Light following system and control method thereof

Abstract

The invention relates to a light following system and a control method thereof. The method comprises the steps of receiving identification data output by a server, determining a target light following object from candidate light following objects included in the identification data, obtaining space coordinate data of the target light following object in a lamp coordinate system according to two-dimensional coordinate information corresponding to the target light following object, and sending the space coordinate data to a follow light, the space coordinate data is used for indicating the follow spot to adjust the irradiation angle, so that the light of the follow spot irradiates the target follow spot object; by adopting the method, automatic light tracking can be realized, the control accuracy is improved while the labor cost is reduced, and the light tracking object does not need to wear a transmitting device on the body, so that the light tracking cost is further reduced.

Description

Technical Field

[0001] The present application relates to the technical field of lamp control, and in particular to a light chasing system and a control method thereof. Background Art

[0002] A follow spot is a device that allows actors to chase light in real time during performances. It can use light beams to highlight actors or other targets when the stage is completely dark, focusing on the follow spot to attract the audience's attention.

[0003] There are usually two existing chasing light methods. One requires the user to perform remote control to control the light of the chasing light to follow the chasing object, which has the problem of high labor cost and low control accuracy; the other requires the chasing object to wear a transmitting device on the body and locate it through radio communication to achieve the light of the chasing light following the chasing object, which has the problem of high cost. Summary of the invention

[0004] Based on this, it is necessary to provide a light chasing system and a control method thereof that can reduce costs and improve control accuracy in response to the above technical problems.

[0005] In a first aspect, the present application provides a control method for a light chasing system, which is applied to a pan / tilt in the light chasing system. The light chasing system further includes a server, a light chasing light, and an image acquisition device respectively connected to the pan / tilt, and the image acquisition device is respectively connected to the pan / tilt and the server. The method includes:

[0006] Receiving identification data output by the server, wherein the identification data includes two-dimensional coordinate information corresponding to the candidate light-chasing object; the identification data is obtained by the server after performing identification processing on the image data output by the image acquisition device;

[0007] Determine the target light-chasing object from the candidate light-chasing objects, and obtain the spatial coordinate data of the target light-chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light-chasing object. The lamp coordinate system is a spatial coordinate system constructed with the chasing light as a reference;

[0008] The spatial coordinate data is sent to the chasing spot, and the spatial coordinate data is used to instruct the chasing spot to adjust the irradiation angle so that the light of the chasing spot can illuminate the target chasing object.

[0009] In one of the embodiments, the identification data further includes an object identifier corresponding to the candidate light-chasing object;

[0010] Determining a target light-chasing object from candidate light-chasing objects includes:

[0011] In response to an object selection operation on a candidate light-chasing object triggered by a user based on an object identifier, a target light-chasing object corresponding to the object selection operation is determined among the candidate light-chasing objects.

[0012] In one embodiment, the method further comprises:

[0013] Receiving current image data transmitted by an image acquisition device;

[0014] The current image data is matched with the two-dimensional coordinate information and the object identifier corresponding to the candidate light-chasing object to update the two-dimensional coordinate information corresponding to the candidate light-chasing object in real time.

[0015] In one embodiment, the method further comprises:

[0016] Receive current image data transmitted by an image acquisition device; the current image data contains a light spot generated by the follow-up light;

[0017] The gimbal is adjusted according to the overlap between the target light-chasing object and the light spot, and the horizontal and vertical parameters of the gimbal after adjustment are obtained;

[0018] The horizontal parameters and the vertical parameters are converted into spatial coordinate parameters of a spatial coordinate system with the chasing light as a reference, and the spatial coordinate parameters are transmitted to the chasing light for chasing.

[0019] In a second aspect, the present application further provides a control method for a light chasing system, which is applied to a server in the light chasing system. The light chasing system further includes a pan / tilt connected to the server, and a light chasing lamp and an image acquisition device respectively connected to the pan / tilt, and the image acquisition device is connected to the server. The method includes:

[0020] Receiving image data output by an image acquisition device, and performing recognition processing on the image data to obtain recognition data; wherein the recognition data includes two-dimensional coordinate information corresponding to the candidate light-chasing object;

[0021] The identification data is output to the gimbal; the identification data is used to instruct the gimbal to determine the target light chasing object from the candidate light chasing objects, and obtain the spatial coordinate data of the target light chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light chasing object, and the lamp coordinate system is a spatial coordinate system constructed with the chasing spot as a reference; and the spatial coordinate data is sent to the chasing spot, and the spatial coordinate data is used to instruct the chasing spot to adjust the illumination angle so that the light of the chasing spot illuminates the target light chasing object.

[0022] In one of the embodiments, the identification data further includes an object identifier corresponding to the candidate light-chasing object;

[0023] Perform recognition processing on the image data to obtain recognition data, including:

[0024] The image data is input into the target recognition model, the candidate light-chasing object in the image data is determined by using the target recognition model, and the two-dimensional coordinate information corresponding to the candidate light-chasing object is obtained;

[0025] An object identifier corresponding to the candidate light-chasing object is created.

