide a target object detection method, device and computer equipment capable of improving detection accuracy.

[0005] In a first aspect, a target object detection method is provided, which comprises:

[0006] controlling an ultrasonic module to send ultrasonic waves, the ultrasonic module being configured to send ultrasonic waves to the activity space of the target object;

[0007] receiving ultrasonic echoes, the ultrasonic echoes being echoes reflected by objects in the activity space;

[0008] determining a correlation coefficient of the ultrasonic echoes of the to-be-detected frame according to the ultrasonic echoes of the to-be-detected frame and the ultrasonic echoes of the last frame of the to-be-detected frame;

[0009] determining whether the target object is in the activity space within the time corresponding to the ultrasonic echoes of the to-be-detected frame according to the comparison result of the correlation coefficient of the ultrasonic echoes of the to-be-detected frame and the reference threshold value;

[0010] The reference threshold value refers to a numerical judgment condition for judging whether the target object exists.

[0011] In one embodiment, the correlation coefficient of the ultrasonic echoes of the to-be-detected frame is determined according to the ultrasonic echoes of the to-be-detected frame and the ultrasonic echoes of the last frame of the to-be-detected frame, which comprises:

[0012] The correlation coefficient of the ultrasonic echoes of the to-be-detected frame is determined according to the voltage value and the voltage average value of the ultrasonic echoes of the to-be-detected frame, the voltage value and the voltage average value of the ultrasonic echoes of the last frame of the to-be-detected frame, and the following correlation coefficient calculation formula:

[0013]

[0014] wherein, r represents a correlation coefficient, n represents a length of a frame of ultrasonic echo, x i represents a voltage value of an i-th sample point of a frame of ultrasonic echo to be measured, represents a voltage average value of a frame of ultrasonic echo to be measured; y i represents a voltage value of an i-th sample point of a frame of ultrasonic echo to be measured, represents a voltage average value of a frame of ultrasonic echo to be measured.

[0015] In one of the embodiments, the target object detection method further comprises:

[0016] According to the correlation coefficient of the frame of ultrasonic echo to be measured, a reference threshold corresponding to the correlation coefficient of each frame of ultrasonic echo is determined.

[0017] In one of the embodiments, according to the correlation coefficient of the frame of ultrasonic echo to be measured, a reference threshold corresponding to the correlation coefficient of each frame of ultrasonic echo is determined, comprising:

[0018] At least three correlation coefficients in a preset time window are obtained;

[0019] A middle element of the correlation coefficients is determined; the middle element is a correlation coefficient at a middle position;

[0020] An average value of the correlation coefficients on both sides of the middle element is calculated respectively to obtain a first average value and a second average value;

[0021] According to any one of the first average value and the second average value and a compensation value, a reference threshold of the middle element is determined; the compensation value is used to correct the reference threshold;

[0022] According to the reference threshold of the middle element, a reference threshold corresponding to the correlation coefficient of each frame of ultrasonic echo is determined.

[0023] In one of the embodiments, according to any one of the first average value and the second average value and a compensation value, a reference threshold of the middle element is determined, comprising:

[0024] The minimum average value of the first average value and the second average value is selected as a middle threshold;

[0025] The compensation value is added to the middle threshold to obtain the reference threshold.

[0026] In one of the embodiments, the preset time window is a time window with the middle element as the center and the same number of correlation coefficients on both sides of the middle element.

[0027] In one of the embodiments, according to the comparison result of the correlation coefficient of the frame of ultrasonic echo to be measured and the corresponding reference threshold, whether a target object exists in the active space in the time corresponding to the frame of ultrasonic echo to be measured is determined, comprising:

[0028] If the intermediate element is less than or equal to a reference threshold value of the intermediate element, it is determined that the target object is in the active space in the time window corresponding to the intermediate element.

[0029] In one of the embodiments, the method further comprises:

[0030] If the intermediate element is greater than the reference threshold value of the intermediate element, it is determined that the target object is not in the active space in the time window corresponding to the intermediate element.

[0031] In a second aspect, a target object detection device is provided, which comprises:

[0032] An ultrasonic wave sending control module is configured to control an ultrasonic wave module to send ultrasonic waves to the active space of the target object.

[0033] An ultrasonic wave receiving module is configured to receive ultrasonic echoes, which are echoes of the ultrasonic waves reflected by objects in the active space.

