Object identification method and system based on single-feedback millimeter wave radar

Abstract

The invention discloses an object identification method and system based on a single-feedback millimeter-wave radar. The method comprises the following steps: acquiring historical moment data and current moment data acquired by the single-feedback millimeter-wave radar; according to the previous moment time and the previous moment distance corresponding to an existing object in the historical moment data and the current moment time and the current moment distance corresponding to a to-be-identified object in the current moment data, calculating a comparison speed relative to the existing object; and comparing the comparison speed with a first comparison threshold value, if a condition is satisfied, obtaining a first object identification result, otherwise, comparing the current moment distance with a second comparison threshold value, and obtaining a second object identification result according to the comparison result. According to the invention, only the single-feedback millimeter wave radar is adopted to identify and distinguish a plurality of different moving human bodies or objects, the cost is low, the accuracy is high, and the method has a wide application prospect in various application scenes.

Description

Technical Field

[0001] The present invention relates to the field of radar signal processing technology, and in particular to an object recognition method, system, terminal and computer-readable storage medium based on a single-feedback millimeter-wave radar. Background Art

[0002] With the continuous advancement and development of smart home technology, the recognition and perception function of the human body has become increasingly important. Various sensors and cameras are used to detect and identify the presence and behavior of family members, thereby achieving a more intelligent and personalized home environment. Through human body recognition and perception, the smart home system can automatically adjust the lighting, temperature, music, etc. to adapt to the preferences and needs of different users. In addition, human body recognition and perception can also improve home security. Through real-time monitoring and abnormal behavior detection, potential security threats can be discovered in time and corresponding measures can be taken. In short, human body recognition and perception are more and more widely used in smart homes, bringing users a more convenient and comfortable life experience. In fact, the so-called human body recognition and perception is object recognition and perception. In the existing technology, multi-sensor collaboration is usually required to achieve recognition and perception of multiple different moving human bodies or objects, which is costly and has a low recognition and perception accuracy.

[0003] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0004] The main purpose of the present invention is to provide an object recognition method, system, terminal and computer-readable storage medium based on a single-feedback millimeter-wave radar, aiming to solve the problem that the prior art requires the collaboration of multiple sensors to recognize and perceive multiple different human bodies or objects, which is costly and has low recognition and perception accuracy.

[0005] To achieve the above-mentioned object of the invention, the present invention provides an object recognition method based on a single feedback millimeter wave radar, and the object recognition method based on a single feedback millimeter wave radar comprises:

[0006] Acquire historical time data and current time data collected by the single feedback millimeter wave radar, wherein the historical time data includes the time, distance and energy value corresponding to the existing object, and the current time data includes the time, distance and energy value corresponding to the object to be identified;

[0007] Calculate the comparative speed relative to the existing object according to the previous time and distance at the previous time corresponding to the existing object in the historical time data, and the current time and distance at the current time corresponding to the object to be identified in the current time data;

[0008] The comparison speed is compared with a first comparison threshold, and if the condition is met, a first object recognition result is obtained; otherwise, the current moment distance is compared with a second comparison threshold, and a second object recognition result is obtained according to the comparison result.

[0009] Optionally, the acquiring of historical moment data and current moment data collected by the single-feedback millimeter-wave radar specifically includes:

[0010] Acquire the stored historical moment data corresponding to the existing object collected by the single feedback millimeter wave radar, wherein the historical moment data includes the historical moment time, the historical moment distance and the historical moment energy value;

[0011] The historical time corresponding to the existing object is recorded as T n-1 ,T n-2 ,…,T n-N+1 ,T n-N , the historical time distance corresponding to the existing object is recorded as S n-1 ,S n-2 ,…,S n-N+1 ,S n-N , the energy value of the existing object at the historical moment is recorded as E n-1 ,E n-2 ,…,E n-N+1 ,E n-N ;

[0012] Acquire current moment data corresponding to the object to be identified collected in real time by the single-feedback millimeter-wave radar, wherein the current moment data includes current moment time, current moment distance and current moment energy value;

[0013] The current time corresponding to the object to be identified is recorded as T n , the current distance of the object to be identified is recorded as S n , the energy value corresponding to the object to be identified at the current moment is recorded as E n ;

[0014] Wherein, n represents the current moment, n-1 represents the last moment closest to the current moment, N depends on the number of times the historical moment data corresponding to the existing object is stored, N≤M, and M is the number threshold.

[0015] Optionally, the calculating the comparative speed relative to the existing object according to the previous moment time and the previous moment distance corresponding to the existing object in the historical moment data, and the current moment time and the current moment distance corresponding to the object to be identified in the current moment data, specifically includes:

[0016] According to the previous moment time and the previous moment distance corresponding to the existing object in the historical moment data, and the current moment time and the current moment distance corresponding to the object to be identified in the current moment data, the comparative speed relative to the existing object is calculated:

[0017]

[0018] Wherein, V is the comparative speed relative to the existing object, S n-1 is the distance of the existing object at the previous moment, T n-1 The previous time corresponding to the existing object.