[0026] In one embodiment, before performing recognition processing on the image data and obtaining recognition data, the method further includes:

[0027] The acquired image samples are randomly divided into a first sample set and a second sample set;

[0028] Annotate the first sample set to obtain a test data set;

[0029] Each candidate recognition model is trained respectively through the test data set to obtain each candidate recognition model that has completed training;

[0030] Recognize the second sample set based on each trained candidate recognition model to obtain a recognition result;

[0031] The current best candidate recognition model is determined according to the recognition result, and the current best candidate recognition model is used as the target recognition model.

[0032] In a third aspect, the present application further provides a light-chasing system, the light-chasing system comprising:

[0033] A pan / tilt platform, which is used to execute the steps of the above method;

[0034] A server, connected to the PTZ, and used to execute the steps of the above method;

[0035] Follow spot light, connect to PTZ;

[0036] The image acquisition device is connected to the pan / tilt head and the server respectively.

[0037] In one of the embodiments, the gimbal is equipped with a first rotating mechanism and an angle sensor, the first rotating mechanism is used to drive the gimbal to rotate, and the angle sensor is used to obtain horizontal parameters and vertical parameters of the gimbal after rotation.

[0038] In one of the embodiments, the follow spot light is provided with a second rotating mechanism, and the second rotating mechanism is used for driving the follow spot light to rotate.

[0039] In the above-mentioned light-chasing system and control method thereof, the gimbal receives the identification data output by the server, and determines the target light-chasing object from the candidate light-chasing objects included in the identification data. The gimbal obtains the spatial coordinate data of the target light-chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light-chasing object. The gimbal sends the spatial coordinate data to the light-chasing light. The spatial coordinate data is used to instruct the light-chasing light to adjust the illumination angle so that the light of the light-chasing light illuminates the target light-chasing object. In the present application, when the target light-chasing object is determined from the candidate light-chasing objects included in the identification data, the spatial coordinate data of the target light-chasing object in the lamp coordinate system is obtained according to the two-dimensional coordinate information corresponding to the target light-chasing object, and the spatial coordinate data is output to the light-chasing light to achieve light chasing for the target light-chasing object. Compared with the existing light-chasing method, the light chasing can be realized automatically throughout the whole process, which reduces the labor cost and improves the control accuracy. There is no need for the light-chasing object to wear a transmitting device on the body, which further reduces the cost of light chasing. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] FIG1 is a schematic diagram of the structure of a light-chasing system in one embodiment;

[0042] FIG2 is a schematic flow chart of a control method of a light-chasing system in one embodiment;

[0043] FIG3 is a schematic flow chart of a control method of a light-chasing system in another embodiment;

[0044] FIG. 4 is a structural block diagram of a light-chasing system in one embodiment. DETAILED DESCRIPTION

[0045] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0046] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art of the technical field of the present application. The terms used herein in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. It is understood that the terms "first", "second", etc. used in the present application can be used to describe various elements in this article, but these elements are not limited by these terms. These terms are only used to distinguish a first element from another element.

[0047] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" and the like specify the presence of stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.

[0048] At present, the use of stage lighting is an indispensable and important means in stage art, which can achieve the purpose of highlighting key points, shaping characters, and setting off the atmosphere of the environment. The follow-spot is a device that actors can use to chase lights in time during performances. When the stage is dark, the light beam can be used to highlight the actors or other targets, and focus on the follow-spot object to attract the audience's attention. However, the existing follow-spot methods, such as users controlling the follow-spot light to follow the follow-spot object through remote control, have the problems of high labor costs and low control accuracy; or the follow-spot object wears a transmitting device on the body and is positioned through radio communication to realize that the follow-spot light follows the follow-spot object, which has the problems of high deployment difficulty, the transmitting device may interfere with the normal performance of the follow-spot object, and high cost.

[0049] The control method of the light-chasing system provided in the embodiment of the present application can be applied to the light-chasing system shown in FIG1 . The light-chasing system includes: a pan-tilt 011, a server 012, a light-chasing lamp 013 and an image acquisition device 014. A pan-tilt 011 is used to track a target light-chasing object. A server 012 can be connected to one or more pan-tilts 011 to achieve light-chasing for the target light-chasing object. The pan-tilt 011 is connected to the server 012 and the light-chasing lamp 013 respectively. The image acquisition device 014 is connected to the pan-tilt 011 and the server 012 respectively. The light-chasing lamp 013 is set above a preset area (set according to actual conditions, and the stage is used as an example in the embodiment of the present application). The pan-tilt 011 can be set on a plane flush with the stage, and the server 012 is fixed on a rack. The light object 015 is generally an actor. By adopting the control method of the light chasing system provided in the embodiment of the present application, the server 012 recognizes and processes the image data collected by the image acquisition device 014, and outputs the recognition result, that is, the recognition data, to the pan-tilt head 011. The pan-tilt head 011 obtains the spatial coordinate data of the target light chasing object 015 in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light chasing object 015 in the recognition result, and sends the spatial coordinate data to the chasing spot 013, instructing the chasing spot 013 to adjust its own angle to illuminate the target light chasing object 015, that is, during the movement of the target light chasing object 015, the chasing spot 013 tracks the target light chasing object 015 in real time to realize automatic light chasing.

