CN116866720A - Camera angle self-adaptive regulation and control method, system and terminal based on sound source localization - Google Patents
Camera angle self-adaptive regulation and control method, system and terminal based on sound source localization Download PDFInfo
- Publication number
- CN116866720A CN116866720A CN202311126727.XA CN202311126727A CN116866720A CN 116866720 A CN116866720 A CN 116866720A CN 202311126727 A CN202311126727 A CN 202311126727A CN 116866720 A CN116866720 A CN 116866720A
- Authority
- CN
- China
- Prior art keywords
- camera
- angle
- vector
- target object
- representing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000004807 localization Effects 0.000 title claims abstract description 23
- 239000013598 vector Substances 0.000 claims abstract description 135
- 238000005457 optimization Methods 0.000 claims abstract description 25
- 230000008569 process Effects 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 claims description 18
- 238000012937 correction Methods 0.000 claims description 14
- 230000003044 adaptive effect Effects 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 230000001276 controlling effect Effects 0.000 description 11
- 230000033001 locomotion Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/18—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using ultrasonic, sonic, or infrasonic waves
- G01S5/20—Position of source determined by a plurality of spaced direction-finders
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
Abstract
The application discloses a camera angle self-adaptive regulation and control method, a system and a terminal based on sound source positioning, which relate to the technical field of intelligent control and have the technical scheme that: performing sound source localization on the target object to obtain spatial position information; controlling the camera to rotate for the first time according to the space position information of the target object and the initial view angle direction of the camera; fitting according to the position information of the target object in the plurality of acquired images to obtain a predicted moving track of the target object in a second period; calculating the position vector of each movable point by the difference between the space coordinates of the movable point and the space coordinates of the camera; solving by taking the minimum sum of the degrees of the first space included angles corresponding to all the movable point positions as an optimization target to obtain an optimal preset vector; and controlling the camera to rotate secondarily by taking the optimal preset vector as the optimal view angle direction of the camera. The application can reduce the vibration noise interference in the frequent rotation process of the camera and comprehensively improve the image acquisition quality in a period of time.
Description
Technical Field
The application relates to the technical field of intelligent control, in particular to a camera angle self-adaptive regulation and control method, a camera angle self-adaptive regulation and control system and a camera angle self-adaptive regulation and control terminal based on sound source positioning.
Background
Cameras are one of the most commonly used devices for observing field conditions in some important places, and are widely applied to large-scale public places, important security areas, critical process production stages and high-voltage electrified areas, such as monitoring of abnormal conditions in large-scale public places and monitoring of animal invasion in high-voltage electrified areas.
In order to enable the camera to cover a wider monitoring area, the camera generally adopts a fixed rotating speed to carry out unidirectional cyclic rotation, the control process is simple to realize, but the emergency can not be monitored in time. For this reason, a technology for flexibly controlling the viewing angle direction of a camera by applying a sound source localization technology is disclosed in the prior art, which recognizes the position of a certain target object having a specific sound source through the sound source localization technology, and then controls the viewing angle direction of the camera to rotate to the target object. However, with the movement of the target object, in order to ensure the quality of image acquisition, it is generally required to dynamically update the position information of the sound source localization, which requires frequent regulation of the rotation of the camera, even real-time regulation of the rotation of the camera. The vibration noise in the frequent rotation process of the camera is easy to reduce the quality of image acquisition, and when a movable object sensitive to environmental changes is monitored, the frequent rotation of the camera also can interfere the normal behavior of the movable object.
Therefore, how to research and design a camera angle self-adaptive regulation and control method, system and terminal based on sound source positioning, which can overcome the defects, is a problem which needs to be solved in the current state.
Disclosure of Invention
In order to solve the defects in the prior art, the application aims to provide a camera angle self-adaptive regulation and control method, a camera angle self-adaptive regulation and control system and a camera terminal based on sound source positioning, which can reduce vibration noise interference in the frequent rotation process of a camera and comprehensively improve the image acquisition quality in a period of time.
