Air conditioner, target recognition method thereof, and computer-readable storage medium

Abstract

The present invention discloses a radar-based target recognition method, which includes: obtaining a first position parameter and a first signal feature value; the first position parameter characterizes the positional relationship between a first target and the radar, and the first signal feature value is the signal feature value of the radar detection signal corresponding to the first target; determining a first signal recognition threshold of the radar according to the first position parameter; different first position parameters correspond to different first signal recognition thresholds; determining whether the first target is a moving target according to the first signal feature value and the first signal recognition threshold. The present invention also discloses a radar-based air conditioner and a computer-readable storage medium. The present invention aims to improve the accuracy of radar in detecting human bodies.

Description

Technical Field

[0001] The present invention relates to the technical field of radar detection, and particularly to a target recognition method, an air conditioner, and a computer-readable storage medium. Background Art

[0002] Currently, many household appliances (such as air conditioners) use radar to detect the state of the human body and perform corresponding controls. Generally, radar identifies whether there is a person by detecting moving targets in space. During the detection process, the radar emits detection signals into space and receives the signals reflected back by the moving targets, and identifies whether there is a moving target based on the comparison between the reflected signals and a preset signal threshold.

[0003] However, during the recognition process, regardless of how the detection scenario changes, the signal threshold used for moving target recognition is fixed, which may easily lead to misjudgment of the recognition result of the moving target, resulting in the radar being unable to accurately identify the human body situation in space. Summary of the Invention

[0004] The main object of the present invention is to provide a target recognition method, an air conditioner, and a computer-readable storage medium, aiming to improve the accuracy of radar detection of the human body.

[0005] To achieve the above object, the present invention provides a target recognition method based on radar, and the target recognition method includes the following steps:

[0006] Obtain a first position parameter and a first signal feature value; the first position parameter characterizes the positional relationship between a first target and the radar, and the first signal feature value is the signal feature value of the radar detection signal corresponding to the first target;

[0007] Determine a first signal recognition threshold of the radar according to the first position parameter; different first position parameters correspond to different first signal recognition thresholds;

[0008] Determine whether the first target is a moving target according to the first signal feature value and the first signal recognition threshold.

[0009] Optionally, the step of obtaining the first position parameter includes:

[0010] Obtain the distance between the first target and the radar, and / or obtain the direction of the first target relative to the radar, and the first position parameter includes the distance and / or the direction;

[0011] Wherein, the first signal recognition threshold increases as the distance decreases; and / or, the first signal recognition threshold increases as the target angle corresponding to the direction decreases, where the target angle is the angle between the direction and the set direction, and the detection signal emitted by the radar has the maximum intensity in the set direction.

[0012] Optionally, the first position parameter includes the distance and the direction, and the step of determining the first signal recognition threshold of the radar according to the first position parameter includes:

[0013] Determine the preset distance interval where the distance is located, and determine the preset angle interval where the target angle is located;

[0014] Based on the preset mapping relationship, determine the preset signal threshold corresponding to the preset distance interval and the preset angle interval, and the first signal recognition threshold is the preset signal threshold; the preset mapping relationship is the mapping relationship between the preset distance interval, the preset angle interval and the preset signal threshold set in advance;

[0015] In the preset mapping relationship, the smaller the distance value of the preset distance interval, the larger the corresponding preset signal threshold, and the smaller the angle value of the preset angle interval, the larger the corresponding preset signal threshold.

[0016] Optionally, the step of obtaining the first position parameter and the first signal feature value includes:

[0017] Receive the reflected signal corresponding to the first target, and the radar detection signal is the reflected signal; wherein, the reflected signal is formed by the first target reflecting the detection signal emitted by the radar;

[0018] Determine the first position parameter and the first signal feature value according to the reflected signal.

[0019] Optionally, the first signal feature value includes signal intensity, the first signal recognition threshold includes a signal intensity threshold, and the step of determining whether the first target is a moving target according to the first signal feature value and the first signal recognition threshold includes:

[0020] When the signal intensity is greater than the signal intensity threshold, determine that the first target is a moving target;

[0021] When the signal intensity is less than or equal to the signal intensity threshold, determine that the first target is a non-moving target.

[0022] Optionally, after the step of determining whether the first target is a moving target according to the first signal feature value and the first signal recognition threshold, further includes:

[0023] When the first target is a moving target, obtain a first target area where interference objects are located within the detection range of the radar, where the interference objects are objects whose movement range is restricted within the first target area;

[0024] If the first target is located outside the first target area, determine that the first target is a human body;

[0025] If the first target is located within the first target area, determine that the first target is the interference object.

[0026] Optionally, the detection range is divided into multiple sub-areas, and the first target area is one of the multiple sub-areas. The step of obtaining the first target area where interference objects are located within the detection range of the radar includes:

[0027] Obtain target frequency information corresponding to each of the sub-areas; the target frequency information is the frequency information of the corresponding sub-area where a moving target appears within a target duration;

[0028] Among the multiple sub-areas, determine the sub-area that meets the preset condition as the first target area;

[0029] Wherein, the preset condition is that the target frequency information corresponding to the sub-area is greater than or equal to a set frequency threshold.

[0030] Optionally, each of the sub-areas has a corresponding statistical count, and the detection process of the target frequency information is as follows:

[0031] Within the target duration, repeatedly execute the moving target recognition process;

[0032] After the target duration ends, determine the target frequency information corresponding to the sub-area according to the current statistical count of the sub-area;

[0033] Wherein, the moving target recognition process includes:

[0034] Obtain a second position parameter and a second signal feature value, where the second target is the target currently detected by the radar; the second position parameter characterizes the position relationship between the second target and the radar, and the second signal feature value is the signal feature value of the radar detection signal corresponding to the second target;

[0035] Determine a second signal recognition threshold of the radar according to the second position parameter;

[0036] Determine whether the second target is a moving target according to the second signal feature value and the second signal recognition threshold;

[0037] If the second target is a moving target, determine the sub-region where the second target is located as the second target region, and increment the statistical count corresponding to the second target region by one.

