WO2021204298A1

WO2021204298A1 - Photographing method, device and system

Info

Publication number: WO2021204298A1
Application number: PCT/CN2021/086726
Authority: WO
Inventors: 刘琳
Original assignee: 华为技术有限公司
Priority date: 2020-04-10
Filing date: 2021-04-12
Publication date: 2021-10-14
Also published as: CN113518174A

Abstract

A photographing method based on matching of a box camera and a dome camera, comprising the box camera captures a panoramic image, the panoramic image comprising a plurality of objects; the box camera selects, according to geographical positions of the plurality of objects, a corresponding target dome camera to send a single photographing instruction, the photographing instruction carrying a PTZ value; after receiving the photographing instruction, the dome camera adjusts the position of the dome camera according to the PTZ value, and photographs the plurality of objects one by one, so that the dome camera completes separate photographing of the plurality of objects only by adjusting the position once.

Description

Shooting method, device and system

Technical field

The embodiments of the present application relate to the field of image processing technology, and in particular, to a shooting method, device, and system.

Background technique

In recent years, with the development of image processing technology and the upgrading of related hardware equipment, video surveillance and face recognition have been widely used in the construction of safe cities, intelligent transportation and other projects. Among them, person shooting is the basis of video analysis, motion tracking, face detection and recognition technology, and is of great significance in the realization of video surveillance, face recognition and other technologies.

At present, the shooting of characters is mainly realized by the way of gun-ball linkage (the action of the gun-camera and the ball-camera linkage). The process includes: the gun camera obtains the panoramic video of the monitoring area, analyzes the traveling direction of the target person in the panoramic video, and drives the dome camera that manages the direction of the target person to shoot the details of the target person. The dome camera performs positioning and focus adjustment according to the instructions of the camera, and then obtains the detailed information of the target person and reports it to the user.

Since the existing shot-and-ball machine linkage method is used to shoot the target person, each time the shooting object is a target person, when the shot-gun machine detects multiple target persons at the same time, it is necessary to perform the shot-ball machine linkage shooting multiple times. This process It is necessary to adjust the angle and focal length of the dome multiple times, thereby reducing the service life of the dome; and repeated adjustments take a long time, resulting in a high rate of missed shots.

Summary of the invention

This application provides a shooting method, device and system. In a scene where multiple objects are captured to obtain their object information, if the multiple objects are within the field of view of the same detail camera, the position of the detail camera only needs to be adjusted once. It can complete the shooting of multiple objects, prolong the service life of the detail camera, and reduce the missed shooting rate.

This application adopts the following technical solutions:

In a first aspect, a shooting method is provided. A panoramic camera communicates with multiple detail cameras, and the visual range of the panoramic camera spans the visual range of the multiple detail cameras. The method may include: the panoramic camera captures a panoramic image, and the panoramic image It includes a target object set with multiple objects; the panoramic camera selects the target detail camera from multiple detail cameras, where the target object set is within the visible range of the target detail camera; the panoramic camera sends shooting instructions to the target detail camera, The shooting command carries a single pan/tilt/zoom (pan/tilt/zoom) PTZ value, and the shooting command is used to instruct the target detail camera to execute: adjust the shooting position according to the PTZ value included in the shooting command so that the target object set is in the field of view of the target detail camera In, and shooting; the panoramic camera receives the response of the shooting completion instruction sent by the target detail camera; the panoramic camera marks the objects in the target object set as the shooting completed.

With the shooting method provided in this application, when multiple objects in the field of view of the panoramic camera correspond to the same detail camera, the panoramic camera sends a single PTZ value to the detail camera, indicating that the detail camera adjusts its position according to the single PTZ value. You can get detailed information about multiple objects. Sending a single PTZ value to achieve detailed shooting of multiple objects (rather than sending the PTZ value for each object separately as in the prior art), reducing the number of PTZ values sent by the panoramic camera; correspondingly, the detail camera only needs to be received according to the received Adjust the position of the PTZ value once (adjusting the position of the detail camera can also be understood as adjusting the posture of the detail camera), thus reducing the number of adjustments of the detail camera, thereby prolonging the service life of the detail camera, and further, because the detail camera is adjusting itself It is impossible to take pictures when adjusting the position of the detail camera. Therefore, when adjusting the position of the detail camera, moving objects (such as vehicles) may be missed. Compared with the solution of repeatedly adjusting the position of the detail camera, this application reduces the number of adjustments to one time. The missed shot rate.

Among them, the objects in the panoramic image can be regarded as different object sets according to the detailed cameras corresponding to the objects, that is, the panoramic objects include one or more object sets, and one object set has multiple objects. The panoramic camera can treat the objects corresponding to the same detail camera in the panoramic image as a set of objects.

When an object corresponds to multiple detail cameras, it can be determined according to a preset rule that the object corresponds to a certain detail camera. The user can configure the preset rules according to the actual situation, which is not limited in this application.

It should be noted that the objects included in the object set may be objects that have not been photographed.

In a possible implementation manner, the panoramic camera may randomly select an object set as the target object set.

With reference to the first aspect, in a possible implementation manner, the method may further include: before sending the shooting instruction, the panoramic camera marks the state of all objects in the target object set as the state to be shot. Among them, the panoramic camera marks the objects in the target object set as shooting completed, specifically: the panoramic camera updates the state of all objects in the target object set to the state of shooting completed.

With reference to the first aspect, in a possible implementation manner, the method may further include: the target detail camera receives a shooting instruction sent by the panoramic camera; the target detail camera adjusts the shooting position according to the PTZ value included in the shooting instruction; N objects in the field of view are shot once respectively, and the object information of N objects is obtained. The N objects include all objects in the target object set; the target detail camera sends the response to the panoramic camera to complete the shooting instruction; the target detail camera sets N The object information of M objects in the object is reported, and the reported object is a panoramic camera or a host. M is greater than or equal to 1 and less than or equal to N. In this possible implementation manner, the detail camera obtains object information of multiple objects according to the first PTZ value, which reduces the number of adjustments of the detail camera, further extends the service life of the detail camera, and reduces the missed shot rate.

Combining the first aspect and any of the foregoing possible implementations, in another possible implementation, the object information of an object may be the original image captured by the target detail camera for its field of view, which contains an image sub-region of the object. , The method may further include: the target detail camera reports the original images of the M objects. In this possible implementation, the original image of the object is sent to the panoramic camera or the host along with the object information. While the detailed information of the object is saved, the surrounding environment information when the object was taken is also saved, which is convenient for the user to further process. .

Combining the first aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the object information of an object may be an image with indication information added to the original image captured by the target detail camera for its field of view, The indication information is used to indicate the position of an object in the original image. In this possible implementation manner, the stored object information of an object includes detailed information of the object and surrounding environment information, which improves storage efficiency while ensuring the integrity of the storage information.

Combining the first aspect and any of the foregoing possible implementation manners, in another possible implementation manner, for the first object, the first object is any one of the N objects, and the method may further include: a target detail camera From the object information of the first object, obtain the feature of the first object; the target detail camera compares the feature of the first object with the feature library of the target detail camera, and the feature library of the target detail camera stores the target detail camera’s shots. The feature of the object; if there is a feature matching the feature of the first object in the feature library of the target detail camera, the target detail camera deletes the object information of the first object; the reported object information of the M objects does not contain the first object’s Object information; if there is no feature matching the feature of the first object in the feature library of the target detail camera, the reported object information of the M objects includes the object information of the first object. In this possible implementation, the object information reported by the detail camera to the host or the panoramic camera is the object information after its own deduplication, which reduces the repetition rate, improves the storage efficiency, and is convenient for users to find.

Combining the first aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the method may further include: the panoramic camera receives the object information of M objects sent by the target detail camera, and M is greater than or equal to 1. ; The panoramic camera obtains the features of the M objects according to the object information of the M objects; the panoramic camera compares the features of the M objects with the feature library of the panoramic camera; the feature library of the panoramic camera stores the objects shot by multiple detail cameras The feature; the panoramic camera will delete the remaining object information after deleting the object information of the object with matching features in the feature library of the panoramic camera among the object information of the M objects to the host. In this possible implementation manner, the object information reported by the panoramic camera to the host is the object information after cross deduplication, which reduces the repetition rate, improves the storage efficiency, and is convenient for users to find.

Combining the first aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the method may further include: the panoramic camera acquires the subject of the target detail camera, and the subject of the target detail camera may also include the target Objects outside the set of objects; after the panoramic camera receives a response to the completion of the shooting instruction, the panoramic camera marks the objects outside the set of target objects shot by the target detail camera as shooting completed. In this possible implementation, the panoramic camera can mark each object captured by the detail camera. Further, the panoramic camera can use unmarked objects as objects in the target object set, which improves the efficiency of shooting and reduces repetition. Rate.

Combining the first aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the panoramic image includes multiple object sets, and the target object set is the object set with the highest priority in the panoramic image. After the panoramic camera receives the response of the shooting completion instruction sent by the target detail camera, the method may further include: the panoramic camera re-shoots to obtain a new panoramic image, the new panoramic image includes a new target object set with multiple objects; the new target object set It is the set of objects with the highest priority in the new panoramic image; the panoramic camera selects a new target detail camera from multiple detail cameras, and sends a new shooting instruction carrying a single pan/tilt/zoom PTZ value to the new target detail camera. New shooting The instruction is used to instruct the new target detail camera to execute: adjust the shooting position according to the PTZ value included in the new shooting instruction so that the new target object set is located in the field of view of the target detail camera and shoot. In this possible implementation manner, each processing object is the object set with the highest priority in the object set, which can effectively reduce the missed detection rate.

