Lighting device group adaptive control method and device based on sound source positioning

Abstract

The application discloses a lighting device group self-adaptive control method and device based on sound source positioning. The method comprises the following steps: acquiring an audio matrix collected by an audio collection array, identifying and acquiring target object audio features, and correspondingly analyzing to obtain a target object position; if the number of target object positions is less than a preset number, first, a control instruction is sent to the corresponding lighting light source device according to the target object position; if the number is not less than the preset number, the object motion track is obtained by trajectory prediction according to the target object position, and the pre-control information is correspondingly acquired, the control instruction is generated according to the pre-control information, and is sent to the corresponding lighting light source device. Through the above method, the trajectory prediction is carried out according to the multiple target object positions obtained by sound source positioning, and the self-adaptive control is carried out on the lighting light source device group; the number of audio collection devices required is reduced, the audio is integrated through the Internet of Things technology and is jointly analyzed, the networking and joint control of the lighting light source device group are realized, and the control flexibility is improved.

Description

Technical Field

[0001] This invention relates to the technical field of Internet of Things (IoT) devices, and in particular to an adaptive control method and apparatus for a lighting equipment group based on sound source localization. Background Technology

[0002] Some large, open indoor spaces require lighting equipment to be installed in groups to improve safety. For example, indoor parking lots often require multiple lighting units. However, if each unit operates continuously, it consumes a lot of electricity and shortens its lifespan. Conversely, reducing the brightness of individual units while keeping them running continuously can lead to insufficient light and potential safety hazards. Existing technologies can also install volume detection devices on each lighting unit; if sound is detected, the unit is activated. However, this method requires a large number of volume detection devices, resulting in high installation costs. Furthermore, it can lead to multiple surrounding lights operating simultaneously, wasting energy. When an object moves, the volume detection devices have a certain lag in sound detection, preventing the lighting from effectively illuminating the moving object. Therefore, existing technologies for indoor lighting groups suffer from poor control flexibility. Summary of the Invention

[0003] This invention provides an adaptive control method and apparatus for lighting equipment groups based on sound source localization, aiming to solve the problem of poor control flexibility of existing methods for lighting equipment groups used in indoor places.

[0004] In a first aspect, embodiments of the present invention provide an adaptive control method for a lighting device group based on sound source localization. The method is applied in a control terminal, which is communicatively connected to an audio acquisition array and a lighting source device group. The audio acquisition array is an array composed of multiple IoT audio acquisition devices, and the lighting source device group is a device group formed by combining multiple lighting source devices. The method includes:

[0005] The audio matrix acquired by the audio acquisition array is obtained, and the corresponding target object audio features are identified by a preset target recognition strategy.

[0006] The audio matrix is ​​parsed according to a preset positioning and analysis strategy and the audio features of the target object to obtain the corresponding target object position;

[0007] If the number of target object locations is less than a preset number, a corresponding control command is sent to the lighting source device corresponding to the target object location based on the current target object location.

[0008] If the number of target object positions is not less than a preset number, the corresponding object motion trajectory is obtained by trajectory prediction based on multiple target object positions.

[0009] Pre-control information corresponding to the lighting source device group is generated based on the preset brightness control strategy and the object's motion trajectory;

[0010] Control commands are generated based on the pre-control information and sent to the corresponding lighting source devices to perform adaptive control on the lighting source device group.

[0011] Secondly, embodiments of the present invention provide an adaptive control device for a lighting equipment group based on sound source localization, wherein the device is configured in a control terminal, the control terminal being communicatively connected to an audio acquisition array and a lighting source equipment group, the audio acquisition array being an array composed of multiple Internet of Things (IoT) audio acquisition devices, and the lighting source equipment group being a group of devices formed by combining multiple lighting source equipment, the adaptive control device for a lighting equipment group based on sound source localization being used to execute the adaptive control method for a lighting equipment group based on sound source localization as described in the first aspect above, the device comprising:

[0012] The target object audio feature acquisition unit is used to acquire the audio matrix acquired by the audio acquisition array and identify the corresponding target object audio features through a preset target recognition strategy.

[0013] The target object location acquisition unit is used to parse the audio matrix according to a preset positioning parsing strategy and the target object audio features to obtain the corresponding target object location.

[0014] The first control command sending unit is used to send a corresponding control command to the lighting source device corresponding to the target object position if the number of target object positions is less than a preset number.

[0015] An object motion trajectory acquisition unit is used to predict the corresponding object motion trajectory based on multiple target object positions if the number of target object positions is not less than a preset number.

[0016] A pre-control information generation unit is used to generate pre-control information corresponding to the lighting source device group based on a preset brightness control strategy and the motion trajectory of the object.

[0017] The second control command sending unit is used to generate control commands based on the pre-control information and send them to the corresponding lighting source devices to perform adaptive control on the lighting source device group.

[0018] Thirdly, embodiments of the present invention also provide an adaptive control device for a lighting equipment group based on sound source localization, wherein the device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0019] Memory, used to store computer programs;

[0020] When the processor executes a program stored in the memory, it implements the adaptive control method for lighting equipment groups based on sound source localization as described in the first aspect above.

[0021] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the adaptive control method for lighting device groups based on sound source localization as described in the first aspect above.