[0038] Optionally, the moving target recognition process further includes: while performing the step of incrementing the statistical count corresponding to the target sub-region by one, associating the target sub-region with the second signal feature value;

[0039] The step of determining the target frequency information corresponding to the sub-region according to the current statistical count of the sub-region includes:

[0040] Determine the target signal value corresponding to the sub-region according to a plurality of the second signal feature values associated with the sub-region;

[0041] Determine the deviation amount between each of the second signal feature values associated with the sub-region and the target signal value;

[0042] Modify the current statistical count of the sub-region according to a plurality of the deviation amounts to obtain the target count of the sub-region;

[0043] Determine the target frequency information corresponding to the sub-region according to the target count of the sub-region.

[0044] Optionally, the step of modifying the current statistical count of the sub-region according to a plurality of the deviation amounts includes:

[0045] Determine the deviation amounts greater than or equal to a preset deviation threshold among the plurality of deviation amounts as target deviation amounts;

[0046] Determine the number of corrections according to the number of the target deviation amounts;

[0047] Modify the current statistical count of the sub-region according to the number of corrections.

[0048] Optionally, when the moving target includes a human body, after the step of determining whether the first target is a moving target according to the first signal feature value and the first signal recognition threshold, the method further includes:

[0049] When the first target is a human body, control the air conditioner to operate in a first air outlet mode;

[0050] When the first target is a target other than a human body, control the air conditioner to operate in a second air outlet mode;

[0051] Wherein, the air outlet speed of the air conditioner corresponding to the first air outlet mode is less than the air outlet speed of the air conditioner corresponding to the second air outlet mode.

[0052] In addition, to achieve the above object, the present application further provides an air conditioner, which includes:

[0053] a radar;

[0054] a control device, connected to the radar, the control device includes: a memory, a processor, and a target recognition program stored on the memory and executable on the processor, and when the target recognition program is executed by the processor, it implements the steps of the target recognition method described in any one of the above.

[0055] In addition, to achieve the above object, the present application further provides a computer-readable storage medium, on which a target recognition program is stored, and when the target recognition program is executed by a processor, it implements the steps of the target recognition method described in any one of the above.

[0056] A target recognition method based on radar proposed by the present invention uses the position parameters of a first target detected by the radar relative to the radar to determine the signal recognition threshold of the radar for identifying moving targets. If the position of the first target relative to the radar is different, the signal recognition threshold is different. Based on this, during the process of moving target recognition, the signal recognition threshold is no longer fixed, but is adjusted according to the position of the first target relative to the radar, thereby avoiding misjudgment of the recognition result of moving targets, ensuring that the radar accurately identifies whether there is a human body in the space, and improving the accuracy of the radar in detecting human bodies. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 Schematic diagram of the hardware structure involved in the operation of an embodiment of the air conditioner of the present invention;

[0058] Figure 2 Schematic diagram of the process of an embodiment of the target recognition method of the present invention;

[0059] Figure 3 Schematic diagram of the angle related to the radar detection area involved in another embodiment of the target recognition method of the present invention;

[0060] Figure 4 Schematic diagram of the process of another embodiment of the target recognition method of the present invention;

[0061] Figure 5 Schematic diagram of the process of still another embodiment of the target recognition method of the present invention.

[0062] The realization, functional features, and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] The main solution of the embodiment of the present invention is: obtaining a first position parameter and a first signal eigenvalue; the first position parameter characterizes the positional relationship between a first target and the radar, and the first signal eigenvalue is the signal eigenvalue of the radar reflection signal corresponding to the first target; determining a first signal recognition threshold of the radar according to the first position parameter; different first position parameters correspond to different first signal recognition thresholds; determining whether the first target is a moving target according to the first signal eigenvalue and the first signal recognition threshold.

[0065] In the prior art, many household appliances (such as air conditioners) use radar to detect the state of the human body and perform corresponding control. Generally, the radar identifies whether there is someone by detecting moving targets in space. During the detection process, the radar emits a detection signal into space and receives the signal reflected back by the moving target of the detection signal, and identifies whether there is a moving target based on the comparison between the reflected signal and a preset signal threshold. However, during the identification process, no matter how the detection scenario changes, the signal threshold used for moving target identification is fixed and unchanged, which may cause the identification result of the moving target to be easily misjudged, resulting in the radar being unable to accurately identify the human body situation in the space.

[0066] The present invention provides the above solution to improve the accuracy of the radar for human body detection.

[0067] The embodiment of the present invention proposes a target recognition device based on radar, which is used to recognize moving targets such as the human body. The target recognition device can be any device equipped with a radar and requiring the recognition of moving targets such as the human body. In this embodiment, the target recognition device is an air conditioner. In other embodiments, the target recognition device can also be an electrical appliance device such as a refrigerator, a speaker, a television, etc. that needs to perform human body recognition for control according to actual requirements.

[0068] Wherein, when the target recognition device is an air conditioner, it can be determined based on the recognition result of the target recognition device whether there is a human body in the range where the distance between the air conditioner and the air conditioner in the action space is less than or equal to a preset distance. If there is a human body, the air conditioner can be controlled to turn on the first air outlet mode. If there is no human body, the air conditioner can be controlled to turn on the second air outlet mode; wherein, the air outlet wind speed of the air conditioner corresponding to the first air outlet mode is less than the air outlet wind speed of the air conditioner corresponding to the second air outlet mode, and the heat exchange amount output by the air conditioner corresponding to the first air outlet mode is less than the heat exchange amount output by the air conditioner corresponding to the second air outlet mode. Based on this, it is realized that the air conditioner can effectively balance the user's air outlet comfort and temperature comfort according to the indoor human body situation.

[0069] In the embodiment of the present invention, refer to Figure 1, the target recognition device (such as an air conditioner) may include a radar 1 and a control device. The control device includes: a processor 1001 (such as a CPU), a memory 1002, etc. The memory 1002 can be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. Optionally, the memory 1002 can also be a storage device independent of the aforementioned processor 1001. The processor 1001 is connected to the memory 1002 through a communication bus.

[0070] Specifically, referring to Figure 1 , the control device is communicatively connected to the radar 1, and based on the communication connection, the control device can obtain the signal detected by the radar 1. Wherein, when the target recognition device is an air conditioner, the control device can be connected to the air outlet component of the air conditioner to switch the air outlet mode of the air conditioner.

[0071] Those skilled in the art can understand that Figure 1 the device structure shown in

[0072] does not constitute a limitation on the device, and may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. Figure 1 As shown in Figure 1 , the memory 1002, as a computer-readable storage medium, may include a target recognition program. In the device shown in

[0073] , the processor 1001 can be used to call the target recognition program stored in the memory 1002 and execute the relevant step operations of the target recognition method in the following embodiments.