[0019] Optionally, the first comparison threshold includes the current energy value and the set energy threshold corresponding to the object to be identified, and the second comparison threshold includes the average distance of the historical moments corresponding to the existing object;

[0020] The comparing speed with the first comparison threshold, if the condition is met, obtaining the first object recognition result, otherwise comparing the current time distance with the second comparison threshold, and obtaining the second object recognition result according to the comparison result, specifically includes:

[0021] Comparing the comparison speed with the energy value of the object to be identified at the current moment;

[0022] If at least one of the comparison speeds is smaller than the energy value corresponding to the object to be identified at the current moment, the object to be identified is identified as the object corresponding to the smallest comparison speed among the existing objects;

[0023] otherwise comparing the comparison speed with a set energy threshold;

[0024] If the comparison speeds are all greater than the set energy threshold, the object to be identified is identified as a new object;

[0025] Otherwise, the average value of the historical distances corresponding to the existing objects is calculated to obtain the average value of the historical distances corresponding to the existing objects, and the current distance corresponding to the object to be identified is compared with the average value of the historical distances corresponding to the existing objects, and the object to be identified is the object corresponding to the average value of the historical distances closest to the current distance among the existing objects;

[0026] Among them, the first object recognition result includes that the object to be recognized is the object corresponding to the minimum comparison speed among the existing objects or the object to be recognized is a new object; the second object recognition result includes that the object to be recognized is the object corresponding to the average value of the historical moment distance that is closest to the current moment among the existing objects.

[0027] Optionally, if the comparison speeds are all greater than the set energy threshold, the object to be identified is identified as a new object, and then the method further includes:

[0028] Store the current time data corresponding to the object to be identified as the current time data corresponding to the new object, denoted as T' n ,S' n ,E' n , where T' n =T n ;S' n =S n ; E' n =E n .

[0029] Optionally, calculating the average value of the historical moment distances corresponding to the existing objects to obtain the average value of the historical moment distances corresponding to the existing objects specifically includes:

[0030] Calculate the average value of the historical time distances corresponding to the existing objects to obtain the average value of the historical time distances corresponding to the existing objects:

[0031]

[0032] Among them, S 均 Represents the average historical distance of the existing object, S n-N Indicates the distance at the nNth moment corresponding to the existing object.

[0033] Optionally, the single-feedback millimeter-wave radar returns data corresponding to only one object with the highest energy value at a time;

[0034] The comparison speed is compared with a first comparison threshold, and if a condition is satisfied, a first object recognition result is obtained; otherwise, the current moment distance is compared with a second comparison threshold, and a second object recognition result is obtained according to the comparison result, and then the following further includes:

[0035] When the object to be identified is identified as a new object, the data of all existing objects are completed;

[0036] When the object to be identified is identified as one of the existing objects, completing the data of all other existing objects except the object to be identified;

[0037] When the number of consecutive times of completing the data of an existing object exceeds a set value, it is determined that the existing object has disappeared, and all the data of the existing object is cleared.

[0038] To achieve the above-mentioned object of the invention, the present invention further provides an object recognition system based on a single feedback millimeter wave radar, the object recognition system based on a single feedback millimeter wave radar comprising:

[0039] Data acquisition module: used to acquire historical moment data and current moment data collected by the single feedback millimeter wave radar, wherein the historical moment data includes the time, distance and energy value corresponding to the existing object, and the current moment data includes the time, distance and energy value corresponding to the object to be identified;

[0040] A comparison speed calculation module: used to calculate the comparison speed relative to the existing object according to the previous time and the previous distance corresponding to the existing object in the historical time data, and the current time and the current distance corresponding to the object to be identified in the current time data;

[0041] Object recognition module: used to compare the comparison speed with a first comparison threshold, and if the condition is met, obtain a first object recognition result; otherwise, compare the current moment distance with a second comparison threshold, and obtain a second object recognition result based on the comparison result.

[0042] To achieve the above-mentioned purpose of the invention, the present invention also provides a terminal, which includes: a memory, a processor, and an object recognition program based on a single feedback millimeter wave radar stored in the memory and executable on the processor, wherein the object recognition program based on a single feedback millimeter wave radar implements the steps of the object recognition method based on a single feedback millimeter wave radar as described above when executed by the processor.

[0043] To achieve the above-mentioned purpose of the invention, the present invention also provides a computer-readable storage medium, which stores an object recognition program based on a single feedback millimeter-wave radar. When the object recognition program based on a single feedback millimeter-wave radar is executed by a processor, the steps of the object recognition method based on a single feedback millimeter-wave radar as described above are implemented.