[0022] This invention provides a method and apparatus for adaptive control of a lighting equipment group based on sound source localization. The method includes: acquiring an audio matrix collected by an audio acquisition array, identifying and obtaining the audio features of a target object, and parsing the corresponding target object position; if the number of target object positions is less than a preset number, first sending control commands to the corresponding lighting source devices based on the target object positions; if the number is not less than the preset number, predicting the object's trajectory based on its position and obtaining corresponding pre-control information, generating control commands based on the pre-control information, and sending them to the corresponding lighting source devices. Through this method, trajectory prediction is performed based on multiple target object positions obtained through sound source localization, and adaptive control of the lighting source equipment group is achieved. This not only reduces the number of IoT audio acquisition devices required but also integrates audio and performs joint analysis through IoT technology, realizing networked control of the lighting source equipment group and significantly improving the flexibility of controlling indoor lighting source equipment groups. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of an adaptive control method for lighting equipment groups based on sound source localization provided in an embodiment of the present invention.

[0025] Figure 2A schematic diagram illustrating an application scenario of the adaptive control method for lighting equipment groups based on sound source localization provided in an embodiment of the present invention;

[0026] Figure 3 An application effect diagram of the adaptive control method for lighting equipment groups based on sound source localization provided in an embodiment of the present invention;

[0027] Figure 4 This is another application effect diagram of the adaptive control method for lighting equipment groups based on sound source localization provided in an embodiment of the present invention;

[0028] Figure 5 A schematic block diagram of an adaptive control device for lighting equipment groups based on sound source localization provided in an embodiment of the present invention;

[0029] Figure 6 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0030] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0032] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0033] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0034] Please see Figure 1 and Figure 2 , Figure 1 This is a flowchart of an adaptive control method for lighting equipment groups based on sound source localization provided in an embodiment of the present invention. Figure 2This is a schematic diagram illustrating an application scenario of the adaptive control method for lighting equipment groups based on sound source localization provided in an embodiment of the present invention. The adaptive control method for lighting equipment groups based on sound source localization is applied to a control terminal 10. The control terminal 10 is communicatively connected to an audio acquisition array 20 and a lighting source equipment group 30. The devices can be connected via wired or wireless communication through an IoT gateway device. The audio acquisition array 20 is an array composed of multiple IoT audio acquisition devices 21, and the lighting source equipment group 30 is a group of lighting source equipment 31. The adaptive control method for lighting equipment groups based on sound source localization is executed by application software installed in the control terminal 10. The control terminal 10 is the terminal device used to execute the adaptive control method for lighting equipment groups based on sound source localization, to receive audio information, and to control the lighting source equipment 31 included in the lighting source equipment group 30. The control terminal 10 can be a desktop computer, laptop computer, tablet computer, or server terminal, or an MCU control chip, FPGA logic circuit, etc., integrated on one side of the IoT gateway device. Figure 1 As shown, the method includes steps S110 to S160.

[0035] S110. Obtain the audio matrix acquired by the audio acquisition array and identify the corresponding target object audio features through a preset target recognition strategy.

[0036] Each IoT audio acquisition device can perform audio acquisition, and the audio collected by multiple IoT audio acquisition devices in the audio acquisition array is summarized to form an audio matrix. Each audio segment in the audio array contains multiple sub-audio segments corresponding to multiple acquisition time periods. Each audio segment group corresponds to the audio content of a certain period of time collected by an IoT audio acquisition device, and each sub-audio segment contains loudness values ​​corresponding to multiple audio frequencies. For example, to facilitate audio analysis, the acquisition time period of a sub-audio segment can be 5ms, and each sub-audio segment corresponds to a time point, which is based on the start time of the audio matrix. If the start time of the audio matrix is ​​"0", then the time point of the first sub-audio segment can be recorded as "2.5ms". The number of sub-audio segments contained in each audio segment group can be 50, and the duration covered by each audio segment group is 0.25 seconds.

[0037] The acquired audio matrix is ​​identified according to a pre-set target recognition strategy, thereby obtaining the corresponding target object audio features. These target object audio features are the feature information in the audio matrix that reflects the audio characteristics of the target object.

[0038] In one embodiment, step S110 specifically includes the following sub-steps: filtering the audio matrix according to the identification frequency band in the target identification strategy to obtain valid feature audio corresponding to the identification frequency band; obtaining the time points in each audio segment of the valid feature audio where the audio loudness is greater than the preset loudness in the target identification strategy as audio marker sites; performing a delayed overlap comparison on the audio segments according to the audio marker sites of each audio segment; if an audio segment with an earlier audio marker site overlaps with multiple audio segments with later audio marker sites, then determining the audio segment with the earlier audio marker site as the target audio segment; and obtaining the audio features of the target audio segment as the corresponding target object audio features.

[0039] Specifically, the audio matrix can be filtered according to the identification frequency band in the target recognition strategy. The identification frequency band can be set according to the specific application environment. For example, in a parking lot, car tire noise and human walking noise are low-frequency noise, so the identification frequency band can be set to 300-1250Hz. After filtering, only the audio corresponding to the identification frequency band is retained as valid feature audio. Each audio segment in the audio matrix is ​​filtered separately to retain the audio corresponding to the identification frequency band in each audio segment, and the number of audio segments remains unchanged after filtering.

[0040] Furthermore, the time points at which the loudness of an audio segment at each audio frequency is greater than a preset loudness are obtained as audio marker sites; these audio marker sites can then serve as simple features for each audio segment. For example, in one embodiment, the preset loudness can be set to 45dB. The time points at which the loudness of an audio segment at each audio frequency is greater than 45dB are then obtained, thus acquiring the audio marker sites for that audio segment; that is, each audio segment can correspond to a set of audio marker sites. In another embodiment, since the background noise of each audio segment may differ, the preset loudness can also be set to a loudness ratio value. For example, if the loudness ratio value is set to 2.75, the average loudness of the audio segment at a certain audio frequency can be calculated. Further, the loudness ratio between the audio loudness of the audio segment at each acquisition time point at that audio frequency and the average loudness of that audio loudness can be calculated. Then, it can be determined whether the loudness ratio at each acquisition time point at that audio frequency is greater than the preset loudness, and the time points at which the loudness ratio of the audio segment at each audio frequency is greater than 2.75 are obtained, thus acquiring the audio marker sites for that audio segment.