The technical aim of the application is realized by the following technical scheme:
in a first aspect, a camera angle adaptive regulation and control method based on sound source localization is provided, including the following steps:
performing sound source localization on the target object according to the collected audio data to obtain the spatial position information of the target object;
controlling the camera to rotate for the first time according to the spatial position information of the target object and the initial view angle direction of the camera so that the target object is in the shooting view angle range of the camera;
continuously acquiring a plurality of acquired images of a target object in a first period, and fitting according to the position information of the target object in the acquired images to obtain a predicted moving track of the target object in a second period;
extracting a plurality of active points from the predicted active track at equal time intervals or equidistant intervals, and calculating the position vector of each active point according to the difference between the spatial coordinates of the active points and the spatial coordinates of the camera;
calculating a first space angle degree between the position vector of the single movable point and a preset vector, and solving by taking the minimum sum of the first space angle degrees corresponding to all the movable point as an optimization target to obtain an optimal preset vector;
and controlling the camera to rotate secondarily by taking the optimal preset vector as the optimal view angle direction of the camera, and acquiring real-time images of the target object in a second period by the camera after the secondary rotation.
Further, the process of controlling the camera to primarily rotate according to the spatial position information of the target object and the initial view angle direction of the camera specifically includes:
calculating to obtain an initial vector of the target object according to the difference between the spatial position information of the target object and the spatial coordinates of the camera;
calculating a second space included angle degree between the view angle vector corresponding to the initial view angle direction and the initial vector;
calculating to obtain a deflection angle difference value according to the difference between the visual angle deflection angle of the camera and a preset minimum deflection angle;
calculating a control deflection angle according to the difference between the degree of the second space included angle and the deflection angle difference value;
establishing a reference plane by using the view angle vector and the initial vector to be in the same plane;
the initial view angle direction of the camera is controlled to deviate from the initial view angle direction to the initial vector in the reference plane to control the deflection angle, so that the initial rotation control of the camera is completed.
Further, the expression of the optimization target solution is:
;
wherein ,indicate->Space coordinates of the movable points; />Representing the spatial coordinates of the camera; />Indicate->Position vectors of the active points; />Representing a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Representing the number of active points; />Representing equal time intervals of adjacent activity points; />Representing a second period; />Representing a preset first angle; />A first space included angle degree between the position vector representing the 1 st active point position and a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Position vector representing the 1 st active point and +.>A first degree of spatial included angle between the position vectors of the movable points; />Representing a preset second angle.
Further, the method also distributes correction parameters for the corresponding first space angle degrees according to the modular length of the position vector, and the larger the modular length of the position vector is, the smaller the correction parameters distributed for the corresponding first space angle degrees are.
Further, the distribution formula of the correction parameter is as follows:
;
wherein ,indicate->Correction parameters allocated to the position vectors of the active points; />Indicate->Modulo length of the position vector of each active point location; />Representing the number of active sites.
Further, the expression of the optimization target solution is:
;
wherein ,indicate->Space coordinates of the movable points; />Representing the spatial coordinates of the camera; />Indicate->Position vectors of the active points; />Representing a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Indicate->Correction parameters allocated to the position vectors of the active points; />Representing the number of active points; />Representing equal time intervals of adjacent activity points; />Representing a second period;representing a preset first angle; />A first space included angle degree between the position vector representing the 1 st active point position and a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Position vector representing the 1 st active point and +.>A first degree of spatial included angle between the position vectors of the movable points; />Representing a preset second angle.
Further, if the predicted moving track is folded along the track in the circumferential direction taking the camera as the center, extracting a local track positioned in front of the folding point in the predicted moving track to perform camera angle self-adaptive regulation and control, and simultaneously replacing the second period with a third period corresponding to the local track.
Furthermore, the method also restarts the adaptive regulation and control of the camera angle according to the trigger signal;
the trigger signal includes:
a first signal generated when the target object is not in the acquired real-time image;
a second signal generated when the target object is shifted by more than a threshold between the actual activity trajectory and the predicted activity trajectory in the second period;
and updating the third signal generated when the target object is updated.