Specifically, the panoramic camera may first obtain priority information of each object set in the panoramic image, and then select the object set with the highest priority as the target object set.

In a possible implementation manner, the panoramic camera may determine the priority of each object in the panoramic image, and use the priority of the object with the highest priority in the object set as the priority of the object set.

In another possible implementation manner, the panoramic camera can determine the priority for each object in the panoramic image, and use the average value of the sum of the priorities of the first X objects with priority from high to low in the object set as the object set Priority. Among them, X is greater than or equal to 2.

Specifically, the panoramic camera may configure the priority of each object in the panoramic image according to the actual situation, which is not limited in this application.

Combining the first aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the panoramic camera is a box camera, and the detail camera is a dome camera.

In a second aspect, a shooting method is provided, which can be applied to a target detail camera in a shooting system. The shooting system may include a panoramic camera and multiple detail cameras, the panoramic camera communicates with the multiple detail cameras, and the viewing range of the panoramic camera It spans the visible range of multiple detail cameras. The target detail camera is the detail camera selected by the panoramic camera among the multiple detail cameras. The method may include: the target detail camera receives a shooting instruction sent by the panoramic camera; the target detail camera adjusts the shooting position according to the PTZ value included in the shooting instruction; the target detail camera shoots N objects in its field of view once to obtain N objects The N objects include all objects in the target object set; the target detail camera sends a response to the panoramic camera to complete the shooting instruction; the target detail camera reports the object information of M objects in the N objects, and the reported object is a panoramic camera Or host, M is greater than or equal to 1 and less than or equal to N.

With the shooting method provided in this application, when multiple objects in the field of view of the panoramic camera correspond to the same detail camera, the detail camera receives a single PTZ value sent by the panoramic camera, and after the detail camera adjusts the position according to the single PTZ value, multiple objects are acquired The detail information of multiple objects is obtained, which reduces the number of adjustments of the detail camera, prolongs the service life of the detail camera, and reduces the missed shot rate.

With reference to the second aspect, in another possible implementation manner, the object information of an object may be the target detail camera and the original image captured by its field of view contains an image sub-region of the object. The method may also include: target detail The camera reports the original images of M objects. In this possible implementation, the original image of the object is reported to the panoramic camera or the host along with the object information. While the detailed information of the object is saved, the surrounding environment information when the object was shot is also saved, which is convenient for the user to further process .

In combination with the second aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the object information of an object may be an image of indication information added to the original image captured by the target detail camera for its field of view, The indication information is used to indicate the position of an object in the original image. In this possible implementation manner, the stored object information of an object includes detailed information of the object and surrounding environment information, which improves storage efficiency while ensuring the integrity of the storage information.

In combination with the second aspect and any of the foregoing possible implementation manners, in another possible implementation manner, for the first object, the first object is any one of the N objects, and the method may further include: a target detail camera From the object information of the first object, obtain the feature of the first object; the target detail camera compares the feature of the first object with the feature library of the target detail camera, and the feature library of the target detail camera stores the target detail camera’s shots. The feature of the object; if there is a feature matching the feature of the first object in the feature library of the target detail camera, the target detail camera deletes the object information of the first object; the reported object information of the M objects does not contain the first object’s Object information; if there is no feature matching the feature of the first object in the feature library of the target detail camera, the reported object information of the M objects includes the object information of the first object. In this possible implementation, the object information reported by the detail camera to the host or the panoramic camera is the object information after its own deduplication, which reduces the repetition rate, improves the storage efficiency, and is convenient for users to find.

In a third aspect, a photographing device is provided. The photographing device can be deployed on a panoramic camera, the panoramic camera communicates with multiple detail cameras, and the visual range of the panoramic camera spans the visual range of the multiple detail cameras. The device may include: The shooting unit is used to shoot a panoramic image, which includes a target object set with multiple objects; the selection unit is used to select a target detail camera from a plurality of detail cameras, wherein the target object set is located in the target detail camera. Within the viewing range; the sending unit is used to send shooting instructions to the target detail camera. The shooting command carries a single pan/tilt/zoom PTZ value. The shooting command is used to instruct the target detail camera to execute: adjust the shooting according to the PTZ value included in the shooting command The position is such that the target object set is located in the field of view of the target detail camera and photographed; the receiving unit is used to receive the response of the shooting completion instruction sent by the target detail camera; the marking unit is used to mark the objects in the target object set as photographing completed.

With the shooting device provided by this application, when multiple objects in the field of view of the panoramic camera correspond to the same detail camera, the panoramic camera sends a single PTZ value to the detail camera, indicating that the detail camera adjusts its position according to the single PTZ value to obtain the multiple Details of each object. Using a single PTZ value to achieve detailed shooting of multiple objects, reducing the number of adjustments of the detail camera, further extending the service life of the detail camera, and reducing the missed shot rate.

With reference to the third aspect, in a possible implementation manner, the marking unit is further configured to mark the states of all objects in the target object set as the states to be photographed before sending the photographing instruction. The marking unit is specifically used to: update the state of all objects in the target object set to a state where the shooting is completed.

With reference to the third aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the receiving unit is further configured to receive object information of M objects sent by the target detail camera, where M is greater than or equal to 1; The device may further include: a first acquisition unit for acquiring features of M objects from the object information of the M objects; a comparison unit for comparing features of M objects with the feature library of the panoramic camera; panoramic camera The feature library stores the features of the objects photographed by multiple detail cameras; the sending unit is used to delete the object information of the M objects from the object information of the object with matching features in the feature library of the panoramic camera. The information is sent to the host. In this possible implementation manner, the object information reported by the panoramic camera to the host is the object information after cross deduplication, which reduces the repetition rate, improves the storage efficiency, and is convenient for users to find.

In combination with the third aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the device may further include: a second acquisition unit configured to acquire the subject of the target detail camera, and the target detail camera captures The objects also include objects outside the target object set; the marking unit is also used to mark the objects outside the target object set captured by the target detail camera as the completion of shooting after the receiving unit receives a response to the completion of the shooting instruction. In this possible implementation, the panoramic camera can mark each object captured by the detail camera. Further, the panoramic camera can use unmarked objects as objects in the target object set, which improves the efficiency of shooting and reduces repetition. Rate.

In combination with the third aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the panoramic image includes multiple object sets, and the target object set is the object set with the highest priority in the scene image. The shooting unit is also used to: after the receiving unit receives the response to the shooting completion instruction sent by the target detail camera, re-shoot to obtain a new panoramic image, the new panoramic image includes a new target object set with multiple objects; the new target object set is new The set of objects with the highest priority in the panoramic image; the selection unit is also used to: select a new target detail camera from multiple detail cameras; the sending unit is also used to: send a single pan/tilt/zoom PTZ value to the new target detail camera The new shooting instruction is used to instruct the new target detail camera to execute: adjust the shooting position according to the PTZ value included in the new shooting instruction so that the new target object set is in the field of view of the target detail camera and shoot. In this possible implementation manner, each processing object is the object set with the highest priority in the object set, which can effectively reduce the missed detection rate.

In a fourth aspect, a photographing device is provided. The photographing device can be deployed in a target detail camera in a photographing system. The panoramic camera communicates with multiple detail cameras, and the visual range of the panoramic camera spans the visual range of the multiple detail cameras. The target detail camera is the detail camera selected by the panoramic camera among the multiple detail cameras. The device may include: a receiving unit for receiving a shooting instruction sent by the panoramic camera; an adjustment unit for adjusting the shooting position according to the PTZ value included in the shooting instruction; a processing unit for shooting N objects in the field of view once respectively , Get the object information of N objects, N objects include all objects in the target object set; the first sending unit is used to send the response to the panoramic camera to complete the shooting instruction; the second sending unit is used to transfer the N objects The object information of M objects is reported. The reported object is a panoramic camera or a host, and M is greater than or equal to 1 and less than or equal to N.

With the shooting device provided by this application, when multiple objects in the field of view of the panoramic camera correspond to the same detail camera, the detail camera receives a single PTZ value sent by the panoramic camera, and the detail camera obtains multiple values after adjusting the position according to the single PTZ value. Detailed information about the object. Using a single PTZ value to achieve detailed shooting of multiple objects, reducing the number of adjustments of the detail camera, further extending the service life of the detail camera, and reducing the missed shot rate.

With reference to the fourth aspect, in a possible implementation manner, the object information of an object is an image subregion containing an object in the original image captured by the processing unit on the field of view, and the second sending unit is also used to: The original image of the object is reported. In this possible implementation, the original image of the object is sent to the panoramic camera or the host along with the object information. While the detailed information of the object is saved, the surrounding environment information when the object was taken is also saved, which is convenient for the user to further process. .

In combination with the fourth aspect and any of the foregoing possible implementation manners, in another possible implementation manner, the object information of an object may be an image with indication information added to the original image captured by the processing unit on the field of view. Used to indicate the position of an object in the original image. In this possible implementation manner, the stored object information of an object includes detailed information of the object and surrounding environment information, which improves storage efficiency while ensuring the integrity of the storage information.

With reference to the fourth aspect and any of the foregoing possible implementation manners, in another possible implementation manner, for the first object, the first object is any one of the N objects, and the apparatus may further include: an acquiring unit, It is used to obtain the feature of the first object from the object information of the first object; the comparison unit is used to compare the feature of the first object with the feature library of the device, and the feature library of the device stores the photos taken by the processing unit The feature of the object; the feature library of the target detail camera stores the features of the object photographed by the target detail camera; the processing unit is specifically used for: if the feature library of the target detail camera has a feature that matches the feature of the first object, the target detail The camera deletes the object information of the first object; the reported object information of the M objects does not include the object information of the first object; if there is no feature matching the feature of the first object in the feature library of the target detail camera, the reported M The object information of each object includes the object information of the first object. In this possible implementation, the object information reported by the detail camera to the host or the panoramic camera is the object information after its own deduplication, which reduces the repetition rate, improves the storage efficiency, and is convenient for users to find.