[0041] Furthermore, the audio markers of each audio segment are compared and delayed to ensure overlap. The first few audio markers in each audio segment are obtained, and their time average is calculated (e.g., the time points of the first three audio markers are obtained and their average is calculated). Delay overlap is then performed based on the time average of each audio segment. For example, if the time average of audio segment A is "62.5ms" and the time average of audio segment B is "77.5ms", then the time point of each sub-audio segment in audio segment B is shifted "forward" by 15ms, thus achieving delay overlap between audio segment B and audio segment A. Using this method, each audio segment can be delayed to overlap with the audio segment with the smallest time average (i.e., the starting audio segment, which is the audio segment acquired by the IoT audio acquisition device closest to the target object), thus achieving alignment of the audio segments.

[0042] The audio segments after delay and overlap are compared for overlap. Specifically, it is determined whether each audio marker in the audio segment overlaps with the audio marker with the same sequence number in the starting audio segment. The time deviation between two audio markers with the same sequence number can be calculated. If the time deviation is within a preset deviation range (e.g., the deviation range can be set to [0, 10ms]), then the two audio markers with the same sequence number are determined to overlap. It is also determined whether each audio segment overlaps with the first N audio markers of the starting audio segment, thus quickly determining whether the audio segment overlaps with the starting audio segment. For example, N can be set to 5-10.

[0043] If an audio segment overlaps with the first N audio markers of the starting audio segment, then the audio segment is determined to overlap with the starting audio segment; otherwise, the audio segment is determined not to overlap with the starting audio segment.

[0044] Furthermore, if an audio segment with an audio marker preceding it overlaps with multiple audio segments with audio markers following it, the starting audio segment is determined to be the target audio segment. The number of subsequent audio segments to be judged can be set to 7-12. For example, if the number of judgments is set to 8, if an audio segment with an audio marker preceding it is the starting audio segment, it can be determined whether the subsequent 8 audio segments all overlap with the starting audio segment. If the subsequent 8 audio segments all overlap with the starting audio segment, the starting audio segment is determined to be the target audio segment. If any of the subsequent 8 audio segments does not overlap with the starting audio segment, the audio segment after the starting audio segment that is closest to the audio marker is used as the reference audio segment to replace the starting audio segment. The audio markers in each audio segment are then judged again to see if they overlap with the audio markers with the same sequence number in the replaced starting audio segment. If they overlap, the replaced starting audio segment is obtained as the target audio segment; otherwise, the next audio segment is obtained sequentially as the reference audio segment to replace the current starting audio segment.

[0045] The audio features of the target audio segment are obtained as the corresponding audio features of the target object. The audio features of the target object include loudness features and frequency features. The loudness fluctuation information of the M audio frequencies with the largest average loudness value in the target audio segment is obtained as the corresponding audio features of the target object. For example, M can be set to 5. The loudness fluctuation information can be represented by the ratio of the loudness of the audio frequency at a certain time point to the average loudness of the audio frequency.

[0046] S120. The audio matrix is ​​parsed according to the preset positioning and parsing strategy and the audio features of the target object to obtain the corresponding target object position.

[0047] The audio matrix is ​​further analyzed based on the localization analysis strategy and the obtained target object audio features to obtain the target object position corresponding to the target object. The target object position is the position information corresponding to the current audio matrix obtained by analysis.

[0048] In one embodiment, step S120 specifically includes the following sub-steps: selecting multiple audio segments corresponding to the audio features of the target object from the valid feature audio corresponding to the audio matrix based on the audio features of the target object as candidate audio segments; obtaining the delay time corresponding to the audio features of the target object for each candidate audio segment; obtaining the device location of the IoT audio acquisition device in the audio acquisition array corresponding to the candidate audio segments and the audio features of the target object; constructing a position analysis equation corresponding to the delay time and the device location based on the positioning analysis strategy; and analyzing the position analysis equation to obtain the corresponding target object location.

[0049] Specifically, multiple audio segments can be selected from the effective feature audio corresponding to the audio matrix as candidate audio segments based on the audio features of the target object. Here, it is necessary to first align other audio segments in the effective feature audio with the audio segments corresponding to the audio features of the target object, and then compare the aligned audio segments as a whole.

[0050] The system can acquire loudness fluctuation information for the M audio frequencies with the highest average loudness values ​​among other audio segments in the valid feature audio. To eliminate the influence of background noise and the distance from the target location on feature comparison, the loudness fluctuation information can be represented by the ratio of the loudness of an audio frequency at a certain time point to the average loudness of that audio frequency. For example, first, calculate the average loudness value of each audio frequency in the valid feature audio, and determine one of the audio frequencies as 450Hz. Calculate the ratio of the loudness at each time point of the audio frequency 450Hz to the average loudness of that audio frequency to obtain the loudness fluctuation curve of that audio frequency. Then, the loudness fluctuation curves of the M audio frequencies with the highest average loudness values ​​constitute the loudness fluctuation information of that audio frequency. If the target location is close to the location of the IoT audio acquisition device, the overall audio loudness will be relatively high; if the target location is far from the location of the IoT audio acquisition device, the overall audio loudness will be relatively low. Considering only the numerical value of audio loudness will lead to distortion in audio feature comparison. Therefore, the technical method of this application generates a loudness fluctuation curve by calculating the ratio of loudness to the average loudness of audio frequency. The generated loudness fluctuation curve ignores the differences in loudness values ​​of audio collected by different IoT audio acquisition devices and focuses on the differences in loudness ratio, thereby improving the accuracy of audio feature comparison.