[0044] In the present invention, historical moment data and current moment data collected by a single feedback millimeter wave radar are obtained, wherein the historical moment data includes the time, distance and energy value corresponding to the existing object, and the current moment data includes the time, distance and energy value corresponding to the object to be identified; according to the previous moment time and previous moment distance corresponding to the existing object in the historical moment data, and the current moment time and current moment distance corresponding to the object to be identified in the current moment data, the comparison speed relative to the existing object is calculated; the comparison speed is compared with the first comparison threshold, and if the condition is met, the first object recognition result is obtained, otherwise the current moment distance is compared with the second comparison threshold, and the second object recognition result is obtained according to the comparison result. The present invention only uses a single feedback millimeter wave radar to identify and distinguish multiple different moving human bodies or objects, with low cost and high accuracy, and has a wide range of application prospects in various application scenarios, especially suitable for smart home systems, through human body recognition perception, to achieve a more intelligent and personalized home environment, and can also improve family security, timely discover potential security threats and take corresponding measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a preferred embodiment of the object recognition method based on single feedback millimeter wave radar of the present invention;

[0046] Figure 2 is another flow chart of a preferred embodiment of the object recognition method based on single feedback millimeter wave radar of the present invention;

[0047] Figure 3 It is a structural diagram of a preferred embodiment of an object recognition system based on a single feedback millimeter wave radar of the present invention;

[0048] Figure 4 It is a structural diagram of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. 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.

[0050] With the continuous advancement and development of smart home technology, the recognition and perception function of the human body has become increasingly important. Various sensors and cameras are used to detect and identify the presence and behavior of family members, thereby achieving a more intelligent and personalized home environment. Through human body recognition and perception, the smart home system can automatically adjust the lighting, temperature, music, etc. to adapt to the preferences and needs of different users. In addition, human body recognition and perception can also improve home security. Through real-time monitoring and abnormal behavior detection, potential security threats can be discovered in time and corresponding measures can be taken. In short, human body recognition and perception are more and more widely used in smart homes, bringing users a more convenient and comfortable life experience. In fact, the so-called human body recognition and perception is object recognition and perception. In the existing technology, multi-sensor collaboration is usually required to achieve recognition and perception of multiple different moving human bodies or objects, which is costly and has a low recognition and perception accuracy.

[0051] In order to solve the above technical problems, the present invention provides an object recognition method based on a single feedback millimeter wave radar, obtaining historical moment data and current moment data collected by the single feedback millimeter wave radar, wherein the historical moment data includes the time, distance and energy value corresponding to the existing object, and the current moment data includes the time, distance and energy value corresponding to the object to be recognized; according to the previous moment time and previous moment distance corresponding to the existing object in the historical moment data, and the current moment time and current moment distance corresponding to the object to be recognized in the current moment data, calculate the comparison speed relative to the existing object; compare the comparison speed with the first comparison threshold, if the condition is met, then obtain the first object recognition result, otherwise compare the current moment distance with the second comparison threshold, and obtain the second object recognition result according to the comparison result. The present invention only uses a single feedback millimeter wave radar to identify and distinguish multiple different moving human bodies or objects, with low cost and high accuracy, and has a wide range of application prospects in various application scenarios, especially suitable for smart home systems, through human body recognition perception, to achieve a more intelligent and personalized home environment, and can also improve family security, timely discover potential security threats and take corresponding measures.

[0052] The application content is further explained below through the description of embodiments in conjunction with the accompanying drawings.

[0053] A preferred embodiment of the object recognition method based on single feedback millimeter wave radar of the present invention is as follows: Figure 1 and 2 As shown, specifically including:

[0054] S1: Acquire historical moment data and current moment data collected by a single feedback millimeter wave radar, wherein the historical moment data includes the time, distance and energy value corresponding to an existing object, and the current moment data includes the time, distance and energy value corresponding to an object to be identified.

[0055] In an implementation of this embodiment, the acquisition of historical moment data and current moment data collected by the single feedback millimeter wave radar, wherein the historical moment data includes the time, distance and energy value corresponding to the existing object, and the current moment data includes the time, distance and energy value corresponding to the object to be identified, specifically includes:

[0056] Acquire the stored (i.e., recorded) historical moment data corresponding to the existing object collected by the single-feedback millimeter-wave radar, wherein the historical moment data includes the historical moment time, the historical moment distance, and the historical moment energy value;

[0057] The historical time corresponding to the existing object is recorded as T n-1 ,T n-2 ,…,T n-N+1 ,T n-N , the historical time distance corresponding to the existing object is recorded as S n-1 ,S n-2 ,…,S n-N+1 ,S n-N , the energy value of the existing object at the historical moment is recorded as E n-1 ,E n-2 ,…,E n-N+1 ,E n-N ;