In a second aspect, a camera angle adaptive regulation and control system based on sound source localization is provided, including:
the sound source positioning module is used for performing sound source positioning on the target object according to the collected audio data to obtain the spatial position information of the target object;
the primary rotation module is used for controlling the camera to rotate for the first time according to the spatial position information of the target object and the initial view angle direction of the camera so that the target object is in the shooting view angle range of the camera;
the track prediction module is used for continuously acquiring a plurality of acquired images of the target object in a first period and fitting according to the position information of the target object in the acquired images to obtain a predicted moving track of the target object in a second period;
the point position extraction module is used for extracting a plurality of active point positions from the predicted active track at equal time intervals or equidistant intervals, and calculating the position vector of each active point position according to the difference between the space coordinates of the active point positions and the space coordinates of the camera;
the optimization solving module is used for calculating first space angle degrees between the position vector of the single movable point position and the preset vector, and solving the optimal preset vector by taking the minimum sum of the first space angle degrees corresponding to all the movable point positions as an optimization target;
and the optimization control module is used for controlling the camera to rotate secondarily by taking the optimal preset vector as the optimal view angle direction of the camera, and the camera after the secondary rotation acquires the real-time image of the target object in the second period.
In a third aspect, a computer terminal is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the camera angle adaptive regulation and control method based on sound source localization according to any one of the first aspects when executing the program.
Compared with the prior art, the application has the following beneficial effects:
1. according to the sound source positioning-based camera angle self-adaptive regulation and control method, the whole camera angle self-adaptive regulation and control is divided into early short-time regulation and control and later long-time regulation and control, the position change of a target object is analyzed in the short-time regulation and control to obtain a predicted moving track, and the camera is regulated and controlled by optimizing and selecting an optimal preset vector corresponding to the condition that the influence of direction deviation on the image acquisition quality is small based on the predicted moving track, so that the vibration noise interference in the frequent rotation process of the camera can be reduced, and the image acquisition quality in a period of time is comprehensively improved;
2. on the basis of considering the influence of the direction deviation on the image acquisition quality, the influence of the image acquisition distance on the image acquisition quality is also considered, so that the self-adaptive regulation and control of the camera angle is more reasonable and reliable;
3. when the predicted moving track is folded along the track in the circumferential direction taking the camera as the center, the local track positioned in front of the folding point in the predicted moving track is extracted to carry out camera angle self-adaptive regulation and control, so that the interference of intensive activities on optimal preset vector optimization solution can be effectively reduced, and the accuracy and reliability of the optimal preset vector optimization solution are improved;
4. the application also considers the influence of random movement of the target object on image acquisition in the first period, and can reduce the situation that the target object is separated from the shooting visual angle range of the camera;
5. in the optimal preset vector optimization solving process, the application can filter partial scenes with smaller camera regulation angles by restraining the angles between the preset vector and the shooting view angle boundary of the camera, thereby further enhancing the stability of camera angle self-adaptive regulation.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:
FIG. 1 is a flow chart in embodiment 1 of the present application;
fig. 2 is a schematic diagram of initial rotation of a camera according to embodiment 1 of the present application;
fig. 3 is a system block diagram in embodiment 2 of the present application.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present application, the present application will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present application and the descriptions thereof are for illustrating the present application only and are not to be construed as limiting the present application.
Example 1: a camera angle self-adaptive regulation and control method based on sound source localization, as shown in figure 1, comprises the following steps:
s1: performing sound source localization on the target object according to the collected audio data to obtain the spatial position information of the target object;
s2: controlling the camera to rotate for the first time according to the spatial position information of the target object and the initial view angle direction of the camera so that the target object is in the shooting view angle range of the camera;
s3: continuously acquiring a plurality of acquired images of a target object in a first period, and fitting according to the position information of the target object in the acquired images to obtain a predicted moving track of the target object in a second period;
s4: extracting a plurality of active points from the predicted active track at equal time intervals or equidistant intervals, and calculating the position vector of each active point according to the difference between the spatial coordinates of the active points and the spatial coordinates of the camera;
s5: calculating a first space angle degree between the position vector of the single movable point and a preset vector, and solving by taking the minimum sum of the first space angle degrees corresponding to all the movable point as an optimization target to obtain an optimal preset vector;
s6: and controlling the camera to rotate secondarily by taking the optimal preset vector as the optimal view angle direction of the camera, and acquiring real-time images of the target object in a second period by the camera after the secondary rotation.