[0050] Exemplarily, the server 012 may be connected to the pan / tilt head 011 via an RJ45 harness 017 , and the pan / tilt head 011 may be connected to the follow spot 013 via an RJ45 harness 017 .

[0051] It should be noted that a human-computer interaction device (set according to actual conditions, at least one touch display screen) is provided on the pan-tilt head 011, and the server 012 transmits the candidate light-chasing objects identified after recognition processing to the pan-tilt head 011, and the user can select the target light-chasing object to be tracked on the pan-tilt head 011; the image acquisition device 014 is a device that can shoot or record the stage. In the embodiment of the present application, the image acquisition device 014 is taken as a camera as an example for explanation.

[0052] In an exemplary embodiment, as shown in FIG2 , a control method for a light chasing system is provided, and the method is described by taking the application of the method to the pan / tilt head in FIG1 as an example. The method includes:

[0053] S202, receiving identification data output by the server, wherein the identification data includes two-dimensional coordinate information corresponding to the candidate light-chasing object; the identification data is obtained by the server after performing identification processing on image data output by the image acquisition device.

[0054] The two-dimensional coordinate information includes two-dimensional coordinate data of the candidate light-chasing object in the stage coordinate system, and the stage coordinate system is a two-dimensional coordinate system constructed with the stage as a reference.

[0055] Specifically, the user can output automatic control instructions to the gimbal through the human-computer interaction device of the gimbal, and the gimbal enters the automatic control mode according to the automatic control instructions. At this time, the image acquisition device collects the image data on the stage in real time and transmits it to the server. The server identifies all candidate light-chasing objects in the image data in real time, records the two-dimensional coordinate information of each candidate light-chasing object and makes a unique object identification. The server outputs the identification data to the gimbal in real time.

[0056] S204, determining a target light chasing object from the candidate light chasing objects, and acquiring spatial coordinate data of the target light chasing object in a lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light chasing object, wherein the lamp coordinate system is a spatial coordinate system constructed with the chasing light as a reference.

[0057] Specifically, the user can select the target light-chasing object to be tracked on the gimbal. The gimbal determines the target light-chasing object based on the user's operation and obtains the two-dimensional coordinate information corresponding to the target light-chasing object. The gimbal calculates the spatial coordinate data of the target light-chasing object in the lamp coordinate system based on the two-dimensional coordinate information corresponding to the target light-chasing object.

[0058] It can be understood that the field of view of the target light-chasing object transmitted by the server and the field of view of the pan-tilt head are both the fields of view of the image acquisition device. In the stage coordinate system, the coordinate offset of the target light-chasing object and the horizontal and vertical movement of the spotlight have a certain coefficient relationship. The pan-tilt head converts the two-dimensional coordinate information into spatial coordinate data in the lamp coordinate system based on the coefficient relationship.

[0059] Exemplarily, the gimbal continuously receives identification data output by the server. If the identification data received at the current moment contains a target light-chasing object, the gimbal executes steps based on the two-dimensional coordinate information corresponding to the target light-chasing object. Otherwise, the gimbal does not execute steps based on the two-dimensional coordinate information corresponding to the target light-chasing object.

[0060] S206, sending the spatial coordinate data to the chasing spot, where the spatial coordinate data is used to instruct the chasing spot to adjust the irradiation angle so that the light of the chasing spot can illuminate the target chasing object.

[0061] Specifically, the gimbal sends the spatial coordinate data to the chasing light, and the chasing light adjusts its own angle to the corresponding position according to the spatial coordinate data, thereby completing the automated chasing of the target object.

[0062] In the control method of the above-mentioned light chasing system, when the gimbal determines the target light chasing object from the candidate light chasing objects included in the identification data, it obtains the spatial coordinate data of the target light chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light chasing object, and outputs the spatial coordinate data to the light chasing light to achieve light chasing for the target light chasing object. Compared with the existing light chasing method, the light chasing can be fully automated throughout the process, which reduces labor costs and improves control accuracy. There is no need for the light chasing object to wear a transmitting device on the body, which further reduces the cost of light chasing.

[0063] In one of the embodiments, the identification data further includes an object identifier corresponding to the candidate light-chasing object;

[0064] Determining a target light-chasing object from candidate light-chasing objects includes:

[0065] In response to an object selection operation on a candidate light-chasing object triggered by a user based on an object identifier, a target light-chasing object corresponding to the object selection operation is determined among the candidate light-chasing objects.

[0066] Specifically, the server identifies all candidate light-chasing objects in the image data in real time, and assigns a unique object identifier to each candidate light-chasing object according to the matched features. Each object identifier can be displayed on the human-computer interaction device of the gimbal. The human-computer interaction device responds to the object selection operation for the candidate light-chasing object triggered by the user based on the object identifier, thereby determining the corresponding target light-chasing object among the candidate light-chasing objects. That is, the user clicks on the human-computer interaction device to select the object identifier to be tracked, and the gimbal determines the target light-chasing object corresponding to the object selection operation among the candidate light-chasing objects.