[0034] A correlation coefficient calculation module is configured to determine a correlation coefficient of the to-be-detected frame of ultrasonic echoes based on the to-be-detected frame of ultrasonic echoes and a previous frame of ultrasonic echoes of the to-be-detected frame.

[0035] A target object determination module is configured to determine whether the target object is in the active space in a time corresponding to the to-be-detected frame of ultrasonic echoes based on a comparison result of the correlation coefficient of the to-be-detected frame of ultrasonic echoes and a corresponding reference threshold value.

[0036] The reference threshold value refers to a numerical judgment condition for determining whether the target object exists.

[0037] In a third aspect, a computer device is provided, which comprises a memory and a processor. The memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 8 when executing the computer program.

[0038] The target object detection method, device, computer device, storage medium and computer program product have at least the following beneficial effects:

[0039] The ultrasonic module sends ultrasonic waves to the moving space of the target object, and receives ultrasonic echoes carrying information of the objects in the moving space. Then, according to the to-be-detected frame ultrasonic echo and the last frame ultrasonic echo of the to-be-detected frame, the correlation coefficient of the to-be-detected frame ultrasonic echo is determined, and the obtained correlation coefficient is compared with a corresponding reference threshold value, wherein the reference threshold value refers to a numerical judgment condition for judging whether the target object exists. Further, according to the comparison result, it is determined whether the target object exists in the moving space in the time corresponding to the to-be-detected frame ultrasonic echo. Since the correlation coefficient can better reflect the information carried in the ultrasonic echo, and the correlation coefficient determined based on the to-be-detected frame and the last frame of the ultrasonic echo is used to determine whether the target object exists in the current moving space, the detection accuracy of the target object can be improved, and false judgment can be avoided. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 An application environment diagram of the target object detection method in an embodiment;

[0041] Figure 2 A flowchart of the target object detection method in an embodiment;

[0042] Figure 3 A flowchart of the target object detection method in another embodiment;

[0043] Figure 4 A flowchart of the target object detection method in another embodiment;

[0044] Figure 5 A position diagram of the correlation coefficient on the time axis in an embodiment;

[0045] Figure 6 A flowchart of the target object detection method in another embodiment;

[0046] Figure 7 A flowchart of the target object detection method in another embodiment;

[0047] Figure 8 A correlation coefficient and a corresponding reference threshold value curve diagram in an embodiment when there is no one in the car;

[0048] Figure 9 A correlation coefficient and a corresponding reference threshold value curve diagram in an embodiment when there is someone in the car and the person is performing a slight action;

[0049] Figure 10 A correlation coefficient and a corresponding reference threshold value curve diagram in an embodiment when there is someone in the car and the person is breathing;

[0050] Figure 11A structural block diagram of the target object detection device in an embodiment;

[0051] Figure 12 An internal structural diagram of the computer device in an embodiment. DETAILED DESCRIPTION

[0052] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not to limit the present application.

[0053] The target object detection method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 The ultrasonic module 102 and the terminal 104 communicate. The terminal 104 can control the ultrasonic module 102 to send ultrasonic waves, and the ultrasonic module 102 is configured to send ultrasonic waves to the activity space of the target object. The terminal 104 receives ultrasonic echoes, which are echoes of the ultrasonic waves reflected by objects in the activity space. The terminal 104 determines the correlation coefficient of the to-be-detected frame ultrasonic echoes according to the to-be-detected frame ultrasonic echoes and the last frame ultrasonic echoes of the to-be-detected frame. The terminal 104 determines whether the target object is in the activity space within the time corresponding to the to-be-detected frame ultrasonic echoes according to the comparison result of the correlation coefficient of the to-be-detected frame ultrasonic echoes and the corresponding reference threshold. The reference threshold refers to a numerical judgment condition for judging whether the target object exists. The terminal 104 can be, but is not limited to, a vehicle-mounted controller of a vehicle.

[0054] In an embodiment, as shown in Figure 2 A target object detection method is provided. The method is described below by taking the terminal 104 in Figure 1 as an example, which includes the following steps:

[0055] S202, controlling the ultrasonic module to send ultrasonic waves, and the ultrasonic module is configured to send ultrasonic waves to the activity space of the target object.

