CN112243581A

CN112243581A - Pan-tilt, control device of pan-tilt, control method of pan-tilt and storage medium

Info

Publication number: CN112243581A
Application number: CN201980038365.4A
Authority: CN
Inventors: 杨龙超; 朱高; 熊风
Original assignee: SZ DJI Technology Co Ltd
Current assignee: SZ DJI Technology Co Ltd; SZ DJI Innovations Technology Co Ltd
Priority date: 2019-11-26
Filing date: 2019-11-26
Publication date: 2021-01-19
Also published as: WO2021102695A1

Abstract

A head, a control device of a head, a control method of a head, and a storage medium, wherein the head (100) includes: a memory (102) configured to store computer instructions; and a processor (104) configured to execute computer instructions to implement: receiving image information of a shot picture in real time, wherein a shot object exists in the shot picture (S102); detecting composition information of a first recognition target in the shooting picture according to the image information, wherein the first recognition target is at least one part of the shooting object (S104); it is determined whether a recognition target switching instruction is generated according to composition information of the first recognition target (S106). The cloud platform determines whether to generate an identification target switching instruction or not according to the detected composition information of the first identification target, namely whether to switch the identification target or not can be reasonably selected according to the composition information of the first identification target of the shooting object in the current shooting picture, so that the identification success rate is improved, and the composition is beautified.

Description

Pan-tilt, control device of pan-tilt, control method of pan-tilt and storage medium

Technical Field

The present application relates to the field of electronic technology application, and in particular, to a cradle head, a control device for a cradle head, a control method for a cradle head, and a computer-readable storage medium.

Background

When a user shoots a specific object, such as a person or an animal, a scene that is often generated is a scene that allows a shot picture to be locked on the object in a field of view of an image capturing apparatus (such as a camera) and then continuously shot. In general, such shooting with continuous alignment of the target can be performed by using a shooting device with automatic following, such as a pan-tilt. However, in any of the above-mentioned operation scenarios, when the subject changes from far to near with respect to the image capturing apparatus, the recognition may fail or the composition may be not beautiful, for example, when the subject is the whole body of a person, and when the person walks into the camera, only a part of the person remains in the camera image, the recognition may fail and the composition may not be beautiful; when the subject to be followed is the head and shoulder of a person, the head and shoulder of the person becomes small in the camera picture and easily confused with the background when the person is far from the camera, resulting in a failure in recognition.

Disclosure of Invention

The present application is directed to solving at least one of the problems of the prior art or the related art.

To this end, a first aspect of the present application proposes a head.

A second aspect of the present application proposes a control device of a pan and tilt head.

A third aspect of the present application provides a control method of a pan/tilt head.

A fourth aspect of the present application proposes a computer-readable storage medium.

In view of this, according to a first aspect of the present application, there is provided a head comprising: a memory configured to store computer instructions; and a processor configured to execute the computer instructions to implement: receiving image information of a shot picture in real time, wherein a shot object exists in the shot picture; detecting composition information of a first recognition target in a shooting picture according to the image information, wherein the first recognition target is at least one part of a shooting object; whether to generate a recognition target switching instruction is determined based on composition information of the first recognition target.

According to a second aspect of the present application, there is provided a control apparatus of a pan/tilt head, comprising: a memory configured to store computer instructions; and a processor configured to execute the computer instructions to implement: receiving image information of a shot picture in real time, wherein a shot object exists in the shot picture; detecting composition information of a first recognition target in a shooting picture according to the image information, wherein the first recognition target is at least one part of a shooting object; whether to generate a recognition target switching instruction is determined based on composition information of the first recognition target.

According to a third aspect of the present application, there is provided a control method of a pan/tilt head for a pan/tilt head or a control apparatus of a pan/tilt head, the control method of a pan/tilt head comprising: receiving image information of a shot picture in real time, wherein a shot object exists in the shot picture; detecting composition information of a first recognition target in a shooting picture according to the image information, wherein the first recognition target is at least one part of a shooting object; whether to generate a recognition target switching instruction is determined based on composition information of the first recognition target.

According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out the steps of the method for controlling a head according to any one of the preceding claims.

The embodiment of the application provides a cloud deck and a control scheme thereof, whether an identification target switching instruction is generated or not is determined according to detected composition information of a first identification target, namely whether the identification target is switched or not is reasonably selected according to the composition information of the first identification target of a shooting object in a current shooting picture, so that the identification success rate is improved, and composition beautification is facilitated. The scheme can be applied to the automatic following shooting function (namely the automatic following shooting function) of the cloud deck based on the automatic following technology so as to switch and adjust following targets in time, thereby not only ensuring the following success, but also enabling the composition to be attractive and improving the following shooting effect; the automatic camera shooting device can be used when the cradle head is aligned to a shooting object through a human hand without starting the automatic camera shooting function, so that the reasonable adjustment of the recognition target is facilitated, the composition is optimized, and the shooting effect is improved.

Additional aspects and advantages of the present application will be set forth in part in the description which follows, or may be learned by practice of the present application.

Drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 shows a schematic structural view of a head of an embodiment of the present application;

fig. 2 shows a schematic structural diagram of a control device of a pan-tilt head of an embodiment of the present application;

fig. 3 shows a schematic flow chart of a control method of a pan-tilt head of an embodiment of the present application;

fig. 4 shows a schematic flow chart of a control method of a pan-tilt head of another embodiment of the present application;

fig. 5 shows a schematic flow chart of a control method of a pan-tilt head of a further embodiment of the present application;

fig. 6 shows a schematic flow chart of a control method of a pan and tilt head according to a further embodiment of the present application.

Detailed Description

In order that the above objects, features and advantages of the present application can be more clearly understood, the present application will be described in further detail with reference to the accompanying drawings and detailed description. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited by the specific embodiments disclosed below.

As shown in fig. 1, an embodiment of the first aspect of the present application provides a pan and tilt head 100, including: a memory 102 configured to store computer instructions; and a processor 104 configured to execute computer instructions to implement: receiving image information of a shot picture in real time, wherein a shot object exists in the shot picture; detecting composition information of a first recognition target in a shooting picture according to the image information, wherein the first recognition target is at least one part of a shooting object; whether to generate a recognition target switching instruction is determined based on composition information of the first recognition target.