[0074] Referring to Figure 2 , an embodiment of the target recognition method of the present application is proposed. In this embodiment, the target recognition method includes:

[0075] Step S10, obtaining a first position parameter and a first signal feature value; the first position parameter characterizes the positional relationship between the first target and the radar, and the first signal feature value is the signal feature value of the radar detection signal corresponding to the first target;

[0076] The radar emits a detection signal into space. The detection signal reaches the location of the target in space, and the target reflects the detection signal. The radar receives the signal reflected by the target. Based on this, the first target specifically refers to any target in space that reflects the signal emitted by the radar. The radar detection signal specifically refers to the reflected signal formed by the first target.

[0077] The first position parameter may specifically include the distance between the first target and the radar, the direction of the first target relative to the radar, the direction of the radar relative to the first target, the sub-region where the first target is located within the radar detection area, and so on. The first position parameter can be obtained by analyzing the radar detection signal corresponding to the first target, or can be determined based on the human body position parameters detected by other positioning modules in the space (such as image positioning modules, infrared detection modules, etc.) and the preset radar position parameters, and so on.

[0078] The first signal eigenvalue specifically includes an intensity characteristic parameter representing signal strength (such as energy amplitude, energy minimum value, and / or energy maximum value, etc.) and / or a frequency characteristic parameter representing signal frequency (such as frequency band, wavelength, etc.). Specifically, the first signal eigenvalue here can be obtained by processing the radar detection signal according to a preset rule.

[0079] In this embodiment, in order to avoid setting additional detection modules and improve the efficiency of obtaining the first position parameter and the first signal eigenvalue, the process of obtaining the first position parameter and the first signal eigenvalue is specifically as follows: Receive the reflected signal corresponding to the first target, and the radar detection signal is the reflected signal; wherein, the reflected signal is formed by the first target reflecting the detection signal emitted by the radar; Determine the first position parameter and the first signal eigenvalue according to the reflected signal.

[0080] Step S20, determine the first signal recognition threshold of the radar according to the first position parameter; different first position parameters correspond to different first signal recognition thresholds;

[0081] Different first position parameters correspond to different first signal recognition thresholds. Specifically, a corresponding relationship between the first position parameter and the first signal recognition threshold can be established in advance, and the corresponding relationship can have forms such as a calculation relationship, a mapping relationship, an algorithm model, etc. Based on the preset corresponding relationship, the first signal recognition threshold corresponding to the first position parameter can be determined.

[0082] Step S30, determine whether the first target is a moving target according to the first signal eigenvalue and the first signal recognition threshold.

[0083] The moving target here includes any target that can move in space. Specifically, in this embodiment, the moving target includes people, animals, curtains swaying in the wind, and / or placed objects with moving parts in a fixed position, and so on.

[0084] Specifically, the first signal feature value can be directly compared with the first signal recognition threshold, and whether the first target is a moving target can be determined based on the comparison result. In addition, the quantitative relationship value (such as the difference or ratio) between the first signal feature value and the first signal recognition threshold can also be determined. After comparing the quantitative relationship value with the corresponding preset relationship threshold, whether the first target is a moving target can be determined according to the comparison result. For example, when the quantitative relationship value is the deviation value between the first signal feature value and the first signal recognition threshold, and the preset relationship threshold is the preset deviation, if the actually determined deviation value is less than the preset deviation, it can be considered that the first target is a moving target. If the actually determined deviation value is greater than or equal to the preset deviation, it can be considered that the first target is a non-moving target. Another example is that when the quantitative relationship value is the ratio between the first signal feature value and the first signal recognition threshold, and the preset relationship threshold is 1, if the deviation between the actually determined ratio and 1 is less than the set threshold, it can be considered that the first target is a moving target. If the deviation between the actually determined ratio and 1 is greater than or equal to the set threshold, it can be considered that the first target is a non-moving target.

[0085] Specifically, in this embodiment, the first signal feature value includes the signal intensity. Specifically, the energy amplitude of the reflected signal corresponding to the first target can be obtained as the signal intensity here. Correspondingly, the first signal recognition threshold includes the signal intensity threshold. Based on this, step S30 includes: when the signal intensity is greater than the signal intensity threshold, determining that the first target is a moving target; when the signal intensity is less than or equal to the signal intensity threshold, determining that the first target is a non-moving target. Based on this, the accurate recognition of whether there is a moving target in the space can be realized based on the signal intensity of the radar detection signal.

[0086] A radar-based target recognition method proposed in an embodiment of the present invention uses the position parameters of the first target detected by the radar relative to the radar to determine the signal recognition threshold of the radar for identifying moving targets. Different positions of the first target relative to the radar result in different signal recognition thresholds. Based on this, during the process of moving target recognition, the signal recognition threshold is no longer fixed, but is adjusted according to the position of the first target relative to the radar, thereby avoiding misjudgment of the recognition result of the moving target, ensuring that the radar accurately recognizes whether there is a human body in the space, and improving the accuracy of the radar in detecting the human body.

[0087] Further, based on the above embodiment, another embodiment of the target recognition method of the present application is proposed. In this embodiment, in step S10, the step of obtaining the first position parameter includes:

[0088] Step S11, obtaining the distance between the first target and the radar, and / or obtaining the direction of the first target relative to the radar, where the first position parameter includes the distance and / or the direction.

[0089] After receiving the radar reflection signal corresponding to the first target, record the first time when the radar reflection signal is received, obtain the second time when the radar emits the detection signal, and calculate the distance between the first target and the radar according to the time deviation between the first time and the second time and the propagation speed of the radar detection signal in space. For example, the product of the time difference and the propagation speed is used as the distance here.

[0090] Specifically, the radar may have more than one antenna, and each antenna can send and receive detection signals. By analogy with the above distance detection method, the set of positions where the first target is detected corresponding to each antenna can be determined. Each antenna corresponds to a position set, and the intersection position in all position sets can be used as the target position where the first target is located. Based on the target position and the preset position corresponding to the radar, the direction of the first target relative to the radar can be determined; alternatively, the signal intensities of the reflection signals of the first target received by each antenna can also be compared, and the preset direction corresponding to the antenna with the strongest signal intensity can be used as the direction of the first target relative to the radar.