The camera in this embodiment can adopt the panorama camera, both can realize azimuth regulation and control, can realize pitch angle regulation and control again, and the camera can also dispose the structure such as self-cleaning, automatic light filling etc. function, and is not limited here.
It should be noted that, when the sound source is located, the target tracking may be performed according to a preset specific sound source, or the direction with the largest sound energy may be selected as the identification direction, or the direction with the largest sound energy density may be selected as the identification direction, which is not limited herein. And when the space position information of the target object is obtained, a three-dimensional coordinate system can be established by taking the installation position of the camera as the origin, so that the three-dimensional coordinate of the target object is obtained.
In addition, the duration of the first period is smaller than that of the second period, and in order to further ensure the accuracy of predicting the activity track, if a target object exists in the image of the first period, a part of the historical image can be selected to participate in track prediction.
In addition, the initial view angle direction and the optimized view angle direction of the camera in the application refer to the acquisition center direction of the camera.
Considering the influence of random movement of the target object on image acquisition in the first period, the situation that the target object is separated from the shooting visual angle range of the camera is reduced. In this embodiment, as shown in fig. 2, the process of controlling the camera to primarily rotate according to the spatial position information of the target object and the initial view direction of the camera specifically includes: calculating to obtain an initial vector of the target object by using the difference between the spatial position information A of the target object and the spatial coordinate Q of the camera; calculating a second space included angle degree 4 between the view angle vector corresponding to the initial view angle direction and the initial vector; calculating to obtain a deflection angle difference value 3 according to the difference between the visual angle deflection angle 1 of the camera and the preset minimum deflection angle 2; calculating a control deflection angle 5 according to the difference between the second space angle degree 4 and the deflection angle difference 3; establishing a reference plane by using the view angle vector and the initial vector to be in the same plane; the initial view angle direction of the camera is controlled to deviate from the initial view angle direction to the initial vector in the reference plane to control the deflection angle, so that the initial rotation control of the camera is completed.
In this embodiment, the view vector corresponding to the initial view direction may be a unit vector of the initial view direction. The angle of view deflection is the space included angle between the acquisition center direction of the camera and the view boundary.
As an alternative embodiment, the expression for the optimization objective solution is:
;
wherein ,indicate->Space coordinates of the movable points; />Representing the spatial coordinates of the camera; />Indicate->Position vectors of the active points; />Representing a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Representing the number of active points; />Representing equal time intervals of adjacent activity points; />Representing a second period; />Representing a preset first angle; />A first space included angle degree between the position vector representing the 1 st active point position and a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Position vector representing the 1 st active point and +.>A first degree of spatial included angle between the position vectors of the movable points; />Representing a preset second angle.
As another alternative implementation manner, the application also allocates correction parameters for the corresponding first space angle degrees according to the modular length of the position vector, and the larger the modular length of the position vector is, the smaller the correction parameters allocated for the corresponding first space angle degrees are.
For example, the allocation formula of the correction parameter is:
;
wherein ,indicate->Correction parameters allocated to the position vectors of the active points; />Indicate->Modulo length of the position vector of each active point location; />Representing the number of active sites.
And the expression of the optimization target solution is:
;
wherein ,indicate->Space coordinates of the movable points; />Representing the spatial coordinates of the camera; />Indicate->Position vectors of the active points; />Representing a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Indicate->Individual activity pointsCorrection parameters assigned to the position vectors of the bits; />Representing the number of active points; />Representing equal time intervals of adjacent activity points; />Representing a second period;representing a preset first angle; />A first space included angle degree between the position vector representing the 1 st active point position and a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Position vector representing the 1 st active point and +.>A first degree of spatial included angle between the position vectors of the movable points; />Representing a preset second angle.
In order to reduce the interference of intensive activities on optimal preset vector optimization solution, if the predicted activity track is folded back along the track in the circumferential direction taking the camera as the center, extracting a local track positioned in front of a folding point in the predicted activity track to carry out camera angle self-adaptive regulation and control, and simultaneously replacing the second period with a third period corresponding to the local track.