The cloud deck 100 provided in the embodiment of the present application, through configuring the processor 104, determines whether to generate the recognition target switching instruction according to the detected composition information of the first recognition target when executing the computer instruction stored in the memory 102, that is, whether to switch the recognition target according to the composition information of the first recognition target of the shooting object in the current shooting picture is reasonably selected, which not only improves the recognition success rate, but also helps to beautify the composition. It is understood that the recognition targets before and after the switching all belong to the same photographic subject. In addition, the scheme can be applied to the automatic following and shooting function of the holder 100 based on an automatic following technology so as to switch and adjust following targets in time, thereby ensuring the following success, making the composition beautiful and improving the following and shooting effect; the automatic shooting tracking function can be used when the cradle head 100 is aligned to the shooting object through hands without starting the automatic shooting tracking function, for example, when the cradle head 100 is manually controlled to track the shooting, the reasonable adjustment of the recognition target is facilitated, the picture composition is optimized, the shooting effect is improved, and if only the cradle head 100 is manually controlled to align to the shooting object and the shooting is not started temporarily, the better recognition state and the picture composition state can be ensured, so that the shooting can be started at any time.

In some embodiments, the composition information includes a size, and the processor 104 executing computer instructions to determine whether to generate the recognition target switching instruction based on the composition information of the first recognition target includes: and determining that the size of the first recognition target is out of the preset size range, and generating a recognition target switching instruction.

In this embodiment, the composition information is specifically limited to include a size, and accordingly, a scheme for determining whether to generate the recognition target switching instruction is to determine that the size of the first recognition target in the shooting picture is unreasonable when the size of the first recognition target is outside a preset size range, and further generate the recognition target switching instruction so as to switch to a recognition target with a more reasonable size, so that the recognition success rate is improved, and the composition is beautified.

In some embodiments, identifying the target switch instruction comprises identifying a target expand instruction, and the processor 104 executes computer instructions to determine that the size of the first identification target is outside of the preset size range, and generating the identification target switch instruction comprises: and determining that the size of the first recognition target is smaller than the lower limit size of the preset size range, and generating a recognition target expansion instruction.

In this embodiment, it is further defined that when it is detected that the size of the first recognition target is smaller than the lower limit size, the first recognition target is considered to be too small in size in the shooting screen, and a recognition target enlarging instruction may be generated accordingly to switch to a larger recognition target corresponding to a case where the photographic subject is far from the pan/tilt head 100. It is understood that the larger recognition target means a recognition target that occupies a larger proportion of the photographic subject than the first recognition target. The first recognition target may be included in a larger recognition target, for example, the first recognition target is the head and shoulder of the photographic subject, and the larger recognition target is the whole body of the photographic subject; the first recognition target may also be completely different from the larger recognition target, e.g. the first recognition target is a head and the larger recognition target is a torso; the first recognition target may also be partially overlapped with a larger recognition target, for example, the first recognition target is a head and a shoulder, the larger recognition target is an upper limb, and the overlapped part of the two is the shoulder. Along with the distance of the shooting object, the size of the first recognition target in the shooting picture is gradually reduced, and when the size of the first recognition target is too small, the first recognition target is easy to be confused with the background, so that the recognition accuracy is reduced, the recognition is failed, and the composition effect and the realization of the automatic follow shooting function are influenced. By generating the identification target expansion instruction, the identification target can be switched to a larger identification target which is convenient to identify in time, the identification success rate is improved, the composition is beautified, and the reliable operation of the automatic follow shooting function is ensured.

In some embodiments, identifying the target switch instruction comprises identifying a target shrink instruction, and the processor 104 executing the computer instructions to determine that the size of the first identified target is outside of the preset size range, generates the identifying the target switch instruction, comprising: and determining that the size of the first recognition target is larger than the upper limit size of the preset size range, and generating a recognition target reduction instruction.

In this embodiment, similar to the recognition target expansion instruction, the recognition target switching instruction may further include a recognition target reduction instruction and be generated upon detecting that the size of the first recognition target is larger than the upper limit size to switch to a smaller recognition target, corresponding to a case where the photographic subject approaches the pan/tilt head 100. It is understood that the relationship between the first recognition target and the smaller recognition target is the same as the relationship between the larger recognition target and the first recognition target, and the first recognition target is not fixed, but refers to the recognition target currently in use, and can be switched and changed along with the movement of the shooting object. Along with the approach of a shooting object, the size of the first recognition target in the shooting picture is gradually enlarged, when the size of the first recognition target is too large, if composition is continuously executed according to the first recognition target, the composition attractiveness can be reduced, even the situation that the first recognition target overflows the shooting picture and recognition fails occurs, at the moment, a recognition target reduction instruction is generated, the smaller recognition target can be timely switched to, the composition can be beautified, the problem that the first recognition target overflows the shooting picture is solved, the recognition success rate is improved, and the reliable operation of the automatic follow-up shooting function can be ensured.

In some embodiments, the processor 104, when executing the computer instructions, further implements: and responding to the identification target switching instruction, switching from a first identification target to a second identification target, wherein the second identification target is at least one part of the shooting object, and the proportion of the first identification target to the shooting object is different from that of the second identification target to the shooting object.

In this embodiment, the processor 104 may further switch the recognition target from the first recognition target of the photographic subject to the second recognition target of the photographic subject based on the recognition target switching instruction, so as to implement automatic switching of the recognition target, without manual operation by a user, and improve convenience of operation and timeliness of switching. The first recognition target and the second recognition target respectively occupy different proportions in the shot object, so that the recognition in the shooting process can be effectively adjusted, the recognition success rate can be improved, and the composition can be beautified.

In some embodiments, the composition information further comprises a location, and the processor 104 when executing the computer instructions further implements: and adjusting the shooting parameters according to the composition information of the first recognition target so that the imaging of the first recognition target in the shooting picture meets the composition rule.

In this embodiment, the composition information further includes a position, and based on the composition information of the first recognition target in the captured image and the composition rule, the processor 104 may automatically adjust the capturing parameters according to the movement and change of the first recognition target in the captured image, so as to adjust and beautify the composition. It can be understood that when the pan/tilt head 100 is aligned to the shooting object by human hand, the shooting parameters can be automatically fine-tuned in combination with the present solution, so as to realize automatic composition.

In some embodiments, processor 104 executes computer-implemented instructions to switch from a first recognition goal to a second recognition goal, including: detecting composition information of a second recognition target in the shooting picture; and adjusting the shooting parameters to enable the position and the size of the second recognition target in the shooting picture to gradually change until the imaging of the second recognition target in the shooting picture meets the composition rule.