[0067] Exemplarily, the target identifier can be determined by the characteristics of the candidate light-chasing object, which is not elaborated in the embodiments of the present application. The gimbal can store object identifiers corresponding to different objects, and the gimbal uses the corresponding object identifier as the target identifier based on the user's object selection operation, that is, confirms the corresponding candidate light-chasing object as the target light-chasing object.

[0068] In an embodiment of the present application, by responding to an object selection operation for a candidate light-chasing object triggered by a user based on an object identifier, a target light-chasing object is determined from the candidate light-chasing objects, thereby facilitating subsequent light-chasing for the target light-chasing object.

[0069] In one embodiment, the method further comprises:

[0070] Receiving current image data transmitted by an image acquisition device;

[0071] The current image data is matched with the two-dimensional coordinate information and the object identifier corresponding to the candidate light-chasing object to update the two-dimensional coordinate information corresponding to the candidate light-chasing object in real time.

[0072] Specifically, in order to ensure the timeliness and accuracy of light chasing, in addition to receiving the identification data output by the server, the gimbal also needs to receive the current image data transmitted by the image acquisition device. The server can quickly identify and process the image data and output the identification data. At this time, the identification data received by the gimbal is obtained after the server processes the current image data. The gimbal matches the current image data with the two-dimensional coordinate information and object identification corresponding to the candidate light chasing object, and re-synthesizes it to update the two-dimensional coordinate information corresponding to the candidate light chasing object in real time.

[0073] Exemplarily, the human-computer interaction device of the gimbal can display the two-dimensional coordinate information corresponding to the candidate light-chasing object and the object identification in real time.

[0074] In an embodiment of the present application, the gimbal will match the current image data received from the image acquisition device with the two-dimensional coordinate information and object identification corresponding to the candidate light chasing object, and update the two-dimensional coordinate information corresponding to the candidate light chasing object in real time, thereby reducing the impact of delays in data transmission between the server and the gimbal, and improving the timeliness and accuracy of light chasing.

[0075] In one embodiment, the method further comprises:

[0076] Receive current image data transmitted by an image acquisition device; the current image data contains a light spot generated by the follow-up light;

[0077] The gimbal is adjusted according to the overlap between the target light-chasing object and the light spot, and the horizontal and vertical parameters of the gimbal after adjustment are obtained;

[0078] The horizontal parameters and the vertical parameters are converted into spatial coordinate parameters of a spatial coordinate system with the chasing light as a reference, and the spatial coordinate parameters are transmitted to the chasing light for chasing.

[0079] The horizontal parameter includes a PAN value, the vertical parameter includes a TILT value, and the spatial coordinate parameter includes a PAN value and a TILT value. The PAN value is used to represent a horizontal rotation angle, and the TILT value is used to represent a vertical rotation angle.

[0080] Specifically, the gimbal is equipped with a sensor that senses the gimbal's own rotation angle information. When the gimbal is adjusted according to the degree of overlap between the target light-chasing object and the light spot displayed in the current image data, the gimbal rotates, and the sensor senses the PAN value and TILT value of the gimbal and transmits them back to the gimbal. The gimbal converts the received PAN value and TILT value into PAN value and TILT value of a spatial coordinate system with the chase light as a reference, and transmits them to the chase light for chasing, so as to achieve the overlap of the light spot generated by the chase light with the target object, thereby improving the accuracy of chasing.

[0081] For example, when automatic light chasing is not needed or is not suitable, for example, when the stage environment is dark, or when there is no optional light chasing target (target light chasing object) on the stage, but a light column is needed to guide the host or actor to appear, the light chasing system provided by the present application can also cancel the automatic light chasing mode and switch to the remote manual light chasing mode. The user can output a manual control command to the pan-tilt through the human-computer interaction device of the pan-tilt, and the pan-tilt enters the manual control mode according to the manual control command. Then, the user holds the handle of the pan-tilt and adjusts the pan-tilt according to the overlap between the target light chasing object and the light spot. Since the pan-tilt is equipped with a sensor that senses the rotation angle information of the pan-tilt itself, and converts the rotation angle information into the Pan value and Tilt value of the light chasing light, and transmits it to the light chasing light, the light chasing light tracks the target according to the corresponding Pan value and Tilt value, thereby achieving the purpose of remote manual light chasing. Therefore, the light chasing system provided by the present application can freely switch between the automatic light chasing mode and the remote manual light chasing mode according to different occasions, and has greater flexibility and adaptability.

[0082] It can be understood that the user can adjust the gimbal according to the overlap degree of the target light-chasing object and the light spot by holding the handle of the gimbal. For example, the gimbal can adjust itself according to the overlap degree of the target light-chasing object and the light spot based on the current image data and the two-dimensional coordinate information of the target light-chasing object, which is not elaborated in the embodiments of the present application.