[0051] Based on the audio features of the target object, the overlap between the loudness fluctuation information of each candidate audio segment and the audio features of the target object is calculated. The specific calculation can be expressed by formula (1):

[0052] (1);

[0053] Where M is the number of audio frequencies being compared, m takes the value [1, M], i is the sequence number of each time point in the audio frequency, and P is the total number of time points in the audio frequency. For example, if P is set to 50, b 1i b represents the loudness ratio of the m-th audio frequency at the i-th time point in the loudness fluctuation information of other audio segments. 0i C represents the loudness ratio of the m-th audio frequency in the audio features of the target object at the i-th time point. m Let C be the frequency overlap of the m-th audio frequency, and C be the overall overlap of the M audio frequencies. Therefore, apart from the audio segment corresponding to the audio features of the target object, each other audio feature can be assigned a degree of overlap.

[0054] The system determines whether the overlap of each audio segment is greater than a filtering threshold, such as 0.79. If the overlap of an audio segment is greater than the filtering threshold, it is identified as a candidate audio segment; otherwise, it is filtered out.

[0055] Further, the delay time between each candidate audio segment and the audio segment corresponding to the audio feature of the target object is obtained. This delay time is also the translation time for the candidate audio segment to overlap with the audio segment corresponding to the audio feature of the target object. Generally speaking, with the audio segment corresponding to the audio feature of the target object as the reference time, the delay time of the candidate audio segment is the translation time of forward translation based on the reference time.

[0056] If the control terminal stores the device locations corresponding to each IoT audio acquisition device, then the device locations of the IoT audio acquisition devices corresponding to the candidate audio segments and the audio features of the target object can be obtained, such as... Figure 3 As shown, the IoT audio acquisition devices obtained corresponding to the candidate audio segments and the audio features of the target object are respectively associated with the target object S. M The system retrieves the device locations of five IoT audio acquisition devices numbered W1, W2, W3, W4, and W5. In this embodiment, to simplify the calculation process, some IoT audio acquisition devices are placed on lighting source devices; therefore, the IoT audio acquisition devices placed on lighting source devices share the same device location as the corresponding lighting source devices. In practical applications, the IoT audio acquisition devices and lighting source devices can be set up separately, so that the IoT audio acquisition devices do not share the same device location with the lighting source devices.

[0057] Furthermore, based on the positioning analysis strategy, a position analysis equation corresponding to the delay time and device location is constructed. The positioning analysis strategy includes analytical expressions, and the position analysis equation can be constructed based on these expressions. For example, based on... Figure 3 The illustrated embodiment corresponds to the following positional analytical equation:

[0058] (2);

[0059] Where L1 is the distance between the IoT audio acquisition device W1 and the target object, (x s ,y s (x) represents the coordinates of the target object, v0 represents the speed of sound in the air, and (x) represents the coordinates of the target object. w1 ,y w1 (x) represents the device location of the IoT audio acquisition device for W1. w2 ,y w2) represents the device location of the IoT audio acquisition device for W2, and so on; ▽T2 represents half the delay time of the audio segment corresponding to the IoT audio acquisition device for W2 (the actual distance difference is the one-way transmission distance, and needs to be calculated based on half of the delay time); ▽T3 represents half the delay time of the audio segment corresponding to the IoT audio acquisition device for W3, and so on.

[0060] The position of the target object can be obtained by analyzing the position equation. Any three formulas in the above position equation can be used to obtain (x) s ,y s As the position of the target object, the redundant formula can be used as an auxiliary verification or error elimination for solving the coordinate position of the target object.

[0061] In one embodiment, after parsing the position analysis equation to obtain the corresponding target object position, the method further includes: performing position verification on the target object position according to a preset position verification rule, the target object audio features, and the candidate audio segments to obtain a position verification result; if the position verification result is successful, the method of sending a corresponding control command to the lighting source device corresponding to the target object position is executed.

[0062] Furthermore, after obtaining the location of the target object, its location can be verified based on location verification rules, the target object's audio features, and candidate audio segments. For example, the average loudness of the target object's audio features and the average loudness of candidate audio segments can be obtained. According to the principle of sound propagation, the farther the location, the lower the audio intensity. Therefore, the location of the target object can be verified based on the principle of sound transmission.

[0063] Based on the location of the target object and the device locations of the IoT audio acquisition devices corresponding to the candidate audio segments and the audio characteristics of the target object, the sound propagation distance between each device location and the target object location is calculated. Thus, a corresponding sound propagation distance can be calculated for each device location. For example... Figure 3 The five devices in the system can sequentially calculate the sound propagation distances as L1, L2, L3, L4, and L5. The calculated sound propagation distances are sorted from smallest to largest, and the mean loudness of each sound propagation distance is checked against the position verification rules to determine if the sorting is also from largest to smallest. If the result is yes, the target object's position is accurately calculated, and a successful position verification result is obtained. If the result is no, the target object's position is inaccurate, and a failed position verification result is obtained; in this case, the target object's position cannot be obtained.

[0064] S130. If the number of target object positions is less than a preset number, send a corresponding control command to the lighting source device corresponding to the target object position according to the current target object position.

[0065] The system determines whether the number of target object locations is less than a preset number, which can be set to 4. If the number of target object locations is less than the preset number, the system retrieves the lighting source devices around the target object location based on the latest target object location and sends corresponding control commands to the lighting source devices around the target object location.

[0066] S140. If the number of target object positions is not less than a preset number, the corresponding object motion trajectory is obtained by trajectory prediction based on the multiple target object positions.