In the embodiment, in the process of automatically switching the recognition targets, by detecting the composition information of the second recognition target and automatically adjusting the shooting parameters in combination with the composition rule, the position and the size of the second recognition target in the shooting picture are gradually changed until the imaging of the second recognition target in the shooting picture meets the composition rule, the switching process of the recognition targets can be made smooth and stable, and the shooting effect is ensured based on the composition of the second recognition target. It can be understood that, when the recognition target switching instruction includes the above recognition target expansion instruction and the recognition target reduction instruction, the recognition target and the composition can be automatically adjusted along with the distance between the shooting object and the pan/tilt head 100, which not only improves the recognition success rate, but also helps to beautify the composition.

In some embodiments, the composition rules include at least one of: the method comprises the steps of completely imaging a recognition target, positioning the recognition target in a specified area in a shooting picture, performing balanced composition, symmetric composition, diagonal composition, triangular composition, Sudoku composition, centripetal composition and split composition.

In this embodiment, the content of the composition rule is specifically defined, and the shooting effect of the shot object can be ensured by taking the complete imaging and/or the position in the specified area in the shooting picture as the composition rule for the current recognition target; and the imaging of the whole shooting picture can be realized, so that different composition forms are met, and the integral attractiveness of the shooting picture is ensured.

In some embodiments, the head 100 further comprises: a cradle device capable of supporting a camera device for acquiring image information and/or a camera device for acquiring image information; the shooting parameters include at least one of: the height of the shooting device, the inclination angle of the shooting device, the direction of the shooting device, and the focal length of the shooting device.

In this embodiment, it is specifically defined that the shooting parameters include at least one of a height, an inclination, a direction, and a focal length of the shooting device, and by adjusting the shooting parameters, the shooting device can be controlled to achieve shooting. The shooting device may be a structure of the cradle head 100 itself, or may be a third-party structure, and for the latter, the cradle head 100 needs to be configured with a support device to support the shooting device.

In some embodiments, one of the first recognition target and the second recognition target is an entirety of the photographic subject, and the other of the first recognition target and the second recognition target is a designated portion of the photographic subject.

In this embodiment, it is specifically defined that the entire subject can be regarded as one recognition target, and a specified portion of the subject, for example, the head and shoulder, can be regarded as another recognition target, so that the full/half body composition is automatically switched so that the subject is always at the optimal composition position according to the change in the distance of the subject from the pan/tilt head 100 by using the pedestrian detection technology, the head and shoulder detection technology, or the detection technology and the automatic following technology of another specified portion. The pedestrian detection and the head and shoulder detection are techniques of automatically detecting the whole body and the head and shoulders of a pedestrian in a sensor field of view by taking various sensors (such as a camera) as input, and obtaining the position and the occupied size of the pedestrian in a picture.

In some embodiments, the processor 104, when executing the computer instructions, further implements: and outputting a target switching identification instruction.

In this embodiment, the processor 104 may also directly output a recognition target switching instruction to prompt the user to manually switch the recognition target, ensuring autonomous control of the user. It will be appreciated that both the automatic switching mode and the manual switching mode may be configured for the pan/tilt head 100, with the user selecting which one to employ. In addition, if the recognition target needs to be switched in the process of recording the video, the recording can be suspended firstly, and the recording is continued after the recognition target is manually selected again.

In some embodiments, the processor 104, when executing the computer instructions, further implements: outputting at least one alternative recognition target; switching from the first recognition target to the selected one of the at least one alternative recognition target.

In the embodiment, at least one reasonable alternative recognition target can be provided for the user to select during manual switching, and the user does not need to manually frame a specific part of the shooting object as the recognition target to be switched, so that the switching speed is increased, the situation that the selected recognition target is inconvenient to recognize is avoided, and the efficiency and the success rate of manually switching the recognition target are improved. It is conceivable that the candidate recognition target may be a plurality of recognition targets corresponding to a plurality of different portions of the photographic subject, or may be at least one recognition target determined to be suitable for switching by filtering, and for the latter, when one candidate recognition target is present, may be the second recognition target in the automatic switching mode.

In some embodiments, the processor 104, when executing the computer instructions, further implements: detecting an alternative recognition target of at least one alternative photographic object based on the condition that at least one alternative photographic object exists in the photographic picture; outputting at least one alternative recognition target; and taking the selected candidate recognition target as a first recognition target, and taking a candidate shooting object to which the first recognition target belongs as a shooting object.

In this embodiment, how the photographic subject and its first recognition target are determined in the initial stage is further defined. When the alternative shooting objects exist in the shooting picture, the recognition targets of the alternative shooting objects can be detected to serve as the alternative recognition targets and output for the user to select, and then the alternative recognition target selected by the user and the alternative shooting object to which the alternative recognition target belongs serve as the first recognition target and the shooting object respectively, so that the efficiency of selecting the shooting object and the first recognition target in the initial stage is improved.

In some embodiments, processor 104 executes computer-implemented instructions to output at least one alternative recognition objective, including: and outputting one alternative recognition target for each alternative shooting object.

In the embodiment, only one candidate recognition target is specifically limited to be output for each candidate shooting object, so that the selection amount faced by a user in selection can be reasonably reduced, the user can make a decision conveniently, and the efficiency of selecting the shooting object and the first recognition target thereof in the initial stage is further improved.

In some embodiments, processor 104 executes computer instructions to output an alternative recognition goal, including: determining the number of the alternative recognition targets corresponding to the alternative shooting objects as one, and outputting the corresponding alternative recognition targets; and determining the number of the candidate recognition targets corresponding to the candidate shooting objects to be at least two, and outputting one corresponding candidate recognition target.

In this embodiment, it is specifically defined that, for one candidate photographic subject, if the number of candidate recognition targets is one, the candidate recognition targets are directly output, and if the number of candidate recognition targets is at least two, one of the candidate recognition targets is selected, and specifically, one currently suitable for recognition may be selected to ensure recognition effect.

In some embodiments, the processor 104 executes one of the alternative recognition targets corresponding to the computer-implemented output, including: and detecting the sizes of all the corresponding alternative recognition targets in the shooting picture, and determining the output alternative recognition targets according to the sizes.