[0056] The target object can refer to a living body, and more specifically, can refer to a person. The activity space can be defined according to the actual scene. For example, when the target object refers to a person and is in the interior of a vehicle, the activity space at this time refers to the interior of the vehicle. For example, when in an elevator car, the activity space at this time refers to the interior of the car. It should be noted that the target object and the activity space thereof can be defined according to different actual application scenarios, which are not limited herein. The activity space of the target object may not necessarily contain the target object at a certain moment, and should be understood as a space for the target object to move.

[0057] S204, receiving ultrasonic echoes, which are echoes of the ultrasonic waves reflected by objects in the activity space.

[0058] Wherein, due to the physical properties of the ultrasonic wave, the ultrasonic wave will produce reflection after being sent to the object, and the physical properties of the ultrasonic wave (such as frequency, period, etc.) will change, thereby forming an ultrasonic echo carrying the object information, that is, the ultrasonic echo can be understood as a reflection echo carrying the object information in the activity space. For example, when the object in the activity space is a person, the vital sign signals of the human body (such as breathing, pulse, micro-motion action, etc.) will change the physical properties of the ultrasonic wave after the ultrasonic wave is sent to the human body, that is, at this time, the ultrasonic echo reflected by the human body and carrying the vital sign signals of the human body will be generated. It should be understood that the object in the activity space referred to herein can include other objects in addition to the target object. For example, when the activity space is a car cabin, when there is no one in the car, the reflected echo will also be generated after the emitted ultrasonic wave is reflected by the objects such as the car window glass and the car body. When a person is moving in the car cabin, part of the reflected echo is formed by the reflection of the human body, and the difference between the reflected echoes in the two cases can be used to determine whether there is a person moving in the car.

[0059] S206, determining the correlation coefficient of the ultrasonic echo of the to-be-measured frame according to the ultrasonic echo of the to-be-measured frame and the ultrasonic echo of the last frame of the to-be-measured frame.

[0060] Wherein, it can be understood that the ultrasonic echo and the electrical signal are both waveform signals, and each waveform signal is composed of continuous multiple frames. The time of each frame of ultrasonic echo is usually related to the distance of the object. For example, when the distance between the object and the ultrasonic wave emission position is 1.5 meters, according to the sound propagation speed, the time t of each frame at this time is 1.5 / (343*2) = 8.75 ms. The correlation coefficient is used to represent the correlation between frames, that is, it can reflect whether there is a mutation in the to-be-measured frame relative to the last frame; for example, in the received last frame of ultrasonic echo, the waveform reflects that there is no target object in the above-mentioned activity space, and in the to-be-measured frame of ultrasonic echo, the waveform produces mutation due to the target object in the activity space, and the role of the correlation coefficient is to reflect the waveform mutation in a short time, so as to more accurately reflect whether there is a target object in the activity space.

[0061] S208, determining whether there is a target object in the activity space in the time corresponding to the to-be-measured frame of ultrasonic echo according to the comparison result of the correlation coefficient of the to-be-measured frame of ultrasonic echo and the corresponding reference threshold. Wherein, the reference threshold refers to the numerical judgment condition for judging whether there is a target object.

[0062] The reference threshold can be a numerical judgment condition pre-stored in a data storage system for judging whether the target object exists, and is directly called when judging whether the target object exists in the active space. It should be noted that each correlation coefficient of the to-be-tested frame ultrasonic echo has a corresponding reference threshold. Of course, the reference threshold can also be a threshold that is dynamically updated during the monitoring process.

[0063] In the above target object detection method, the ultrasonic wave module is controlled to send ultrasonic waves to the active space of the target object, and receive ultrasonic echoes carrying object information of the active space, which are generated by reflection of the ultrasonic waves on the objects in the active space. Then, the correlation coefficient of the to-be-tested frame ultrasonic echo is determined according to the to-be-tested frame ultrasonic echo and the last frame ultrasonic echo, and the obtained correlation coefficient is compared with the corresponding reference threshold, wherein the reference threshold is a numerical judgment condition for judging whether the target object exists. Then, according to the comparison result, it is determined whether the target object exists in the active space in the time corresponding to the to-be-tested frame ultrasonic echo. Since the correlation coefficient can better reflect the information carried in the ultrasonic echo, and the correlation coefficient determined based on the last frame ultrasonic echo and the to-be-tested frame ultrasonic echo is used to determine whether the target object exists in the active space, the detection accuracy of the target object can be improved, and false judgment can be avoided.