[0091] The first position parameter includes the distance between the radar and the first target, and different distances correspond to different first signal recognition thresholds. The first correspondence between the distance and the recognition threshold can be preset, and it can be a calculation relationship, a mapping relationship, an algorithm model, etc. In the first correspondence, the first signal recognition threshold increases as the distance between the radar and the first target decreases. Based on the first correspondence, the first signal recognition threshold corresponding to the current distance between the radar and the first target can be determined.

[0092] The first position parameter includes the direction of the first target relative to the radar, and different directions correspond to different first signal recognition thresholds. The second correspondence between the direction and the recognition threshold can be preset, and it can be a calculation relationship, a mapping relationship, an algorithm model, etc. In the second correspondence, the first signal recognition threshold increases as the target angle corresponding to the direction of the first target relative to the radar decreases. The target angle is the angle between the direction of the first target relative to the radar and the set direction, and the radar emits the detection signal with the maximum intensity in the set direction. That is to say, the signal intensity of the detection signal emitted by the radar in the set direction is greater than the signal intensities of the detection signals in all other directions within the radar detection range. Based on the second correspondence, the first signal recognition threshold corresponding to the current direction of the first target relative to the radar can be determined.

[0093] The first position parameter includes the distance between the radar and the first target and the direction of the first target relative to the radar. Different distances and different directions correspond to different first signal recognition thresholds. The third correspondence relationship between the distance, direction, and recognition threshold can be preset, which can be a calculation relationship, a mapping relationship, an algorithm model, etc. In the third correspondence relationship, the first signal recognition threshold increases as the distance between the radar and the first target decreases, and the first signal recognition threshold increases as the target angle corresponding to the direction of the first target relative to the radar decreases. The target angle is the angle between the direction of the first target relative to the radar and the set direction, and the detection signal emitted by the radar has the maximum intensity in the set direction. Based on the third correspondence relationship, the first signal recognition threshold corresponding to the current direction of the first target relative to the radar and the distance between the radar and the first target can be determined.

[0094] Among them, with reference to Figure 3 , point O is the location of the radar, the closed area formed by line ACB and line AOB is the detection range of the radar, OC is the midline of the detection range of this radar. Within this detection range, the intensity of the detection signal emitted by the radar has the maximum value in the direction of OC. Based on this, OC can be used as the above-mentioned set direction. Point D is the current location of the first target. Based on this, OD is the direction of the first target relative to the radar, angle COD is the above-mentioned target angle, and the length of OD is the distance between the radar and the first target.

[0095] In this embodiment, the first position parameter includes the distance between the radar and the first target and the direction of the first target relative to the radar. The correspondence relationship between the distance between the radar and the first target, the direction of the first target relative to the radar, and the first signal recognition threshold is a mapping relationship. Based on this, step S20 includes:

[0096] Step S21, determining the preset distance interval where the distance is located and the preset angle interval where the target angle is located;

[0097] Step S22, based on the preset mapping relationship, determining the preset signal threshold corresponding to the preset distance interval and the preset angle interval, and the first signal recognition threshold is the preset signal threshold; the preset mapping relationship is the mapping relationship between the preset distance interval, the preset angle interval, and the preset signal threshold set in advance;

[0098] In the preset mapping relationship, the smaller the distance value in the preset distance interval, the larger the corresponding preset signal threshold, and the smaller the angle value in the preset angle interval, the larger the corresponding preset signal threshold.

[0099] Specifically, a corresponding relationship can be pre - established between multiple different preset distance intervals, multiple different preset angle intervals and different signal recognition thresholds to form a preset mapping relationship. Determine the preset distance interval in which the distance between the current radar and the first target is located among the multiple preset distance intervals, and determine the preset angle interval in which the direction of the current first target relative to the radar is located among the multiple preset angle intervals. Query the preset mapping relationship through the currently determined preset distance interval and preset angle interval, and use the signal recognition threshold matched by the currently determined preset distance interval and preset angle interval as the first signal recognition threshold here.

[0100] Specifically, in this embodiment, based on Figure 3 , where OC is the set direction, D is the position of the first target, OD is the direction of the first target relative to the radar, and the angle COD is the target angle. The preset mapping relationship among the distance between the radar and the first target, the direction of the first target relative to the radar, and the first signal recognition threshold is as follows in the table:

[0101]

[0102] Based on the mapping relationship shown in the above table, if the distance between the current radar and the first target is 0.8, and the target angle of the direction of the first target relative to the radar is 13 degrees, then the corresponding first signal recognition threshold can be determined to be 800. If the distance between the current radar and the first target is 1.35, and the target angle of the direction of the first target relative to the radar is 65 degrees, then the corresponding first signal recognition threshold can be determined to be 210, and so on.

[0103] Since the distance or direction of the first target relative to the radar is different, the signal characteristic values detected by the radar for the first target are different. Based on this, in this embodiment, the signal recognition threshold is adjusted according to the distance or direction of the first target relative to the radar, avoiding the situation that when the moving target is far from the radar, the threshold is too small to recognize the moving target, and also avoiding the situation that when the moving target is close to the radar, the threshold is too large to misjudge the nearby non - moving target as a moving target. Based on this, the accuracy of the signal recognition threshold can be ensured, the accurate recognition of the moving target can be guaranteed, and thus the accuracy of the human detection by the radar based on the recognition of the moving target can be improved.

[0104] Further, based on any of the above - mentioned embodiments, another embodiment of the target recognition method of the present application is proposed. In this embodiment, referring to Figure 4 , after the step S30, it further includes:

[0105] Step S40, when the first target is a moving target, obtain the first target area where the interference objects are located within the detection range of the radar, where the interference objects are objects whose movement range is restricted within the first target area;

[0106] The interfering object can be a curtain swaying in the wind, a pet in a cage, and / or an object placed in a fixed position but having moving parts, etc. The interfering object is an object outside the human body. The whole or part of the interfering object can move, but its movement range will not exceed the first target area and it cannot move to an area outside the first target area.

[0107] The area range of the first target area is smaller than the total range detected by the radar. Specifically, the total range detected by the radar can be pre-divided into multiple sub-areas, and the sub-area where the interfering object is located is determined as the first target area here. In addition, the position where the interfering object is located can also be obtained, and the range with a distance less than or equal to the set distance threshold from this position can be determined as the first target area here.

[0108] The first target area where the interfering object is located can be obtained by acquiring the parameters input by the user. For example, the user can input the position of the window within the radar detection range by themselves, and based on the position of the window input by the user, the first target area where the interfering object curtain is located can be determined.