In this embodiment, a scheme of selecting one of the at least two candidate recognition targets for output is specifically defined. The sizes of all the alternative recognition targets of one shooting object in the shooting picture can be absolute sizes, such as width and height, or relative sizes, such as proportion of the whole shooting picture, and the sizes of the alternative recognition targets can be reflected, so that the alternative recognition targets with the sizes suitable for recognition are selected and output, and the recognition effect is ensured.

In some embodiments, the processor 104, when executing the computer instructions, further implements: and outputting the image information in real time.

In this embodiment, it is further defined that the processor 104 can also output the image information of the shot picture in real time to present the change of the shot object and the composition to the user in real time, so that the user can know the shooting condition or make an adjustment operation.

In some embodiments, the head 100 further comprises: and the display screen is used for displaying the image information.

In this embodiment, it is further defined that the cradle head 100 is further configured with a display screen so as to display the image information of the shot picture, and the reliability of the output is ensured.

As shown in fig. 2, an embodiment of the second aspect of the present application provides a control apparatus 200 of a pan/tilt head, including: a memory 202 configured to store computer instructions; and a processor 204 configured to execute computer instructions to implement: receiving image information of a shot picture in real time, wherein a shot object exists in the shot picture; detecting composition information of a first recognition target in a shooting picture according to the image information, wherein the first recognition target is at least one part of a shooting object; whether to generate a recognition target switching instruction is determined based on composition information of the first recognition target.

According to the control device 200 of the pan/tilt head provided by the embodiment of the application, when the processor 204 is configured to execute the computer instruction stored in the memory 202, whether to generate the identification target switching instruction is determined according to the detected composition information of the first identification target, that is, whether to switch the identification target can be reasonably selected according to the composition information of the first identification target of the shooting object in the current shooting picture, so that the identification success rate is improved, and the composition is beautified. It is understood that the recognition targets before and after the switching all belong to the same photographic subject. In addition, the scheme can be applied to the automatic following and shooting function of the cloud deck based on the automatic following technology so as to switch and adjust following targets in time, thereby ensuring the following success, enabling the composition to be attractive and improving the following and shooting effect; the automatic shooting tracking device can be used when the cradle head is aligned to the shooting object through a human hand without starting the automatic shooting tracking function, for example, when the cradle head is manually controlled to track the shooting object, the reasonable adjustment of the recognition target is facilitated, the picture composition is optimized, the shooting effect is improved, and if only the cradle head is manually controlled to align the shooting object and the shooting is not started temporarily, the better recognition state and the picture composition state can be ensured, so that the shooting can be started at any time.

In some embodiments, the composition information includes a size, and the processor 204 executing computer instructions to determine whether to generate the recognition target switching instruction based on the composition information of the first recognition target includes: and determining that the size of the first recognition target is out of the preset size range, and generating a recognition target switching instruction.

In some embodiments, identifying the target switch instruction comprises identifying a target expand instruction, and the processor 204 executes computer instructions to determine that the size of the first identification target is outside of the preset size range, and generating the identifying the target switch instruction comprises: and determining that the size of the first recognition target is smaller than the lower limit size of the preset size range, and generating a recognition target expansion instruction.

In this embodiment, it is further defined that when it is detected that the size of the first recognition target is smaller than the lower limit size, the first recognition target is considered to be too small in size in the shooting screen, and a recognition target enlarging instruction may be generated accordingly to switch to a larger recognition target corresponding to a case where the photographic subject is far from the pan/tilt head. It is understood that the larger recognition target means a recognition target that occupies a larger proportion of the photographic subject than the first recognition target. The first recognition target may be included in a larger recognition target, for example, the first recognition target is the head and shoulder of the photographic subject, and the larger recognition target is the whole body of the photographic subject; the first recognition target may also be completely different from the larger recognition target, e.g. the first recognition target is a head and the larger recognition target is a torso; the first recognition target may also be partially overlapped with a larger recognition target, for example, the first recognition target is a head and a shoulder, the larger recognition target is an upper limb, and the overlapped part of the two is the shoulder. Along with the distance of the shooting object, the size of the first recognition target in the shooting picture is gradually reduced, and when the size of the first recognition target is too small, the first recognition target is easy to be confused with the background, so that the recognition accuracy is reduced, the recognition is failed, and the composition effect and the realization of the automatic follow shooting function are influenced. By generating the identification target expansion instruction, the identification target can be switched to a larger identification target which is convenient to identify in time, the identification success rate is improved, the composition is beautified, and the reliable operation of the automatic follow shooting function is ensured.

In some embodiments, identifying the target switching instruction comprises identifying a target reduction instruction, and the processor 204 executes computer instructions to determine that the size of the first identification target is outside the preset size range, and generating the identification target switching instruction comprises: and determining that the size of the first recognition target is larger than the upper limit size of the preset size range, and generating a recognition target reduction instruction.

In this embodiment, similar to the recognition target expansion instruction, the recognition target switching instruction may further include a recognition target reduction instruction and be generated when it is detected that the size of the first recognition target is larger than the upper limit size, to switch to a smaller recognition target corresponding to a case where the photographic subject approaches the pan/tilt head. It is understood that the relationship between the first recognition target and the smaller recognition target is the same as the relationship between the larger recognition target and the first recognition target, and the first recognition target is not fixed, but refers to the recognition target currently in use, and can be switched and changed along with the movement of the shooting object. Along with the approach of a shooting object, the size of the first recognition target in the shooting picture is gradually enlarged, when the size of the first recognition target is too large, if composition is continuously executed according to the first recognition target, the composition attractiveness can be reduced, even the situation that the first recognition target overflows the shooting picture and recognition fails occurs, at the moment, a recognition target reduction instruction is generated, the smaller recognition target can be timely switched to, the composition can be beautified, the problem that the first recognition target overflows the shooting picture is solved, the recognition success rate is improved, and the reliable operation of the automatic follow-up shooting function can be ensured.

In some embodiments, the processor 204, when executing the computer instructions, further implements: and responding to the identification target switching instruction, switching from a first identification target to a second identification target, wherein the second identification target is at least one part of the shooting object, and the proportion of the first identification target to the shooting object is different from that of the second identification target to the shooting object.

In this embodiment, the processor 204 may further switch the recognition target from the first recognition target of the photographic object to the second recognition target of the photographic object based on the recognition target switching instruction, so as to implement automatic switching of the recognition target, without manual operation of a user, and improve convenience of operation and timeliness of switching. The first recognition target and the second recognition target respectively occupy different proportions in the shot object, so that the recognition in the shooting process can be effectively adjusted, the recognition success rate can be improved, and the composition can be beautified.