[0058] Acquire the current moment data corresponding to the object to be identified collected in real time by the single feedback millimeter wave radar, wherein the current moment data (i.e., new data) includes the current moment time, the current moment distance, and the current moment energy value;

[0059] The current time corresponding to the object to be identified is recorded as T n , the current distance of the object to be identified is recorded as S n , the energy value corresponding to the object to be identified at the current moment is recorded as E n ;

[0060] Among them, n represents the current moment, n-1 represents the previous moment closest to the current moment, N depends on the number of times the historical moment data corresponding to the existing object is stored, N≤M, M is the number threshold (the number threshold is 5 in this embodiment), when the number of times the historical moment data of the existing object is stored is less than M, N is the number of times the historical moment data of the existing object is stored; when the number of times the historical moment data of the existing object is stored is not less than M, N=M.

[0061] It should be noted that the existing object may be one or more. When the existing objects include object a and object b, the historical time of object a is recorded as Tan-1 ,Ta n-2 ,…,Ta n-N+1 ,Ta n-N , the historical distance of object a is recorded as Sa n-1 ,Sa n-2 ,…,Sa n-N+1 ,Sa n-N , the energy value of object a at the historical moment is recorded as Ea n-1 ,Ea n-2 ,…,Ea n-N+1 ,Ea n-N ; Record the historical time of object b as Tb n-1 ,Tb n-2 ,…,Tb n-N+1 ,Tb n-N , the historical distance of object b is recorded as Sb n-1 ,Sb n-2 ,…,Sb n-N+1 ,Sb n-N , the energy value of object b at the historical moment is recorded as Eb n-1 ,Eb n-2 ,…,Eb n-N+1 ,Eb n-N .

[0062] Specifically, the single-feedback millimeter-wave radar collects data every 1 second, and the subscript is the current global record mark. Each time data is collected, this mark will increase by 1. The number threshold M is set to 5, and the data recorded / stored for the previous N times of an object a is obtained. N depends on the number of unit times that the object is found to exist, that is, the corresponding number of recorded / stored data. For example, if the object has only the most recent 3 recorded / stored data, then N = 3. When N>5, N is 5, and the time of the previous N data is Ta n-1 ,Ta n-2 ,…,Ta n-N+1 ,Ta n-N , where Ta n-1 is the time of the most recent collection, Ta n-2 is the time of the most recent previous collection, and so on; the distance value collected at the corresponding time is Sa n-1 ,Sa n-2 ,…,Sa n-N+1 ,Sa n-N , the energy value is Ea n-1 ,Ea n-2 ,…,Ea n-N+1 ,Ea n-N , if the system records the existence of object b, it is recorded as Tb, Sb, Eb, and the same applies to other objects, which can include any number of different objects. n, get a new set of data S n ,E n .

[0063] In addition, regarding the single-feedback millimeter-wave radar, the single-feedback millimeter-wave radar will only return the data of a micro-movement or moving object with the highest energy value at a time. The energy value = coefficient × object projection area × object projection change distance per unit time. The final result should be in the range of 0-100, where the object projection area represents the shadow area of ​​the dynamic object projected on the millimeter-wave radar (the object photographed by the single-feedback millimeter-wave radar is similar to the camera photography, but it is more blurred and only has the outline); the object projection change distance per unit time means that within a unit time (generally 1 second), the single-feedback millimeter-wave radar will capture multiple data, and this distance is the offset change of multiple projections; the coefficient is generally related to the optimal distance for identification. For example, the optimal distance for watching TV is 3m, so the optimal distance for identification should be located at 3m. It needs to be adjusted according to actual needs and hardware structure, and there is no special requirement. The data includes: the energy value corresponding to the object and the distance of the object (in cm), where the distance of the object represents the distance from the object to the single-feedback millimeter-wave radar.

[0064] S2: Calculate the comparative speed relative to the existing object according to the previous time and distance corresponding to the existing object in the historical time data, and the current time and distance corresponding to the object to be identified in the current time data.

[0065] In an implementation of this embodiment, the calculating of the comparative speed relative to the existing object according to the previous time and the previous distance corresponding to the existing object in the historical time data, and the current time and the current distance corresponding to the object to be identified in the current time data, specifically includes:

[0066] According to the previous moment time and the previous moment distance corresponding to the existing object in the historical moment data, and the current moment time and the current moment distance corresponding to the object to be identified in the current moment data, the comparative speed relative to the existing object is calculated:

[0067]

[0068] Wherein, V is the comparative speed relative to the existing object, S n-1 is the distance of the existing object at the previous moment, T n-1 The previous time corresponding to the existing object.