[0083] It should be noted that the chasing spot and the pan-tilt head preferably transmit data through the DMX512 communication protocol, and may also use communication protocols such as Art-net or ACN for data transmission, and may also use other communication interfaces or networks to transmit data, which is not limited in the embodiments of the present application; the user can also control the working state of the chasing spot through the pan-tilt head, for example: the color of the light, the light spot and other parameters. It can be understood that the pan-tilt head responds to the user's trigger operation, outputs light control instructions (other channel parameters) to the chasing spot, and instructs the chasing spot to enter the corresponding working state.

[0084] In the embodiment of the present application, by rotating and adjusting the degree of overlap between the light spot generated by the chasing spot light contained in the current image data and the target chasing spot object, the adjusted horizontal and vertical parameters of the gimbal are obtained, and the rotation angle of the chasing spot light is adjusted according to the horizontal and vertical parameters, so as to achieve the overlap between the light spot generated by the chasing spot light and the target object, thereby improving the accuracy of the chasing spot light.

[0085] Based on the same inventive concept, the embodiment of the present application also provides a control device for a light-chasing system for implementing the control method of the light-chasing system involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more control devices for light-chasing systems provided below can refer to the limitations of the control method for light-chasing systems above, and will not be repeated here.

[0086] In an exemplary embodiment, a control device of a light chasing system is provided, which is applied to a pan-tilt head in the light chasing system. The light chasing system further includes a server, a light chasing light, and an image acquisition device respectively connected to the pan-tilt head. The image acquisition device is respectively connected to the pan-tilt head and the server. The control device includes:

[0087] A receiving module, used to receive identification data output by the server, wherein the identification data includes two-dimensional coordinate information corresponding to the candidate light-chasing object; the identification data is obtained by the server after performing identification processing on the image data output by the image acquisition device;

[0088] A determination module is used to determine a target light-chasing object from candidate light-chasing objects, and obtain spatial coordinate data of the target light-chasing object in a lamp coordinate system according to two-dimensional coordinate information corresponding to the target light-chasing object. The lamp coordinate system is a spatial coordinate system constructed with the light-chasing lamp as a reference.

[0089] The output module is used to send the spatial coordinate data to the chasing spot, and the spatial coordinate data is used to instruct the chasing spot to adjust the irradiation angle so that the light of the chasing spot can illuminate the target chasing object.

[0090] In one of the embodiments, the identification data further includes an object identifier corresponding to the candidate light-chasing object;

[0091] The determination module is also used to respond to an object selection operation on the candidate light-chasing objects triggered by the user based on the object identifier, and determine the target light-chasing object corresponding to the object selection operation among the candidate light-chasing objects.

[0092] In one of the embodiments, the control device includes a matching module for receiving current image data transmitted by the image acquisition device;

[0093] The current image data is matched with the two-dimensional coordinate information and the object identifier corresponding to the candidate light-chasing object to update the two-dimensional coordinate information corresponding to the candidate light-chasing object in real time.

[0094] In one embodiment, the control device includes an adjustment module for receiving current image data transmitted by the image acquisition device; the current image data contains a light spot generated by the follow-up light;

[0095] The gimbal is adjusted according to the overlap between the target light-chasing object and the light spot, and the horizontal and vertical parameters of the gimbal after adjustment are obtained;

[0096] The horizontal parameters and the vertical parameters are converted into spatial coordinate parameters of a spatial coordinate system with the chasing light as a reference, and the spatial coordinate parameters are transmitted to the chasing light for chasing.

[0097] In an exemplary embodiment, as shown in FIG3 , a control method of a light-chasing system is provided, and the method is described by taking the application of the method to the server in FIG1 as an example. The method includes:

[0098] S302, receiving image data output by an image acquisition device, and performing recognition processing on the image data to obtain recognition data; wherein the recognition data includes two-dimensional coordinate information corresponding to the candidate light-chasing object.

[0099] Specifically, the camera collects image data on the stage and transmits it to the server. The server identifies all candidate light-chasing objects in the image data in real time, records the two-dimensional coordinate information of each candidate light-chasing object, and makes a unique object identification to obtain identification data.

[0100] Exemplarily, the camera can capture images or videos on the stage, and transmit the images or videos as image data to the server; wherein the camera and the server preferably transmit the image data via the RTSP protocol.

[0101] S304, output the identification data to the gimbal; the identification data is used to instruct the gimbal to determine the target light chasing object from the candidate light chasing objects, obtain the spatial coordinate data of the target light chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light chasing object, the lamp coordinate system is a spatial coordinate system constructed with the chasing spot as a reference; and send the spatial coordinate data to the chasing spot, the spatial coordinate data is used to instruct the chasing spot to adjust the illumination angle so that the light of the chasing spot illuminates the target light chasing object.

[0102] Specifically, the server outputs the identification data to the gimbal in real time. The gimbal receives the identification data and determines the target light-chasing object according to the user's operation, and obtains the two-dimensional coordinate information corresponding to the target light-chasing object. The gimbal calculates the spatial coordinate data of the target light-chasing object in the lamp coordinate system based on the spatial coordinate system and the two-dimensional coordinate information corresponding to the target light-chasing object. The gimbal sends the spatial coordinate data to the chasing light. The chasing light adjusts its own angle to the corresponding position according to the spatial coordinate data, thereby completing the automated chasing of the target light-chasing object.