[0109] In addition, the first target area where the interfering object is located can be confirmed by acquiring the detection parameters of other detection modules outside the radar within the radar detection range. For example, when other detection modules include an infrared detection module, the area within the radar detection range where the temperature is lower or higher than the human body temperature range can be determined as the first target area where the interfering object is located based on the parameters detected by the infrared detection module; another example is that when other detection modules include an image recognition module, the scene image can be collected by the image recognition module, the interfering object image in the scene image can be recognized, and based on the position of the interfering object image in the scene image, the first target area where the interfering object is located within the radar detection range can be determined, and so on.

[0110] In addition, in order to simplify the user operation and obtain the area where the interfering object is located without setting additional modules, the first target area where the interfering object is located here can be analyzed based on the recognition results of the radar module for moving targets multiple times within a certain period of time.

[0111] Step S50, determine whether the first target is located outside the first target area;

[0112] When the first target is located in an area outside the first target area, execute step S60; when the first target is located within the first target area, execute step S70;

[0113] Step S60, determine that the first target is a human body;

[0114] Step S70, determine that the first target is an interfering object.

[0115] The number of first target regions can be one or more than one. Among them, when the number of first target regions is more than one, if the first target is located within any one of the first target regions, it can be determined that the first target is an interference object; if the first target is not within any one of the first target regions, it can be determined that the first target is a human body.

[0116] Here, in order to ensure the accuracy of human body detection based on moving target recognition, after determining that there is a moving target, it is determined whether the moving target is located in the area where the interference object is located, and based on the determination result, it is determined whether the moving target is an interference object or a human body.

[0117] In addition, in other embodiments, when the accuracy requirement for human body detection is not high, when it is determined that the first target is a moving target, it can also be directly determined that the first target is a human body. Specifically, the determination rule for whether the first target is a human body can be selected based on the recognition requirement information input by the user.

[0118] Further, based on the above embodiments, another embodiment of the target recognition method of the present application is proposed. In this embodiment, referring to Figure 5 , the detection range is divided into multiple sub-regions, and the first target region is one of the multiple sub-regions. In the above step S40, the process of obtaining the above first target region is specifically as follows:

[0119] Step S41, obtain the target frequency information corresponding to each of the sub-regions; the target frequency information is the frequency information of the corresponding sub-region where a moving target appears within the target duration;

[0120] The target frequency information can be obtained by reading the pre-detected and stored data, or can be obtained by real-time detection.

[0121] The target duration here can be set based on a pre-set rule, or can be a time period specified by the user (determined based on the parameters input by the user), etc. For example, the preset duration before the current moment can be used as the target duration here, or the preset duration starting from the current moment can be used as the target duration here, or the duration information input by the user can be obtained to determine the target duration here. In addition, the preset time period currently located (such as morning or afternoon or evening, etc.) can be determined, and the preset time period corresponding to each day in the preset days before the current day can be used as the target duration here, and so on.

[0122] Each sub-region has a corresponding target frequency information. The target frequency information can be the total number of times a moving target appears in its corresponding sub-region within the target duration; in addition, the total number of times a moving target appears in a sub-region within the target duration can be defined as the first number, and the total number of times a moving target appears in all sub-regions within the target duration can be defined as the second number. The ratio of the first number corresponding to each sub-region to the second number can be used as the target frequency information corresponding to the sub-region.

[0123] The target frequency information can be obtained based on the analysis of the results of the radar's recognition of moving targets within the target duration, or can be obtained based on the analysis of the recognition results of the detection modules other than the radar in the radar detection area for the characteristics corresponding to the moving targets within the target duration.

[0124] Step S42, in the multiple sub-regions, determine the sub-regions that meet the preset conditions as the first target regions; wherein, the preset condition is that the target frequency information corresponding to the sub-region is greater than or equal to the set frequency threshold.

[0125] The number of the first target regions can be one or more than one. Specifically, all the sub-regions that meet the preset conditions can be used as the first target regions; or a preset number of sub-regions with the highest target frequency information among all the sub-regions that meet the preset conditions can be used as the first target regions.

[0126] For example, the target frequency information is the proportion of the number of times a moving target appears in a sub-region to the total number of detections. If the proportion exceeds a certain value (such as 40%), it is considered that there are interfering objects in the sub-region.

[0127] Here, through the frequency statistics of the appearance of moving targets in different sub-regions in the radar detection area within the target duration, the area where the interfering objects in the radar detection area can be accurately obtained. Among them, when the target frequency information is obtained through the analysis of multiple recognition results of the radar's recognition of moving targets within the target duration, the process of obtaining the target frequency information can be simplified, and at the same time, without adding additional functional modules, the sub-region where the interfering objects in the radar detection area can be determined at low cost and accurately.

[0128] Furthermore, in this embodiment, each of the sub-regions has a corresponding statistical number of times. At the start of the target duration timing, the statistical number of times corresponding to each sub-region can be initialized. For example, the statistical number of times of all sub-regions is initialized to 0 times. Based on this, the detection process of the target frequency information corresponding to each sub-region is as follows:

[0129] Step S01, within the target duration, loop to execute the moving target recognition process;

[0130] Specifically, within the target duration, the moving target recognition process can be executed once at an interval of a set time. For example, the target duration is 10 minutes, and the moving target recognition process is executed once at an interval of 200 ms.

[0131] Among them, the moving target recognition process includes:

[0132] Step S011: Obtain a second position parameter and a second signal eigenvalue, where the second target is the target currently detected by the radar; the second position parameter characterizes the positional relationship between the second target and the radar, and the second signal eigenvalue is the signal eigenvalue of the radar detection signal corresponding to the second target;

[0133] The radar emits a detection signal into space. The detection signal reaches the location of the target in space, and the target reflects the detection signal. The radar receives the signal reflected by the target. Based on this, the second target specifically refers to any target in the current space that reflects the signal emitted by the radar. The radar detection signal specifically refers to the reflected signal formed by the second target.

[0134] The second position parameter may specifically include the distance between the second target and the radar, the direction of the second target relative to the radar, the direction of the radar relative to the second target, the sub-region where the second target is located in the radar detection area, etc. The second position parameter can be obtained by analyzing the radar detection signal corresponding to the second target, or can be determined based on the human body position parameters detected by other positioning modules in the space (such as an image positioning module, an infrared detection module, etc.) and the pre-set radar position parameters, and so on.