[0064] In one embodiment, the correlation coefficient of the to-be-tested frame ultrasonic echo is determined according to the to-be-tested frame ultrasonic echo and the last frame ultrasonic echo of the to-be-tested frame, comprising:

[0065] The correlation coefficient of the to-be-tested frame ultrasonic echo is determined according to the voltage value and the voltage average value of the to-be-tested frame ultrasonic echo, the voltage value and the voltage average value of the last frame ultrasonic echo of the to-be-tested frame, and the following correlation coefficient calculation formula:

[0066]

[0067] wherein r represents the correlation coefficient of the to-be-tested frame ultrasonic echo, n represents the length of a frame of ultrasonic echo, x i represents the voltage value of the i-th sampling point of the to-be-tested frame ultrasonic echo, represents the voltage average value of the to-be-tested frame ultrasonic echo; y i represents the voltage value of the i-th sampling point of the last frame ultrasonic echo of the to-be-tested frame, represents the voltage average value of the last frame ultrasonic echo of the to-be-tested frame.

[0068] In the above embodiment, since each frame of ultrasonic echo has multiple sampling points, after sampling, the audio signal is converted into an electric signal, the voltage values of corresponding sampling points of adjacent two frames of ultrasonic echo are cumulatively compared and analyzed, the correlation coefficient of the to-be-detected frame of ultrasonic echo is determined based on the correlation coefficient calculation formula established above, so that the correlation coefficient obtained can better reflect the correlation degree between the to-be-detected frame and the previous frame of ultrasonic echo.

[0069] In one embodiment, as shown in Figure 3 , the method further comprises:

[0070] S302, determining a reference threshold corresponding to the correlation coefficient of each frame of ultrasonic echo according to the correlation coefficient of the to-be-detected frame of ultrasonic echo.

[0071] Specifically, since each correlation coefficient has a corresponding reference threshold, for each determined correlation coefficient, the corresponding reference threshold can be directly found from the data storage system, that is, the reference threshold can be directly determined from the mapping relationship between the two. Alternatively, according to the correlation coefficient of each frame obtained after processing the ultrasonic echo each time, the reference threshold corresponding to each frame is updated and adjusted to obtain a reference threshold suitable for the current correlation coefficient.

[0072] In the above embodiment, the corresponding reference threshold is determined based on the correlation coefficient, which can provide a more accurate judgment basis for the subsequent detection result of the target object.

[0073] In one embodiment, as shown in Figure 4 , the reference threshold corresponding to the correlation coefficient of each frame of ultrasonic echo is determined according to the correlation coefficient of the to-be-detected frame of ultrasonic echo, comprising:

[0074] S402, obtaining at least three correlation coefficients in a preset time window.

[0075] The preset time window can refer to a time interval in which the frame signals corresponding to the multiple correlation coefficients determined in the above embodiment are located. For example, as shown in Figure 5 , n1-n10 represents the correlation coefficient (each correlation coefficient corresponds to a frame of ultrasonic echo, which is not shown in the figure), at this time, the preset time window can refer to the time interval from the correlation coefficient n1 to the correlation coefficient n10. It should be noted that the selection of the preset time window can be selected according to the detection accuracy, which is not limited herein.

[0076] Specifically, the obtaining of the above at least three correlation coefficients can be random selection or continuous selection. For example, in one specific embodiment, three continuous correlation coefficients n5, n6, and n7 can be selected.

[0077] S404, determine the middle element of the correlation coefficients; the middle element is the correlation coefficient in the middle position.

[0078] Wherein, since the determination of each correlation coefficient is in accordance with the order of each frame of the ultrasound echo, the determination of the correlation coefficient also has a corresponding order, and the middle element refers to the correlation coefficient in the middle position in the at least three correlation coefficients obtained above, such as Figure 5 As shown, when the obtained correlation coefficients are n5, n6, and n7, the middle element is n6, and when the selected correlation coefficients are n3, n7, and n8, the middle element is n7. Further, when the number of selected correlation coefficients is even, the definition of the middle element can refer to any one of the two correlation coefficients in the middle position, for example, when the obtained correlation coefficients are n4, n5, n6, and n7, the middle element can be any one of n5 or n6.