In a fifth aspect, a photographing device is provided. The photographing device may include a processor and a memory, the memory and the processor are coupled, the memory is connected to the processor, and the memory is used to store a computer program. When the processor executes the computer program, the photographing device executes The action of the panoramic camera in the first aspect or any possible implementation manner of the first aspect.

In a sixth aspect, a photographing device is provided. The photographing device may include a processor and a memory, the memory and the processor are coupled, the memory is connected to the processor, and the memory is used to store a computer program. When the processor executes the computer program, the photographing device executes The action of the detail camera in the second aspect or any possible implementation manner of the second aspect.

In a seventh aspect, a photographing system is provided. The photographing system may include a panoramic camera and multiple detail cameras, the panoramic camera communicates with the multiple detail cameras, and the visual range of the panoramic camera spans the visual range of the multiple detail cameras; The panoramic camera is used to capture a panoramic image, which includes a target object set with multiple objects; select a target detail camera from multiple detail cameras, where the target object set is within the visible range of the target detail camera; Send a shooting command to the target detail camera. The shooting command carries a single pan/tilt/zoom PTZ value. The shooting command is used to instruct the target detail camera to execute: adjust the shooting position according to the PTZ value included in the shooting command so that the target object set is located in the target detail camera In the field of view, and shoot; the detail camera as the target detail camera is used to receive the shooting instruction sent by the panoramic camera; adjust the shooting position according to the PTZ value included in the shooting instruction; shoot each of the N objects in the field of view once to obtain N Object information of three objects; N objects include all objects in the target object set; send the response to the panoramic camera to complete the shooting instruction; report the object information of M objects in the N objects, and the reported object is the panoramic camera or the host, M It is greater than or equal to 1 and less than or equal to N; the panoramic camera is also used to receive the response of the shooting completion instruction sent by the target detail camera; and mark the object in the target object set as the shooting completed.

An eighth aspect provides a photographing system, which may include any possible photographing device of the third aspect or the third aspect and any possible photographing device of the fourth aspect or the fourth aspect. When the shooting system is running, the shooting method in any one of the foregoing aspects or any one of the possible implementation manners is executed.

In a ninth aspect, an embodiment of the present application provides a chip system. The chip system includes a processor and may also include a memory for realizing the function of the panoramic camera in the foregoing method. The chip system can be composed of chips, and can also include chips and other discrete devices.

In a tenth aspect, an embodiment of the present application provides a chip system. The chip system includes a processor and may also include a memory for realizing the function of the detail camera in the above method. The chip system can be composed of chips, and can also include chips and other discrete devices.

In an eleventh aspect, an embodiment of the present application also provides a computer-readable storage medium, including instructions, which when run on a computer, cause the computer to execute any one of the foregoing aspects or any one of the possible implementations of the shooting method .

In a twelfth aspect, the embodiments of the present application also provide a computer program product, which when it runs on a computer, causes the computer to execute any one of the above-mentioned aspects or the shooting method in any one of the possible implementation manners.

Description of the drawings

FIG. 1A is a schematic diagram of a typical joint shooting scene provided by the prior art;

Fig. 1 is a schematic structural diagram of a joint shooting system provided by the prior art;

2 is a schematic diagram of the field of view and the visible range of a detail camera provided by an embodiment of the application;

3 is a schematic diagram of the positional relationship between the panoramic camera and the visible range of multiple detail cameras provided by an embodiment of the application;

FIG. 4 is a schematic structural diagram of a photographing device provided by an embodiment of the application;

FIG. 5 is a schematic flowchart of a shooting method provided by an embodiment of the application;

FIG. 6 is a schematic diagram of a joint shooting scene provided by an embodiment of the application;

FIG. 7 is a schematic diagram of an original image and object information of an object provided by an embodiment of this application;

FIG. 8 is a schematic diagram of the original image and object information of another object provided by an embodiment of this application;

FIG. 9 is a schematic flowchart of another shooting method provided by an embodiment of the application;

FIG. 10 is a schematic diagram of another joint shooting scene provided by an embodiment of the application;

FIG. 11 is a schematic diagram of an original image of a person and object information provided by an embodiment of this application;

FIG. 12 is a schematic structural diagram of a photographing device provided by an embodiment of the application;

FIG. 13 is a schematic structural diagram of another photographing device provided by an embodiment of the application;

FIG. 14 is a schematic structural diagram of yet another photographing device provided by an embodiment of the application;

FIG. 15 is a schematic structural diagram of yet another photographing device provided by an embodiment of the application;

FIG. 16 is a schematic structural diagram of yet another photographing device provided by an embodiment of the application;

FIG. 17 is a schematic structural diagram of another photographing device provided by an embodiment of the application.

Detailed ways

The terms "first", "second", and "third" in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to limit a specific order.

In the embodiments of the present application, words such as "exemplary" or "for example" are used as examples, illustrations, or illustrations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferable or advantageous than other embodiments or design solutions. To be precise, words such as "exemplary" or "for example" are used to present related concepts in a specific manner to facilitate understanding.

In the description of this application, unless otherwise specified, "/" means that the associated objects before and after are in an "or" relationship. For example, A/B can mean A or B; the "and/or" in this application is only It is a kind of association relationship that describes the associated objects, which means that there can be three kinds of relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, and B exists alone, where A, B It can be singular or plural. Also, in the description of this application, unless otherwise specified, "plurality" means two or more than two. "The following at least one item (a)" or similar expressions refers to any combination of these items, including any combination of a single item (a) or a plurality of items (a). For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple .

In the embodiments of the present application, at least one may also be described as one or more, and the multiple may be two, three, four or more, which is not limited in the present application.

In order to facilitate understanding, the terms involved in this application are explained first.

Objects can refer to people or things. Specifically, the object can refer to a certain person, can also refer to a certain animal, of course, can also refer to other subjects, such as automobiles and license plates.

Panoramic camera, as opposed to detail camera, can refer to a camera that can shoot large-range and wide-angle video images. In this article, the images in various scenes captured by a panoramic camera are called panoramic images. For example, the panoramic camera may be a box camera. The visual range of a panoramic camera and the visual range of multiple detail cameras overlap. For example, the visual range of a panoramic camera includes the visual range of multiple detail cameras.

A detail camera can refer to a camera that has a smaller shooting range than a panoramic camera and can shoot video images in different directions and at different focal lengths. Among them, the detail camera usually adjusts the position first, and then shoots to obtain the detailed information of the person. In this article, the image captured by the detail camera is called the original image or object information. For example, the detail camera may be a dome camera.

The field of view of the camera can refer to the area range in which the camera can obtain the picture when the camera is in a certain position (fixed angle, fixed focal length). For non-adjustable cameras (cameras that cannot adjust the angle, focal length and other parameters), the field of view is fixed; for adjustable cameras, the field of view changes correspondingly every time the posture is adjusted according to the PTZ value.

The visual range of the camera can refer to the maximum area of the picture that the camera can obtain. Specifically, the visual range of the adjustable camera may be the union of the visual fields at different angles and different focal lengths. It should be understood that the visual range of the adjustable camera is smaller than the visual range. The field of view of the non-adjustable camera is the same size as the visual range.

A joint shooting scene can refer to a scene in which a panoramic camera is deployed to shoot a large-scale panoramic image, and multiple detailed cameras supporting the panoramic camera are deployed to capture object information. In the joint shooting scene, the visual range of the panoramic camera spans the visual range of multiple detail cameras that are matched with it. The visual range of each detail camera corresponds to different areas of the visual range of the panoramic camera. There can be intersections between the viewing ranges. Specifically, in the joint shooting scene, the panoramic camera monitors the objects within its visible range. When the target object is detected, it calculates the detail camera (which can be called the object information of the target object) according to the position of the target object. Is the PTZ value of the detail camera corresponding to the target object, the panoramic camera sends the calculated PTZ value to the detail camera, and the detail camera adjusts the position (angle, focal length, etc.) according to the PTZ value, and then shoots the target object in its field of view.

The detail camera corresponding to the area in the visual range of the panoramic camera refers to the detail camera whose visual range includes the area.

The detail camera corresponding to the object refers to the detail camera corresponding to the area where the object is located in the panoramic image, and the correspondence here means that the location of the object is within the visible range of the detail camera. When the same object is within the visible range of multiple detail cameras, select one of the detail cameras as the corresponding detail camera of the object.

Exemplarily, in the typical joint shooting scene of the bolt-camera linkage as shown in FIG. 1A, the panoramic camera is a bolt-camera, and the detail camera is a dome camera. This scene may be referred to as a bullet-camera linkage scene. In the shot-ball linkage scene shown in Figure 1A, the positions of the bolt-camera and the dome camera are configured in the deployment phase, the bolt-camera and the dome camera are calibrated, and the coordinate mapping relationship between the bolt-camera and the dome camera is established. The coordinate mapping relationship can determine the details of the person appearing in which area of the camera's visual range and which detail camera will shoot its details, and can also determine the correspondence between different areas in the camera's visual range and the detail camera.