[0069] It should be noted that when the existing objects include object a and object b, the comparison speed relative to object a is:

[0070]

[0071] Among them, Va is the relative speed relative to object a, Sa n-1 is the distance of object a at the last moment, Ta n-1 is the last moment time of object a;

[0072] Comparative speed relative to object b:

[0073]

[0074] Where Vb is the relative speed of object b, Sb n-1 is the distance of object b at the last moment, Tb n-1 is the last moment time of object b.

[0075] Specifically, because energy is actually equal to the distance moved per unit time multiplied by the projected area, that is, the speed at that time multiplied by the projected area, and the projected areas of different human bodies or objects are not much different, that is, the impact of the projected area on energy is very small, the present invention directly uses speed for comparison to improve efficiency.

[0076] S3: Compare the comparison speed with a first comparison threshold, and if the condition is met, obtain a first object recognition result; otherwise, compare the current distance with a second comparison threshold, and obtain a second object recognition result according to the comparison result.

[0077] In an implementation of this embodiment, the first comparison threshold includes the current energy value and the set energy threshold corresponding to the object to be identified, and the second comparison threshold includes the average distance of the historical time corresponding to the existing object;

[0078] The comparing speed with the first comparison threshold, if the condition is met, obtaining the first object recognition result, otherwise comparing the current time distance with the second comparison threshold, and obtaining the second object recognition result according to the comparison result, specifically includes:

[0079] Comparing the comparison speed with the energy value of the object to be identified at the current moment;

[0080] If at least one of the comparison speeds is smaller than the energy value corresponding to the object to be identified at the current moment, the object to be identified is identified as the object corresponding to the smallest comparison speed among the existing objects;

[0081] otherwise comparing the comparison speed with a set energy threshold;

[0082] If the comparison speeds are all greater than the set energy threshold (the set energy threshold is 100 in this embodiment), the object to be identified is identified as a new object;

[0083] Otherwise, the average value of the historical distances corresponding to the existing objects is calculated to obtain the average value of the historical distances corresponding to the existing objects, and the current distance corresponding to the object to be identified is compared with the average value of the historical distances corresponding to the existing objects, and the object to be identified is the object corresponding to the average value of the historical distances closest to the current distance among the existing objects;

[0084] Among them, the first object recognition result includes that the object to be recognized is the object corresponding to the minimum comparison speed among the existing objects or the object to be recognized is a new object; the second object recognition result includes that the object to be recognized is the object corresponding to the average value of the historical moment distance that is closest to the current moment among the existing objects.

[0085] Specifically, taking objects a and b as examples, if one of Va and Vb is less than E n , it is considered that this set of new data (i.e. the data at the current moment) corresponds to one of the existing objects. At this time, the corresponding object is considered to be the object corresponding to the smallest comparison speed V value, otherwise continue with the following steps.

[0086] If Va and Vb are both greater than 100, then this set of new data is considered to correspond to a new object, recorded as object c, and the corresponding Tc is generated n ,Sc n ,Ec n Store in the system for subsequent calculations, otherwise continue with the next step.

[0087] Calculate the average distance If N<5, the actual number of times is used to take the average value. n Closer to Sa 均 , then the object corresponding to this set of new data is considered to be the same object as a, otherwise it is considered to be the same object as b.

[0088] It should be noted that energy value = coefficient × object projection area × distance changed per unit time. Since the coefficient and the object projection area are basically unchanged, the influence is very small and can be ignored. Therefore, the energy value is approximately equal to the distance changed per unit time (that is, speed). Therefore, the speed and energy value can be directly compared to improve efficiency.

[0089] In an implementation of this embodiment, if the comparison speeds are all greater than the set energy threshold, the object to be identified is identified as a new object, and then the method further includes:

[0090] Store the current time data corresponding to the object to be identified as the current time data corresponding to the new object, denoted as T'n ,S' n ,E' n , where T' n =T n ;S' n =S n ; E' n =E n .

[0091] It should be noted that here T' n ,S' n ,E' n That corresponds to the Tc in the previous text n ,Sc n ,Ec n If the object to be identified is one of the existing objects (such as object a), the current moment data stored is the current moment data corresponding to object a, Ta n =T n ;Sa n =S n ;Ea n =E n .

[0092] In an implementation of this embodiment, calculating the average value of the historical moment distances corresponding to the existing objects to obtain the average value of the historical moment distances corresponding to the existing objects specifically includes:

[0093] Calculate the average value of the historical time distances corresponding to the existing objects to obtain the average value of the historical time distances corresponding to the existing objects:

[0094]

[0095] Among them, S 均 Represents the average historical distance of the existing object, S n-N Indicates the distance at the nNth moment corresponding to the existing object.