[0135] The second signal eigenvalue specifically includes an intensity characteristic parameter (such as energy amplitude, energy minimum value, and / or energy maximum value, etc.) characterizing the signal intensity and / or a frequency characteristic parameter (such as frequency band, wavelength, etc.) characterizing the signal frequency. Specifically, the second signal eigenvalue here can be obtained by processing the radar detection signal according to a preset rule.

[0136] In this embodiment, in order to avoid setting additional detection modules and improve the efficiency of obtaining the second position parameter and the second signal eigenvalue, the process of obtaining the second position parameter and the second signal eigenvalue is specifically as follows: Receive the reflected signal corresponding to the second target, and the radar detection signal is the reflected signal; where the reflected signal is formed by the second target reflecting the detection signal emitted by the radar; determine the second position parameter and the second signal eigenvalue according to the reflected signal.

[0137] Step S012: Determine a second signal recognition threshold of the radar according to the second position parameter;

[0138] Different second position parameters correspond to different second signal recognition thresholds. Specifically, a corresponding relationship between the second position parameter and the second signal recognition threshold can be established in advance. The corresponding relationship can have forms such as a calculation relationship, a mapping relationship, an algorithm model, etc. Based on the pre-set corresponding relationship, the second signal recognition threshold corresponding to the second position parameter can be determined.

[0139] Step S013: Determine whether the second target is a moving target according to the second signal eigenvalue and the second signal recognition threshold;

[0140] The moving targets here include any targets that can move in space. Specifically, in this embodiment, the moving targets include people, animals, curtains swaying in the wind, and / or placed objects with moving parts at fixed positions, and so on.

[0141] Specifically, the second signal eigenvalue can be directly compared with the second signal recognition threshold, and based on the comparison result, it is determined whether the second target is a moving target. In addition, the quantitative relationship value (such as the difference or ratio) between the second signal eigenvalue and the second signal recognition threshold can also be determined. After comparing the quantitative relationship value with the corresponding preset relationship threshold, it is determined whether the second target is a moving target according to the comparison result. For example, when the quantitative relationship value is the deviation value between the second signal eigenvalue and the second signal recognition threshold, the preset relationship threshold is the preset deviation. If the actually determined deviation value is less than the preset deviation, it can be considered that the second target is a moving target. If the actually determined deviation value is greater than or equal to the preset deviation, it can be considered that the second target is a non-moving target. Another example is that when the quantitative relationship value is the ratio between the second signal eigenvalue and the second signal recognition threshold, the preset relationship threshold is 1. If the deviation between the actually determined ratio and 1 is less than the set threshold, it can be considered that the second target is a moving target. If the deviation between the actually determined ratio and 1 is greater than or equal to the set threshold, it can be considered that the second target is a non-moving target.

[0142] Specifically, in this embodiment, the second signal eigenvalue includes the signal strength. Specifically, the energy amplitude of the reflected signal corresponding to the second target can be obtained as the signal strength here. Correspondingly, the second signal recognition threshold includes the signal strength threshold. Based on this, step S013 includes: when the signal strength is greater than the signal strength threshold, determine that the second target is a moving target; when the signal strength is less than or equal to the signal strength threshold, determine that the second target is a non-moving target. Based on this, the accurate recognition of whether there are moving targets in the space can be realized based on the signal strength of the radar detection signal.

[0143] The specific refinement steps of steps S011 to S013 here can be analogously referred to the specific implementation processes of steps S10 to S40 above, and will not be elaborated here.

[0144] Step S014: If the second target is a moving target, determine the sub-region where the second target is located as the second target region, and increase the statistical count corresponding to the second target region by one.

[0145] Specifically, the sub-region where the second target is located can be determined based on the second position information, or the sub-region where the second target is located can be determined by linking other detection modules outside the radar with the information detected by the radar.

[0146] Among them, if there are more than one second target at a certain moment, when the statistical count is updated, the statistical count of the second target area corresponding to each second target can be increased by one respectively.

[0147] For example, multiple sub-regions include a first sub-region, a second sub-region, and a third sub-region, and the initial statistical count of each sub-region is 0. After the target time period starts timing, during the first execution of the moving target recognition process, if it is detected that the current second target is a moving target and it is determined that the second target is in the first sub-region, the statistical count of the first sub-region is updated from 0 to 1; later, when the moving target recognition process is executed again, if it is detected that the current second targets are moving targets and there are two of them, one moving target is in the first sub-region and the other moving target is in the third sub-region, then the statistical count of the first sub-region is updated from 1 to 2, and the statistical count of the third sub-region is updated from 0 to 1, and so on, until the timing duration reaches the target time period, then the update of the statistical count corresponding to each sub-region ends.

[0148] Step S02, after the target time period ends, determine the target frequency information corresponding to the sub-region according to the current statistical count of the sub-region.

[0149] When the timing duration is greater than or equal to the target time period, the statistical count corresponding to each sub-region can be directly used as the target frequency information; or, calculate the proportion of the statistical count corresponding to each sub-region in the total of the statistical counts of all sub-regions as the target frequency information; or, calculate the proportion of the statistical count corresponding to each sub-region in the total number of executions of the moving target recognition process within the target time period as the target frequency information.

[0150] For example, the statistical counts corresponding to the above-mentioned first sub-region, second sub-region, and third sub-region at the end of the target time period are 10 times, 2 times, and 3 times respectively, and the total number of executions of the moving target recognition process within the target time period is 20 times. Based on this, 10 times can be used as the target frequency information corresponding to the first sub-region, or 10 / 20 can be used as the target frequency information corresponding to the first sub-region; 2 times can be used as the target frequency information corresponding to the second sub-region, or 2 / 20 can be used as the target frequency information corresponding to the second sub-region; 3 times can be used as the target frequency information corresponding to the third sub-region, or 3 / 20 can be used as the target frequency information corresponding to the third sub-region.