[0067] If the number of target object positions is not less than a preset number, trajectory prediction can be performed based on multiple target object positions to obtain the corresponding object motion trajectory. The object motion trajectory can reflect the trajectory prediction information of the target object over a period of time in the future. For example, if the prediction duration is set to 3 seconds, the object motion trajectory can predict the movement trajectory of the target object in the next 3 seconds.

[0068] In one embodiment, step S140 specifically includes the following sub-steps: obtaining the average motion speed of multiple target object positions and the trajectory line obtained by connecting them; determining whether the trajectory line is a straight line; if the trajectory line is a straight line, extending the trajectory line according to a preset prediction duration and the average motion speed to obtain multiple corresponding prediction positions; if the trajectory line is not a straight line, fitting the trajectory line to obtain a corresponding fitting curve function; solving the prediction duration and the average motion speed according to the fitting curve function to obtain multiple corresponding prediction positions; combining and connecting the multiple prediction positions to obtain the corresponding object motion trajectory.

[0069] Specifically, the average velocity of multiple target object positions can be obtained. For example, if the acquisition interval t0 of adjacent audio matrices is 0.25s, the corresponding average velocity can be calculated based on the current target object position and the positions of the three previous target objects. The formula for calculating the average velocity can be expressed as: ; among which, L S1 The current target object position S M Position S of the previous target object M-1 The distance between them, L S2 The position S of the target object M-1 Position S of the previous target object M-2 The distance between them, L S3 The position S of the target object M-2 Position S of the previous target object M-3The distance between them, t0 is the acquisition interval, v r The average velocity of the calculated target object position.

[0070] The current target object's position is connected to the positions of the three previously identified target objects, resulting in a trajectory line. To further determine whether this trajectory line is a straight line, the slope values ​​of the three line segments corresponding to the four target object positions are calculated, and the three sets of differences between the slope values ​​of the three line segments are checked against a preset difference interval. If all three sets of differences between the slope values ​​of the three line segments are within the difference interval, the trajectory line is determined to be a straight line; otherwise, the trajectory line is determined to be a non-straight line.

[0071] If the trajectory line is a straight line, it is extended based on the prediction duration and average moving speed to obtain multiple predicted positions. The trajectory line is extended, and an interval t0 is used as a position prediction period based on the prediction duration to obtain multiple predicted positions. For example, the current target object position S... M To ensure that the direction of movement is consistent with the trajectory line, the next predicted position and the target object position S are obtained. M The distance between them is t0×v r The next predicted position and the target object position S M The spacing between them is 2×t0×v r And so on.

[0072] If the trajectory line is not a straight line, a fitting curve function is obtained by fitting the trajectory line. This fitting curve function can be obtained based on the coordinates of each target object's position in the trajectory line and the changes in the slope of the line segments. The fitting curve function is expressed in a functional form, such as a quadratic equation, a hyperbola equation, or a logarithmic equation. Furthermore, the prediction time and average motion speed are solved based on the fitting curve function to obtain multiple predicted positions.

[0073] For example, it can be based on the current target object position S M Then the next predicted position and the target object position S can be obtained. M The length of the curve segment between them (not the straight-line distance, but the length of the curvilinear motion along the curve function) is t0×v r The next predicted position and the target object position S M The length of the curve segment between them is 2×t0×v r And so on. Based on the target object's position S MBy combining the actual position in the fitted curve function with the curve segment lengths corresponding to each predicted position, the curve coordinates corresponding to each curve segment length on the fitted curve function are obtained, thus yielding the corresponding predicted position. Furthermore, by combining and connecting multiple predicted positions, the corresponding object trajectory is obtained.

[0074] S150. Generate pre-control information corresponding to the lighting source device group based on the preset brightness control strategy and the object's motion trajectory.

[0075] Furthermore, based on the brightness control strategy and the object's motion trajectory, pre-control information corresponding to the lighting source equipment group is generated. The pre-control information is the control information that predicts the movement trajectory of the target object and controls the lighting source equipment in the lighting source equipment group to turn on and off in advance.

[0076] In one embodiment, step S150 specifically includes the following sub-steps: obtaining the sequence of nearest lighting devices corresponding to each predicted position in the object's motion trajectory according to the installation position of the lighting devices in the lighting device group; sorting the lighting devices in the nearest lighting device sequence from nearest to farthest according to the distance between the lighting devices in the nearest lighting device sequence and their corresponding predicted positions; determining the illuminance information of each lighting device in the nearest lighting device sequence according to the illuminance determination rules in the brightness control strategy and the predicted positions; extracting the lighting devices in each of the nearest lighting device sequences according to the target illuminance in the brightness control strategy to obtain the target devices corresponding to each of the nearest lighting device sequences; and determining the device illumination duration information corresponding to each target device as the corresponding pre-control information based on the target devices corresponding to each predicted position in the object's motion trajectory.

[0077] Specifically, the sequence of nearest lighting devices corresponding to each predicted position in the object's trajectory can be obtained sequentially based on the installation locations of the lighting source devices in the lighting source device group. Each predicted position in the object's trajectory can then correspond to a set of nearest lighting device sequences, and the number of lighting source devices included in the nearest lighting device sequence can be K, where K can be set to an integer not less than 5. For example... Figure 4 As shown, K is set to 5, and a predicted position in the object's trajectory is S. Y Then the predicted position S can be obtained. Y The corresponding sequence of the nearest lighting devices is [Z1, Z2, Z3, Z4, Z5].

[0078] Furthermore, the illumination distance between each lighting source device in the recent lighting device sequence and its corresponding predicted location is calculated. The lighting source devices in the recent lighting device sequence are then sorted according to their illumination distances, from smallest to largest.