[0096] Specifically, taking objects a and b as examples, the average distance of the historical moments corresponding to object a is:

[0097]

[0098] Among them, Sa 均 Represents the average distance of object a at the historical moment, Sa n-N Indicates the distance of object a at the nNth moment;

[0099] The average distance of object b at the historical moment:

[0100]

[0101] Among them, Sb 均 Represents the average distance of object b at historical moments, Sb n-N Indicates the distance of object b at the nNth moment.

[0102] In one implementation of this embodiment, the single-feedback millimeter-wave radar returns data corresponding to only one object with the highest energy value at a time;

[0103] The comparison speed is compared with a first comparison threshold, and if a condition is satisfied, a first object recognition result is obtained; otherwise, the current moment distance is compared with a second comparison threshold, and a second object recognition result is obtained according to the comparison result, and then the following further includes:

[0104] When the object to be identified is identified as a new object, the data of all existing objects are completed;

[0105] When the object to be identified is identified as one of the existing objects, completing the data of all other existing objects except the object to be identified;

[0106] When the number of consecutive times that the existing object completes the data exceeds a set value (the set value is 5 in this embodiment), it is determined that the existing object has disappeared, and all the data of the existing object is cleared.

[0107] Specifically, taking object a and object b as examples, when T n If the object identified at the moment is a new object, then all the data of object a and object b need to be completed, that is, Ta n =T n , Sa n =Sa n-1 , Ea n =Ea n-1 ;Tb n =T n , Sb n =Sb n-1 , Eb n =Eb n-1 , if T n If the object identified at the moment is object a, only the data of object b is completed, otherwise only the data of object a is completed. In addition, the setting value is 5. If the data of a certain object is completed for the first 4 times, when it is not recognized and needs to be completed for the fifth time, it is considered that the object has disappeared, and all the recorded data of this object are removed.

[0108] For human recognition perception in smart home systems, people's movements in front of the TV have certain tendencies and limits. For example, people don't move quickly when watching TV normally, and basically keep a certain distance. If other people pass by or join, the distance will change rapidly, so it can be judged as a new object. Completion and disappearance rules: Because the single-feedback millimeter-wave radar will only return data of an object with the highest energy, if person A moves repeatedly and another person B is relatively inactive, only A's data may be returned. Therefore, it is necessary to automatically complete B's data. When B is not detected for many times, it is considered that he has left.

[0109] In an implementation of this embodiment, the object recognition method based on the single feedback millimeter wave radar further includes:

[0110] Distance reminder: When the distance of an object is less than the preset distance threshold, a distance reminder will be given;

[0111] Distance detection: Returns the current distance value of the object.

[0112] To assist in the description, an embodiment of an object recognition method based on a single feedback millimeter wave radar is provided, as follows:

[0113] Embodiment 1:

[0114] The current global record mark (subscript) n is 11. Object a exists, and only three data are recorded / stored, that is, object a only exists for three units of time. Object b exists, and the data recorded before object a and object b (that is, historical moment data) are shown in Table 1:

[0115] Table 1: Data table of object a and object b in Example 1

[0116]

[0117] When a new set of data (i.e. current time data) is obtained: T 11 =11, S 11 =240, E 11 =20, calculation comparison speed At this time, Va>E 11 、Vb>E 11 , so continue with the following judgment.

[0118] At this time, Va and Vb are not both greater than 100 (the set energy threshold), so it is not considered to be a new object and the subsequent judgment continues.

[0119] Calculate the distance average Sa 均 =290; Sb 均 =360, S 11 Closer to Sa 均, so it is considered to be object a.

[0120] Record the current data in Ta 11 , Sa 11 , Ea 11 And according to the automatic completion rules, the data of object b is completed to obtain a new data table, as shown in Table 2:

[0121] Table 2: New data table of object a and object b in Example 1

[0122]

[0123] Embodiment 2:

[0124] The current global record mark (subscript) n is 11, and there are objects a and b. The data previously recorded by objects a and b (i.e., historical moment data) are shown in Table 3:

[0125] Table 3: Data table of object a and object b in Example 2

[0126]

[0127]

[0128] When a new set of data (i.e. current time data) is obtained: T 11 =11, S 11 =140, E 11 =20, calculation comparison speed At this time, Va>E 11 、Vb>E 11 , so continue with the following judgment.

[0129] At this time, Va and Vb are both greater than 100 (the threshold is set to 100), so it is considered to be a new object, and according to the automatic completion rule, the data of object b is completed, and according to the object disappearance rule, object a is deleted to obtain a new data table, as shown in Table 4:

[0130] Table 4: New data table of object a and object b in Example 2

[0131]

[0132] It should be noted that the data tables in Example 1 and Example 2 only present five recorded data (stored historical data), and the data before five times are automatically deleted because the present invention only needs to obtain five historical moment data at most for object identification.