In the bolt-camera linkage scene shown in Figure 1A, the plan for shooting a target person is: the bolt-camera shoots a panoramic image in its visible range, analyzes the person in the panoramic image to determine the target person; and then determines the target person’s traveling direction The field of view includes the ball machine in the forward direction of the target person as the target ball machine. The PTZ value of the target ball machine is calculated to ensure that the target person is in the field of view after the adjustment position of the ball machine. Then the gun machine sends the calculated value to the target ball machine. PTZ value, instruct the target dome camera to adjust the position according to the PTZ value to shoot the details of the target person.

Furthermore, in the shooting scheme of the target person in the scene of the bolt-camera linkage shown in FIG. 1A, the shooting scheme of the bolt-camera for each target person is the same. When there is a target person, it will send multiple PTZ values to the same ball machine to adjust the position, and execute the gun-ball linkage multiple times.

For example, when three target persons appear in the visible range of the ball machine R in the panoramic image taken by the gun camera, the gun camera first sends a PTZ value to the ball machine R for the target person 1, and the ball machine R is based on the PTZ value. Adjust the shooting position, shoot the detailed information of each person in the field of view (including the target person 1), and notify the camera to complete the shooting; then, the gun camera sends a PTZ value to the dome camera R again for the target person 2, and the dome camera R adjusts the shooting position again according to the new PTZ value, shoots the detailed information of each person in its field of view (including the target person 2), and informs the gun camera to complete the shooting; after that, the gun camera sends again to the dome camera R for the target person 3 A PTZ value, the dome camera R adjusts the shooting position again according to the new PTZ value, shoots the detailed information of each person in its field of view (including the target person 3), and informs the camera to complete the shooting.

It can be seen from the above that in the existing shooting process of target characters, when multiple target characters correspond to the same dome camera, multiple shots and ball linkages need to be performed, and the dome camera needs to adjust the angle and focal length multiple times. On the one hand, it reduces the dome camera. On the other hand, repeated adjustments take a long time, and it may happen that the target person has walked out of the field of view of the ball machine, resulting in a high missed shot rate.

Based on this, an embodiment of the present application provides a shooting method. When multiple objects in the field of view of the panoramic camera correspond to the same detail camera, the panoramic camera sends a single PTZ value to the detail camera, indicating that the detail camera is based on the single PTZ value once. After adjusting the position sexually, the detailed information of multiple objects can be obtained. Sending a single PTZ value to achieve detailed shooting of multiple objects (rather than sending the PTZ value for each object separately as in the prior art), reducing the number of PTZ values sent by the global camera; correspondingly, the detail camera only needs to be received according to the received Adjust the position of the PTZ value once (adjusting the position of the detail camera can also be understood as adjusting the posture of the detail camera), thus reducing the number of adjustments of the detail camera, thereby prolonging the service life of the detail camera, and further, because the detail camera is adjusting itself It is not possible to shoot at the position, so when you adjust the position of the detail camera, you may miss the shot of the moving object. Compared with the solution of repeatedly adjusting the position of the detail camera, this application reduces the number of adjustments to one time, which can also reduce the missed shot rate. .

The implementation of the embodiments of the present application will be described in detail below in conjunction with the accompanying drawings.

The solution provided by the embodiment of the present application can be applied to the joint photographing system 10 shown in FIG. 1. As shown in FIG. 1, the joint shooting system 10 may include a panoramic camera 101, multiple detail cameras 102, and multiple objects 103. Among them, the panoramic camera 101 communicates with a plurality of detail cameras 102, and instructs the detail camera 102 to obtain the detailed information of the object 103 and report it.

Optionally, the shooting system 10 may further include a host 104, and the detailed information of the object 103 acquired by the detail camera 102 may be reported to the host 104 or the panoramic camera 101, and the panoramic camera 101 reports to the host 104.

Among them, the panoramic camera 101 is used to capture a scene in its field of view to obtain a panoramic image. For example, the panoramic camera 101 may be a box camera, or other electronic equipment that can shoot large-range and wide-angle video images, which is not limited in this application.

The detail camera 102 is used to obtain detailed information of the object 103. For example, the detail camera 102 may be a dome camera, or other electronic equipment that can realize video image shooting in different directions and different focal lengths, which is not limited in this application.

The object 103 may refer to the subject whose detailed information the user needs to obtain. In the application scenario of this application, the object 103 can refer to a certain person in the panoramic image, can also refer to a certain animal in the panoramic image, and can also refer to other subjects in the panoramic image, such as cars and license plates. In FIG. 1, a person is taken as the object 103 for illustration, which should not constitute a specific limitation on the attributes of the target object.

The field of view and visible range of the detail camera can be shown in Figure 2. The area formed by the dotted line in FIG. 2 represents the visible range of the detail camera, and the area formed by the solid line in FIG. 2 represents the field of view of the detail camera at a specific angle and focal length.

FIG. 3 illustrates the positional relationship between the viewing range of the panoramic camera 101 and the multiple detail cameras 102. The area formed by the solid line in FIG. 3 indicates the visible range of the panoramic camera 101, and the area formed by the broken line indicates the visible range of the detail camera 102. The visual ranges of the multiple detail cameras 102 overlap, and the visual range of the panoramic camera 101 spans the visual ranges of the multiple detail cameras.

Of course, the panoramic camera 101 and the multiple detail cameras 102 can be configured for the visual range according to actual conditions, and this application will not list them one by one.

The solutions provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

On the one hand, an embodiment of the present application provides a photographing device 40 for executing the photographing method provided in the present application. The photographing device 40 may be deployed in the panoramic camera 101 or the detail camera 102 in the joint photographing system 10 shown in FIG. 1.

FIG. 4 illustrates a structural diagram of a photographing device 40 provided by an embodiment of the present application. As shown in FIG. 4, the photographing device 40 may include a processor 401, a memory 402, a transceiver 403, and an image collector 404.

The components of the camera 40 will be specifically introduced below in conjunction with FIG. 4.

The memory 402 may be a volatile memory (volatile memory), such as a random-access memory (RAM); or a non-volatile memory (non-volatile memory), such as a read-only memory (read-only memory, ROM), flash memory (flash memory), hard disk (HDD) or solid-state drive (solid-state drive, SSD); or a combination of the above types of memory, used to store the program code that can implement the method of this application , Configuration files, data information or other content.

The transceiver 403 is used for information interaction between the camera 40 and other equipment.

The processor 401 may be the control center of the camera 40. For example, the processor 401 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application. Circuits, for example: one or more microprocessors (digital singnal processors, DSP), or one or more field programmable gate arrays (FPGA).

The image collector 404 is used to capture images. For example, the image collector 404 may be an independent camera, a mobile phone camera, a computer camera, a dome camera, an augmented reality (AR)\virtual reality (VR) device, etc.

In a possible implementation manner, the shooting device 40 is a panoramic camera or is deployed in a panoramic camera, and the processor 401 runs or executes software programs and/or modules stored in the memory 402 and calls video images stored in the memory 402. Data, perform the following functions:

A panoramic image is taken, and the panoramic image includes a target object set with multiple objects; the target detail camera is selected from a plurality of detail cameras, where the target object set is located within the visible range of the target detail camera; The target detail camera sends a shooting command (the number of shooting commands is single), and the shooting command carries a single pan/tilt/zoom PTZ value. The shooting command is used to instruct the target detail camera to execute: adjust the shooting position according to the PTZ value included in the shooting command to make the target The object set is located in the field of view of the target detail camera and is photographed; the response to the shooting completion instruction sent by the target detail camera is received through the transceiver 403; the objects in the target object set are marked as being photographed.

In another possible implementation manner, the shooting device 40 is a detail camera or is deployed in a detail camera, and the processor 401 runs or executes a software program and/or module stored in the memory 402 and calls the video stored in the memory 402. Image data, perform the following functions:

The target detail camera receives the shooting command sent by the panoramic camera; the target detail camera adjusts the shooting position according to the PTZ value included in the shooting command; the target detail camera shoots each of the N objects in its field of view once to obtain the object information of the N objects, N The objects include all objects in the target object set; the target detail camera sends a response to the panoramic camera through the transceiver 403 to complete the shooting instruction; the target detail camera reports the object information of M objects in the N objects, and the reported object is a panoramic camera or Host, M is greater than or equal to 1 and less than or equal to N.

On the other hand, the embodiment of the present application provides a shooting method, which can be applied to the interaction process between the panoramic camera and the detail camera in the joint shooting system shown in FIG. 1. As shown in FIG. 5, the shooting method provided by the embodiment of the present application may include:

S501: A panoramic image is captured by a panoramic camera.

Specifically, S501 may be implemented as: an image obtained by a panoramic camera shooting a scene within its visible range is used as a panoramic image. Among them, multiple objects, such as multiple pedestrians, are recorded in the panoramic image. A panoramic camera can detect objects in a panoramic image through a recognition algorithm.

Further, the objects in the panoramic image can be regarded as different object sets according to the detailed cameras corresponding to the objects, that is, the panoramic objects include one or more object sets, and one object set has multiple objects.

It should be noted that the objects included in the object set may be objects that have not been photographed by the detail camera.

Optionally, the panoramic camera marks the state of all objects in the target object set as the state to be photographed.

Among them, the panoramic camera may regard the objects corresponding to the same detail camera in the panoramic image as a set of objects.

It should be noted that when an object is within the visible range of multiple detail cameras, it can be determined according to a preset rule that the object corresponds to a certain detail camera.

Exemplarily, the preset rule may be: selecting the detail camera with the largest number of objects in the visible range as the detail camera corresponding to the object; or selecting the detail camera with the object closest to the center area as the detail corresponding to the object Camera.