In some embodiments, the composition information further comprises a location, and the processor 204 when executing the computer instructions further implements: and adjusting the shooting parameters according to the composition information of the first recognition target so that the imaging of the first recognition target in the shooting picture meets the composition rule.

In this embodiment, specifically defining that the composition information further includes a position, based on the composition information of the first recognition target in the shooting picture and the composition rule, the processor 204 may automatically adjust the shooting parameters along with the movement and change of the first recognition target in the shooting picture, so as to adjust and beautify the composition. It can be understood that when the holder is aligned to the shooting object by hands, the shooting parameters can be automatically finely adjusted by combining the scheme, so that automatic composition is realized.

In some embodiments, processor 204 executes computer-implemented instructions to switch from a first recognition goal to a second recognition goal, including: detecting composition information of a second recognition target in the shooting picture; and adjusting the shooting parameters to enable the position and the size of the second recognition target in the shooting picture to gradually change until the imaging of the second recognition target in the shooting picture meets the composition rule.

In the embodiment, in the process of automatically switching the recognition targets, by detecting the composition information of the second recognition target and automatically adjusting the shooting parameters in combination with the composition rule, the position and the size of the second recognition target in the shooting picture are gradually changed until the imaging of the second recognition target in the shooting picture meets the composition rule, the switching process of the recognition targets can be made smooth and stable, and the shooting effect is ensured based on the composition of the second recognition target. It can be understood that when the recognition target switching instruction comprises the recognition target expansion instruction and the recognition target reduction instruction, the recognition target and the composition can be automatically adjusted along with the distance between the shooting object and the holder, so that the recognition success rate is improved, and the composition is beautified.

In some embodiments, the head further comprises: a cradle device capable of supporting a camera device for acquiring image information and/or a camera device for acquiring image information; the shooting parameters include at least one of: the height of the shooting device, the inclination angle of the shooting device, the direction of the shooting device, and the focal length of the shooting device.

In this embodiment, it is specifically defined that the shooting parameters include at least one of a height, an inclination, a direction, and a focal length of the shooting device, and by adjusting the shooting parameters, the shooting device can be controlled to achieve shooting. The shooting equipment can be a structure of the cradle head, and can also be a third-party structure, and for the latter, the cradle head needs to be provided with support equipment to support the shooting equipment.

In this embodiment, it is specifically defined that the entire photographic subject can be regarded as one recognition target, and a specified portion of the photographic subject, for example, the head and the shoulder, can be regarded as another recognition target, so that the full/half body composition is automatically switched according to the change of the distance of the photographic subject from the pan/tilt head by using the pedestrian detection technology, the head and shoulder detection technology, or the detection technology and the automatic following technology of other specified portions, so that the photographic subject is always at the optimal composition position. The pedestrian detection and the head and shoulder detection are techniques of automatically detecting the whole body and the head and shoulders of a pedestrian in a sensor field of view by taking various sensors (such as a camera) as input, and obtaining the position and the occupied size of the pedestrian in a picture.

In some embodiments, the processor 204, when executing the computer instructions, further implements: and outputting a target switching identification instruction.

In this embodiment, the processor 204 may also directly output a recognition target switching instruction to prompt the user to manually switch the recognition target, ensuring autonomous control of the user. It will be appreciated that both the automatic switching mode and the manual switching mode may be configured for the pan/tilt head, with the user selecting which one to employ. In addition, if the recognition target needs to be switched in the process of recording the video, the recording can be suspended firstly, and the recording is continued after the recognition target is manually selected again.

In some embodiments, the processor 204, when executing the computer instructions, further implements: outputting at least one alternative recognition target; switching from the first recognition target to the selected one of the at least one alternative recognition target.

In some embodiments, the processor 204, when executing the computer instructions, further implements: detecting an alternative recognition target of at least one alternative photographic object based on the condition that at least one alternative photographic object exists in the photographic picture; outputting at least one alternative recognition target; and taking the selected candidate recognition target as a first recognition target, and taking a candidate shooting object to which the first recognition target belongs as a shooting object.

In some embodiments, processor 204 executes computer-implemented instructions to output at least one alternative recognition goal, including: and outputting one alternative recognition target for each alternative shooting object.

In some embodiments, processor 204 executes computer instructions to output an alternative recognition goal, including: determining the number of the alternative recognition targets corresponding to the alternative shooting objects as one, and outputting the corresponding alternative recognition targets; and determining the number of the candidate recognition targets corresponding to the candidate shooting objects to be at least two, and outputting one corresponding candidate recognition target.

In some embodiments, the processor 204 executes one of the alternative recognition targets corresponding to the computer-implemented output, including: and detecting the sizes of all the corresponding alternative recognition targets in the shooting picture, and determining the output alternative recognition targets according to the sizes.

In some embodiments, the processor 204, when executing the computer instructions, further implements: and outputting the image information in real time.

In this embodiment, it is further defined that the processor 204 can also output the image information of the shot picture in real time to present the change of the shot object and the composition to the user in real time, so that the user can know the shooting condition or make an adjustment operation.

In particular, the memories referred to in the embodiments of the first and second aspects above may comprise mass storage for data or instructions. By way of example, and not limitation, memory may include a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or Universal Serial Bus (USB) Drive or a combination of two or more of these. The memory may include removable or non-removable (or fixed) media, where appropriate. The memory may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory is non-volatile solid-state memory. In a particular embodiment, the memory includes Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.

Embodiments of the first and second aspects described above relate to a processor (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of embodiments of the present Application.

An embodiment of a third aspect of the present application provides a control method for a pan/tilt head, which is used for a pan/tilt head or a control device for a pan/tilt head.

Fig. 3 shows a schematic flow chart of a control method of a pan/tilt head according to an embodiment of the present application. As shown in fig. 3, the control method of the pan/tilt head includes:

step S102, receiving image information of a shooting picture in real time, wherein a shooting object exists in the shooting picture;

step S104, detecting composition information of a first recognition target in the shooting picture according to the image information, wherein the first recognition target is at least one part of the shooting object;

step S106, determining whether to generate a recognition target switching instruction according to the composition information of the first recognition target.