[0133] In addition, based on the above-mentioned object recognition method based on single feedback millimeter wave radar, the present invention also provides an object recognition system based on single feedback millimeter wave radar, wherein a preferred embodiment of the object recognition system based on single feedback millimeter wave radar is as follows: Figure 3 As shown, specifically including:

[0134] Data acquisition module 01: used to acquire historical moment data and current moment data collected by the single feedback millimeter wave radar, wherein the historical moment data includes the time, distance and energy value corresponding to the existing object, and the current moment data includes the time, distance and energy value corresponding to the object to be identified;

[0135] Comparative speed calculation module 02: used to calculate the comparative speed relative to the existing object according to the previous time and distance corresponding to the existing object in the historical time data, and the current time and distance corresponding to the object to be identified in the current time data;

[0136] Object recognition module 03: used to compare the comparison speed with a first comparison threshold, and if the condition is met, obtain a first object recognition result; otherwise, compare the current distance with a second comparison threshold, and obtain a second object recognition result according to the comparison result.

[0137] In addition, based on the above-mentioned object recognition method and system based on single feedback millimeter wave radar, the present invention also provides a terminal accordingly, wherein a preferred embodiment of the terminal is as follows: Figure 4 As shown, it specifically includes a processor 10, a memory 20 and a display 30. Figure 4 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0138] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card) equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as program codes of the storage terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, an object recognition program 40 based on a single feedback millimeter wave radar is stored on the memory 20, and the object recognition program 40 based on a single feedback millimeter wave radar can be executed by the processor 10, thereby realizing the steps of the object recognition method based on a single feedback millimeter wave radar in the present application.

[0139] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 20, such as executing an object recognition program 40 based on a single feedback millimeter wave radar.

[0140] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface.

[0141] In one embodiment, when the processor 10 executes the object recognition program 40 based on the single feedback millimeter wave radar in the memory 20 , the steps of the object recognition method based on the single feedback millimeter wave radar as described above are implemented.

[0142] The present invention also provides a computer-readable storage medium accordingly, wherein the computer-readable storage medium stores an object recognition program based on a single feedback millimeter-wave radar, and when the object recognition program based on a single feedback millimeter-wave radar is executed by a processor, the steps of the object recognition method based on a single feedback millimeter-wave radar as described above are implemented.

[0143] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or terminal including the element.

[0144] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.

[0145] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. An object recognition method based on single feedback millimeter wave radar, characterized in that: The object recognition method based on single feedback millimeter wave radar includes: Acquire historical time data and current time data collected by the single feedback millimeter wave radar, wherein the historical time data includes the time, distance and energy value corresponding to the existing object, and the current time data includes the time, distance and energy value corresponding to the object to be identified; Calculate the comparative speed relative to the existing object according to the previous time and distance at the previous time corresponding to the existing object in the historical time data, and the current time and distance at the current time corresponding to the object to be identified in the current time data; The comparison speed is compared with a first comparison threshold, and if the condition is met, a first object recognition result is obtained; otherwise, the current moment distance is compared with a second comparison threshold, and a second object recognition result is obtained according to the comparison result.

2. The object recognition method based on single feedback millimeter wave radar according to claim 1, characterized in that: The obtaining of historical time data and current time data collected by the single feedback millimeter wave radar specifically includes: Acquire the stored historical moment data corresponding to the existing object collected by the single feedback millimeter wave radar, wherein the historical moment data includes the historical moment time, the historical moment distance and the historical moment energy value; The historical time corresponding to the existing object is recorded as T n-1 ,T n-2 ,…,T n-N+1 ,T n-N , the historical time distance corresponding to the existing object is recorded as S n-1 ,S n-2 ,…,S n-N+1 ,S n-N , the energy value of the existing object at the historical moment is recorded as E n-1 ,E n-2 ,…,E n-N+1 ,E n-N ; Acquire current moment data corresponding to the object to be identified collected in real time by the single-feedback millimeter-wave radar, wherein the current moment data includes current moment time, current moment distance and current moment energy value; The current time corresponding to the object to be identified is recorded as T n , the current distance of the object to be identified is recorded as S n , the energy value corresponding to the object to be identified at the current moment is recorded as E n ; Wherein, n represents the current moment, n-1 represents the last moment closest to the current moment, N depends on the number of times the historical moment data corresponding to the existing object is stored, N≤M, and M is the number threshold.