[0103] In the control method of the above-mentioned light chasing system, the server identifies and processes the received image data, and outputs the processed identification data to the gimbal, so that the gimbal can subsequently obtain the spatial coordinate data of the target light chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light chasing object when determining the target light chasing object, and output the spatial coordinate data to the light chasing light to achieve light chasing for the target light chasing object. Compared with the existing light chasing method, the light chasing can be realized automatically throughout the process, which reduces labor costs and improves control accuracy. There is no need for the light chasing object to wear a transmitting device on the body, which further reduces the cost of light chasing.

[0104] In one of the embodiments, the identification data further includes an object identifier corresponding to the candidate light-chasing object;

[0105] Perform recognition processing on the image data to obtain recognition data, including:

[0106] The image data is input into the target recognition model, the candidate light-chasing object in the image data is determined by using the target recognition model, and the two-dimensional coordinate information corresponding to the candidate light-chasing object is obtained;

[0107] An object identifier corresponding to the candidate light-chasing object is created.

[0108] Specifically, a target recognition model is configured inside the server. The server inputs the received image data into the target recognition model. The target recognition model recognizes the image data, obtains all candidate light-chasing objects in the image data, and obtains the two-dimensional coordinate information corresponding to each candidate light-chasing object in the image data. The server creates a unique object identifier corresponding to the candidate light-chasing object based on the features corresponding to each candidate light-chasing object.

[0109] In an embodiment of the present application, a target recognition model is configured in the server to obtain all candidate light-chasing objects in the image data, as well as the two-dimensional coordinate information corresponding to each candidate light-chasing object, and an object identifier corresponding to the candidate light-chasing object is created, thereby facilitating subsequent instructions to the pan / tilt head and the follow-spot light to chase the light, thereby improving the control accuracy of the follow-spot light.

[0110] In one embodiment, before performing recognition processing on the image data and obtaining recognition data, the method further includes:

[0111] The acquired image samples are randomly divided into a first sample set and a second sample set;

[0112] Annotate the first sample set to obtain a test data set;

[0113] Each candidate recognition model is trained respectively through the test data set to obtain each candidate recognition model that has completed training;

[0114] Recognize the second sample set based on each trained candidate recognition model to obtain a recognition result;

[0115] The current best candidate recognition model is determined according to the recognition result, and the current best candidate recognition model is used as the target recognition model.

[0116] Among them, the number of samples contained in the first sample set and the second sample set can be set according to actual conditions and is not limited in the embodiments of the present application; the image samples can be videos or pictures of a single or multiple people of different colors moving under the camera.

[0117] Specifically, the server randomly divides the image samples into a first sample set and a second sample set, uses a labeling tool to label the first sample set, labels the coordinates of the minimum outline of the candidate light-chasing object, imports the labeled file set as a test data set into the YOLO big data recognition training framework environment, and sets multiple weights for training. It can be understood that by importing the test data set into a YOLO model with different training weights, multiple candidate recognition models that have completed training can be obtained after training. The second sample set is used to backtest each candidate recognition model that has completed training to obtain a recognition result, and the accuracy of each candidate recognition model that has completed training is determined based on the recognition result. The candidate recognition model with the highest recognition accuracy, that is, the current best candidate recognition model, is confirmed as the target recognition model, and the target recognition model is set in the server to facilitate subsequent recognition processing of the image data.

[0118] Exemplarily, the candidate recognition models include the YOLOv8n model, the YOLOv8s model, the YOLOv8m model, the YOLOv8l model, and the YOLOv8x model; among them, the YOLOv8n model (YOLOv8n-cls model), which is the lightest model in the series, has the fastest processing speed but relatively low accuracy, and is suitable for scenarios with limited resources or high speed requirements; the YOLOv8s model (YOLOv8s-cls model), compared with the YOLOv8n model, has improved accuracy while maintaining a higher speed, and is suitable for scenarios that require both speed and accuracy. The YOLOv8m model (YOLOv8m-cls model) has significantly improved accuracy and is suitable for scenarios with higher requirements for accuracy but still need to consider processing speed; the YOLOv8l model (YOLOv8l-cls model) has higher accuracy, making it suitable for applications with high accuracy requirements, but with slower processing speed; the YOLOv8x model (YOLOv8x-cls model) in this series provides the highest accuracy, but the slowest speed and requires strong hardware support, making it suitable for high-end applications where accuracy is critical.

[0119] It should be noted that the candidate recognition model may also be other YOLO models, which are not limited to the models provided in the embodiments of the present application.

[0120] In an embodiment of the present application, a first sample set is used to train each candidate recognition model, and a second sample set is used to backtest each candidate recognition model that has completed training, and the candidate recognition model with the highest accuracy is selected as the target recognition model to facilitate subsequent recognition processing of image data and improve the control accuracy of the chase light.