The application also restarts the adaptive regulation and control of the camera angle according to the trigger signal. And the trigger signal may be any of the following: a first signal as generated when the target object is not in the acquired real-time image; a second signal generated when the target object is shifted by more than a threshold between the actual activity trajectory and the predicted activity trajectory in the second period; and updating the third signal generated when the target object is updated.
Example 2: the camera angle self-adaptive regulation and control system based on sound source localization is used for realizing the camera angle self-adaptive regulation and control method based on sound source localization described in the embodiment 1, and comprises a sound source localization module, a primary rotation module, a track prediction module, a point position extraction module, an optimization solving module and an optimization control module, as shown in fig. 3.
The sound source positioning module is used for performing sound source positioning on the target object according to the collected audio data to obtain the spatial position information of the target object; the primary rotation module is used for controlling the camera to rotate for the first time according to the spatial position information of the target object and the initial view angle direction of the camera so that the target object is in the shooting view angle range of the camera; the track prediction module is used for continuously acquiring a plurality of acquired images of the target object in a first period and fitting according to the position information of the target object in the acquired images to obtain a predicted moving track of the target object in a second period; the point position extraction module is used for extracting a plurality of active point positions from the predicted active track at equal time intervals or equidistant intervals, and calculating the position vector of each active point position according to the difference between the space coordinates of the active point positions and the space coordinates of the camera; the optimization solving module is used for calculating first space angle degrees between the position vector of the single movable point position and the preset vector, and solving the optimal preset vector by taking the minimum sum of the first space angle degrees corresponding to all the movable point positions as an optimization target; and the optimization control module is used for controlling the camera to rotate secondarily by taking the optimal preset vector as the optimal view angle direction of the camera, and the camera after the secondary rotation acquires the real-time image of the target object in the second period.
Working principle: the application divides the self-adaptive regulation of the whole camera angle into the early short-time regulation and the later long-time regulation, analyzes the position change of the target object in the short-time regulation to obtain the predicted moving track, optimizes and selects the optimal preset vector corresponding to the moment that the direction deviation has small influence on the image acquisition quality based on the predicted moving track to regulate the camera, can reduce the vibration noise interference in the frequent rotation process of the camera, and comprehensively improves the image acquisition quality in a period of time.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the application, and is not meant to limit the scope of the application, but to limit the application to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the application are intended to be included within the scope of the application.
Claims (10)
1. The camera angle self-adaptive regulation and control method based on sound source localization is characterized by comprising the following steps:
performing sound source localization on the target object according to the collected audio data to obtain the spatial position information of the target object;
controlling the camera to rotate for the first time according to the spatial position information of the target object and the initial view angle direction of the camera so that the target object is in the shooting view angle range of the camera;
continuously acquiring a plurality of acquired images of a target object in a first period, and fitting according to the position information of the target object in the acquired images to obtain a predicted moving track of the target object in a second period;
extracting a plurality of active points from the predicted active track at equal time intervals or equidistant intervals, and calculating the position vector of each active point according to the difference between the spatial coordinates of the active points and the spatial coordinates of the camera;
calculating a first space angle degree between the position vector of the single movable point and a preset vector, and solving by taking the minimum sum of the first space angle degrees corresponding to all the movable point as an optimization target to obtain an optimal preset vector;
and controlling the camera to rotate secondarily by taking the optimal preset vector as the optimal view angle direction of the camera, and acquiring real-time images of the target object in a second period by the camera after the secondary rotation.
2. The camera angle self-adaptive regulation and control method based on sound source localization according to claim 1, wherein the process of controlling the primary rotation of the camera according to the spatial position information of the target object and the initial view angle direction of the camera specifically comprises:
calculating to obtain an initial vector of the target object according to the difference between the spatial position information of the target object and the spatial coordinates of the camera;
calculating a second space included angle degree between the view angle vector corresponding to the initial view angle direction and the initial vector;
calculating to obtain a deflection angle difference value according to the difference between the visual angle deflection angle of the camera and a preset minimum deflection angle;
calculating a control deflection angle according to the difference between the degree of the second space included angle and the deflection angle difference value;
establishing a reference plane by using the view angle vector and the initial vector to be in the same plane;
the initial view angle direction of the camera is controlled to deviate from the initial view angle direction to the initial vector in the reference plane to control the deflection angle, so that the initial rotation control of the camera is completed.