According to the control method of the cloud deck, whether the identification target switching instruction is generated or not is determined according to the detected composition information of the first identification target, namely whether the identification target is switched or not can be reasonably selected according to the composition information of the first identification target of the shooting object in the current shooting picture, so that the identification success rate is improved, and composition beautification is facilitated. It is understood that the recognition targets before and after the switching all belong to the same photographic subject. In addition, the scheme can be applied to the automatic following and shooting function of the cloud deck based on the automatic following technology so as to switch and adjust following targets in time, thereby ensuring the following success, enabling the composition to be attractive and improving the following and shooting effect; the automatic shooting tracking device can be used when the cradle head is aligned to the shooting object through a human hand without starting the automatic shooting tracking function, for example, when the cradle head is manually controlled to track the shooting object, the reasonable adjustment of the recognition target is facilitated, the picture composition is optimized, the shooting effect is improved, and if only the cradle head is manually controlled to align the shooting object and the shooting is not started temporarily, the better recognition state and the picture composition state can be ensured, so that the shooting can be started at any time.

In some embodiments, the composition information includes a size, and the S106 specifically includes: and determining that the size of the first recognition target is out of the preset size range, and generating a recognition target switching instruction.

In some embodiments, the identifying the target switching instruction includes identifying a target enlarging instruction, and the S106 further includes: and determining that the size of the first recognition target is smaller than the lower limit size of the preset size range, and generating a recognition target expansion instruction.

In some embodiments, the identifying the target switching instruction includes identifying a target reduction instruction, and the S106 further includes: and determining that the size of the first recognition target is larger than the upper limit size of the preset size range, and generating a recognition target reduction instruction.

Fig. 4 shows a schematic flow chart of a control method of a pan/tilt head according to another embodiment of the present application. As shown in fig. 4, the control method of the pan/tilt head includes:

step S202, receiving image information of a shooting picture in real time, wherein a shooting object exists in the shooting picture;

step S204, composition information of a first recognition target in the shooting picture is detected according to the image information, wherein the first recognition target is at least one part of the shooting object;

step S206, determining whether to generate an identification target switching instruction according to the composition information of the first identification target;

and step S208, responding to the identification target switching instruction, switching from a first identification target to a second identification target, wherein the second identification target is at least one part of the photographic object, and the proportion of the first identification target to the photographic object is different from that of the second identification target to the photographic object.

In the embodiment, the recognition target can be switched from the first recognition target of the shooting object to the second recognition target of the shooting object based on the recognition target switching instruction, so that automatic switching of the recognition target is realized, manual operation of a user is not needed, and convenience in operation and timeliness in switching are improved. The first recognition target and the second recognition target respectively occupy different proportions in the shot object, so that the recognition in the shooting process can be effectively adjusted, the recognition success rate can be improved, and the composition can be beautified.

Further, in some embodiments, the composition information further includes a position, and the control method of the pan/tilt head further includes: and adjusting the shooting parameters according to the composition information of the first recognition target so that the imaging of the first recognition target in the shooting picture meets the composition rule.

In this embodiment, the composition information is specifically defined to further include a position, and based on the composition information and composition rules of the first recognition target in the shooting picture, the shooting parameters can be automatically adjusted along with the movement and change of the first recognition target in the shooting picture, so as to perform the functions of adjusting and beautifying the composition. It can be understood that when the holder is aligned to the shooting object by hands, the shooting parameters can be automatically finely adjusted by combining the scheme, so that automatic composition is realized.

In some embodiments, the switching from the first recognition target to the second recognition target of step S208 includes: detecting composition information of a second recognition target in the shooting picture; and adjusting the shooting parameters to enable the position and the size of the second recognition target in the shooting picture to gradually change until the imaging of the second recognition target in the shooting picture meets the composition rule.

Fig. 5 shows a schematic flow chart of a control method of a pan/tilt head according to still another embodiment of the present application. As shown in fig. 5, the control method of the pan/tilt head includes:

step S302, receiving image information of a shooting picture in real time, wherein a shooting object exists in the shooting picture;

step S304, composition information of a first recognition target in the shooting picture is detected according to the image information, wherein the first recognition target is at least one part of the shooting object;

step S306, determining whether to generate an identification target switching instruction according to the composition information of the first identification target;

in step S308, a recognition target switching instruction is output.

In the embodiment, the identification target switching instruction can be directly output to prompt the user to manually switch the identification target, so that the autonomous control of the user is ensured. It is understood that the automatic switching mode in the embodiment shown in fig. 4 and the manual switching mode in the embodiment may be configured for the pan/tilt head at the same time, and the user selects which one is to be used. In addition, if the recognition target needs to be switched in the process of recording the video, the recording can be suspended firstly, and the recording is continued after the recognition target is manually selected again.

Further, in some embodiments, the control method of the pan/tilt head further includes: outputting at least one alternative recognition target; switching from the first recognition target to the selected one of the at least one alternative recognition target.

Fig. 6 shows a schematic flow chart of a control method of a pan and tilt head according to a further embodiment of the present application. As shown in fig. 6, the control method of the pan/tilt head includes:

step S402, receiving image information of a shooting picture in real time, wherein a shooting object exists in the shooting picture;

step S404, detecting a candidate recognition target of at least one candidate shooting object based on the condition that at least one candidate shooting object exists in the shooting picture;

step S406, outputting at least one candidate recognition target;

step S408, taking the selected alternative recognition target as a first recognition target, and taking an alternative shooting object to which the first recognition target belongs as a shooting object;

step S410, detecting composition information of the first recognition target in the shooting picture according to the image information;

step S412, determining whether to generate a recognition target switching instruction according to the composition information of the first recognition target.

In some embodiments, step S406 specifically includes: and outputting one alternative recognition target for each alternative shooting object.

Further, in some embodiments, outputting an alternative recognition target includes: determining the number of the alternative recognition targets corresponding to the alternative shooting objects as one, and outputting the corresponding alternative recognition targets; and determining the number of the candidate recognition targets corresponding to the candidate shooting objects to be at least two, and outputting one corresponding candidate recognition target.

Further, in some embodiments, outputting the corresponding one of the candidate recognition targets includes: and detecting the sizes of all the corresponding alternative recognition targets in the shooting picture, and determining the output alternative recognition targets according to the sizes.

In some embodiments, the control method of the pan/tilt head further comprises: and outputting the image information in real time.