[0079] The illuminance information of each lighting source device in the nearest lighting device sequence is determined based on the illuminance determination rules and predicted positions in the brightness control strategy. Specifically, the lighting distance between each lighting source device in the nearest lighting device sequence and its corresponding predicted position is obtained in the above steps. The illuminance of a lighting source device is inversely proportional to the square of the lighting distance between the lighting source device and the predicted position, and the lighting requirements can be met when the lighting distance is relatively short. Therefore, the illuminance information of each lighting source device in the nearest lighting device sequence can be determined sequentially according to the illuminance determination rules and the lighting distances of each lighting source device. Specifically, based on the characteristics of the lighting source devices, the illuminance determination rules can be expressed as the following calculation formula:

[0080] (3);

[0081] Where Q represents the calculated illuminance information, and r is the illumination distance of the lighting source device, with r in meters. Based on the above lighting determination rules, the illuminance information corresponding to the illumination distance of each lighting source device can be determined. For example... Figure 4 As shown in the embodiment of this application, the lateral and longitudinal distances between adjacent lighting source devices are both set to 10m. The illuminance information of each lighting source device in the nearest lighting device sequence [Z1, Z2, Z3, Z4, Z5] is obtained sequentially as shown in Table 1:

[0082] Table 1

[0083] Equipment serial number Z1 Z2 Z3 Z4 Z5 Lighting distance r (meters) 7.42 10.41 11.76 13.84 20.54 Illuminance information Q 0.6539 0.3322 0.2603 0.1879 0

[0084] Based on the target illuminance in the brightness control strategy, the lighting source devices included in each of the nearest lighting device sequences are extracted to obtain the target device corresponding to each nearest lighting device sequence. The illuminance information of the lighting source devices in the nearest lighting device sequence can be accumulated to obtain an accumulated illuminance value. If the accumulated illuminance value is greater than the target illuminance, then the lighting source device currently participating in the accumulation calculation is determined to be the target device.

[0085] For example, the target illuminance can be set to 1.2. Based on the illuminance information shown in Table 1, the illuminance information of lighting source devices Z1 and Z2 is accumulated to obtain an accumulated illuminance value of 0.9861. Since this accumulated illuminance value is less than the target illuminance, the illuminance information of lighting source devices Z1, Z2 and Z3 is accumulated to obtain an accumulated illuminance value of 1.2464. At this point, the accumulated illuminance value is greater than the target illuminance, and thus lighting source devices Z1, Z2 and Z3 are extracted as target devices.

[0086] Based on the above method, the target devices corresponding to each predicted position can be obtained. According to the predicted positions arranged sequentially in the object's motion trajectory, the illumination duration of the target devices at each predicted position is accumulated to obtain the device illumination duration information corresponding to each target device. For example, the illumination duration of the target device can be set to an acquisition interval t0. If the target device at the previous predicted position includes a lighting source device Z1, and the target device at the next predicted position also includes a lighting source device Z1, then the illumination duration t0 corresponding to the two predicted positions for the lighting source device Z1 is accumulated, resulting in the device illumination duration information for the lighting source device Z1 being 2t0. Based on the above method, the device illumination duration information for each device can be obtained and combined into corresponding pre-control information.

[0087] S160. Generate control commands based on the pre-control information and send them to the corresponding lighting source devices to perform adaptive control on the lighting source device group.

[0088] Furthermore, corresponding control commands are generated based on the pre-control information and sent to the lighting source devices corresponding to the pre-control information, thereby achieving adaptive control of the lighting source device group. The control commands include turn-on commands to control the lighting source devices to turn on, and turn-off commands to control the lighting source devices to turn off.

[0089] After a preset interval, the process returns to the step of predicting the trajectory based on the continuously acquired positions of multiple target objects to obtain the corresponding object motion trajectory.

[0090] According to steps S110 and S120, the positions of target objects can be continuously acquired and stored. After a preset interval, the process can directly return to step S140 (since the number of stored target object positions will definitely exceed the preset number). Based on the newly stored multiple target object positions, trajectory prediction is performed again to obtain the object's motion trajectory. At this time, the object's motion trajectory is updated based on the newly acquired multiple target object positions. The pre-control information is then updated based on the updated object motion trajectory. The interval time can be set to 2s or 3s.

[0091] If the position of the target object cannot be obtained according to step S120, the execution of the above steps will be terminated.

[0092] In the adaptive control method for lighting equipment groups based on sound source localization provided in this embodiment of the invention, the method includes: acquiring an audio matrix collected by an audio acquisition array, identifying and acquiring the audio features of target objects, and parsing the corresponding target object positions; if the number of target object positions is less than a preset number, first sending control commands to the corresponding lighting source devices based on the target object positions; if the number is not less than the preset number, predicting the trajectory of the objects based on their positions and acquiring corresponding pre-control information, generating control commands based on the pre-control information, and sending them to the corresponding lighting source devices. Through the above method, trajectory prediction is performed based on the multiple target object positions obtained from sound source localization, and adaptive control of the lighting source equipment group is achieved; this not only reduces the number of IoT audio acquisition devices required, but also integrates audio and performs joint analysis through IoT technology, realizing networked control of the lighting source equipment group and significantly improving the flexibility of controlling the lighting source equipment group in indoor venues.

[0093] This invention also provides a sound source localization-based adaptive control device for lighting equipment groups. This device can be configured in a control terminal 10, which is communicatively connected to an audio acquisition array 20 and a lighting source equipment group 30. The audio acquisition array 20 is an array composed of multiple IoT audio acquisition devices 21, and the lighting source equipment group 30 is a group of lighting source equipment 31. This sound source localization-based adaptive control device is used to execute any embodiment of the aforementioned sound source localization-based adaptive control method for lighting equipment groups. Specifically, please refer to... Figure 5 , Figure 5 This is a schematic block diagram of an adaptive control device for a lighting equipment group based on sound source localization, provided in an embodiment of the present invention.