3. The object recognition method based on single feedback millimeter wave radar according to claim 2, characterized in that: The calculating of the comparison speed relative to the existing object according to the previous time and the previous distance corresponding to the existing object in the historical time data, and the current time and the current distance corresponding to the object to be identified in the current time data, specifically includes: According to the previous moment time and the previous moment distance corresponding to the existing object in the historical moment data, and the current moment time and the current moment distance corresponding to the object to be identified in the current moment data, the comparative speed relative to the existing object is calculated: Wherein, V is the comparative speed relative to the existing object, S n-1 is the distance of the existing object at the previous moment, T n-1 The previous time corresponding to the existing object.

4. The object recognition method based on single feedback millimeter wave radar according to claim 3 is characterized in that: The first comparison threshold includes the current energy value and the set energy threshold corresponding to the object to be identified, and the second comparison threshold includes the average distance of the historical time corresponding to the existing object; The comparing speed with the first comparison threshold, if the condition is met, obtaining the first object recognition result, otherwise comparing the current time distance with the second comparison threshold, and obtaining the second object recognition result according to the comparison result, specifically includes: Comparing the comparison speed with the energy value of the object to be identified at the current moment; If at least one of the comparison speeds is smaller than the energy value corresponding to the object to be identified at the current moment, the object to be identified is identified as the object corresponding to the smallest comparison speed among the existing objects; otherwise comparing the comparison speed with a set energy threshold; If the comparison speeds are all greater than the set energy threshold, the object to be identified is identified as a new object; Otherwise, the average value of the historical distances corresponding to the existing objects is calculated to obtain the average value of the historical distances corresponding to the existing objects, and the current distance corresponding to the object to be identified is compared with the average value of the historical distances corresponding to the existing objects, and the object to be identified is the object corresponding to the average value of the historical distances closest to the current distance among the existing objects; Among them, the first object recognition result includes that the object to be recognized is the object corresponding to the minimum comparison speed among the existing objects or the object to be recognized is a new object; the second object recognition result includes that the object to be recognized is the object corresponding to the average value of the historical moment distance that is closest to the current moment among the existing objects.

5. The object recognition method based on single feedback millimeter wave radar according to claim 4, characterized in that: If the comparison speeds are all greater than the set energy threshold, the object to be identified is identified as a new object, and then the method further includes: Store the current time data corresponding to the object to be identified as the current time data corresponding to the new object, denoted as T' n ,S' n ,E' n , where T' n =T n ;S' n =S n ; E' n =E n .

6. The object recognition method based on single feedback millimeter wave radar according to claim 4 or 5, characterized in that: The calculating the average value of the historical time distances corresponding to the existing objects to obtain the average value of the historical time distances corresponding to the existing objects specifically includes: Calculate the average value of the historical time distances corresponding to the existing objects to obtain the average value of the historical time distances corresponding to the existing objects: Among them, S 均 Represents the average historical distance of the existing object, S n-N Indicates the distance at the nNth moment corresponding to the existing object.

7. The object recognition method based on single feedback millimeter wave radar according to claim 4, characterized in that: The single-feedback millimeter-wave radar only returns data corresponding to an object with the highest energy value at a time; The comparison speed is compared with a first comparison threshold, and if a condition is satisfied, a first object recognition result is obtained; otherwise, the current moment distance is compared with a second comparison threshold, and a second object recognition result is obtained according to the comparison result, and then the following further includes: When the object to be identified is identified as a new object, the data of all existing objects are completed; When the object to be identified is identified as one of the existing objects, completing the data of all other existing objects except the object to be identified; When the number of consecutive times of completing the data of an existing object exceeds a set value, it is determined that the existing object has disappeared, and all the data of the existing object is cleared.

8. An object recognition system based on single feedback millimeter wave radar, characterized in that: The object recognition system based on single feedback millimeter wave radar includes: Data acquisition module: used to acquire historical moment data and current moment data collected by the single feedback millimeter wave radar, wherein the historical moment data includes the time, distance and energy value corresponding to the existing object, and the current moment data includes the time, distance and energy value corresponding to the object to be identified; A comparison speed calculation module: used to calculate the comparison speed relative to the existing object according to the previous time and the previous distance corresponding to the existing object in the historical time data, and the current time and the current distance corresponding to the object to be identified in the current time data; Object recognition module: used to compare the comparison speed with a first comparison threshold, and if the condition is met, obtain a first object recognition result; otherwise, compare the current moment distance with a second comparison threshold, and obtain a second object recognition result based on the comparison result.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and an object recognition program based on a single feedback millimeter-wave radar stored in the memory and executable on the processor. When the object recognition program based on the single feedback millimeter-wave radar is executed by the processor, the steps of the object recognition method based on the single feedback millimeter-wave radar as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an object recognition program based on a single feedback millimeter-wave radar, and when the object recognition program based on a single feedback millimeter-wave radar is executed by a processor, the steps of the object recognition method based on a single feedback millimeter-wave radar as described in any one of claims 1 to 7 are implemented.

Images