[0079] S406, respectively calculate the average values of the correlation coefficients on both sides of the middle element to obtain a first average value and a second average value.

[0080] Specifically, in one specific embodiment, when the selected at least three correlation coefficients are n5, n6, and n7, the middle element is n6, the first average value is n5, and the second average value is n7. For example, when the selected at least three correlation coefficients are n1, n5, n6, n7, and n9, the middle element is n6, the first average value is (n1+n5) / 2, and the second average value is (n7+n9) / 2. For the selection of correlation coefficients of different numbers and different positions, the specific calculation of the corresponding first average value and second average value can refer to the above examples.

[0081] S408, determine the reference threshold of the middle element according to any one of the first average value and the second average value and a compensation value; the compensation value is used to correct the reference threshold.

[0082] Wherein, the selection of the compensation value can be set according to the actual application scenario, which is not limited here.

[0083] S410, determine the reference threshold corresponding to the correlation coefficient of each frame of ultrasound echo according to the reference threshold of the middle element.

[0084] Wherein, it should be noted that the correlation coefficient of each frame of ultrasound echo includes the middle element in a plurality of preset time windows, i.e. includes a plurality of correlation coefficients. Because each frame of ultrasound echo corresponds to a correlation coefficient, and each correlation coefficient has its corresponding reference threshold. In the case of determining the reference threshold of multiple middle elements, the reference threshold corresponding to the correlation coefficient of each frame of ultrasound echo is easily obtained.

[0085] In the above embodiment, by acquiring at least three correlation coefficients and determining the middle element in the three correlation coefficients, further determining the reference threshold of the middle element based on the average values on both sides of the middle element and the compensation value, thereby determining the reference threshold corresponding to the correlation coefficient of each frame of ultrasonic echo, ensuring the accuracy of the reference threshold.

[0086] In one embodiment, as shown in Figure 6 determining the reference threshold of the middle element according to any one of the first average value and the second average value and the compensation value comprises:

[0087] S602, selecting the minimum average value of the first average value and the second average value as the intermediate threshold.

[0088] In actual application scenarios, such as the detection of human bodies inside a car, when the physical characteristics of ultrasonic echoes change due to the micro-motion of human bodies or vital signs signals such as breathing, the correlation coefficient corresponding to each frame of ultrasonic echo tends to be smaller, so that the reference threshold determined by the correlation coefficient tends to be smaller, and the average value determined by the correlation coefficient tends to be smaller. Based on the above reasons, selecting the minimum average value as the intermediate threshold can better reflect the changes in ultrasonic echoes, and provide accurate data basis for accurate detection of target objects.

[0089] S604, adding the compensation value to the intermediate threshold to obtain the reference threshold.

[0090] In the above embodiment, by selecting the minimum average value as the intermediate threshold for determining whether there is a target object, the final reference threshold can better reflect the changes in ultrasonic echoes, and provide accurate data basis for accurate detection of target objects.

[0091] In one embodiment, the preset time window is a time window centered on the middle element and having the same number of correlation coefficients on both sides of the middle element.

[0092] Specifically, in one specific embodiment, as shown in Figure 5 when the selected number of correlation coefficients on both sides of the middle element is 2, the preset time window is the time window in which the correlation coefficients n4 to n8 are located. It should be noted that the selection of the preset time window is only for illustration and is not limited herein.

[0093] In the above embodiments, by limiting the preset time window, the number of correlation coefficients used to calculate the first average and the second average is equal, so that the calculated first average and the second average avoid excessive error due to the difference in the number of coefficients. This ensures that the reference threshold can better reflect the correlation between the intermediate element and the correlation coefficients on both sides, and provides accurate data for the detection accuracy of the target object.

[0094] In one embodiment, such as Figure 7 As shown, based on the comparison results of the correlation coefficient of the ultrasonic echo of the frame under test and the corresponding reference threshold, it is determined whether there is a target object in the active space within the time corresponding to the ultrasonic echo of the frame under test, including:

[0095] S702, if the intermediate element is less than or equal to the reference threshold of the intermediate element, then it is determined that there is a target object in the active space within the time window corresponding to the intermediate element.

[0096] S704, if the intermediate element is greater than the reference threshold of the intermediate element, it is determined that there is no target object in the active space within the time window corresponding to the intermediate element.