In the embodiment, the image information of the shooting picture can be further output in real time, so that the change of the shooting object and the composition can be presented to the user in real time, and the user can know the shooting condition or make an adjustment operation conveniently.

Next, taking an automatic following shooting function applied to a pan-tilt and a mobile phone taking a shooting device as a user as an example, a control method of the pan-tilt provided by the present application is introduced through a specific embodiment, and the method is mainly based on pedestrian whole body, head and shoulder detection and automatic following technologies, relates to technical features in the above embodiments, and mainly comprises the following three steps:

the method comprises the following steps: and (4) intelligent suggestion prompting.

When the user starts the automatic follow-up shooting function, the pedestrian whole body and head and shoulder detection technology is utilized to detect the appropriate pedestrian whole body and head and shoulder in the picture, then the detected pedestrian whole body and head and shoulder are previewed in the picture of the mobile phone in real time, and the user can select an object to be tracked by clicking, so that a first recognition target is selected and the object is shot.

When the same person detects both the whole body and the head and the shoulder of the person, the scheme of the application can automatically select a proper one of the whole body and the head and the shoulder of the person to be displayed to a user for selection according to the proportion of the whole body and the head and the shoulder of the person in a shot picture.

Step two: switching and composition is automatically followed.

The cradle head starts automatic following through the first recognition target selected by the user in the first step, continuously acquires the image information of the shot picture, calculates the position and the size of the first recognition target in the shot picture, and then controls the shooting parameters of the cradle head to enable the first recognition target to be kept at the composition position of the shot picture. When the shooting object is far away from the cloud platform, the recognition target can be automatically and smoothly switched to be followed by the whole body of the pedestrian and the composition is performed according to the following, so that the following distance is longer, and the composition is more reasonable; when the shooting object continuously walks close to the cloud platform, the recognition target can be automatically switched to the head and the shoulder of the pedestrian, and the composition is formed, so that the close-range following is more stable, and the composition is more reasonable.

Step three: and (6) previewing in real time.

The change in the subject and the composition are presented to the user in real time.

The control method of the cradle head can automatically switch the full (half) body of the shooting object to follow and compose shooting when the shooting object is far away from or close to the cradle head, namely far away from or close to the shooting equipment, so that the following transition is more stable, and the composition is more reasonable. It can be understood that, the pan/tilt head 100 provided in the embodiment of the first aspect and the control device 200 provided in the embodiment of the second aspect of the present application can implement the control method of the pan/tilt head described in this specific embodiment, and are not described herein again.

An embodiment of the fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when being executed by a processor, implements the steps of the method for controlling a pan/tilt head according to any of the above embodiments, so that all the beneficial technical effects of the method for controlling a pan/tilt head are achieved, and are not described herein again.

In particular, computer-readable storage media may include any medium that can store or transfer information. Examples of computer readable storage media include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.

In this application, the term "plurality" means two or more unless explicitly defined otherwise. The terms "mounted," "connected," "fixed," and the like are to be construed broadly, and for example, "connected" may be a fixed connection, a removable connection, or an integral connection; "coupled" may be direct or indirect through an intermediary. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.

In the description herein, the description of the terms "one embodiment," "some embodiments," "specific embodiments," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A head, comprising:

a memory configured to store computer instructions; and

a processor configured to execute the computer instructions to implement:

receiving image information of a shooting picture in real time, wherein a shooting object exists in the shooting picture;

detecting composition information of a first recognition target in the shooting picture according to the image information, wherein the first recognition target is at least one part of the shooting object;

and determining whether to generate a recognition target switching instruction according to the composition information of the first recognition target.

2. A tripod head according to claim 1, wherein said composition information comprises a size, and said processor executing said computer instructions for determining whether to generate a recognition target switching instruction based on the composition information of said first recognition target comprises:

and determining that the size of the first recognition target is out of a preset size range, and generating the recognition target switching instruction.

3. A tripod head according to claim 2, wherein said recognition target switching instructions comprise recognition target expansion instructions, said processor executing said computer instructions to determine that the size of said first recognition target is outside a preset size range, generating said recognition target switching instructions comprising:

and determining that the size of the first recognition target is smaller than the lower limit size of the preset size range, and generating the recognition target expansion instruction.

4. A tripod head according to claim 2, wherein said recognition target switching instruction comprises a recognition target reduction instruction, said processor executing said computer instructions to determine that the size of said first recognition target is outside a preset size range, generating said recognition target switching instruction comprising:

and determining that the size of the first recognition target is larger than the upper limit size of the preset size range, and generating the recognition target reduction instruction.

5. A head according to any one of claims 1 to 4, wherein said processor, when executing said computer instructions, further effects:

and responding to the identification target switching instruction, switching from the first identification target to a second identification target, wherein the second identification target is at least one part of the shooting object, and the proportion of the first identification target in the shooting object is different from that of the second identification target in the shooting object.

6. A head according to claim 5, wherein said composition information further comprises a position, said processor when executing said computer instructions further effects:

and adjusting shooting parameters according to the composition information of the first recognition target so that the imaging of the first recognition target in the shooting picture meets composition rules.

7. A head according to claim 6, wherein said processor executing said computer instructions for switching from said first identification target to a second identification target comprises:

detecting composition information of the second recognition target in the shooting picture;

and adjusting the shooting parameters to enable the position and the size of the second recognition target in the shooting picture to gradually change until the imaging of the second recognition target in the shooting picture meets the composition rule.

8. A head according to claim 6 or 7,

the composition rule includes at least one of: the imaging of the recognition target is complete, the recognition target is located in a designated area in the shooting picture, and the recognition target comprises a balanced composition, a symmetrical composition, a diagonal composition, a triangular composition, a Sudoku composition, a centripetal composition and a bisection composition.

9. A head according to claim 6 or 7,

the cloud platform still includes:

a cradle apparatus capable of supporting a photographing apparatus for acquiring the image information,

and/or, a shooting device for acquiring the image information;

the shooting parameters comprise at least one of the following: the height of the shooting device, the inclination angle of the shooting device, the direction of the shooting device, and the focal length of the shooting device.

10. A head according to claim 5,

one of the first recognition target and the second recognition target is an entirety of the photographic subject, and the other of the first recognition target and the second recognition target is a designated portion of the photographic subject.

11. A head according to any one of claims 1 to 4, wherein said processor, when executing said computer instructions, further effects:

and outputting the identification target switching instruction.