[0151] It should be noted that during the execution of each motion target recognition process, further recognition of whether there is a human body can be performed based on steps S40 to S70 and their corresponding refinement steps, and the device where the radar is located can be controlled based on the recognition result of whether there is a human body. Specifically, in this embodiment, the device where the radar is located is an air conditioner, and the motion target includes a human body. After the step of determining whether the first target is a motion target according to the first signal feature value and the first signal recognition threshold, the following steps are further included: when the first target is a human body, controlling the air conditioner to operate in a first air outlet mode; when the first target is a target other than a human body, controlling the air conditioner to operate in a second air outlet mode; wherein, the air outlet speed of the air conditioner corresponding to the first air outlet mode is less than the air outlet speed of the air conditioner corresponding to the second air outlet mode. Based on this, when the recognition result is that the first target is a human body, it can be considered that there is a human body in the range where the distance between the air conditioner and the air conditioner in the action space of the air conditioner is less than or equal to the preset distance, and the air conditioner can be controlled to turn on the first air outlet mode. If the recognition result is that there is no human body (that is, the above-mentioned interference exists), it can be considered that there is no human body in the range where the distance between the air conditioner and the air conditioner in the action space of the air conditioner is less than or equal to the preset distance, and the air conditioner can be controlled to turn on the second air outlet mode; wherein, the air outlet speed of the air conditioner corresponding to the first air outlet mode is less than the air outlet speed of the air conditioner corresponding to the second air outlet mode, and the heat exchange amount output by the air conditioner corresponding to the first air outlet mode is less than the heat exchange amount output by the air conditioner corresponding to the second air outlet mode.

[0152] Based on this, within the target duration, the presence or absence of motion targets in the space is cyclically recognized according to the above steps S011 to S013. Based on the recognition results of multiple recognitions within the target duration, without the need to rely on other means, the device can autonomously learn the relevant information about the location of the interference objects with fixed positions to ensure the accuracy of radar human body detection.

[0153] Furthermore, in this embodiment, the motion target recognition process further includes: while performing the step of increasing the statistical count corresponding to the target sub-region by one, associating the target sub-region with the second signal feature value; wherein, at the start of the target duration timing, none of the sub-regions are associated with the second signal feature value. Based on this, step S02 includes:

[0154] Step S021, determining the target signal value corresponding to the sub-region according to a plurality of the second signal feature values associated with the sub-region;

[0155] In this embodiment, the average value of all the second signal feature values associated with the sub-region is used as the target signal value here. In other embodiments, the median or minimum value, etc. of all the second signal feature values associated with the sub-region can also be used as the target signal value here.

[0156] Step S022, determine the deviation amount between each of the second signal eigenvalues associated with the sub-region and the target signal value;

[0157] Specifically, the deviation amount here refers to the total value of the difference between each second signal eigenvalue and the target signal value.

[0158] Step S023, correct the current statistical count of the sub-region according to a number of the deviation amounts to obtain the target count of the sub-region;

[0159] If the magnitudes of a number of deviation amounts are different, the corresponding correction values of the statistical count are different. The correction value is specifically greater than or equal to 0 times, and the difference between the statistical count and the correction value can be used as the target count.

[0160] Specifically, in this embodiment, determine the deviation amounts greater than or equal to a preset deviation threshold among a number of the deviation amounts as target deviation amounts; determine the correction count according to the number of the target deviation amounts; correct the current statistical count of the sub-region according to the correction count. In this embodiment, the number of target deviation amounts can be the same as the value of the correction count. For example, if there are 2 target deviation amounts, the correction count is 2 times. In other embodiments, the number of target deviation amounts may not be the same as the value of the correction count, and the ratio of the number of target deviation amounts to a preset number can be used as the correction count. For example, if the preset number is 2, when the number of target deviation amounts is 2, the correction count is 1 time, and when the number of target deviation amounts is 4, the correction count is 2 times. For example, all the second signal eigenvalues associated with a certain sub-region include N1, N2, and N3, then N0 = (N1 + N2 + N3) / 3 can be used as the target signal value. Based on this, all the deviation amounts corresponding to the sub-region can include ∣N1 - N0∣, ∣N2 - N0∣, ∣N3 - N0∣. The preset deviation threshold can be M, ∣N1 - N0∣ is greater than M, and ∣N2 - N0∣ and ∣N3 - N0∣ are both less than M, the correction count can be 1 time, and ∣N1 - N0∣, ∣N2 - N0∣, and ∣N3 - N0∣ are all less than M, the correction count can be 2 times.

[0161] In addition, in other embodiments, the mean value of a number of deviation amounts can also be calculated, compare the mean value with a preset deviation amount, and the correction count can be determined according to the magnitude relationship or quantity relationship between the mean value of the deviation amounts and the preset deviation amount. For example, if the mean value of the deviation amounts is greater than the preset deviation amount, the correction count is 1 time.

[0162] Step S024, determine the target frequency information corresponding to the sub-region according to the target count of the sub-region.

[0163] For example, the target number of times corresponding to the first sub-region, the second sub-region, and the third sub-region are 8 times, 2 times, and 3 times respectively, and the total number of times the motion target recognition process is executed within the target duration is 20 times. Based on this, 8 times can be used as the target frequency information corresponding to the first sub-region, or 8 / 20 can be used as the target frequency information corresponding to the first sub-region; 2 times can be used as the target frequency information corresponding to the second sub-region, or 2 / 20 can be used as the target frequency information corresponding to the second sub-region; 3 times can be used as the target frequency information corresponding to the third sub-region, or 3 / 20 can be used as the target frequency information corresponding to the third sub-region.

[0164] Since the human body can move freely in space, there will be obvious differences in the signal amplitude and signal frequency band of the signal reflected back received by the radar compared to the signal amplitude and signal frequency band of the reflected signal formed by an object with a relatively fixed position at other locations in the radar. Based on this, in this embodiment, by performing the above steps S021 to S023 to correct the statistical number corresponding to each sub-region, it can be ensured that the determined target frequency information can accurately reflect the position of the interference object in the space, so as to accurately identify whether the moving target is a human body based on the position of the interference object. Among them, since the signal amplitude of the reflected signal corresponding to the human body is greater than the signal amplitude of the reflected signal of an object with a relatively fixed position at other locations, based on this, by correcting the statistical number corresponding to the sub-region based on the number of target deviation amounts greater than or equal to the preset deviation threshold, it can be ensured that the target frequency information obtained can accurately reflect the position of the interference object in the space, so as to accurately identify whether the moving target is a human body based on the position of the interference object.

[0165] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a target recognition program is stored. When the target recognition program is executed by a processor, it implements the relevant steps of any one of the above target recognition methods.

[0166] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to this process, method, article or system. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, article or system including that element.