[0094] like Figure 5 As shown, the adaptive control device 100 for lighting equipment groups based on sound source localization includes a target object audio feature acquisition unit 110, a target object position acquisition unit 120, a first control command sending unit 130, an object motion trajectory acquisition unit 140, a pre-control information generation unit 150, and a second control command sending unit 160.

[0095] The target object audio feature acquisition unit 110 is used to acquire the audio matrix acquired by the audio acquisition array and identify the corresponding target object audio features through a preset target recognition strategy.

[0096] The target object position acquisition unit 120 is used to parse the audio matrix according to a preset positioning parsing strategy and the target object audio features to obtain the corresponding target object position.

[0097] The first control command sending unit 130 is used to send a corresponding control command to the lighting source device corresponding to the target object position if the number of target object positions is less than a preset number.

[0098] The object motion trajectory acquisition unit 140 is used to predict the corresponding object motion trajectory based on the multiple target object positions if the number of target object positions is not less than a preset number.

[0099] The pre-control information generation unit 150 is used to generate pre-control information corresponding to the lighting source device group based on the preset brightness control strategy and the motion trajectory of the object.

[0100] The second control command sending unit 160 is used to generate control commands based on the pre-control information and send them to the corresponding lighting source devices to perform adaptive control on the lighting source device group.

[0101] The adaptive control device for lighting equipment groups based on sound source localization provided in this embodiment of the invention applies the aforementioned adaptive control method for lighting equipment groups based on sound source localization. The method includes: acquiring an audio matrix collected by an audio acquisition array, identifying and acquiring the audio features of a target object, and correspondingly parsing to obtain the target object's position; if the number of target object positions is less than a preset number, first sending control commands to the corresponding lighting source devices based on the target object positions; if the number is not less than the preset number, predicting the object's trajectory based on the target object positions to obtain the object's motion trajectory and correspondingly acquiring pre-control information, generating control commands based on the pre-control information, and sending them to the corresponding lighting source devices. Through this method, trajectory prediction is performed based on multiple target object positions obtained through sound source localization, and adaptive control of the lighting source equipment group is achieved. This not only reduces the number of IoT audio acquisition devices required but also integrates audio and performs joint analysis through IoT technology, realizing networked control of the lighting source equipment group and significantly improving the flexibility of controlling indoor lighting source equipment groups.

[0102] The aforementioned adaptive control device for lighting equipment groups based on sound source localization can be implemented as a computer program, which can be used in various ways, such as... Figure 6 The computer device shown runs on the computer. The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor; when the computer device executes the computer program, it implements the adaptive control method for lighting device groups based on sound source localization as described in the above embodiments.

[0103] Please see Figure 6 , Figure 6 This is a schematic block diagram of a computer device provided in an embodiment of the present invention. The computer device may be a terminal device for executing an adaptive control method for a lighting device group based on sound source localization, to receive audio information and control the lighting source devices 31 included in the lighting source device group 30.

[0104] See Figure 6 The computer device 500 includes a processor 502, a memory, and a communication interface 505 connected via a system bus 501. The memory may include a storage medium 503 and internal memory 504.

[0105] The storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it causes the processor 502 to execute an adaptive control method for a lighting device group based on sound source localization. The storage medium 503 may be a volatile storage medium or a non-volatile storage medium.

[0106] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0107] The internal memory 504 provides an environment for the operation of the computer program 5032 in the storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an adaptive control method for lighting equipment groups based on sound source localization.

[0108] This communication interface 505 is used for network communication, such as providing data transmission. Those skilled in the art will understand that... Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device 500 to which the present invention is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0109] The processor 502 is used to run the computer program 5032 stored in the memory to implement the corresponding functions in the above-mentioned adaptive control method for lighting equipment groups based on sound source localization.

[0110] Those skilled in the art will understand that Figure 6The embodiments of the computer device shown do not constitute a limitation on the specific configuration of the computer device. In other embodiments, the computer device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. For example, in some embodiments, the computer device may include only memory and a processor. In such embodiments, the structure and function of the memory and processor are different from those shown. Figure 6 The embodiments shown are consistent and will not be described again here.

[0111] It should be understood that, in this embodiment of the invention, the processor 502 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0112] In another embodiment of the invention, a computer-readable storage medium is provided. This computer-readable storage medium may be volatile or non-volatile. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps included in the above-described adaptive control method for lighting device groups based on sound source localization.

[0113] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention.

[0114] In the embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Units with the same function may be grouped into one unit. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, or it may be an electrical, mechanical, or other form of connection.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0116] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0117] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a computer-readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks.

[0118] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for adaptive control of lighting equipment groups based on sound source localization, characterized in that, The method is applied in a control terminal, which is communicatively connected to an audio acquisition array and a lighting source device group. The audio acquisition array is an array composed of multiple IoT audio acquisition devices, and the lighting source device group is a device group formed by combining multiple lighting source devices. The method includes: The audio matrix acquired by the audio acquisition array is obtained, and the corresponding target object audio features are identified by a preset target recognition strategy. The audio matrix is ​​parsed according to a preset positioning and analysis strategy and the audio features of the target object to obtain the corresponding target object position; If the number of target object locations is less than a preset number, a corresponding control command is sent to the lighting source device corresponding to the target object location based on the current target object location. If the number of target object positions is not less than a preset number, the corresponding object motion trajectory is obtained by trajectory prediction based on multiple target object positions. Pre-control information corresponding to the lighting source device group is generated based on the preset brightness control strategy and the object's motion trajectory; Control commands are generated based on the pre-control information and sent to the corresponding lighting source devices to perform adaptive control on the lighting source device group.