[0097] The relevant details regarding intermediate elements, time windows, and target objects can be found in the above embodiments and will not be repeated here. It is understood that by appropriately selecting multiple preset time windows, the correlation coefficient corresponding to each frame of ultrasonic echo can be determined as the intermediate element, thereby enabling continuous monitoring of the presence or absence of target objects within the activity space.

[0098] Specifically, in one particular implementation, for example, when detecting a person inside a car, the relevant data of the ultrasonic echoes calculated above, such as... Figure 8 As shown, this figure represents the correlation coefficient and reference threshold curves calculated based on ultrasonic echoes when no one is inside the car. The horizontal axis represents the number of correlation coefficients, and the vertical axis represents the numerical value; curve 802 is the correlation coefficient curve, and curve 804 is the reference threshold curve corresponding to each selected intermediate element in the correlation coefficient; if the intermediate element is greater than the reference threshold, it is determined that no human being is inside a living car within the time window corresponding to the intermediate element; For example... Figures 9-10 As shown, Figure 9 This graph shows the correlation coefficient and reference threshold curves calculated from ultrasound echoes when there are people inside the car and the people are making slight movements. Curve 902 is the correlation coefficient curve, and curve 904 is the reference threshold curve corresponding to each correlation coefficient. Figure 10In the case of a person in the car, and the correlation coefficient calculated according to the ultrasonic echo when the human body is breathing is greater than the reference threshold curve, the curve 1002 is the correlation coefficient curve, and the curve 1004 is the reference threshold curve corresponding to the correlation coefficient; when the intermediate element is less than or equal to the reference threshold, it is determined that the human body in the time window corresponding to the intermediate element is in the car, that is, the position marked by the circle in the figure, which indicates that the intermediate element is less than or equal to the reference threshold, thereby determining that the human body in the time window corresponding to the intermediate element is in the car.

[0099] In the above embodiment, the correlation data calculated based on the ultrasonic echo is used to detect the target object, which can realize application scenarios such as automatic alarm when a baby is left alone in the car, thereby avoiding accidents.

[0100] It should be understood that although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least part of other steps or steps or stages in other steps.

[0101] Based on the same inventive concept, the embodiments of the present application also provide a target object detection device for implementing the target object detection method described above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more target object detection device embodiments provided below can refer to the limitations of the target object detection method described above, and will not be repeated here.

[0102] In one embodiment, as shown in Figure 11 , a target object detection device is provided, comprising:

[0103] The ultrasonic wave sending control module 1102 is configured to control the ultrasonic wave module to send ultrasonic waves to the target object activity space.

[0104] The ultrasonic wave receiving module 1104 is configured to receive ultrasonic echoes, which are echoes reflected by objects in the activity space.

[0105] The correlation coefficient calculation module 1106 is configured to determine the correlation coefficient of the to-be-tested frame of ultrasonic echoes according to the to-be-tested frame of ultrasonic echoes and the last frame of ultrasonic echoes of the to-be-tested frame.

[0106] The target object determination module 1108 is configured to determine whether a target object is in the active space in the time corresponding to the to-be-tested frame of ultrasonic echoes according to a comparison result of the correlation coefficient of the to-be-tested frame of ultrasonic echoes and the corresponding reference threshold.

[0107] The reference threshold refers to a numerical judgment condition for judging whether the target object exists.

[0108] In an embodiment, the correlation coefficient calculation module 1106 includes:

[0109] The correlation coefficient calculation unit is configured to determine the correlation coefficient of the to-be-tested frame of ultrasonic echoes according to the voltage value and the voltage average value of the to-be-tested frame of ultrasonic echoes, the voltage value and the voltage average value of the last frame of ultrasonic echoes of the to-be-tested frame, and the following correlation coefficient calculation formula:

[0110]

[0111] Wherein, r represents the correlation coefficient, n represents the length of a frame of ultrasonic echoes, x i represents the voltage value of the i-th sampling point of the to-be-tested frame of ultrasonic echoes, represents the voltage average value of the to-be-tested frame of ultrasonic echoes; y i represents the voltage value of the i-th sampling point of the last frame of ultrasonic echoes of the to-be-tested frame, represents the voltage average value of the last frame of ultrasonic echoes of the to-be-tested frame.