[0167] The serial numbers of the above embodiments of the present invention are only for description and do not represent the merits of the embodiments.

[0168] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0169] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A target recognition method based on radar, characterized in that, The target recognition method includes the following steps: Obtain a first position parameter and a first signal feature value; the first position parameter characterizes the positional relationship between a first target and the radar, and the first signal feature value is the signal feature value of the radar detection signal corresponding to the first target; Determine a first signal recognition threshold of the radar according to the first position parameter; different first position parameters correspond to different first signal recognition thresholds; Determine whether the first target is a moving target according to the first signal feature value and the first signal recognition threshold, where the moving target includes a human body; The step of obtaining the first position parameter includes: Obtain the distance between the first target and the radar, and / or obtain the direction of the first target relative to the radar, where the first position parameter includes the distance and / or the direction; Wherein, the first signal recognition threshold increases as the distance decreases; and / or, the first signal recognition threshold increases as the target angle corresponding to the direction decreases, where the target angle is the angle between the direction and a set direction, and the detection signal emitted by the radar has the maximum intensity in the set direction.

2. The target recognition method according to claim 1, wherein The first position parameter includes the distance and the direction, and the step of determining the first signal recognition threshold of the radar according to the first position parameter includes: Determine the preset distance interval where the distance is located, and determine the preset angle interval where the target angle is located; Based on a preset mapping relationship, determine the preset signal threshold corresponding to the preset distance interval and the preset angle interval, and the first signal recognition threshold is the preset signal threshold; the preset mapping relationship is the mapping relationship between the preset distance interval, the preset angle interval and the preset signal threshold set in advance; In the preset mapping relationship, the smaller the distance value of the preset distance interval, the larger the corresponding preset signal threshold, and the smaller the angle value of the preset angle interval, the larger the corresponding preset signal threshold.

3. The object recognition method according to claim 2, wherein The step of obtaining the first position parameter and the first signal feature value includes: Receive the reflected signal corresponding to the first target, and the radar detection signal is the reflected signal; wherein, the reflected signal is formed by the first target reflecting the detection signal emitted by the radar; Determine the first position parameter and the first signal feature value according to the reflected signal.

4. The target recognition method according to claim 1, characterized in that, The first signal feature value includes signal intensity, and the first signal recognition threshold includes a signal intensity threshold. The step of determining whether the first target is a moving target according to the first signal feature value and the first signal recognition threshold includes: When the signal intensity is greater than the signal intensity threshold, determine that the first target is a moving target; When the signal intensity is less than or equal to the signal intensity threshold, determine that the first target is a non-moving target.

5. The object recognition method according to claim 1, characterized in that, After the step of determining whether the first target is a moving target according to the first signal feature value and the first signal recognition threshold, it further includes: When the first target is a moving target, obtain a first target area where interference objects are located within the detection range of the radar, where the interference objects are objects whose movement range is restricted within the first target area; If the first target is located outside the first target area, determine that the first target is a human body; If the first target is located within the first target area, determine that the first target is the interference object.

6. The target recognition method according to claim 5, characterized in that, The detection range is divided into multiple sub-areas, and the first target area is one of the multiple sub-areas. The step of obtaining the first target area where interference objects are located within the detection range of the radar includes: Obtain target frequency information corresponding to each of the sub-areas; the target frequency information is the frequency information of the occurrence of moving targets in the corresponding sub-area within a target duration; Among the multiple sub-areas, determine the sub-area that meets the combined preset conditions as the first target area; Wherein, the preset condition is that the target frequency information corresponding to the sub-area is greater than or equal to a set frequency threshold.

7. The target recognition method according to claim 6, characterized in that, Each of the sub-areas has a corresponding statistical count, and the detection process of the target frequency information is as follows: Within the target duration, repeatedly execute the moving target recognition process; After the target duration ends, determine the target frequency information corresponding to the sub-area according to the current statistical count of the sub-area; Wherein, the moving target recognition process includes: Obtain a second position parameter and a second signal feature value, where the second target is the target currently detected by the radar; the second position parameter characterizes the positional relationship between the second target and the radar, and the second signal feature value is the signal feature value of the radar detection signal corresponding to the second target; Determine a second signal recognition threshold of the radar according to the second position parameter; Determine whether the second target is a moving target according to the second signal feature value and the second signal recognition threshold; If the second target is a moving target, determine the sub-area where the second target is located as the second target area, and increase the statistical count corresponding to the second target area by one.

8. The object recognition method according to claim 7, wherein The moving target recognition process further includes: while executing the step of increasing the statistical count corresponding to the target sub-area by one, associate the target sub-area with the second signal feature value; The step of determining the target frequency information corresponding to the sub-area according to the current statistical count of the sub-area includes: Determine the target signal value corresponding to the sub-area according to several second signal feature values associated with the sub-area; Determine the deviation amount between each of the second signal feature values associated with the sub-area and the target signal value; Correct the current statistical count of the sub-area according to several of the deviation amounts to obtain the target count of the sub-area; Determine the target frequency information corresponding to the sub-area according to the target count of the sub-area.

9. The target recognition method according to claim 8, wherein, The step of correcting the current statistical count of the sub-area according to several of the deviation amounts includes: Determine the deviation amounts greater than or equal to a preset deviation threshold among several of the deviation amounts as target deviation amounts; Determine the correction times according to the number of the target deviation amounts; Modify the current statistical count of the sub-region according to the number of corrections.

10. The target recognition method according to any one of claims 1 to 9, characterized in that, After the step of determining whether the first target is a moving target according to the first signal eigenvalue and the first signal recognition threshold, the method further includes: When the first target is a human body, control the air conditioner to operate in a first air outlet mode; When the first target is a target other than a human body, control the air conditioner to operate in a second air outlet mode; Wherein, the air outlet speed of the air conditioner corresponding to the first air outlet mode is less than the air outlet speed of the air conditioner corresponding to the second air outlet mode.

11. An air conditioner, characterized in that, The air conditioner includes: A radar; A control device, the control device is connected to the radar, the control device includes: a memory, a processor, and a target recognition program stored on the memory and executable on the processor, and when the target recognition program is executed by the processor, it realizes the steps of the target recognition method as described in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that, A target recognition program is stored on the computer-readable storage medium, and when the target recognition program is executed by a processor, it realizes the steps of the target recognition method as described in any one of claims 1 to 10.

Images