For example, as shown in Figure 6, a joint shooting scene is shown in which a panoramic camera communicates with three detail cameras, which are recorded as detail camera 1, detail camera 2, and detail camera 3. The visibility of the three detail cameras The range is shown in the area formed by the dashed line in FIG. 6, and the visible range of the panoramic camera is shown in the area formed by the solid line in FIG. 6. The panoramic image captured by the panoramic camera includes 7 objects (object A to object G in FIG. 6). According to the corresponding detail camera, the 7 objects can be regarded as 3 different object sets. Specifically, as shown in Figure 6, the object A, object B, and object C corresponding to the detail camera 1 can be regarded as the object set 1, and the object D and object E corresponding to the detail camera 2 can be regarded as the object set 2. The object F and the object G of the camera 3 are regarded as the object set 3.

Further, in S501, the panoramic camera may select an object set as the target object set from the multiple object sets included in the panoramic image, and perform joint shooting to obtain detailed information of the objects in the target object set. That is, the panoramic image may include a set of target objects with multiple objects.

Optionally, the manner in which the panoramic camera selects the target object set may include, but is not limited to, the following implementation 1 and implementation 2.

Realization 1. The panoramic camera can randomly select an object set as the target object set.

Realization 2. The panoramic camera selects the object set with the highest priority as the target object set.

Specifically, in implementation 2, the panoramic camera first obtains the priority information of each object set in the panoramic image, and then selects the object set with the highest priority as the target object set.

Specifically, the panoramic camera may configure the priority of each object in the panoramic image according to the actual situation, which is not limited in this application. Exemplarily, the panoramic camera may predict the time when each object leaves the visible range of its corresponding detail camera, and configure the priority of the object according to the predicted leaving time. For example, objects whose predicted departure time is closer to the current moment have higher priority.

For example, a panoramic camera detects and tracks objects within its visible range, obtains the position, speed, direction, and appearance duration information of each object in the panoramic image, and calculates according to the position, speed, direction, and appearance duration information of each object The predicted departure time of each object is calculated, and each object is sorted in the order of the predicted departure time from near to far, so that the object with the shorter predicted departure time has a higher priority, thereby obtaining the priority of each object.

S502. The panoramic camera selects a target detail camera from a plurality of detail cameras.

Among them, the target object set is located within the visible range of the target detail camera. That is, the detail camera corresponding to the target object set is the target detail camera.

S503. The panoramic camera sends a shooting instruction to the target detail camera.

Among them, the shooting instruction sent in S503 is single, and the shooting instruction carries a single PTZ value. The shooting instruction is used to instruct the target detail camera to execute: adjust the shooting position according to the PTZ value included in the shooting command so that the target object set is in the field of view of the target detail camera And shoot.

Specifically, in S503, the panoramic camera first calculates the PTZ value, and then sends a shooting instruction carrying a single PTZ value to the target detail camera.

Specifically, the panoramic camera is calculated according to the position of the target object set in the panoramic image, the position information, the desired display area of the target object set in the target detail camera, and the coordinate conversion relationship between the panoramic camera and the target detail camera. The PTZ value makes the target detail camera adjust its position according to the calculated PTZ value, and the target object set is in its field of view. Among them, the coordinate conversion relationship between the panoramic camera and the target detail camera is configured in the early deployment control stage of the panoramic camera and multiple detail cameras. This application will not repeat the configuration process and the process of calculating the PTZ according to the coordinate conversion relationship.

For example, the calculation process of PTZ may be: a panoramic camera determines a detection area according to a set of target objects. The detection area includes each object in the target object set, and the aspect ratio of the detection area is the same as the aspect ratio of the picture obtained by the target detail camera. The panoramic camera obtains the width and height of the picture according to the size of the detection area in the panoramic image and the target detail camera, and calculates the zoom (Z) value. The panoramic camera calculates the position of the detection area in the panoramic image, as well as the panoramic camera and the target detail camera. The coordinate conversion relationship of, calculates the translation (Pan, P) value and the pitch (Tilt, T) value.

For example, the detection area can be determined as: in the panoramic image, the person with the highest priority in the target object set is the center, and the

Is the width, with

Is the height area. Among them, h is the height of the person with the highest priority in the panoramic image, and _rh is the expected height of the person with the highest priority in the target detail camera image.

Get the aspect ratio of the screen for the target detail camera.

S504: The target detail camera receives a shooting instruction sent by the panoramic camera.

It should be noted that the shooting instruction received by the target detail camera in S504, that is, the shooting instruction sent by the panoramic camera in S503, will not be repeated here.

S505: The target detail camera adjusts the shooting position according to the PTZ value included in the shooting instruction.

Among them, after the target detail camera adjusts the shooting position in S505, its field of view includes each object in the target object set.

S506: The target detail camera shoots each object in its field of view once to obtain object information of N objects.

Among them, N objects include all objects in the target object set.

Specifically, in S506, the target detail camera monitors the object in its field of view. When it detects that the object in the field of view meets the shooting condition, the target detail camera shoots once to obtain the object information of the object that meets the shooting adjustment.

Among them, the shooting condition is a pre-configured condition that can obtain the most detailed information of the object. For example, the shooting condition may be that the object is facing the target detail camera, or it may be that the angle between the line of sight of the object and the central axis of the field of view of the target detail camera is less than or equal to a preset degree. The value of the preset degree can be configured according to actual needs, which is not limited in the embodiment of the present application.

Specifically, the target detail camera allocates a shooting once for each object in its field of view when it meets the shooting conditions, and obtains its object information. If the field of view of the target detail camera includes N objects, the object information of the N objects can be obtained. Among them, N is greater than or equal to 1.

It should be noted that the field of view of the target detail camera may include part or all of the objects in the target object set. Further, the field of view of the target detail camera may also include objects outside the set of target objects, for example, when a new object enters the field of view of the target detail camera.

Specifically, the object information of an object is used to reflect the detailed information of the object, and the content and form of the object information can be configured according to actual needs, which is not limited in this application. When the content and form of the object information are different, the methods for obtaining the object information in S506 are also different, and the specific methods may include, but are not limited to, the following two methods.

Manner a. The object information of an object is an image in which the target detail camera adds indication information to the original image captured by its field of view, and the indication information is used to indicate the position of the object in the original image.

In method a, the object information of the object obtained by the target detail camera can be specifically realized as follows: when the target detail camera detects that an object in its field of view meets the shooting conditions, the original image is obtained by shooting its field of view, and indication information is added to the original image. Get the object information of the object.

Wherein, the indication information may be coordinate information, or an indication frame or others.

Exemplarily, suppose that when the target detail camera satisfies the shooting conditions of the object A, the original image obtained by shooting its field of view is shown on the left in Figure 7, and a rectangular frame is added to the position of the object A in the original image to indicate the object A, The image to which the rectangular frame is added (the right image in FIG. 7) is used as the object information of the object A.

Manner b. The object information of an object is the image sub-region of the object contained in the original image captured by the target detail camera for its field of view.

In method b, the object information of the object obtained by the target detail camera can be specifically implemented as follows: when the target detail camera detects that an object in its field of view meets the shooting conditions, the original image is obtained from its field of view, and the original image is obtained from the original image containing the object. The image sub-area of the sub-area, the sub-area image as the object information of the object.

Exemplarily, suppose that when the target detail camera satisfies the shooting conditions, the original image obtained by shooting its field of view is shown on the left in Figure 8, and the target detail camera cuts out the area containing the object B in the original image as a picture. In the right image in 8, the image obtained by the cutout is used as the object information of object B.

S507: The target detail camera reports the object information of M objects among the N objects.

Among them, the report object reported by the target detail camera in S507 is the panoramic camera or the host. M is greater than or equal to 1 and less than or equal to N.

In a possible implementation manner, the target detail camera may perform the operation of S507 after obtaining the object information of an object, and finally report the object information of M objects.

In another possible implementation manner, after the target detail camera obtains the object information of the N objects, it executes the operation of S507 to report the object information of M objects among the N objects.

It should be noted that when the object information of an object is that the original image captured by the target detail camera for its field of view contains the image sub-region of the object, it corresponds to the method b in S506. When S507 is executed, it is also necessary to execute: The target detail camera reports the original images of M objects.

Optionally, S507 can be implemented through the following two solutions (solution A or solution B).

Solution A: The target detail camera directly reports the object information of the object obtained in S506.

In scheme A, the target detail camera can report the object information of an object every time it obtains it in S506. Alternatively, the target detail camera may obtain the object information of the N objects in S506 and report them together.

Solution B: The target detail camera performs its own deduplication, and reports the object information of objects that do not match the features in the feature library, and does not report the object information of objects that match the features in the feature library.

In scheme B, the target detail camera can obtain the object information of an object in S506, and then after self-de-duplication, it will report the object information that does not match the feature in the feature library, (the object that matches the feature in the feature library will be The information is deleted and not reported). Alternatively, the target detail camera may obtain the object information of the N objects in S506 and then perform self-deduplication, and report the object information of the M objects that do not match the features in the feature library together.

Taking the first object as an example, the self-deduplication process is described. As shown in FIG. 9, the self-deduplication process of the target detail camera may include the following S507a and S507b. The first object is any one of the N objects.

S507a. The target detail camera acquires the feature of the first object from the object information of the first object.

Specifically, the target detail camera uses a feature extraction algorithm to extract the feature of the first object from the object information of the first object.

Among them, the characteristics of the first object can be used to represent different characteristics of the first object. For example, when the first object is a certain person, the characteristics of the first object can be used to represent the person's appearance, age, body shape, and facial information.