[0121] In an exemplary embodiment, a control device for a light chasing system is provided, which is applied to a server in the light chasing system. The light chasing system further includes a pan / tilt connected to the server, and a light chasing lamp and an image acquisition device respectively connected to the pan / tilt. The image acquisition device is connected to the server. The device includes:

[0122] The recognition processing module is used to receive the image data output by the image acquisition device, and perform recognition processing on the image data to obtain recognition data; wherein the recognition data includes the two-dimensional coordinate information corresponding to the candidate light-chasing object;

[0123] The data output module is used to output the identification data to the gimbal; the identification data is used to instruct the gimbal to determine the target light-chasing object from the candidate light-chasing objects, and obtain the spatial coordinate data of the target light-chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light-chasing object. The lamp coordinate system is a spatial coordinate system constructed with the chasing spot as a reference; and the spatial coordinate data is sent to the chasing spot. The spatial coordinate data is used to instruct the chasing spot to adjust the illumination angle so that the light of the chasing spot illuminates the target light-chasing object.

[0124] In one of the embodiments, the identification data further includes an object identifier corresponding to the candidate light-chasing object;

[0125] The recognition processing module is further used to input the image data into the target recognition model, determine the candidate light-chasing object in the image data using the target recognition model, and obtain the two-dimensional coordinate information corresponding to the candidate light-chasing object;

[0126] An object identifier corresponding to the candidate light-chasing object is created.

[0127] In one of the embodiments, the recognition processing module is further used to randomly divide the acquired image samples into a first sample set and a second sample set;

[0128] Annotate the first sample set to obtain a test data set;

[0129] Each candidate recognition model is trained respectively through the test data set to obtain each candidate recognition model that has completed training;

[0130] Recognize the second sample set based on each trained candidate recognition model to obtain a recognition result;

[0131] The current best candidate recognition model is determined according to the recognition result, and the current best candidate recognition model is used as the target recognition model.

[0132] Each module in the control device of the above-mentioned light chasing system can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0133] In an exemplary embodiment, as shown in FIG4 , a light-chasing system is provided, and the light-chasing system includes:

[0134] A pan / tilt platform 10, which is used to execute the steps of the above method;

[0135] A server 20, connected to the PTZ 10, and configured to execute the steps of the above method;

[0136] A follow spot light 30 connected to the PTZ 10;

[0137] The image acquisition device 40 is connected to the pan / tilt station 10 and the server 20 respectively.

[0138] Specifically, as shown in FIG. 4 , the server 20 performs recognition processing on the image data collected by the image acquisition device 40, and outputs the recognition data obtained through the recognition processing to the gimbal 10. The gimbal 10 obtains the spatial coordinate data of the target light-chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light-chasing object in the recognition result, and sends the spatial coordinate data to the chasing spot 013, instructing the chasing spot 013 to adjust its own angle to illuminate the target light-chasing object 015, that is, during the movement of the target light-chasing object 015, the chasing spot 013 tracks the target light-chasing object 015 in real time to realize automatic light chasing.

[0139] In one of the embodiments, the gimbal is equipped with a first rotating mechanism and an angle sensor, the first rotating mechanism is used to drive the gimbal to rotate, and the angle sensor is used to obtain horizontal parameters and vertical parameters of the gimbal after rotation.

[0140] Wherein, the first rotating mechanism includes a first horizontal rotating mechanism and a first vertical rotating mechanism; the angle sensor includes a horizontal sensor and a vertical sensor.

[0141] Specifically, the first horizontal rotation mechanism is used to drive the gimbal to rotate horizontally, and the first vertical rotation mechanism is used to drive the gimbal to rotate vertically. The horizontal sensor senses the horizontal rotation angle (PAN value) of the gimbal itself, and the vertical sensor senses the vertical rotation angle (TILT value) of the gimbal itself, and both are transmitted to the gimbal. The gimbal converts its own PAN value and TILT value received into PAN value and TILT value of the spatial coordinate system with the chasing light as reference, and transmits them to the chasing light for chasing light.

[0142] In the embodiment of the present application, by configuring a first rotating mechanism and an angle sensor on the gimbal, the gimbal can obtain its own horizontal parameters and vertical parameters while rotating, which facilitates the subsequent overlap of the light spot generated by the chasing light with the target object, improves the accuracy of the chasing light, and subsequently achieves the purpose of remote manual chasing light, thereby improving the flexibility and adaptability of the chasing light.

[0143] In one of the embodiments, the follow spot light is provided with a second rotating mechanism, and the second rotating mechanism is used for driving the follow spot light to rotate.

[0144] Wherein, the second rotating mechanism includes a second horizontal rotating mechanism and a second vertical rotating mechanism.

[0145] Specifically, the second horizontal rotation mechanism is used to drive the chasing light to rotate horizontally, and the second vertical rotation mechanism is used to drive the chasing light to rotate vertically.

[0146] Exemplarily, the image acquisition device may be disposed on the chasing spot and may rotate together with the chasing spot; or, the image acquisition device is not disposed on the chasing spot, and a third rotating mechanism is provided on the image acquisition device, and the third rotating mechanism is used to drive the image acquisition device to rotate.

[0147] In the embodiment of the present application, a second rotating mechanism is configured on the chasing light to achieve automatic chasing or remote manual chasing.