12. A head according to claim 11, wherein said processor, when executing said computer instructions, further implements:

outputting at least one alternative recognition target;

switching from the first recognition target to a selected one of the at least one alternative recognition target.

13. A head according to any one of claims 1 to 4, wherein said processor, when executing said computer instructions, further effects:

detecting an alternative recognition target of at least one alternative photographic object based on the condition that the at least one alternative photographic object exists in the photographic picture;

outputting at least one of the alternative recognition targets;

and taking the selected candidate recognition target as the first recognition target, and taking the candidate shooting object to which the first recognition target belongs as the shooting object.

14. A head according to claim 13, wherein said processor executes said computer instructions to output at least one of said alternative recognition goals, comprising:

and outputting one alternative recognition target for each alternative shooting object.

15. A head according to claim 14, wherein said processor executes said computer instructions to output one of said alternative recognition targets, comprising:

determining the number of the alternative recognition targets corresponding to the alternative shooting objects to be one, and outputting the corresponding alternative recognition targets;

and determining the number of the candidate recognition targets corresponding to the candidate shooting objects to be at least two, and outputting one corresponding candidate recognition target.

16. A head according to claim 15, wherein said processor executes said computer instructions to output a corresponding one of said alternative recognition targets, comprising:

and detecting the sizes of all the corresponding alternative recognition targets in the shooting picture, and determining the output alternative recognition targets according to the sizes.

17. A head according to any one of claims 1 to 4, wherein said processor, when executing said computer instructions, further effects:

and outputting the image information in real time.

18. A head according to any one of claims 1 to 4, further comprising:

and the display screen is used for displaying the image information.

19. A control device of a pan/tilt head, comprising:

a memory configured to store computer instructions; and

a processor configured to execute the computer instructions to implement:

20. The control apparatus of a pan and tilt head according to claim 19, wherein said composition information includes a size, and said processor executes said computer instructions to determine whether to generate a recognition target switching instruction based on the composition information of the first recognition target, comprising:

21. A control apparatus of a pan and tilt head according to claim 20, wherein said identification target switching instruction comprises an identification target expansion instruction, said processor executing said computer instructions to determine that the size of said first identification target is outside a preset size range, generating said identification target switching instruction comprising:

22. The control device of a pan and tilt head according to claim 20, wherein said identification target switching instruction comprises an identification target reduction instruction, said processor executing said computer instructions to determine that the size of said first identification target is outside a preset size range, generating said identification target switching instruction comprising:

23. A control apparatus of a pan and tilt head according to any one of claims 19 to 22, wherein said processor, when executing said computer instructions, further effects:

24. A control apparatus of a pan and tilt head according to claim 23, wherein said composition information further comprises a position, said processor when executing said computer instructions further effects:

25. A control apparatus of a pan and tilt head according to claim 24, wherein said processor executing said computer instructions to effect a switch from said first identification objective to a second identification objective comprises:

26. A control apparatus of a head according to claim 24 or 25,

27. A control apparatus of a head according to claim 24 or 25,

the cloud platform still includes:

and/or, a shooting device for acquiring the image information;

28. A control apparatus of a head according to claim 23,

29. A control apparatus of a pan and tilt head according to any one of claims 19 to 22, wherein said processor, when executing said computer instructions, further effects:

and outputting the identification target switching instruction.

30. A control apparatus of a pan and tilt head according to claim 29, wherein said processor, when executing said computer instructions, further effects:

outputting at least one alternative recognition target;

31. A control apparatus of a pan and tilt head according to any one of claims 19 to 22, wherein said processor, when executing said computer instructions, further effects:

outputting at least one of the alternative recognition targets;

32. A control apparatus of a pan and tilt head according to claim 31, wherein said processor executes said computer instructions to output at least one of said alternative recognition goals comprising:

33. A control apparatus of a pan and tilt head according to claim 32, wherein said processor executes said computer instructions to output one of said alternative recognition targets, comprising:

34. A control apparatus of a pan and tilt head according to claim 33, wherein said processor executes said computer-implemented instructions to output a corresponding one of said alternative recognition targets, comprising:

35. A control apparatus of a pan and tilt head according to any one of claims 19 to 22, wherein said processor, when executing said computer instructions, further effects:

and outputting the image information in real time.

36. A control method of a pan/tilt head, for a pan/tilt head or a control apparatus of a pan/tilt head, the control method of a pan/tilt head comprising:

37. The method of claim 36, wherein the composition information includes a size, and determining whether to generate a recognition target switching instruction according to the composition information of the first recognition target comprises:

38. A method according to claim 37, wherein said recognition target switching command comprises a recognition target expansion command, determining that the size of said first recognition target is outside a preset size range, generating said recognition target switching command comprising:

39. A method according to claim 37, wherein said recognition target switching command comprises a recognition target reduction command, determining that the size of said first recognition target is outside a preset size range, generating said recognition target switching command, comprises:

40. A method of controlling a head according to any one of claims 36 to 39, further comprising:

41. A control method of a pan and tilt head according to claim 40, wherein said composition information further comprises a position, the control method of a pan and tilt head further comprising:

42. A control method of a head according to claim 41, wherein switching from said first recognition target to a second recognition target comprises:

43. A control method of a head according to claim 41 or 42,

44. A control method of a head according to claim 41 or 42,

the cloud platform still includes:

and/or, a shooting device for acquiring the image information;

45. A control method of a head according to claim 40,

46. A method of controlling a head according to any one of claims 36 to 39, further comprising:

and outputting the identification target switching instruction.

47. A method of controlling a head according to claim 46, wherein said method further comprises:

outputting at least one alternative recognition target;

48. A method of controlling a head according to any one of claims 36 to 39, further comprising:

outputting at least one of the alternative recognition targets;

49. A control method of a head according to claim 48, wherein outputting at least one of said alternative recognition targets comprises:

50. A control method of a pan and tilt head according to claim 49, wherein outputting one of said alternative recognition targets comprises:

51. A control method of a pan and tilt head according to claim 50, wherein outputting a corresponding one of said alternative recognition targets comprises:

52. A method of controlling a head according to any one of claims 36 to 39, further comprising:

and outputting the image information in real time.

53. A computer-readable storage medium, on which a computer program is stored, characterized in that said computer program, when being executed by a processor, carries out the steps of a method for controlling a head according to any one of claims 36 to 52.