S507b. The target detail camera compares the feature of the first object with the feature library of the target detail camera.

Among them, the feature library of the target detail camera stores the features of the object photographed by the target detail camera.

Specifically, the target detail camera respectively calculates the similarity between the feature of the first object and the feature of each object in the feature library of the target detail camera. If the feature of the first object is between the feature of an object in the feature library If the similarity of the first object is less than the threshold, it is considered that the feature of the first object matches the feature of an object in the feature library; if the similarity between the feature of the first object and the feature of an object in the feature library is greater than the threshold , It is considered that the feature of the first object does not match the feature of an object in the feature library; each feature in the feature library is traversed to determine whether the feature library of the target detail camera matches the feature of the first object feature.

Among them, the specific value of the threshold can be configured according to actual needs, which is not limited in the embodiment of the present application.

It should be noted that if the similarity between the feature of the first object and the feature of an object in the feature library is equal to the threshold, the feature of the first object can be considered to be the same as that of an object in the feature library according to actual needs. Feature matches or does not match.

Optionally, if there is no feature matching the feature of the first object in the feature library of the target detail camera, the target detail camera in S507 reports the object information of the first object, and the reported object information of the M objects includes the first object. The object information of the object; if there is a feature matching the feature of the first object in the feature library of the target detail camera, the target detail camera deletes the object information of the first object in S507, and the reported object information of the M objects does not include the first object. Object information of the object.

S508. The target detail camera sends a response to the panoramic camera to complete the shooting instruction.

Specifically, the target detail camera may perform S508 after shooting all the objects in its field of view to send a response of the shooting completion instruction to the panoramic camera. The response of the shooting completion instruction is used to indicate that the target detail camera is included in the shooting instruction The shooting of all objects has been completed under the PTZ value.

S509. The panoramic camera receives a response to the shooting completion instruction sent by the target detail camera.

It should be noted that the shooting instruction received by the panoramic camera in S509, that is, the shooting instruction sent by the detail camera in S508, will not be repeated here.

S510. The panoramic camera marks an object in the target object set as being photographed.

Specifically, after receiving the response of the shooting completion instruction in S509, the panoramic camera executes S510 to mark the objects in the target object set as shooting completed.

In a possible implementation manner, if the panoramic camera marks the state of all objects in the target object set as the state to be photographed before S510, the panoramic camera marking the objects in the target object set as photographed in S510 specifically includes: The panoramic camera updates the state of all objects in the target object set to the state where the shooting is completed.

Exemplarily, the panoramic camera establishes a table according to the detected objects, and configures the shooting attributes of each object in the table, and the shooting attributes may include the state to be shot or the state that the shooting is completed. Before sending the shooting instruction, the panoramic camera marks all the object shooting attributes in the target object set as the state to be shot. In S510, the shooting attribute of each object included in the target object set in the table is updated to the shooting completed status.

In another possible implementation manner, in S510, the panoramic camera marking the objects in the target object set as shooting completed specifically includes: the panoramic camera sets the state of all the objects in the target object set as the shooting completed state.

Further optionally, the panoramic camera can also perform image monitoring and identify objects within its visual range. Correspondingly, in S510, in addition to marking the objects in the target object set as photographing completed, the panoramic camera may also mark objects other than the target object set in the target detail camera's field of view during screen monitoring as photographing completed.

Further, if the target detail camera in S507 sends the object information of M objects among the N objects to the panoramic camera, as shown in Fig. 9, the shooting method provided in this application may further include:

S511. The panoramic camera receives the object information of the M objects sent by the target detail camera.

It should be noted that when the object information of an object is that the original image captured by the target detail camera for its field of view contains the image sub-region of the object, it corresponds to the method b in S506, and the panoramic camera in S511 can also receive M The original image of each object.

S512. The panoramic camera sends the object information of the H objects to the host.

Among them, H is less than or equal to M.

It should be noted that when the object information of an object is that the original image captured by the target detail camera for its field of view contains the image sub-region of the object, it corresponds to the method b in S506. When S512 is executed, it is also necessary to execute: The panoramic camera sends the original images of H objects to the host.

Optionally, S512 can be implemented by the following two methods (method A or method B).

Method A: The panoramic camera sends the content received in S511 to the host.

In method A, the panoramic camera can send the object information to the host every time it obtains the object information of an object in S511. Or, the panoramic camera may obtain the object information of M objects in S511, and send them to the host together.

Method B: The panoramic camera sends the object information of the H objects after cross-deduplication of the object information of the M objects to the host.

In method B, the panoramic camera can perform cross deduplication every time it obtains the object information of an object in S511, and send the object information that does not match the features in the feature library to the host. Alternatively, the panoramic camera may obtain the object information of the M objects in S511 and then perform cross deduplication, and send the object information of the H objects that do not match the features in the feature library to the host.

The cross-de-duplication process of the object information of M objects with a panoramic camera is now described in detail. This process may include the following S512a and 512b.

S512a. The panoramic camera acquires the features of the M objects according to the object information of the M objects.

Specifically, the panoramic camera uses a feature extraction algorithm to extract features of M objects from the object information of M objects.

S512b. The panoramic camera compares the features of the M objects with the feature library of the panoramic camera.

Among them, the feature library of the panoramic camera stores the features of the objects photographed by multiple detail cameras.

Specifically, the panoramic detail camera compares the feature of each object in the M objects with each feature in the feature library of the panoramic detail camera, and judges whether the feature library of the panoramic detail camera is different from that of the M objects. Feature matching feature.

For the specific feature matching process, refer to the specific implementation of feature matching in S507b, which will not be repeated here.

Optionally, if there are no features matching the features of the M objects in the feature library of the panoramic camera, the panoramic camera in S512 sends the object information of the M objects to the host; The feature matching the feature of some or all of the objects in the object, the panoramic camera in S512 deletes the object information of the M objects with matching features in the feature library of the panoramic camera and sends the remaining object information to the host .

Optionally, the shooting method provided in this application may further include: updating the feature database. Including the panoramic camera update the feature library of the panoramic camera, and/or the detail camera update the feature library of the detail camera. The process of updating the signature database is similar for the two.

Specifically, the feature database can be updated according to preset conditions.

Exemplarily, the preset condition may be: when performing deduplication, directly store the features that do not match the feature library in the feature library; update the features that match the feature library to the feature library, and delete the matching of the feature library at the same time The feature with the longest storage time among the features. Of course, preset rules can also be configured according to actual needs, which are not limited in the embodiment of the present application.

For example, compare the feature of the second object with the feature library of the target detail camera; if there is a feature matching the feature of the second object in the feature library of the target detail camera, the feature of the second object can be updated to the target detail The feature library of the camera, and delete the feature with the longest storage time of the second object in the feature library of the target detail camera; if there is no feature matching the feature of the second object in the feature library of the target detail camera, you can change the feature of the second object The feature is added to the feature library of the target detail camera.

Among them, after the target detail camera completes its own deduplication, the target detail camera can update its feature library according to the preset condition; after the panoramic camera completes cross deduplication, the panoramic camera can update its feature library according to the preset condition.

It should be noted that the panoramic camera can cyclically execute the solution provided in this application for different target object sets.

Further optionally, after the panoramic camera marks the objects in the target object set as being photographed, the shooting method provided in the embodiment of the present application may further include: the panoramic camera selects a second detail camera from a plurality of detail cameras and sends a second shooting instruction , To photograph objects in the second object set, where the second object set includes: objects included in the panoramic image that are not included in the target object set.

Optionally, after the panoramic camera marks the objects in the target object set as being photographed, the method provided in this application may further include: obtaining the highest priority object set in the panoramic image except the target object set, and the object set Assemble for shooting, and perform the above-mentioned related steps, which will not be repeated here.

Optionally, after the above steps are performed, the shooting method provided in this embodiment of the present application may also re-execute S501 panoramic camera to re-shoot to obtain a new panoramic image, and perform part or all of S502 to S512 based on the new panoramic image. Specifically, For the steps, refer to the above S501 to S512, which will not be repeated one by one.

Assuming that the user needs to obtain the detailed information of multiple target persons in a certain scene, the detailed description will now be given by taking the method of shooting provided in this application as an example.

Specifically, the outdoor scene is deployed with one panoramic camera and three detail cameras, which are recorded as detail camera 1, detail camera 2, and detail camera 3 respectively.

The panoramic camera captures a panoramic image of its field of view, and according to the detailed camera corresponding to the object, the people in the panoramic image are regarded as different sets of people. Specifically, as shown in FIG. 10, the character A, the character B, and the character C corresponding to the detail camera 1 are regarded as the character set 1, and the character D and the character E corresponding to the detail camera 2 are regarded as the character set 2. The panoramic camera acquires the priority of 5 characters, and the priority of character A is the highest. The character set 1 is used as the target character set, and the detail camera 1 corresponding to the character set 1 is used as the target detail camera.

The panoramic camera sends a shooting instruction and PTZ value to the detail camera 1, instructing the detail camera 1 to adjust the position according to the PTZ value, so that the set of people 1 is in its field of view.

The detail camera receives the instruction and the PTZ value, adjusts the position according to the PTZ value, and shoots the person A, the person B, and the person C in its field of view respectively once to obtain the original images of the three characters, and then according to the original images of the three characters Obtain the object information of the three characters. As shown in Fig. 11, the left side is the original image of the person A, the person B, and the person C, and the right side is the object information of the person A, the person B, and the person C.

The detail camera 1 performs self-de-duplication on the object information of the three characters. There is no matching feature in the feature library of the detail camera 1, and the detail camera 1 sends the object information of the three characters to the panoramic camera.