[0112] In an embodiment, the target object detection device further includes:

[0113] The reference threshold determination module is configured to determine the reference threshold corresponding to the correlation coefficient of each frame of ultrasonic echoes according to the correlation coefficient of the to-be-tested frame of ultrasonic echoes.

[0114] In an embodiment, the reference threshold determination module includes:

[0115] The correlation coefficient acquisition unit is configured to acquire at least three correlation coefficients in a preset time window.

[0116] The intermediate element determination unit is configured to determine an intermediate element of the correlation coefficients; the intermediate element is a correlation coefficient at a middle position.

[0117] The average value calculation unit is configured to calculate the average values of the correlation coefficients on both sides of the intermediate element respectively to obtain a first average value and a second average value.

[0118] The first reference threshold determination unit is configured to determine a reference threshold of the intermediate element according to any one of the first average value and the second average value and a compensation value, and the compensation value is used to correct the reference threshold.

[0119] The second reference threshold determination unit is configured to determine a reference threshold corresponding to the correlation coefficient of each frame of ultrasonic echo according to the reference threshold of the intermediate element.

[0120] In an embodiment, the first reference threshold determination unit includes:

[0121] The screening unit is configured to select the minimum average value of the first average value and the second average value as the intermediate threshold.

[0122] The reference threshold calculation unit is configured to add the compensation value to the intermediate threshold to obtain the reference threshold.

[0123] In an embodiment, the target object determination module 1108 includes:

[0124] The first comparison unit is configured to determine that the target object is in the active space in the time window corresponding to the intermediate element when the intermediate element is less than or equal to the reference threshold of the intermediate element.

[0125] In an embodiment, the target object determination module 1108 further includes:

[0126] The second comparison unit is configured to determine that the target object is not in the active space in the time window corresponding to the intermediate element when the intermediate element is greater than the reference threshold of the intermediate element.

[0127] Each module in the target object detection device can be realized by software, hardware, and a combination thereof in whole or in part. Each module can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to each module by the processor.

[0128] In an embodiment, a computer device is provided, which can be a terminal, such as a mobile phone, a tablet computer, a personal computer, or the like. Figure 12As shown, when it is a terminal, it can be a vehicle-mounted terminal or the like, and by executing the steps of the target object detection method, monitoring of whether there is a person in the vehicle can be realized. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. Among them, the processor, the memory and the input / output interface are connected through the system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be realized through WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to realize a target object detection method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0129] Those skilled in the art can understand that, Figure 12 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0130] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the steps in the above method embodiments.

[0131] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program is executed by a processor to realize the steps in the above method embodiments.

[0132] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to realize the steps in the above method embodiments.

[0133] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0134] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present application.

[0135] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A target object detection method characterized by, The method comprises: controlling an ultrasonic module to send ultrasonic waves, the ultrasonic module being configured to send ultrasonic waves to an activity space of the target object; receiving ultrasonic echoes, the ultrasonic echoes being echoes of the ultrasonic waves reflected by objects in the activity space; determining a correlation coefficient of the ultrasonic echoes of a to-be-detected frame according to the ultrasonic echoes of the to-be-detected frame and ultrasonic echoes of a previous frame of the to-be-detected frame; determining whether the target object is in the activity space during a time corresponding to the ultrasonic echoes of the to-be-detected frame according to a comparison result of the correlation coefficient of the ultrasonic echoes of the to-be-detected frame and a corresponding reference threshold value; wherein the reference threshold value refers to a numerical judgment condition for judging the presence of the target object; wherein the method further comprises: determining reference threshold values corresponding to the correlation coefficients of the ultrasonic echoes of each frame according to the correlation coefficient of the ultrasonic echoes of the to-be-detected frame; the determining of the reference threshold values corresponding to the correlation coefficients of the ultrasonic echoes of each frame according to the correlation coefficient of the ultrasonic echoes of the to-be-detected frame comprises: obtaining at least three correlation coefficients in a preset time window; determining a middle element of the correlation coefficients; the middle element is a correlation coefficient located in a middle position; calculating average values of the correlation coefficients located on both sides of the middle element respectively to obtain a first average value and a second average value; determining a reference threshold value of the middle element according to any one of the first average value and the second average value and a compensation value; the compensation value is used to correct the reference threshold value; determining the reference threshold values corresponding to the correlation coefficients of the ultrasonic echoes of each frame according to the reference threshold value of the middle element; the determining of the reference threshold value of the middle element according to any one of the first average value and the second average value and the compensation value comprises: selecting a minimum average value of the first average value and the second average value as a middle threshold value; adding the compensation value to the middle threshold value to obtain the reference threshold value.