2. The adaptive control method for lighting equipment groups based on sound source localization according to claim 1, characterized in that, The step of acquiring the audio matrix collected by the audio acquisition array and identifying the corresponding target object audio features through a preset target recognition strategy includes: The audio matrix is ​​filtered according to the identification frequency band in the target identification strategy to obtain valid feature audio that retains the identification frequency band; The time points in each audio segment of the effective feature audio where the audio loudness is greater than the preset loudness in the target recognition strategy are used as audio marker sites; The audio segments are compared for delayed overlap based on the audio marker sites of each audio segment; If an audio segment with an audio marker site preceding it overlaps with multiple audio segments with audio marker sites following it, then the audio segment with the audio marker site preceding it is determined as the target audio segment. The audio features of the target audio segment are obtained as the corresponding audio features of the target object.

3. The adaptive control method for lighting equipment groups based on sound source localization according to claim 2, characterized in that, The step of parsing the audio matrix according to a preset positioning and analysis strategy and the audio features of the target object to obtain the corresponding target object position includes: Based on the audio features of the target object, multiple audio segments corresponding to the audio features of the target object are selected from the valid feature audio corresponding to the audio matrix as candidate audio segments. Obtain the delay time corresponding to the audio features of the target object for each candidate audio segment; Obtain the device location of the IoT audio acquisition device in the audio acquisition array that corresponds to the candidate audio segment and the audio features of the target object; Based on the positioning analysis strategy, a position analysis equation corresponding to the delay time and the device position is constructed; The positional equation is analyzed to obtain the corresponding target object position.

4. The adaptive control method for lighting equipment groups based on sound source localization according to claim 3, characterized in that, After analyzing the position equation to obtain the corresponding target object position, the method further includes: The position of the target object is verified according to the preset position verification rules, the audio features of the target object, and the candidate audio segments to obtain the position verification result of whether it passes or fails. If the position verification result is successful, the step of sending the corresponding control command to the lighting source device corresponding to the position of the target object is executed.

5. The adaptive control method for lighting equipment groups based on sound source localization according to any one of claims 1-4, characterized in that, The step of predicting the trajectory of the corresponding object based on the positions of multiple target objects includes: Obtain the average velocity of multiple target objects and the trajectory line obtained by connecting them; Determine whether the trajectory line is a straight line; If the trajectory line is a straight line, the trajectory line is extended according to the preset prediction time and the average movement speed to obtain multiple corresponding prediction positions. If the trajectory line is not a straight line, the trajectory line is fitted to obtain the corresponding fitted curve function; The predicted duration and the average speed are solved based on the fitted curve function to obtain multiple corresponding predicted positions. By combining and connecting multiple predicted positions, the corresponding object motion trajectory can be obtained.

6. The adaptive control method for lighting equipment groups based on sound source localization according to claim 5, characterized in that, The step of generating pre-control information corresponding to the lighting source device group based on a preset brightness control strategy and the object's motion trajectory includes: Based on the installation positions of the lighting source devices in the group of lighting source devices, the sequence of the nearest lighting devices corresponding to each predicted position in the trajectory of the object is obtained sequentially. The lighting sources in the nearest lighting equipment sequence are sorted from nearest to farthest based on the distance between the lighting source equipment and the corresponding predicted location. The illuminance information of each lighting source device in the nearest lighting device sequence is determined according to the illuminance determination rule in the brightness control strategy and the predicted position. Based on the target illuminance in the brightness control strategy, the lighting source devices included in each of the nearest lighting device sequences are extracted to obtain the target devices corresponding to each of the nearest lighting device sequences; Based on the target devices corresponding to each predicted position in the object's motion trajectory, the device irradiation duration information corresponding to each target device is determined as the corresponding pre-control information.

7. The adaptive control method for lighting equipment groups based on sound source localization according to any one of claims 1-4, characterized in that, After generating control commands based on the pre-control information and sending them to the corresponding lighting source devices to perform adaptive control on the lighting source device group, the method further includes: After a preset interval, return to the step of predicting the trajectory based on the positions of multiple target objects acquired in succession to obtain the corresponding object motion trajectory.

8. A self-adaptive control device for a lighting equipment group based on sound source localization, characterized in that, The device is configured in a control terminal, which is communicatively connected to an audio acquisition array and a lighting source device group. The audio acquisition array is an array composed of multiple IoT audio acquisition devices, and the lighting source device group is a device group formed by combining multiple lighting source devices. The adaptive control device for the lighting device group based on sound source localization is used to execute the adaptive control method for the lighting device group based on sound source localization as described in any one of claims 1-7. The device includes: The target object audio feature acquisition unit is used to acquire the audio matrix acquired by the audio acquisition array and identify the corresponding target object audio features through a preset target recognition strategy. The target object location acquisition unit is used to parse the audio matrix according to a preset positioning parsing strategy and the target object audio features to obtain the corresponding target object location. The first control command sending unit is used to send a corresponding control command to the lighting source device corresponding to the target object position if the number of target object positions is less than a preset number. An object motion trajectory acquisition unit is used to predict the corresponding object motion trajectory based on multiple target object positions if the number of target object positions is not less than a preset number. A pre-control information generation unit is used to generate pre-control information corresponding to the lighting source device group based on a preset brightness control strategy and the motion trajectory of the object. The second control command sending unit is used to generate control commands based on the pre-control information and send them to the corresponding lighting source devices to perform adaptive control on the lighting source device group.

9. A computer device, characterized in that, The device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor, when executing a program stored in memory, implements the adaptive control method for lighting equipment groups based on sound source localization as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the adaptive control method for lighting equipment groups based on sound source localization as described in any one of claims 1 to 7.

Images