The panoramic camera performs cross deduplication on the received object information of the three characters. The feature of character C matches a feature in the feature library of the panoramic camera. The panoramic camera deletes the object information of character C and deletes the objects of character A and character B. The information is sent to the host.

The foregoing mainly introduces the solution provided by the embodiment of the present invention from the perspective of the interaction between the panoramic camera and the detail camera in the shooting system. It can be understood that, in order to realize the above-mentioned functions, each photographing device, such as a panoramic camera, a detail camera, etc., includes a hardware structure and/or software module corresponding to each function. Those skilled in the art should easily realize that in combination with the units and algorithm steps of the examples described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software-driven hardware depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered as going beyond the scope of the present invention.

The embodiment of the present invention may divide the function modules of the photographing device and the like according to the foregoing method examples. For example, each function module may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or software functional modules. It should be noted that the division of modules in the embodiment of the present invention is illustrative, and is only a logical function division, and there may be other division methods in actual implementation.

In the case of dividing each functional module corresponding to each function, FIG. 12 shows a photographing device 120 provided in an embodiment of this application, which is used to implement the function of the panoramic camera in the above method. The photographing device 120 may be a panoramic camera or the photographing device 120 may be deployed in a panoramic camera. As shown in FIG. 12, the photographing device 120 may include: a photographing unit 1201, a selection unit 1202, a sending unit 1203, a receiving unit 1204, and a marking unit 1205. The photographing unit 1201 is used to perform S501 in FIG. 5 or FIG. 9; the selection unit 1202 is used to perform S502 in FIG. 5 or FIG. 9; the sending unit 1203 is used to perform S503 in FIG. 5 or FIG. S509 in FIG. 5 or FIG. 9 and S511 in FIG. 9 are executed; the marking unit 1205 is used to execute S510 in FIG. 5 or FIG. 9. Among them, all relevant content of the steps involved in the above method embodiments can be cited in the functional description of the corresponding functional module, which will not be repeated here.

Further, as shown in FIG. 13, the photographing device 120 may further include: a first acquiring unit 1206, a comparing unit 1207, a sending unit 1208, and a second acquiring unit 1209. The first obtaining unit 1206 is used to perform S512a in FIG. 9; the comparison unit 1207 is used to perform S512b in FIG. 9; the sending unit 1208 is used to perform S512 in FIG. 9; the second obtaining unit 1209 is used to perform S510 in FIG. Related actions. Among them, all relevant content of the steps involved in the above method embodiments can be cited in the functional description of the corresponding functional module, which will not be repeated here.

In the case of using an integrated unit, as shown in FIG. 14, the photographing device 140 provided in this embodiment of the present application is used to implement the function of the panoramic camera in the foregoing method. The photographing device 140 may be a panoramic camera or the photographing device 140 may be deployed in a panoramic camera. The photographing device 140 includes at least one processing module 1401 for implementing the function of the panoramic camera in the method provided in the embodiment of the present application. Exemplarily, the processing module 1401 may be used to execute the processes S502 and S510 in FIG. 5, or the processes S502, S510, S512a, and S512b in FIG. 9. For details, please refer to the detailed description in the method example, which is not repeated here.

The photographing device 140 may also include at least one storage module 1402 for storing program instructions and/or data. The storage module 1402 and the processing module 1401 are coupled. The coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units or modules, and may be in electrical, mechanical or other forms, and is used for information exchange between devices, units or modules. The processing module 1401 may operate in cooperation with the storage module 1402. The processing module 1401 may execute program instructions stored in the storage module 1402. At least one of the at least one storage module may be included in the processing module.

The photographing device 140 may further include a communication module 1403 for communicating with other devices through a transmission medium, so as to determine that the device in the photographing device 140 can communicate with other devices. The communication module 1403 is used for the device to communicate with other devices. Exemplarily, the processor 1401 may use the communication module 1403 to execute the processes S503, S509, and S512 in FIG. 5 or FIG. 9.

The photographing device 140 may further include an image acquisition module 1404 for photographing images. Exemplarily, the image acquisition module 1404 may be used to execute S501 in the process of FIG. 5.

When the processing module 1401 is a processor, the storage module 1402 is a memory, the communication module 1403 is a transceiver, and the image acquisition module 1404 is an image collector, the photographing device 140 involved in FIG. 14 in the embodiment of the present application may be the one shown in FIG. 4 Camera 40.

As mentioned above, the photographing device 120 or the photographing device 140 provided in the embodiments of the present application can be used to implement the functions of the panoramic camera in the methods implemented in the various embodiments of the present application. For parts that are not disclosed in specific technical details, please refer to the various embodiments of this application.

In the case of dividing each functional module corresponding to each function, as shown in FIG. 15, the photographing device 150 provided in this embodiment of the present application is used to implement the function of the detail camera in the above method. The photographing device 150 may be a detail camera or the photographing device 150 may be deployed on a detail camera. As shown in FIG. 15, the photographing device 150 may include: a receiving unit 1501, an adjusting unit 1502, a first sending unit 1503, and a processing unit 1504. The receiving unit 1501 is used to perform S504 in FIG. 5 or FIG. 9; the adjusting unit 1502 is used to perform S505 in FIG. 5 or FIG. 9; the first sending unit 1503 is used to perform S508 in FIG. 5 or FIG. 9; and the processing unit 1504 is used to perform S507 in Figure 5 or Figure 9. Among them, all relevant content of the steps involved in the above method embodiments can be cited in the functional description of the corresponding functional module, which will not be repeated here.

Further, as shown in FIG. 16, the photographing device 150 may further include: an acquisition unit 1505 and a comparison unit 1506. Among them, the obtaining unit 1505 is used to execute S507a in FIG. 9; the comparison unit 1506 is used to execute S507b in FIG. 9. Among them, all relevant content of the steps involved in the above method embodiments can be cited in the functional description of the corresponding functional module, which will not be repeated here.

In the case of an integrated unit, as shown in FIG. 17, the photographing device 170 provided in this embodiment of the application is used to implement the function of the detail camera in the above method. The photographing device 170 may be a detail camera or the photographing device 170 may be deployed in a detail camera. The photographing device 170 includes at least one processing module 1701, which is used to implement the function of the detailed camera in the method provided in the embodiment of the present application. For details, please refer to the detailed description in the method example, which will not be repeated here.

The photographing device 170 may also include at least one storage module 1702 for storing program instructions and/or data. The storage module 1702 and the processing module 1701 are coupled. The coupling in the embodiments of the present application is an indirect coupling or communication connection between devices, units or modules, and may be in electrical, mechanical or other forms, and is used for information exchange between devices, units or modules. The processing module 1701 may operate in cooperation with the storage module 1702. The processing module 1701 may execute program instructions stored in the storage module 1702. At least one of the at least one storage module may be included in the processing module.

The photographing device 170 may further include a communication module 1703 for communicating with other devices through a transmission medium, so as to determine that the device in the photographing device 170 can communicate with other devices. The communication module 1703 is used for the device to communicate with other devices. Exemplarily, the processor 1701 uses the communication module 1703 to execute S504 and S508 in the process of FIG. 5 or FIG. 9.

The photographing device 170 may further include an image acquisition module 1704 for photographing images. Exemplarily, the image acquisition module 1704 may be used to perform related actions in S506 in FIG. 5.

When the processing module 1701 is a processor, the storage module 1702 is a memory, the communication module 1703 is a transceiver, and the image acquisition module 1704 is an image collector, the photographing device 170 involved in FIG. 17 in the embodiment of the present application may be the one shown in FIG. 4 Camera 40.

As mentioned above, the photographing device 150 or the photographing device 170 provided in the embodiments of the present application can be used to implement the functions of the detailed cameras in the methods implemented in the various embodiments of the present application. For parts that are not disclosed in specific technical details, please refer to the various embodiments of this application.

Other embodiments of the present application provide a photographing system, the photographing system may include a first photographing device and a second photographing device, the first photographing device can realize the function of a panoramic camera, and the second pass camera can realize the detail camera Function. For example, the first pass shooting is set to the panoramic camera described in the embodiment of this application, and the second shooting device is the detail camera described in the embodiment of this application.

Other embodiments of the present application provide a chip system. The chip system includes a processor and may also include a memory for realizing the function of the panoramic camera in the embodiment shown in FIG. 5 or FIG. 9. The chip system can be composed of chips, and can also include chips and other discrete devices.

Other embodiments of the present application provide a chip system. The chip system includes a processor and may also include a memory for realizing the function of the detailed camera in the embodiment shown in FIG. 5 or FIG. 9. The chip system can be composed of chips, and can also include chips and other discrete devices.

Other embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium may include a computer program. When the computer program runs on a computer, the computer executes the implementation shown in FIG. 5 or FIG. Each step in the example.

Other embodiments of the present application also provide a computer program product. The computer product includes a computer program. When the computer program product runs on a computer, the computer executes the steps in the embodiment shown in FIG. 5 or FIG. 9.

Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and brevity of the description, only the division of the above-mentioned functional modules is used as an example for illustration. In practical applications, the above-mentioned functions can be allocated according to needs. It is completed by different functional modules, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

In the several embodiments provided in this application, it should be understood that the disclosed device and method may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods, for example, multiple units or components may be divided. It can be combined or integrated into another device, or some features can be omitted or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate parts may or may not be physically separate. The parts displayed as units may be one physical unit or multiple physical units, that is, they may be located in one place, or they may be distributed to multiple different places. . Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

In addition, the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.