[0148] It should be noted that the user information (including but not limited to the two-dimensional coordinate information corresponding to the target light-chasing object, the features corresponding to the target light-chasing object, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0149] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0150] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0151] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A control method for a light chasing system, characterized in that: The pan-tilt used in the light chasing system further comprises a server, a light chasing light and an image acquisition device respectively connected to the pan-tilt, and the image acquisition device is respectively connected to the pan-tilt and the server; the method comprises: Receiving identification data output by the server, wherein the identification data includes two-dimensional coordinate information corresponding to the candidate light-chasing object; the identification data is obtained by the server after performing identification processing on the image data output by the image acquisition device; Determine a target light-chasing object from the candidate light-chasing objects, and obtain spatial coordinate data of the target light-chasing object in a lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light-chasing object, wherein the lamp coordinate system is a spatial coordinate system constructed with the light-chasing lamp as a reference; The spatial coordinate data is sent to the chasing spot, and the spatial coordinate data is used to instruct the chasing spot to adjust the irradiation angle so that the light of the chasing spot can illuminate the target chasing object.

2. The method according to claim 1, characterized in that The identification data also includes an object identifier corresponding to the candidate light-chasing object; The step of determining a target light-chasing object from the candidate light-chasing objects includes: In response to an object selection operation for the candidate light-chasing objects triggered by a user based on the object identifier, a target light-chasing object corresponding to the object selection operation is determined from among the candidate light-chasing objects.

3. The method according to claim 2, characterized in that The method further comprises: Receiving current image data transmitted by the image acquisition device; The current image data is matched with the two-dimensional coordinate information and the object identifier corresponding to the candidate light-chasing object to update the two-dimensional coordinate information corresponding to the candidate light-chasing object in real time.

4. The method according to claim 1, characterized in that: The method further comprises: Receiving current image data transmitted by the image acquisition device; the current image data contains the light spot generated by the chasing light; Adjusting the pan / tilt platform according to the overlap between the target light-chasing object and the light spot, and obtaining horizontal parameters and vertical parameters of the pan / tilt platform after the adjustment; The horizontal parameter and the vertical parameter are converted into space coordinate parameters of a space coordinate system with the chasing spot as a reference, and the space coordinate parameters are transmitted to the chasing spot for chasing light.

5. A control method for a light chasing system, characterized in that: The server used in the light chasing system further comprises a pan-tilt connected to the server, and a light chasing lamp and an image acquisition device respectively connected to the pan-tilt, and the image acquisition device is connected to the server; the method comprises: Receiving image data output by an image acquisition device, and performing recognition processing on the image data to obtain recognition data; wherein the recognition data includes two-dimensional coordinate information corresponding to the candidate light-chasing object; The identification data is output to the gimbal; the identification data is used to instruct the gimbal to determine a target light-chasing object from the candidate light-chasing objects, and obtain the spatial coordinate data of the target light-chasing object in the lamp coordinate system according to the two-dimensional coordinate information corresponding to the target light-chasing object, wherein the lamp coordinate system is a spatial coordinate system constructed with the chasing spot as a reference; and the spatial coordinate data is sent to the chasing spot, and the spatial coordinate data is used to instruct the chasing spot to adjust an illumination angle so that the light of the chasing spot illuminates the target light-chasing object.

6. The method according to claim 5, characterized in that The identification data also includes an object identifier corresponding to the candidate light-chasing object; The step of performing recognition processing on the image data to obtain recognition data includes: Inputting the image data into a target recognition model, determining the candidate light-chasing object in the image data using the target recognition model, and acquiring the two-dimensional coordinate information corresponding to the candidate light-chasing object; Create the object identifier corresponding to the candidate light-chasing object.

7. The method according to claim 6, characterized in that Before the image data is subjected to recognition processing to obtain recognition data, the method further includes: The acquired image samples are randomly divided into a first sample set and a second sample set; Annotating the first sample set to obtain a test data set; Each candidate recognition model is trained using the test data set to obtain each trained candidate recognition model; Recognize the second sample set based on each of the trained candidate recognition models to obtain a recognition result; The current best candidate recognition model is determined according to the recognition result, and the current best candidate recognition model is used as the target recognition model.

8. A light chasing system, characterized in that: The light chasing system comprises: A pan / tilt platform, the pan / tilt platform being used to perform the steps of the method according to any one of claims 1 to 4; A server, connected to the pan / tilt platform, the server being used to perform the steps of the method according to any one of claims 5 to 7; A follow-up light connected to the pan / tilt head; An image acquisition device is connected to the pan-tilt head and the server respectively.

9. The light chasing system according to claim 8, characterized in that: The gimbal is equipped with a first rotating mechanism and an angle sensor. The first rotating mechanism is used to drive the gimbal to rotate, and the angle sensor is used to obtain horizontal parameters and vertical parameters of the gimbal after the rotation.

10. The light chasing system according to claim 8, characterized in that: The chasing spot light is provided with a second rotating mechanism, and the second rotating mechanism is used for driving the chasing spot light to rotate.

Images