3. The camera angle self-adaptive regulation and control method based on sound source localization according to claim 1, wherein the expression of the optimization target solution is:
;
wherein ,indicate->Space coordinates of the movable points; />Representing the spatial coordinates of the camera; />Indicate->Position vectors of the active points; />Representing a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Representing the number of active points; />Representing equal time intervals of adjacent activity points; />Representing a second period; />Representing a preset first angle; />A first space included angle degree between the position vector representing the 1 st active point position and a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Position vector representing the 1 st active point and +.>A first degree of spatial included angle between the position vectors of the movable points; />Representing a preset second angle.
4. The sound source positioning-based camera angle self-adaptive regulation and control method according to claim 1, wherein the method further distributes correction parameters for the corresponding first space angle degrees according to the modular length of the position vector, and the larger the modular length of the position vector is, the smaller the correction parameters distributed for the corresponding first space angle degrees are.
5. The camera angle adaptive regulation and control method based on sound source localization according to claim 4, wherein the distribution formula of the correction parameters is:
;
wherein ,indicate->Correction parameters allocated to the position vectors of the active points; />Indicate->Modulo length of the position vector of each active point location; />Representing the number of active sites.
6. The camera angle adaptive regulation and control method based on sound source localization according to claim 4, wherein the expression of the optimization target solution is:
;
wherein ,indicate->Space coordinates of the movable points; />Representing the spatial coordinates of the camera; />Indicate->Position vectors of the active points; />Representing a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Indicate->Correction parameters allocated to the position vectors of the active points; />Representing the number of active points; />Representing equal time intervals of adjacent activity points; />Representing a second period; />Representing a preset first angle; />A first space included angle degree between the position vector representing the 1 st active point position and a preset vector; />Indicate->A first space included angle degree between the position vector of each movable point and a preset vector; />Position vector representing the 1 st active point and +.>A first degree of spatial included angle between the position vectors of the movable points; />Representing a preset second angle.
7. The camera angle self-adaptive regulation and control method based on sound source localization according to claim 1, wherein if the predicted moving track is folded along the track in the circumferential direction with the camera as the center, a local track positioned in front of the folding point in the predicted moving track is extracted to perform camera angle self-adaptive regulation and control, and the second period is replaced with a third period corresponding to the local track.
8. The sound source positioning-based camera angle adaptive regulation and control method according to claim 1, wherein the method further restarts the camera angle adaptive regulation and control according to a trigger signal;
the trigger signal includes:
a first signal generated when the target object is not in the acquired real-time image;
a second signal generated when the target object is shifted by more than a threshold between the actual activity trajectory and the predicted activity trajectory in the second period;
and updating the third signal generated when the target object is updated.
9. Camera angle self-adaptation regulation and control system based on sound source location, characterized by includes:
the sound source positioning module is used for performing sound source positioning on the target object according to the collected audio data to obtain the spatial position information of the target object;
the primary rotation module is used for controlling the camera to rotate for the first time according to the spatial position information of the target object and the initial view angle direction of the camera so that the target object is in the shooting view angle range of the camera;
the track prediction module is used for continuously acquiring a plurality of acquired images of the target object in a first period and fitting according to the position information of the target object in the acquired images to obtain a predicted moving track of the target object in a second period;
the point position extraction module is used for extracting a plurality of active point positions from the predicted active track at equal time intervals or equidistant intervals, and calculating the position vector of each active point position according to the difference between the space coordinates of the active point positions and the space coordinates of the camera;
the optimization solving module is used for calculating first space angle degrees between the position vector of the single movable point position and the preset vector, and solving the optimal preset vector by taking the minimum sum of the first space angle degrees corresponding to all the movable point positions as an optimization target;
and the optimization control module is used for controlling the camera to rotate secondarily by taking the optimal preset vector as the optimal view angle direction of the camera, and the camera after the secondary rotation acquires the real-time image of the target object in the second period.
10. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the sound source localization based camera angle adaptive regulation method according to any one of claims 1-8 when executing the program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311126727.XA CN116866720B (en) | 2023-09-04 | 2023-09-04 | Camera angle self-adaptive regulation and control method, system and terminal based on sound source localization |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311126727.XA CN116866720B (en) | 2023-09-04 | 2023-09-04 | Camera angle self-adaptive regulation and control method, system and terminal based on sound source localization |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116866720A true CN116866720A (en) | 2023-10-10 |
CN116866720B CN116866720B (en) | 2023-11-28 |
Family
ID=88225332
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311126727.XA Active CN116866720B (en) | 2023-09-04 | 2023-09-04 | Camera angle self-adaptive regulation and control method, system and terminal based on sound source localization |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116866720B (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012143348A1 (en) * | 2011-04-20 | 2012-10-26 | Atlas Elektronik Gmbh | Method and device for determining and representing possible target parameters |
CN106713773A (en) * | 2017-03-31 | 2017-05-24 | 联想(北京)有限公司 | Shooting control method and electronic device |
JP2019068182A (en) * | 2017-09-29 | 2019-04-25 | セコム株式会社 | Monitoring device |
CN109712188A (en) * | 2018-12-28 | 2019-05-03 | 科大讯飞股份有限公司 | A kind of method for tracking target and device |
CN111722186A (en) * | 2020-06-30 | 2020-09-29 | 中国平安人寿保险股份有限公司 | Sound source positioning-based shooting method and device, electronic equipment and storage medium |
WO2021078116A1 (en) * | 2019-10-21 | 2021-04-29 | 维沃移动通信有限公司 | Video processing method and electronic device |
US20210209772A1 (en) * | 2020-01-07 | 2021-07-08 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Cross-camera obstacle tracking method, system and medium |
CN113840073A (en) * | 2020-06-08 | 2021-12-24 | 浙江宇视科技有限公司 | Control method, device, equipment and medium for shooting equipment |
WO2022001407A1 (en) * | 2020-07-01 | 2022-01-06 | 海信视像科技股份有限公司 | Camera control method and display device |
CN115035187A (en) * | 2022-05-19 | 2022-09-09 | 北京声智科技有限公司 | Sound source direction determining method, device, terminal, storage medium and product |
US20230093866A1 (en) * | 2020-04-15 | 2023-03-30 | Sony Group Corporation | Information processing device, information processing method, and program |
CN115996317A (en) * | 2022-11-30 | 2023-04-21 | 旭宇光电(深圳)股份有限公司 | Multifunctional intelligent pole and noise source monitoring method and device based on same |
CN116405778A (en) * | 2023-03-07 | 2023-07-07 | 北京通用人工智能研究院 | Active visual tracking method and device for moving target |
CN116456194A (en) * | 2022-12-19 | 2023-07-18 | 济南轨道交通集团有限公司 | Audio and video acquisition tracking method and device using sound source positioning technology |
WO2023142266A1 (en) * | 2022-01-29 | 2023-08-03 | 深圳壹秘科技有限公司 | Remote interaction method, remote interaction device and computer storage medium |
CN116614709A (en) * | 2023-04-28 | 2023-08-18 | 三峡金沙江川云水电开发有限公司 | Intelligent control method, system, terminal and medium for distributed control ball |
-
2023
- 2023-09-04 CN CN202311126727.XA patent/CN116866720B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012143348A1 (en) * | 2011-04-20 | 2012-10-26 | Atlas Elektronik Gmbh | Method and device for determining and representing possible target parameters |
CN106713773A (en) * | 2017-03-31 | 2017-05-24 | 联想(北京)有限公司 | Shooting control method and electronic device |
JP2019068182A (en) * | 2017-09-29 | 2019-04-25 | セコム株式会社 | Monitoring device |
CN109712188A (en) * | 2018-12-28 | 2019-05-03 | 科大讯飞股份有限公司 | A kind of method for tracking target and device |
WO2021078116A1 (en) * | 2019-10-21 | 2021-04-29 | 维沃移动通信有限公司 | Video processing method and electronic device |
US20210209772A1 (en) * | 2020-01-07 | 2021-07-08 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Cross-camera obstacle tracking method, system and medium |