If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application are essentially or the part that contributes to the prior art, or all or part of the technical solutions can be embodied in the form of a software product, and the software product is stored in a storage medium. It includes several instructions to make a device (which may be a single-chip microcomputer, a chip, etc.) or a processor (processor) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code .

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Any changes or substitutions within the technical scope disclosed in this application shall be covered by the protection scope of this application. . Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

A shooting method, characterized in that a panoramic camera communicates with a plurality of detail cameras, the visual range of the panoramic camera spans the visual range of the multiple detail cameras, and the method includes:

The panoramic camera captures a panoramic image, and the panoramic image includes a set of target objects with multiple objects;

The panoramic camera selects a target detail camera from the plurality of detail cameras, wherein the set of target objects is located within the visible range of the target detail camera;

The panoramic camera sends a shooting instruction to the target detail camera, and the shooting instruction carries a single pan/tilt/zoom PTZ value, and the shooting instruction is used to instruct the target detail camera to execute: The PTZ value adjusts the shooting position so that the target object set is located in the field of view of the target detail camera, and shoots;

Receiving, by the panoramic camera, a response to the completion of the shooting instruction sent by the target detail camera;

The panoramic camera marks the objects in the target object set as being photographed.
The method according to claim 1, wherein the method further comprises:

Before sending the shooting instruction, the panoramic camera marks the state of all objects in the target object set as a state to be shot;

Wherein, the panoramic camera marks the objects in the target object set as being photographed, specifically: the panoramic camera updates the state of all the objects in the target object set to a state where the photographing is completed.
The method according to claim 1 or 2, wherein the method further comprises:

The target detail camera receives the shooting instruction sent by the panoramic camera;

Adjusting the shooting position of the target detail camera according to the PTZ value included in the shooting instruction;

The target detail camera shoots the N objects in its field of view once to obtain object information of the N objects, and the N objects include all objects in the target object set;

Sending, by the target detail camera, a response to complete the shooting instruction to the panoramic camera;

The target detail camera reports object information of M objects among the N objects, the reported object is the panoramic camera or the host, and the M is greater than or equal to 1 and less than or equal to N.
The method according to claim 3, wherein the object information of an object is that the original image captured by the target detail camera includes the image sub-region of the object, and the method further comprises:

The target detail camera reports the original images of the M objects.
The method according to claim 3, wherein the object information of an object is an image with indication information added to the original image captured by the target detail camera for its field of view, and the indication information is used to indicate the one The position of the object in the original image.
The method according to any one of claims 3-5, wherein for a first object, the first object is any one of the N objects, and the method further comprises:

The target detail camera acquires the feature of the first object from the object information of the first object;

The target detail camera compares the feature of the first object with the feature library of the target detail camera, and the feature library of the target detail camera stores the features of the object photographed by the target detail camera;

If there is a feature matching the feature of the first object in the feature library of the target detail camera, the target detail camera deletes the object information of the first object; the reported object information of the M objects is not Contains object information of the first object;

If there is no feature matching the feature of the first object in the feature library of the target detail camera, the reported object information of the M objects includes the object information of the first object.
The method according to any one of claims 1-6, wherein the method further comprises:

The panoramic camera receives object information of M objects sent by the target detail camera, where M is greater than or equal to 1;

Acquiring, by the panoramic camera, the characteristics of the M objects according to the object information of the M objects;

The panoramic camera compares the features of the M objects with the feature library of the panoramic camera; the feature library of the panoramic camera stores the features of the objects photographed by the multiple detail cameras;

The panoramic camera sends the remaining object information after deleting the object information of the objects with matching features in the feature library of the panoramic camera among the object information of the M objects to the host.
The method according to any one of claims 1-7, wherein the method further comprises:

Acquiring, by the panoramic camera, a shooting object of the target detail camera, and the shooting object of the target detail camera also includes objects outside the target object set;

After the panoramic camera receives the response to the completion of the shooting instruction, the panoramic camera marks the objects outside the set of target objects captured by the target detail camera as shooting completed.
The method according to any one of claims 1-8, wherein the panoramic image includes a plurality of object sets, and the target object set is the object set with the highest priority in the panoramic image;

After the panoramic camera receives the response to the completion of the shooting instruction sent by the target detail camera, the method further includes:

The panoramic camera re-shoots to obtain a new panoramic image, the new panoramic image includes a new target object set with multiple objects; the new target object set is the highest priority object set in the new panoramic image;

The panoramic camera selects a new target detail camera from the multiple detail cameras, and sends a new shooting instruction carrying a single pan/tilt/zoom PTZ value to the new target detail camera, and the new shooting instruction is used to instruct all The new target detail camera executes: adjust the shooting position according to the PTZ value included in the new shooting instruction so that the new target object set is located in the field of view of the target detail camera, and shoot.
The method according to any one of claims 1-9, wherein the panoramic camera is a box camera, and the detail camera is a dome camera.
A photographing device, characterized in that the photographing device is deployed on a panoramic camera, the panoramic camera communicates with a plurality of detail cameras, and the visual range of the panoramic camera spans the visual range of the multiple detail cameras, The device includes:

A photographing unit for photographing to obtain a panoramic image, the panoramic image including a set of target objects with multiple objects;

The selection unit is configured to select a target detail camera from a plurality of detail cameras, wherein the set of target objects is located within the visible range of the target detail camera;

The sending unit is configured to send a shooting instruction to the target detail camera, the shooting instruction carries a single pan/tilt/zoom PTZ value, and the shooting instruction is used to instruct the target detail camera to execute: Adjust the shooting position with the PTZ value of, so that the target object set is located in the field of view of the target detail camera, and shoot;

A receiving unit, configured to receive a response to the completion of the shooting instruction sent by the target detail camera;

The marking unit is used to mark the objects in the target object set as being photographed.
The device according to claim 11, wherein:

The marking unit is further configured to mark the state of all objects in the target object set as a state to be photographed before sending the shooting instruction;

The marking unit is specifically configured to: update the state of all objects in the target object set to a state where the shooting is completed.
The device according to claim 11 or 12, wherein:

The receiving unit is further configured to receive object information of M objects sent by the target detail camera, where M is greater than or equal to 1;

The device also includes:

The first obtaining unit is configured to obtain the characteristics of the M objects according to the object information of the M objects;

A comparison unit, configured to compare the features of the M objects with the feature library of the panoramic camera; the feature library of the panoramic camera stores the features of the objects photographed by the multiple detail cameras;

The sending unit is configured to send the remaining object information after deleting the object information of the object that has matching features in the feature library of the panoramic camera among the object information of the M objects to the host.
The device according to any one of claims 11-13, wherein the device further comprises:

The second acquiring unit is configured to acquire the shooting objects of the target detail camera, and the shooting objects of the target detail camera also include objects outside the target object set;

The marking unit is further configured to: after the receiving unit receives the response to the completion of the shooting instruction, mark the objects outside the set of target objects shot by the target detail camera as the shooting completed.
The device according to any one of claims 11-14, wherein the panoramic image includes a plurality of object sets, and the target object set is the object set with the highest priority in the panoramic image;

The shooting unit is further configured to: after the receiving unit receives the response to the completion of the shooting instruction sent by the target detail camera, re-shoot to obtain a new panoramic image, and the new panoramic image includes a new panoramic image with multiple objects. Target object set; the new target object set is the highest priority object set in the new panoramic image;

The selection unit is further configured to: select a new target detail camera from the multiple detail cameras;

The sending unit is further configured to send a new shooting instruction carrying a single pan/tilt/zoom PTZ value to the new target detail camera, and the new shooting instruction is used to instruct the new target detail camera to execute: The PTZ value included in the shooting instruction adjusts the shooting position so that the new target object set is located in the field of view of the target detail camera, and the shooting is performed.
A photographing device, characterized in that the photographing device comprises a processor and a memory, the memory is coupled to the processor, the memory is connected to the processor, and the memory is used to store a computer program. When the processor executes the computer program, the photographing device executes the action of a panoramic camera according to any one of claims 1-10.
A photographing system, characterized in that the photographing system includes a panoramic camera and a plurality of detail cameras, the panoramic camera communicates with the plurality of detail cameras, and the visible range of the panoramic camera spans the multiple detail cameras The visual range of the camera;

The panoramic camera is used to capture a panoramic image, the panoramic image includes a target object set with multiple objects; select a target detail camera from the multiple detail cameras, wherein the target object set is located in the Within the visible range of the target detail camera; send a shooting instruction to the target detail camera, the shooting instruction carries a single pan/tilt/zoom PTZ value, and the shooting instruction is used to instruct the target detail camera to execute: The PTZ value included in the shooting instruction adjusts the shooting position so that the target object set is located in the field of view of the target detail camera, and the shooting is performed;

The detail camera, which is the target detail camera, is used to receive the shooting instruction sent by the panoramic camera; adjust the shooting position according to the PTZ value included in the shooting instruction; and shoot each of the N objects in its field of view once, Obtain the object information of N objects; the N objects include all objects in the target object set; send a response to the panoramic camera to complete the shooting instruction; compare the objects of M objects among the N objects Information report, the report object is the panoramic camera or the host, and the M is greater than or equal to 1 and less than or equal to N;

The panoramic camera is further configured to receive a response to the completion of the shooting instruction sent by the target detail camera; and mark the objects in the target object set as shooting completed.
A computer-readable storage medium, characterized by comprising a computer program, which when running on a computer, causes the computer to execute the shooting method according to any one of claims 1-10.
A computer program product, which is characterized by comprising a computer program, which when running on a computer, causes the computer to execute the shooting method according to any one of claims 1-10.