2. The target object detection method according to claim 1, wherein the determining of the correlation coefficient of the ultrasonic echoes of the to-be-detected frame according to the ultrasonic echoes of the to-be-detected frame and the ultrasonic echoes of the previous frame of the to-be-detected frame comprises: determining the correlation coefficient of the ultrasonic echoes of the to-be-detected frame according to voltage values and voltage average values of the ultrasonic echoes of the to-be-detected frame and the ultrasonic echoes of the previous frame of the to-be-detected frame, and the following correlation coefficient calculation formula: wherein r represents the correlation coefficient, n represents the length of a frame of ultrasound echoes, x i represents the voltage value of the i-th sample point of the frame of ultrasound echoes to be measured, represents the voltage average value of the frame of ultrasound echoes to be measured; y i represents the voltage value of the i-th sample point of the frame of ultrasound echoes to be measured, represents the voltage average value of the frame of ultrasound echoes to be measured.

3. The target object detection method according to claim 1, wherein the preset time window is a time window with the middle element as the center and the same number of correlation coefficients on both sides of the middle element.

4. The target object detection method according to claim 1 or 3, characterized by, the determining of whether the target object is in the activity space during the time corresponding to the ultrasonic echoes of the to-be-detected frame according to the comparison result of the correlation coefficient of the ultrasonic echoes of the to-be-detected frame and the corresponding reference threshold value comprises: if the middle element is less than or equal to the reference threshold value of the middle element, it is determined that the target object is in the activity space during a time window corresponding to the middle element.

5. The target object detection method according to claim 1 or 3, characterized by, the determining of whether the target object is in the activity space during the time corresponding to the ultrasonic echoes of the to-be-detected frame according to the comparison result of the correlation coefficient of the ultrasonic echoes of the to-be-detected frame and the corresponding reference threshold value further comprises: If the intermediate element is greater than a reference threshold of the intermediate element, it is determined that the target object does not exist in the activity space in a time window corresponding to the intermediate element.

6. A target object detection apparatus characterized by comprising: The device comprises: An ultrasonic wave sending control module for controlling an ultrasonic wave module to send ultrasonic waves to an activity space of the target object; An ultrasonic wave receiving module for receiving ultrasonic echoes, which are echoes of the ultrasonic waves reflected by objects in the activity space; A correlation coefficient calculation module for determining a correlation coefficient of the ultrasonic echoes of a to-be-detected frame according to the ultrasonic echoes of the to-be-detected frame and ultrasonic echoes of a previous frame of the to-be-detected frame; A target object determination module for determining whether the target object exists in the activity space in a time corresponding to the ultrasonic echoes of the to-be-detected frame according to a comparison result of the correlation coefficient of the ultrasonic echoes of the to-be-detected frame and a corresponding reference threshold; The reference threshold refers to a numerical judgment condition for judging whether the target object exists; The device further comprises: A reference threshold determination module for determining reference thresholds corresponding to the correlation coefficients of the ultrasonic echoes of each frame according to the correlation coefficient of the ultrasonic echoes of the to-be-detected frame; The reference threshold determination module comprises: A correlation coefficient acquisition unit for acquiring at least three correlation coefficients in a preset time window; An intermediate element determination unit for determining an intermediate element of the correlation coefficients, which is a correlation coefficient at a middle position; An average value calculation unit for calculating average values of the correlation coefficients on both sides of the intermediate element to obtain a first average value and a second average value; A first reference threshold determination unit for determining a reference threshold of the intermediate element according to any one of the first average value and the second average value and a compensation value, which is used to correct the reference threshold; A second reference threshold determination unit for determining the reference thresholds corresponding to the correlation coefficients of the ultrasonic echoes of each frame according to the reference threshold of the intermediate element; The first reference threshold determination unit comprises: A screening unit for selecting a minimum average value of the first average value and the second average value as an intermediate threshold; A reference threshold calculation unit for adding the compensation value to the intermediate threshold to obtain the reference threshold. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 5.

Images