US20230093866A1 (en) * | 2020-04-15 | 2023-03-30 | Sony Group Corporation | Information processing device, information processing method, and program |
CN113840073A (en) * | 2020-06-08 | 2021-12-24 | 浙江宇视科技有限公司 | Control method, device, equipment and medium for shooting equipment |
CN111722186A (en) * | 2020-06-30 | 2020-09-29 | 中国平安人寿保险股份有限公司 | Sound source positioning-based shooting method and device, electronic equipment and storage medium |
WO2022001407A1 (en) * | 2020-07-01 | 2022-01-06 | 海信视像科技股份有限公司 | Camera control method and display device |
WO2023142266A1 (en) * | 2022-01-29 | 2023-08-03 | 深圳壹秘科技有限公司 | Remote interaction method, remote interaction device and computer storage medium |
CN115035187A (en) * | 2022-05-19 | 2022-09-09 | 北京声智科技有限公司 | Sound source direction determining method, device, terminal, storage medium and product |
CN115996317A (en) * | 2022-11-30 | 2023-04-21 | 旭宇光电(深圳)股份有限公司 | Multifunctional intelligent pole and noise source monitoring method and device based on same |
CN116456194A (en) * | 2022-12-19 | 2023-07-18 | 济南轨道交通集团有限公司 | Audio and video acquisition tracking method and device using sound source positioning technology |
CN116405778A (en) * | 2023-03-07 | 2023-07-07 | 北京通用人工智能研究院 | Active visual tracking method and device for moving target |
CN116614709A (en) * | 2023-04-28 | 2023-08-18 | 三峡金沙江川云水电开发有限公司 | Intelligent control method, system, terminal and medium for distributed control ball |
Non-Patent Citations (1)
Title |
---|
刘义亭;董梦超;黄家才;范子霄;宗文锦;郭婧;: "基于OpenMV的目标跟踪系统设计", 南京工程学院学报(自然科学版), no. 01 * |
Also Published As
Publication number | Publication date |
---|---|
CN116866720B (en) | 2023-11-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6310093B2 (en) | Target object detection method, detection apparatus, and robot | |
SanMiguel et al. | Self-reconfigurable smart camera networks | |
US9111148B2 (en) | Unsupervised learning of feature anomalies for a video surveillance system | |
US20200110173A1 (en) | Obstacle detection method and device | |
CN113424079A (en) | Obstacle detection method, obstacle detection device, computer device, and storage medium | |
CN110933372A (en) | Target tracking type monitoring method based on PTZ | |
CN110378216B (en) | Target detection method, target detection device, image pickup apparatus, and storage medium | |
CN112171675B (en) | Obstacle avoidance method and device for mobile robot, robot and storage medium | |
CN112527012B (en) | Method and system for controlling task surrounded by centerless robot cluster | |
CN116866720B (en) | Camera angle self-adaptive regulation and control method, system and terminal based on sound source localization | |
KR20130068603A (en) | Method for assigning roles to multi robot | |
CN110824468B (en) | Method and system for tracking multiple targets based on radar control dome camera | |
CN116614709A (en) | Intelligent control method, system, terminal and medium for distributed control ball | |
CN205490869U (en) | Motion target is caught and tracking device | |
US20230237890A1 (en) | Intruder location-based dynamic virtual fence configuration and multiple image sensor device operation method | |
CN113966496A (en) | Control method, control device, movable platform and computer readable storage medium | |
CN114536326B (en) | Road sign data processing method, device and storage medium | |
CN114979497A (en) | Unmanned aerial vehicle linkage tracking method and system based on pole loading and cloud platform | |
CN205486308U (en) | Laser aims and tracking device | |
CN115185287A (en) | Intelligent multi-underwater-robot dynamic obstacle avoidance and enclosure control system | |
JP6647367B1 (en) | Image processing program, image processing device, image processing system, and image processing method | |
Hoffmann et al. | Dmctrac: Distributed multi camera tracking | |
CN113784361B (en) | Dynamic adjustment method and device for sensor node and storage medium | |
Abdelkader et al. | Angular heuristics for coverage maximization in multi-camera surveillance | |
Li et al. | Simultaneous Coverage and Mapping of Stereo Camera Network for Unknown Deformable Object |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |