CN108471496B - Camera configuration method and device - Google Patents
Camera configuration method and device Download PDFInfo
- Publication number
- CN108471496B CN108471496B CN201810151015.6A CN201810151015A CN108471496B CN 108471496 B CN108471496 B CN 108471496B CN 201810151015 A CN201810151015 A CN 201810151015A CN 108471496 B CN108471496 B CN 108471496B
- Authority
- CN
- China
- Prior art keywords
- camera
- point
- tested
- cost value
- visual
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000000007 visual effect Effects 0.000 claims abstract description 220
- 238000012800 visualization Methods 0.000 claims description 31
- 238000012360 testing method Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 15
- 230000003287 optical effect Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
Abstract
A camera configuration method and apparatus, comprising: in a preset visual area, determining a preset number of camera configuration modes and visual cameras of points to be tested according to the set total number of cameras; setting acquisition weight according to the position information of the point to be tested in the visual area in the camera configuration mode; and calculating the configuration cost value of the camera configuration mode according to the acquisition weight, and determining the final camera configuration mode according to the configuration cost value. In the embodiment of the invention, the acquisition weight is set according to the position information of the point to be tested in the visual area, and the configuration cost value of the camera configuration mode is calculated according to the acquisition weight, so that the calculated configuration cost value is more reasonable, the camera configuration mode is more reasonable, the appropriate number of motion capture cameras are more reasonably configured while the motion capture effect is ensured, and the camera configuration is more economic and reasonable.
Description
Technical Field
The invention relates to the field of computer vision, in particular to a camera configuration method and device.
Background
In the optical motion capture process, the price of the motion capture cameras is very expensive, and it is very important to save the cost to reasonably arrange an appropriate number of motion capture cameras while ensuring the motion capture effect. Therefore, how to reasonably configure a proper number of dynamic cameras becomes a problem to be solved urgently.
The prior art discloses a camera layout scheme, and the idea of the camera layout scheme is as follows: firstly, randomly generating a certain number of camera configuration modes, then calculating the number of the visual cameras of each point to be tested in each camera configuration mode, and finally calculating the configuration cost value of each camera configuration mode according to the number of the visual cameras of each point to be tested. When calculating the configuration cost value of each camera configuration mode, specifically, converting the number of the visual cameras of each point to be tested into the corresponding configuration cost value according to a preset condition, and summing the configuration cost values of all the points to be tested, thereby obtaining the configuration cost value of each camera configuration mode; the configuration cost value is used for identifying the advantages and disadvantages of the camera configuration modes, and the final camera configuration mode is determined according to the configuration cost value of each camera configuration mode.
However, in the prior art, when determining the camera arrangement mode, other factors influencing the camera arrangement mode are not considered, so that the optimization space is improved when determining the camera arrangement mode.
Disclosure of Invention
The invention provides a camera configuration method and a camera configuration device.
According to a first aspect of the present invention, there is provided a camera configuring method comprising:
in a preset visual area, determining a preset number of camera configuration modes and visual cameras of points to be tested according to the set total number of cameras;
setting acquisition weight according to the position information of the point to be tested in the visual area in the camera configuration mode;
and calculating the configuration cost value of the camera configuration mode according to the acquisition weight, and determining the final camera configuration mode according to the configuration cost value.
According to a second aspect of the present invention, there is provided a camera arrangement comprising:
the device comprises a preset module, a display module and a control module, wherein the preset module is used for determining the configuration modes of a preset number of cameras and the visual cameras of points to be tested according to the set total number of the cameras in a preset visual area;
the first processing module is used for setting acquisition weight according to the position information of the point to be tested in the visual area in the camera configuration mode;
and the configuration module is used for calculating the configuration cost value of the camera configuration mode and determining the final camera configuration mode according to the configuration cost value.
According to a third aspect of the present invention, there is provided a camera arrangement comprising:
a memory for storing a program;
a processor for implementing the above method by executing the program stored in the memory.
Due to the adoption of the technical scheme, the invention has the beneficial effects that:
in the embodiment of the invention, the acquisition weight is set according to the position information of the point to be tested in the visual area, and the configuration cost value of the camera configuration mode is calculated according to the acquisition weight, so that the calculated configuration cost value is more reasonable, the camera configuration mode is more reasonable, the proper number of motion capture cameras are more reasonably configured while the motion capture effect is ensured, and the camera configuration is more economic and reasonable.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method provided in a second embodiment of the present invention;
FIG. 3 is a flowchart of a method provided in a third embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for calculating relative cost values according to a third embodiment of the present invention;
fig. 5 is a schematic diagram illustrating an effect that a relative angle between two adjacent visual cameras affects positioning accuracy of a point to be tested;
fig. 6 is a schematic diagram of camera grouping arrangement in the third embodiment of the present invention;
FIG. 7 is a flowchart illustrating a method for calculating relative cost values according to a fourth embodiment of the present invention;
FIG. 8 is a flowchart of determining an effective and reasonable camera configuration according to the fourth embodiment;
FIG. 9 is a flowchart of a method provided in the fifth embodiment of the present invention;
FIG. 10 is a schematic diagram of the intersection point of the visual axis of the camera and the XZ plane in the fifth embodiment of the present invention;
FIG. 11 is a flowchart illustrating a method for calculating a cost value of a drop point according to the fifth embodiment;
fig. 12, 13 and 14 are schematic views of the visual range of the camera according to the sixth embodiment of the present invention;
fig. 15 is a functional block diagram of an apparatus according to a seventh embodiment of the present invention;
fig. 16 is a functional block diagram of an apparatus according to a seventh embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. In all embodiments of the present invention, the terms, such as the visualization area, the capture area, the collection space area, and the capture space, refer to the motion collection space of the optical motion capture system, and the preset important collection space area refers to a certain important area in the specified visualization area. The normal line of the lens plane of the camera and the visual axis of the camera are the same concept.
The first embodiment is as follows:
fig. 1 is a flowchart of a camera configuration method according to an embodiment of the present invention, where an execution main body of the embodiment may be a computer device or a functional unit in the computer device, and the embodiment specifically includes steps S101 to S103, which are detailed as follows:
s101: and in a preset visual area, determining a preset number of camera configuration modes, points to be tested and visual cameras of the points to be tested.
The preset visualization area may be any size created by the user in the optical motion capture system and contains a simulated area of obstacles such as pillars and walls. In the preset visualization area, the user can further set the camera parameters, including the set total number of cameras, which can be actually adjusted.
The camera configuration mode is determined according to the camera parameters set by the user. The possible placing positions and placing angles of the cameras are calculated according to the parameters of the cameras, different calculated results are combined, and the camera configuration modes with the preset number are determined, wherein the preset number can be all the possible combination modes or some combination modes selected according to application scenes, and can be specifically set according to the requirements of practical application, and the method is not limited here.
Further, since the visualization area is usually set to be a quadrangle or a right-angled rectangle, the visualization area usually presents a symmetric feature, and in this case, the user only needs to set the position information of 1 camera, that is, the position information of 4 or 8 cameras can be correspondingly generated, so that the input amount of the camera parameters of the user is reduced, and the efficiency of calculating the preset number of camera configuration modes is improved.
The points to be tested in the visualization area can be understood as marking points. The mark points are specially-made marks or luminous points, the mark points are pasted on the captured object, and the optical motion capture system realizes motion capture by identifying the mark points and processing the data of the mark points. Specifically, in a preset visualization area, a predetermined number of points to be tested are set, wherein the predetermined number can be customized according to application requirements, and the more the predetermined number is, the more points to be tested need to be tested, the longer the testing time is, but the more accurate the testing result is.
In each camera configuration mode, the number of cameras capable of shooting the same point to be tested is determined, so that the number of visual cameras corresponding to the point to be tested is determined.
S102: and setting acquisition weight according to the position information of the point to be tested in the visual area (acquisition space area) in the camera configuration mode.
It should be noted that, in step S101, the camera parameters set by the user include the positions of the points to be tested, and the positions of the points to be tested in the collection space area are different, so that the capturing effect is different. Therefore, according to the influence of the position information of each point to be tested in the acquisition space area in each camera configuration mode on the capturing effect, the configuration cost value can be calculated by combining a preset rule.
Specifically, the advantages and disadvantages of the configuration mode of the test points to be tested are identified through the position information of the test points to be tested in the acquisition space area. For example, the point to be tested is within a certain collection space region, the collection weight is increased, and if the point to be tested exceeds the collection space region, the collection weight is decreased. The acquisition weight identifies the impact of the acquisition weight of the point to be tested on the configuration cost value.
S103: and calculating the configuration cost value of the camera configuration mode according to the acquisition weight, and determining the final camera configuration mode according to the configuration cost value.
Specifically, the final camera configuration mode is determined according to the configuration cost value of each camera configuration mode calculated in step S102, and generally, the determination principle may be that the lower the configuration cost value is, the better the corresponding camera configuration mode is.
The configuration cost value of each camera configuration is calculated according to the acquisition weight, and can be considered by combining other factors. For example, the effect of the number of visual cameras per point to be tested on the value of the configuration cost may be considered. Namely, when the configuration cost value is calculated, the influence of factors such as the number of the visual cameras of the point to be tested on the configuration cost value can be considered. That is, the calculation method of the configuration cost value at this time may be: and multiplying the initial visual cost values corresponding to the number of the visual cameras of the point to be tested by the acquisition weight to obtain the visual cost values of the point to be tested. And taking the visual cost value as the configuration cost value of the camera configuration mode. It can be understood that, before calculating the configuration cost value, an initial visual cost value corresponding to the number of the visual cameras to be tested needs to be calculated. The initial visual cost value of the point to be tested refers to the configuration cost value which is calculated according to the camera configuration mode and does not consider the collection weight of the point to be tested, and the influence of the number of the visual cameras for identifying the point to be tested on the configuration cost value is identified. And (4) performing product calculation on the acquisition weight and the initial visual cost value of the point to be tested to obtain the visual cost value of the point to be tested. And accumulating the visual cost values of all the test points to be tested to obtain the configuration cost value of the camera configuration mode.
In calculating the configuration cost value of each camera configuration, the influence of the intersection position of the visual axis of the camera and the horizontal plane on the configuration cost value (the influence is identified by the drop cost value) can also be considered. At this time, when the configuration cost value is calculated, the drop point cost value and the visual cost value can be specifically summed to be used as the configuration cost value.
In specific implementation, the acquisition weight K3 can be obtained according to the position information of the point to be tested in the camera configuration mode in the acquisition space region. And calculating the initial visual cost value K0 corresponding to the point to be tested according to the number of the visual cameras of the point to be tested, and multiplying the initial visual cost value K0 by K3 to obtain the visual cost value K11 of the point to be tested. Accumulating the visual cost values of all the test points to obtain the visual cost value k1 (namely the visual cost value of the camera configuration mode) of all the test points; and then calculating the falling point cost value of the camera according to the intersection point position of the visual axis of the camera and the horizontal plane, accumulating the falling point cost values of all the cameras in the camera configuration mode to obtain the total falling point cost value K2 (namely the falling point cost value of the camera configuration mode), and summing the K1 and the K2 to obtain the configuration cost value of the camera configuration mode. And determining a final camera configuration mode according to the calculated configuration cost value of each camera configuration mode, and configuring the cameras according to the determined camera configuration mode. In general, the determination principle may be that the lower the cost value of the configuration, the better the corresponding camera configuration.
Example two:
fig. 2 is a flowchart of a camera configuration method according to a second embodiment of the present invention, where an execution main body of the embodiment may be a computer device or a functional unit in the computer device, and the embodiment specifically includes steps S201 to S206, which are detailed as follows:
s201: and in a preset visual area, determining a preset number of camera configuration modes, points to be tested and visual cameras of the points to be tested.
The preset visualization area may be any size created by the user in the optical motion capture system and contains a simulated area of obstacles such as pillars and walls. In the preset visualization area, the user can further set the camera parameters, including the set total number of cameras, which can be actually adjusted.
The camera configuration mode is determined according to the camera parameters set by the user. The possible placing positions and placing angles of the cameras are calculated according to the parameters of the cameras, different calculated results are combined, and the camera configuration modes with the preset number are determined, wherein the preset number can be all the possible combination modes or some combination modes selected according to application scenes, and can be specifically set according to the requirements of practical application, and the method is not limited here.
Further, since the visualization area is usually set to be a quadrangle or a right-angled rectangle, the visualization area usually presents a symmetric feature, and in this case, the user only needs to set the position information of 1 camera, that is, the position information of 4 or 8 cameras can be correspondingly generated, so that the input amount of the camera parameters of the user is reduced, and the efficiency of calculating the preset number of camera configuration modes is improved.
The point to be tested can be understood as a marked point. The mark points are specially-made marks or luminous points, the mark points are pasted on the captured object, and the optical motion capture system realizes motion capture by identifying the mark points and processing the data of the mark points. Specifically, in a preset visualization area, a predetermined number of points to be tested are set, wherein the predetermined number can be customized according to application requirements, and the more the predetermined number is, the more points to be tested need to be tested, the longer the testing time is, but the more accurate the testing result is.
In each camera configuration mode, the number of cameras capable of shooting the same point to be tested is determined, so that the number of visual cameras corresponding to the point to be tested is determined.
S202: judging whether the point to be tested is in a preset key acquisition space area, if so, turning to step S203; otherwise, go to step S204.
The key acquisition space area can be set as required. For example, in a certain game application, the capture area corresponding to the game path may be set as the focus capture area.
S203: and when the point to be tested is in the preset key collection space region and the collection weight is set, increasing the collection weight of the point to be tested.
S204: when the point to be tested is not in the preset key collection space area and the collection weight is set, the collection weight of the point to be tested is reduced or kept unchanged.
When the collection weight of the point to be tested is set, the influence of the specific position information of the point to be tested in the capture area on the configuration cost value is also considered for a specific application scene. And the points to be tested at different positions are endowed with different acquisition weights when calculating the configuration cost value. Under general conditions, if the point to be tested belongs to a key acquisition space region, the point to be tested is shown to fall in a key observation region, and a larger acquisition weight can be set at the moment; if the point to be tested does not belong to the key acquisition space region, a smaller acquisition weight can be set.
The emphasized acquisition regions may be different for a particular application scenario. Therefore, when calculating the configuration cost value, the influence of the position information of the point to be tested on the configuration cost value can be considered, and the specific method is as follows:
and judging whether the point to be tested belongs to a preset key acquisition space region, if so, increasing the acquisition weight of the point to be tested on the basis of a preset standard value when the acquisition weight of the point to be tested is set. And if the point to be tested does not belong to the preset key collection space region, reducing the collection weight of the point to be tested on the basis of a preset standard value or keeping the collection weight of the point to be tested unchanged.
Step S205: and multiplying the acquisition weight by the initial visual cost value of the point to be tested to obtain the visual cost value of the point to be tested, and accumulating the visual cost values of all the points to be tested to obtain the visual cost value of the camera configuration mode.
And step S206, calculating the configuration cost value of each camera configuration mode according to the calculated visual cost value of the camera configuration modes, and determining the final camera configuration mode according to the configuration cost value.
And solving the product of the initial visual cost value of the point to be tested and the acquisition weight of the point to be tested to obtain the visual cost value of the point to be tested. And accumulating the visual cost values of all the test points to obtain the visual cost value of the camera configuration mode. When calculating the configuration cost value of the camera configuration, the calculated visual cost value of the camera configuration is used as the configuration cost value or a part of the configuration cost value. In this embodiment, when the configuration cost value is calculated, the visible cost value and the drop point cost value may be superimposed.
Example three:
fig. 3 is a flowchart of a camera configuration method according to a third embodiment of the present invention, where in the third embodiment, reference may be made to the second embodiment, where steps S301 to S305 may refer to steps S201 to S205 in the second embodiment, and details are not repeated. The difference between this embodiment and the second embodiment is: the relative cost value is increased when calculating the configuration cost value of each camera configuration mode.
Specifically, in the second embodiment, when the configuration cost value of the camera configuration mode is calculated, the influence of the position of the point to be tested in the acquisition space region, the number of the visible cameras of the point to be tested, and other factors on the configuration cost value is considered. The effect of capturing varies from camera to camera, depending on the location of the cameras. Therefore, when calculating the configuration cost value of each camera configuration mode, the present embodiment also considers the influence of the relative position relationship between two adjacent visual cameras of each point to be tested on the capturing effect.
The advantages and disadvantages of the camera configuration mode can be identified through the relative position relationship between two adjacent visual cameras. The relative cost value of each camera configuration mode can be obtained by calculation according to the position relationship of the adjacent visible cameras of all the points to be tested. The relative cost value identifies the influence of the relative position relationship between two adjacent visual cameras of the point to be tested on the configuration cost value. For example, the relative cost value is lower for the angle of the adjacent visual cameras within a certain range, and the relative cost value is higher for a certain angle range.
That is, in this embodiment, when calculating the configuration cost value of each camera configuration mode, the method specifically includes:
step S306: and calculating the relative cost value of the camera configuration mode. The relative cost value identifies the influence of the relative position relationship between two adjacent visual cameras of the point to be tested on the configuration cost value.
And step S307, summing the calculated relative cost value and the visual cost value to obtain the configuration cost value of each camera configuration mode, and determining the final camera configuration mode according to the configuration cost values.
In specific implementation, the initial visual cost value K01 corresponding to each point to be tested can be calculated according to the number of the visual cameras of each point to be tested, and the initial visual cost value K0 is multiplied by the acquisition weight K3 to obtain the visual cost value K11 of the point to be tested. Accumulating the visual cost values of all the test points to obtain the visual cost value k1 (namely the visual cost value of the camera configuration mode) of all the test points; then, calculating an initial relative cost value K04 of the point to be tested according to the relative position relationship between two adjacent visual cameras of the point to be tested, multiplying the initial relative cost value K0 by an acquisition weight K3 to obtain a relative cost value K41 of the point to be tested, and accumulating the relative cost values of all the points to be tested to obtain a total relative cost value K4 (namely the relative cost value of the camera configuration mode). And summing the visual cost value K1 and the relative cost value K4 to obtain the configuration cost value of the camera configuration mode. According to the method, the configuration cost value of each determined camera configuration mode can be calculated, the final camera configuration mode is determined according to the calculated configuration cost value of each camera configuration mode, and the cameras are configured according to the determined camera configuration mode. In general, the determination principle may be that the lower the cost value of the configuration, the better the corresponding camera configuration.
It should be noted that, when calculating the relative cost value corresponding to the relative position relationship between two adjacent visual cameras, that is, when performing step S306, as shown in fig. 4, the method may specifically include the following steps:
s401, two adjacent visual cameras in the visual cameras of the point to be tested form a camera set, and relative angles formed by the two cameras in the camera set and a connecting line between the point to be tested are calculated.
In the plurality of visual cameras of the same point to be tested, a relative angle formed by the connection line between each two adjacent visual cameras and the point to be tested (hereinafter referred to as a relative angle between two visual cameras) may affect the positioning accuracy of the point to be tested, and the specific effect of the effect is shown in fig. 5. The relative angle threshold interval range between two adjacent visual cameras can be set according to specific conditions. As in the present embodiment, when the relative angle between two adjacent visual cameras is 90 °, the positioning accuracy is the best when the test point is positioned, and when the relative angle between two adjacent visual cameras is less than 40 ° or greater than 140 °, the error when the test point is positioned is large. Therefore, when calculating the configuration cost value, the influence of the relative angle between two adjacent cameras on the positioning accuracy of the point to be tested needs to be considered. Therefore, after determining the number of the visual cameras of the point to be tested, the relative angle between two adjacent visual cameras needs to be calculated.
Two adjacent visual cameras form a camera set (clockwise or anticlockwise), the total number of the camera sets of the visual cameras is calculated, and the relative angle formed by connecting lines between the two cameras in each camera set and a point to be tested is calculated. In the present embodiment, the preset relative angle threshold interval ranges from [40 °, 140 ° ].
For example, as shown in fig. 6, it is assumed that there are four visual cameras for the point to be tested a, i.e. the points to be tested can be seen by the cameras 1, 2, 3, 4. In this step, two adjacent cameras are sequentially (clockwise or counterclockwise) combined into a camera group (e.g., camera 1 and camera 2 are combined into camera group a, camera 2 and camera 3 are combined into camera group B, camera 3 and camera 4 are combined into camera group C, and camera 4 and camera 1 are combined into camera group D). And calculating relative angles formed by connecting lines between two cameras in each camera group and the point to be tested respectively, namely calculating the relative angle a1 of the camera group A, calculating the relative angle a2 of the camera group B, calculating the relative angle a3 of the camera group C and calculating the relative angle a4 of the camera group D.
S402: and setting the initial relative cost value of the point to be tested according to the calculated relative angle and a preset relative angle threshold interval.
S403: and multiplying the initial relative cost value by the acquisition weight to obtain the relative cost value of the point to be tested.
S404: and accumulating the relative cost values of all the test points to obtain the relative cost value of the camera configuration mode.
When the relative cost value of the point to be tested is set according to the calculated relative angle and the preset relative angle threshold interval, that is, when step S402 is executed, there are two ways.
The first mode is as follows: calculating the total number of camera sets of the visual cameras of the point to be tested; counting the number of camera groups with relative angles exceeding a preset relative angle threshold interval; and calculating the ratio of the number of the camera sets with the relative angles exceeding the preset relative angle threshold interval to the total number of the camera sets, and setting the relative cost value of the point to be tested according to the ratio. Specifically, after the relative angle a1, the relative angle a2, the relative angle a3, and the relative angle a4 are calculated, it is determined whether the relative angle a1, the relative angle a2, the relative angle a3, and the relative angle a4 are within a predetermined relative angle threshold range. And calculating the ratio of the number of camera groups with relative angles exceeding a preset relative angle threshold interval to the total number of the camera groups, and then setting the relative cost value of the point to be tested in stages according to the ratio. The relative cost value of the points to be tested is set according to the ratio, and the principle is generally followed: the smaller the ratio, the smaller the relative cost value, and the larger the ratio, the larger the relative cost value.
For example, the total number of camera groups is 4, and if the ratio of the number of camera groups exceeding the preset threshold interval of relative angles to the total number of camera groups is 1/4, it indicates that the relative angles between 3 camera groups fall within the preset threshold interval, and the camera positioning effect is good, and at this time, the relative cost value can be set to 10. If the ratio is 2/4, it indicates that the relative angle between 2 groups of camera sets falls within a preset threshold interval, the camera positioning effect is general, and at this time, the relative cost value can be set to 40; if the ratio is 3/4, it indicates that the relative angle between 1 group of camera sets falls within a preset threshold interval, the camera positioning effect is poor, and at this time, the relative cost value can be set to 80; if the ratio is 1, it indicates that the relative angle of no group of camera sets falls within the preset threshold interval, the camera positioning effect is very poor, and at this time, the relative cost value can be set to 150.
The second way is: and judging whether the calculated relative angle exceeds a preset relative angle threshold interval, if so, increasing the group cost value of the camera set, otherwise, reducing the group cost value of the camera set or keeping the group cost value of the camera set unchanged, and accumulating the group cost values of all the camera sets to obtain the relative cost value of the test point. The aim is to find a small configuration cost value, reduce the group cost value of the camera group and further reduce the relative cost value of the points to be tested, and the practical idea is that the configuration mode is a good configuration mode.
Specifically, after the relative angle a1, the relative angle a2, the relative angle a3, and the relative angle a4 are calculated, it is determined whether the relative angle a1, the relative angle a2, the relative angle a3, and the relative angle a4 are within a predetermined relative angle threshold range. If the relative angle is not within the preset relative angle threshold interval, the group cost value of the camera group is increased on the basis of the preset standard value, if the relative angle is within the preset relative angle threshold interval, the group cost value of the camera group is reduced on the basis of the preset standard value, and then the group cost values of all the camera groups are accumulated to obtain the relative cost value of the test point. For example, assuming that the preset standard value is 80, if the relative angle a1 is within the preset relative angle threshold interval, the group cost value of the camera group a is set to 50, if the relative angle a2 is not within the preset relative angle threshold interval, the group cost value of the camera group a is set to 100, and so on, and then the group cost values of the camera group a, the overlay camera group B, the overlay camera group C, and the overlay camera group D are overlaid, so as to obtain the relative cost value of the test point a. And in the same way, the relative cost values of other points to be tested in the visual area can be obtained. And superposing the relative cost values of all the test points to obtain the relative cost value of the camera configuration mode.
Example four:
fig. 7 is a flowchart of a camera configuring method according to a fourth embodiment of the present invention, where the difference between the fourth embodiment and the third embodiment is that, in step S701, a step of determining a preset number of camera configuring modes according to a set total number of cameras is described in detail. In this embodiment, when step S701 is executed, the specific operation manner is:
s701: and determining the preset number of effective and reasonable camera configuration modes according to the height information of the cameras and the included angle between the visual axis of the cameras and the horizontal plane.
In the prior art, when determining the possible placement position of the camera according to the parameters of the camera, the height information of the camera is specifically fixed, that is, only the position and the direction of the camera in the horizontal plane are considered, however, this approach obviously limits the number of camera configurations and is not favorable for motion acquisition during certain application scenarios (whole body motion capture). In the extreme case, a certain camera cannot acquire images within the visualization area at all. In order to avoid the situation that the camera cannot acquire images in the visual area, in the embodiment of the present invention, when determining the configuration mode of the camera, the height information of the camera and the included angle between the visual axis of the camera and the horizontal plane need to be considered. Namely, the height information of the camera and the included angle between the visual axis of the camera and the horizontal plane need to be restrained so as to determine an effective and reasonable camera configuration mode.
It can be understood that after determining the effective and reasonable camera configuration modes, the configuration cost value of each configuration mode is calculated in the subsequent step.
When step S701 is specifically implemented, as shown in fig. 8, a specific operation manner may include:
s801: and randomly generating a plurality of camera configuration modes in a preset visual area according to the set number of cameras.
S802: the height of a camera in a visual area in a camera configuration mode is obtained, and the included angle between the visual axis of the camera and the horizontal plane in the camera configuration mode is obtained.
The method comprises the steps of acquiring the height of a camera in a visual area in a randomly generated camera configuration mode and acquiring the included angle between the visual axis and the horizontal plane of the camera in the camera configuration mode, and aims to further judge whether the randomly generated camera configuration mode is an effective camera configuration mode.
S803: and determining whether the configuration mode of the camera is effective and reasonable according to the height of the camera and the included angle between the visual axis of the camera and the horizontal plane.
If each camera in the camera configuration mode meets one of the following conditions, the camera configuration mode is considered to be effective and reasonable:
the height of the camera is greater than a preset first threshold value, and an included angle between a visual axis of the camera and a horizontal plane is smaller than a preset first angle;
the height of the camera is smaller than a preset second threshold value, and the included angle between the visual axis of the camera and the horizontal plane is larger than a preset second angle; and the number of the first and second groups,
the height of the camera belongs to a preset third threshold interval, and an included angle between a visual axis of the camera and a horizontal plane belongs to a preset third angle interval.
The first threshold and the first angle, the second threshold and the second angle, and the third threshold and the third angle can be adjusted according to actual conditions.
In the visualization area, the plane where the XZ axis is located is defined as a horizontal plane, and then it can be determined whether the camera configuration mode is valid by combining the Y-axis information (height) of the camera and the information of the included angle between the visual axis of the camera and the XZ plane (horizontal plane).
For example, if the Y-axis height of the camera in the visualization area is greater than a preset first threshold (that is, the placement position of the camera is close to the highest value of the visualization area), at this time, if the lens of the camera is upward, the camera cannot capture an image in the visualization area at all, so that an included angle between the visual axis of the camera and an XZ plane (horizontal plane) needs to be constrained (the included angle between the visual axis of the camera and the horizontal plane is smaller than the preset first angle), so that the lens of the camera near the highest value faces downward as much as possible, and the camera can capture an image in the visualization area. Assuming that the viewing angle range of the camera is an a angle, the preset first angle may be an a/2 angle.
For another example, if the Y-axis height of the camera in the visualization area is less than the preset second threshold (i.e. the placement position of the camera is close to the lowest value of the visualization area), at this time, if the lens of the camera is downward, the camera may not capture the image in the visualization area at all, so that the included angle between the visual axis of the camera and the XZ plane (horizontal plane) needs to be constrained (the included angle between the visual axis of the camera and the horizontal plane is greater than the preset second angle), so that the lens of the camera near the lowest value is directed upward as much as possible, and the camera is ensured to capture the image in the visualization area. Assuming that the viewing angle range of the camera is an a angle, the preset second angle may be an a/2 angle.
For another example, if the Y-axis height of the camera in the visualization area belongs to a preset third threshold area (that is, the placement position of the camera is close to a certain set middle area of the visualization area, and a specific numerical value may be determined according to a specific application), the lens direction of the camera needs to be set according to a specific capture requirement (the included angle between the visual axis of the camera and the horizontal plane belongs to a preset third angle interval, that is, the lens of the camera may be upward, downward, or horizontal), so that the included angle between the visual axis of the camera and the horizontal plane needs to be constrained, so that the camera in the middle area can capture an image in the visualization area.
Example five:
fig. 9 is a flowchart of a camera configuring method according to a fifth embodiment of the present invention, and steps S901 to S906 may refer to steps S701 to S706 of the fourth embodiment, which are different from the fourth embodiment in that the method further includes:
s907: and calculating the drop point cost value of the camera configuration mode.
Because the processing step of the drop point cost value is added, when the configuration cost value of each camera configuration mode is calculated, the specific operation is as follows:
s908: and summing the calculated relative cost value, the visible cost value and the drop point cost value to obtain the configuration cost value of each camera configuration mode, and determining the final camera configuration mode according to the configuration cost values.
When step S907 is executed, as shown in fig. 11, the method specifically includes the following steps:
s1101: and judging whether the intersection point of the visual axis of the camera and the horizontal plane is in the visual area.
As shown in fig. 10, x, y, z form the coordinate system of a single camera. First, an intersection q of the camera visual axis (e.g., the normal of the camera lens plane) and the XZ plane, which is a horizontal plane, is calculated. And judging whether the intersection point falls within an XZ plane section of a preset visualization region, such as the intersection point q1 in FIG. 10 falls within the XZ plane section of the visualization region, and the intersection point q2 does not fall within the XZ plane section of the visualization region. The intersection point of the camera visual axis (e.g. the normal of the camera lens plane) and the XZ plane may be affected by the camera height, the camera shooting angle, and the like.
And S1102, the intersection point of the visual axis of the camera and the horizontal plane is located in the visual area, so that the cost value of the falling point of the camera is reduced. Go to step S1104.
If the intersection point q of the visual axis of the camera and the XZ plane is in the XZ plane interval of the acquisition area, and the drop point cost value of the camera configuration mode is calculated, the drop point cost value of the camera is reduced on the basis of the preset standard value, because the aim is to find the small configuration cost value and reduce the drop point cost value of the camera, the configuration mode is actually considered to be a good configuration mode.
And S1103, if the intersection point of the visual axis of the camera and the horizontal plane does not fall into the visual area, increasing the cost value of the falling point of the camera or keeping the cost value of the falling point of the camera unchanged.
If the intersection point q of the visual axis of the camera and the XZ plane is not in the XZ plane interval of the acquisition area, when the drop point cost value of the configuration mode of the camera is calculated, the drop point cost value of the camera is increased or kept unchanged on the basis of a preset standard value, because the aim is to search for a small configuration cost value and increase or keep the drop point cost value of the camera, the configuration mode is actually considered not to be a good configuration mode.
And S1104, accumulating the drop point cost values of all the cameras to obtain the drop point cost value of each camera configuration mode.
After the drop point cost value of each camera is calculated according to steps S1101 to S1103, the drop point cost values of all cameras in each configuration mode are accumulated, so that the drop point cost value of a certain camera configuration mode can be obtained.
Example six:
it should be noted that, in the first to fifth embodiments, the visual camera of the point to be tested is specifically determined through the following steps:
if the point to be tested belongs to the field of view of the camera,
continuously judging whether the distance between the point to be tested and the camera is within a preset threshold interval, if so, considering the camera as the camera of the point to be tested, otherwise, considering the camera not as the visual camera of the point to be tested; and/or
And continuously judging whether a transverse included angle between the tested line of the point to be tested and the visual axis of the current camera is within a preset angle threshold interval, if so, considering the camera as the camera of the point to be tested, and otherwise, considering the camera not as the visual camera of the point to be tested.
In the existing camera layout scheme, when the number of the visual cameras of each point to be tested in each camera configuration mode is calculated, whether each point to be tested belongs to the visual range of the cameras is specifically judged, the number of the visual cameras of each point to be tested is calculated according to the judgment result, and if the point to be tested belongs to the visual area of the cameras, the camera corresponding to the visual area is the visual camera corresponding to the point to be tested. In the process of judging whether each test point to be tested belongs to the visual range of the camera, the adopted judgment standard is as follows:
if the point to be tested does not meet any of the following conditions, the point to be tested is considered to belong to the visual range of the camera, and if the point to be tested meets any of the following conditions, the point to be tested is considered not to belong to the visual range of the camera. The specific conditions are as follows:
a1) and in a user coordinate system established by taking the current camera as a reference object, the third dimensional coordinate value of the point to be tested is a negative number.
a2) The distance between the point to be tested and the central point of the lens plane of the current camera is larger than a preset distance threshold value.
a3) The transverse included angle between the measured line and the normal of the lens plane of the current camera is more than one half of the field angle of the transverse shaft of the visual range of the current camera; the measured line is a connecting line between the point to be measured and the central point of the lens plane of the current camera.
a4) The longitudinal included angle between the measured line and the normal of the lens plane of the current camera is larger than one half of the longitudinal axis field angle of the visual range of the current camera.
a5) The position of the obstacle in the visualization area belongs to a line segment formed by the point to be tested and the center point of the lens plane of the current camera.
The judgment idea of the visual camera in the existing layout scheme is as follows: and when the point to be tested is judged to belong to the visual range of a certain camera, judging that the current camera belongs to the visual camera of the point to be tested.
The embodiment of the invention specifically judges by the following method:
after the point to be tested is determined to belong to the visual range of the camera, the camera is not directly considered as the visual camera of the point to be tested, and a further judgment mechanism is added. At this time, it is further necessary to further determine whether the camera is a visual camera of the point to be tested according to the specific position relationship between the point to be tested and the current camera. The specific judgment method comprises the following steps:
the first method is as follows: judging the distance between the point to be tested and the camera, if the distance between the point to be tested and the central point of the lens plane of the current camera is within a preset threshold interval, if so, determining that the camera is the camera of the point to be tested, otherwise, determining that the camera is not the visual camera of the point to be tested, as shown in fig. 12; if the point to be tested is in the trapezoid area (oblique line area part) formed by d2 and d1, the camera is considered as the visual camera of the point to be tested.
Or,
the second method comprises the following steps: and judging whether the transverse included angle between the tested line of the point to be tested and the visual axis of the camera is within a preset angle threshold interval. If the distance is within the preset angle threshold value interval, the camera is considered as the camera of the point to be tested; otherwise, the camera is not considered to be the visual camera of the point to be tested, as shown in fig. 13. In fig. 13, K0 is the visual axis of the camera, and the area formed by triangle ABC is the visual range of the camera, then in this step, it is determined whether the angle between the point to be tested and the visual axis of the current camera is between K2 and K1, and if the angle is within the area formed by K2 and K1, the camera is considered as the visual camera of the point to be tested. If the area is not the area formed by k2 and k1, the camera is not considered to be the visual camera of the point to be tested.
Alternatively, the second method is combined with the first method:
that is, it is determined whether the distance between the point to be tested and the center point of the lens plane of the current camera is within the preset threshold interval, and also determined whether the lateral included angle between the line to be tested of the point to be tested and the visual axis of the current camera is within the preset angle threshold interval, and only when the two determination results are both yes, the camera is considered as the visual camera of the point to be tested, as shown in fig. 14. Namely, the camera is considered as a visual camera of the point to be tested only when the point to be tested falls into the closed area formed by k2, k1, d2 and d 1.
The first to sixth embodiments describe the camera arrangement method according to the embodiment of the present invention in detail, and the following describes an apparatus for performing camera arrangement in the above manner. It should be noted that the terms defined and explained in the above method are not described in detail in the following apparatuses for avoiding redundancy.
Example seven:
fig. 15 is a schematic structural diagram of a camera configuration apparatus according to a seventh embodiment of the present invention, and only a part related to the seventh embodiment of the present invention is shown for convenience of description. A camera configuration apparatus illustrated in fig. 15 may be an execution subject of the camera configuration method provided in the first embodiment, and may be a computer device or a functional unit in the computer device. The device comprises a preset module, a first processing module and a configuration module.
The device comprises a preset module, a display module and a control module, wherein the preset module is used for determining the configuration modes of a preset number of cameras and the visual cameras of points to be tested according to the set total number of the cameras in a preset visual area;
the first processing module is used for setting acquisition weight according to the position information of the point to be tested in the visual area in the camera configuration mode;
and the configuration module is used for calculating the configuration cost value of the camera configuration mode and determining the final camera configuration mode according to the configuration cost value.
Further, as shown in fig. 16, the first processing module may include a judgment unit and a processing unit;
the judging unit is used for judging whether the test point to be tested is in a preset key acquisition space area or not;
the processing unit is used for increasing the collection weight of the point to be tested when the point to be tested is in a preset key collection space area; otherwise, reducing the collection weight of the point to be tested or keeping the collection weight of the point to be tested unchanged.
Further, the preset module may include a visual camera determination unit;
the visual camera judging unit is used for judging whether the distance between the point to be tested and the camera is within a preset threshold interval when the point to be tested belongs to the visual range of the camera, if so, the camera is considered as the visual camera of the point to be tested, otherwise, the camera is not the visual camera of the point to be tested; and/or, when the point to be tested belongs to the visual range of the camera, judging whether a transverse included angle between a tested line of the point to be tested and a normal line of a lens plane of the current camera is within a preset angle threshold interval, if so, considering the camera as the visual camera of the point to be tested, otherwise, considering the camera not as the visual camera of the point to be tested.
The camera configuring device of the present invention may further include a second processing module including:
the relative angle calculation unit is used for forming a camera set by two adjacent visible cameras in the visible cameras of the point to be tested and calculating the relative angle between the normal lines of the lens planes of the two cameras in the camera set;
the relative cost value calculation unit is used for setting the initial relative cost value of the point to be tested according to the calculated relative angle and a preset relative angle threshold interval; multiplying the initial relative cost value by the collection weight of the point to be tested to obtain the relative cost value of the point to be tested; and accumulating the relative cost values of all the test points to obtain the relative cost value of the camera configuration mode.
In one embodiment, the preset relative angle threshold interval may be [40 °, 140 ° ];
the relative cost value calculating unit can also be used for calculating the total number of the camera groups of the visual cameras of the point to be tested; counting the number of camera groups with relative angles exceeding a preset relative angle threshold interval; calculating the ratio of the number of camera sets with relative angles exceeding a preset relative angle threshold interval to the total number of the camera sets, and setting the relative cost value of the point to be tested according to the ratio; or judging whether the calculated relative angle exceeds a preset relative angle threshold interval, if so, increasing the group cost value of the camera set, otherwise, reducing the group cost value of the camera set or keeping the group cost value of the camera set unchanged, and accumulating the group cost values of all the camera sets to obtain the relative cost value of the test point.
The camera configuration device provided by the invention can further comprise a third processing module;
the third processing module is used for determining whether the configuration mode of the camera is effective or not according to the height information of the camera and the included angle between the visual axis of the camera and the horizontal plane; the final camera configuration mode is an effective camera configuration mode.
In one embodiment, the third processing module considers the camera configuration to be valid if each camera in the camera configuration satisfies one of the following conditions:
the height of the camera is greater than a preset first threshold value, and an included angle between a visual axis of the camera and a horizontal plane is smaller than a preset first angle;
the height of the camera is smaller than a preset second threshold value, and an included angle between a visual axis of the camera and a horizontal plane is larger than a preset second angle; and the number of the first and second groups,
the height of the camera belongs to a preset third threshold interval, and an included angle between a visual axis of the camera and a horizontal plane belongs to a preset third angle interval.
Furthermore, the device provided by the invention can also comprise a fourth processing module for calculating the drop point cost value of each camera configuration mode; the drop point cost value identifies the influence on the configuration cost value of whether the intersection point of the visual axis of the camera and the horizontal plane falls in the visual area;
specifically, the fourth processing module judges whether the intersection point of the visual axis of the camera and the horizontal plane falls within the visual area; if so, reducing the drop point cost value of the camera; otherwise, increasing the drop point cost value of the camera or keeping the drop point cost value of the camera unchanged; and accumulating the placement cost values of all the cameras in the camera configuration mode to obtain the placement cost values of the camera configuration mode.
Example eight:
a camera configuration device includes a memory and a processor. A memory for storing a program; and the processor is used for executing the programs stored in the memory to realize the methods in the first to sixth embodiments.
Those skilled in the art will appreciate that all or part of the steps of the various methods in the above embodiments may be implemented by instructions associated with hardware via a program, which may be stored in a computer-readable storage medium, which may include: read-only memory, random access memory, magnetic or optical disk, and the like.
The foregoing is a more detailed description of the present invention that is presented in conjunction with specific embodiments, and the practice of the invention is not to be considered limited to those descriptions. It will be apparent to those skilled in the art that a number of simple derivations or substitutions can be made without departing from the inventive concept.
Claims (14)
1. A camera configuration method, comprising:
in a preset visual area, determining a preset number of camera configuration modes and visual cameras of points to be tested according to the set total number of cameras;
setting acquisition weight according to the position information of the point to be tested in the visual area in the camera configuration mode;
calculating the configuration cost value of the camera configuration mode according to the acquisition weight, and determining the final camera configuration mode according to the configuration cost value;
the configuration cost value comprises a relative cost value, and the relative cost value identifies the influence of the relative position relationship between two adjacent visual cameras of the point to be tested on the configuration cost value;
the calculating the configuration cost value of the camera configuration mode according to the acquisition weight comprises the following steps:
in the visual cameras of the points to be tested, two adjacent visual cameras form a camera set, and relative angles formed by connecting lines between the two cameras in the camera set and the points to be tested are calculated;
setting the initial relative cost value of the point to be tested according to the calculated relative angle and a preset relative angle threshold interval;
multiplying the initial relative cost value by the collection weight of the point to be tested to obtain the relative cost value of the point to be tested;
and accumulating the relative cost values of all the test points to obtain the relative cost value of the camera configuration mode.
2. The method according to claim 1, wherein the setting of the acquisition weight according to the position information of the point to be tested in the visualization area in the camera configuration mode specifically comprises:
judging whether the test point to be tested belongs to a preset key acquisition space region or not;
if the point to be tested belongs to the key acquisition space region, increasing the acquisition weight of the point to be tested; otherwise, reducing the collection weight of the point to be tested or keeping the collection weight of the point to be tested unchanged.
3. The method according to claim 1 or 2, characterized in that the visual camera of the point to be tested is determined by the following steps:
if the point to be tested belongs to the field of view of the camera,
judging whether the distance between the point to be tested and the camera is within a preset threshold interval, if so, considering the camera as the visual camera of the point to be tested, otherwise, considering the camera not as the visual camera of the point to be tested;
and/or judging whether a transverse included angle between a tested line of the point to be tested and a visual axis of the current camera is within a preset angle threshold interval, if so, considering the camera as the visual camera of the point to be tested, otherwise, considering the camera not as the visual camera of the point to be tested.
4. The method of claim 1 or 2,
the preset relative angle threshold interval is [40 degrees, 140 degrees ]; the setting of the relative cost value of the point to be tested according to the calculated relative angle and the preset relative angle threshold interval specifically includes:
calculating the total number of camera sets of the visual cameras of the point to be tested; counting the number of camera groups with relative angles exceeding a preset relative angle threshold interval; calculating the ratio of the number of camera sets with relative angles exceeding a preset relative angle threshold interval to the total number of the camera sets, and setting the relative cost value of the point to be tested according to the ratio; or,
and judging whether the calculated relative angle exceeds a preset relative angle threshold interval, if so, increasing the group cost value of the camera set, otherwise, reducing the group cost value of the camera set or keeping the group cost value of the camera set unchanged, and accumulating the group cost values of all the camera sets to obtain the relative cost value of the test point.
5. The method according to claim 1 or 2, wherein the determining of the preset number of camera configurations according to the set total number of cameras comprises:
determining whether the configuration mode of the camera is effective or not according to the height information of the camera and the included angle between the visual axis of the camera and the horizontal plane; the final camera configuration mode is an effective camera configuration mode;
when determining whether the camera configuration mode is effective according to the height information of the cameras and the included angle between the visual axis of the cameras and the horizontal plane, if each camera in the camera configuration mode meets one of the following conditions, the camera configuration mode is considered to be effective:
the height of the camera is larger than a preset first threshold value, and the included angle between the visual axis of the camera and the horizontal plane is smaller than a preset first angle, so that the lens of the camera near the highest value faces downwards as much as possible, and the camera can capture images in a visual area;
the height of the camera is smaller than a preset second threshold value, and the included angle between the visual axis of the camera and the horizontal plane is larger than a preset second angle, so that the lens of the camera near the lowest value is upward as much as possible, and the camera can capture images in a visual area; and the number of the first and second groups,
the height of the camera belongs to a preset third threshold interval, and an included angle between a visual axis of the camera and a horizontal plane belongs to a preset third angle interval, so that the camera in the middle area can capture images in a visual area.
6. The method of claim 1 or 2, wherein the configuration cost value comprises a drop point cost value, and the calculating the configuration cost value of the camera configuration mode according to the acquisition weight comprises:
calculating the drop point cost value of each camera configuration mode; the drop point cost value identifies the influence on the configuration cost value of whether the intersection point of the visual axis of the camera and the horizontal plane falls in the visual area;
and summing the relative cost value and the drop point cost value to obtain the configuration cost value of each camera configuration mode.
7. The method of claim 6, wherein calculating a drop point cost value for each camera configuration comprises:
judging whether the intersection point of the visual axis of the camera and the horizontal plane is in a visual area or not;
if so, reducing the drop point cost value of the camera;
otherwise, increasing the drop point cost value of the camera or keeping the drop point cost value of the camera unchanged;
and accumulating the placement cost values of all the cameras in the camera configuration mode to obtain the placement cost values of the camera configuration mode.
8. A camera deployment apparatus, comprising:
the device comprises a preset module, a display module and a control module, wherein the preset module is used for determining the configuration modes of a preset number of cameras and the visual cameras of points to be tested according to the set total number of the cameras in a preset visual area;
the first processing module is used for setting acquisition weight according to the position information of the point to be tested in the visual area in the camera configuration mode;
the configuration module is used for calculating the configuration cost value of the camera configuration mode and determining the final camera configuration mode according to the configuration cost value;
the apparatus further comprises a second processing module comprising:
the relative angle calculation unit is used for forming a camera set by two adjacent visible cameras in the visible cameras of the point to be tested, and calculating the relative angles formed by connecting lines between the two cameras in the camera set and the point to be tested respectively;
the relative cost value calculation unit is used for setting the initial relative cost value of the point to be tested according to the calculated relative angle and a preset relative angle threshold interval; multiplying the initial relative cost value by the collection weight of the point to be tested to obtain the relative cost value of the point to be tested, wherein the relative cost value identifies the influence of the relative position relationship between two adjacent visual cameras of the point to be tested on the configured cost value; and accumulating the relative cost values of all the test points to obtain the relative cost value of the camera configuration mode.
9. The apparatus of claim 8, wherein the first processing module comprises:
the judging unit is used for judging whether the test point to be tested is in a preset key acquisition space area or not;
the processing unit is used for increasing the collection weight of the point to be tested when the point to be tested is in a preset key collection space area; otherwise, reducing the collection weight of the point to be tested or keeping the collection weight of the point to be tested unchanged.
10. The apparatus of claim 8 or 9, wherein the preset module comprises:
the visual camera judging unit is used for judging whether the distance between the point to be tested and the camera is within a preset threshold interval when the point to be tested belongs to the visual range of the camera, if so, the camera is considered as the visual camera of the point to be tested, otherwise, the camera is not the visual camera of the point to be tested; and/or, when the point to be tested belongs to the visual range of the camera, judging whether a transverse included angle between a tested line of the point to be tested and a normal line of a lens plane of the current camera is within a preset angle threshold interval, if so, considering the camera as the visual camera of the point to be tested, otherwise, considering the camera not as the visual camera of the point to be tested.
11. The apparatus of claim 8 or 9,
the preset relative angle threshold interval is [40 degrees, 140 degrees ];
the relative cost value calculating unit is also used for calculating the total number of the camera groups of the visual cameras of the point to be tested; counting the number of camera groups with relative angles exceeding a preset relative angle threshold interval; calculating the ratio of the number of camera sets with relative angles exceeding a preset relative angle threshold interval to the total number of the camera sets, and setting the relative cost value of the point to be tested according to the ratio; or judging whether the calculated relative angle exceeds a preset relative angle threshold interval, if so, increasing the group cost value of the camera set, otherwise, reducing the group cost value of the camera set or keeping the group cost value of the camera set unchanged, and accumulating the group cost values of all the camera sets to obtain the relative cost value of the test point.
12. The apparatus according to claim 8 or 9, wherein the apparatus further comprises a third processing module for determining whether the camera configuration is valid according to the height information of the camera and the angle between the visual axis of the camera and the horizontal plane; the final camera configuration mode is an effective camera configuration mode;
and considering the camera configuration mode to be effective when each camera in the camera configuration mode meets one of the following conditions:
the height of the camera is larger than a preset first threshold value, and the included angle between the visual axis of the camera and the horizontal plane is smaller than a preset first angle, so that the lens of the camera near the highest value faces downwards as much as possible, and the camera can capture images in a visual area;
the height of the camera is smaller than a preset second threshold value, and the included angle between the visual axis of the camera and the horizontal plane is larger than a preset second angle, so that the lens of the camera near the lowest value is upward as much as possible, and the camera can capture images in a visual area; and the number of the first and second groups,
the height of the camera belongs to a preset third threshold interval, and an included angle between a visual axis of the camera and a horizontal plane belongs to a preset third angle interval, so that the camera in the middle area can capture images in a visual area.
13. The apparatus of claim 8 or 9, further comprising a fourth processing module that: the device is used for judging whether the intersection point of the visual axis of the camera and the horizontal plane is in the visual area or not; if so, reducing the drop point cost value of the camera, wherein the drop point cost value identifies the influence on the configuration cost value caused by whether the intersection point of the visual axis of the camera and the horizontal plane falls in the visual area; otherwise, increasing the drop point cost value of the camera or keeping the drop point cost value of the camera unchanged; and accumulating the placement cost values of all the cameras in the camera configuration mode to obtain the placement cost values of the camera configuration mode.
14. A camera arranging apparatus characterized by comprising:
a memory for storing a program;
a processor for implementing the method of any one of claims 1-7 by executing a program stored by the memory.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810151015.6A CN108471496B (en) | 2018-02-13 | 2018-02-13 | Camera configuration method and device |
US16/150,248 US10771715B2 (en) | 2016-08-09 | 2018-10-02 | Camera configuration method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810151015.6A CN108471496B (en) | 2018-02-13 | 2018-02-13 | Camera configuration method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108471496A CN108471496A (en) | 2018-08-31 |
CN108471496B true CN108471496B (en) | 2020-11-03 |
Family
ID=63266364
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810151015.6A Active CN108471496B (en) | 2016-08-09 | 2018-02-13 | Camera configuration method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108471496B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1561640A (en) * | 2001-09-27 | 2005-01-05 | 皇家飞利浦电子股份有限公司 | Optimal multi-camera setup for computer-based visual surveillance |
JP2006074260A (en) * | 2004-08-31 | 2006-03-16 | Sumitomo Electric Ind Ltd | Method for automatically determining camera setting condition in parking lot |
CN101251925A (en) * | 2007-12-29 | 2008-08-27 | 中国科学院计算技术研究所 | Virtual video camera planning and distributing method and system |
CN101355693A (en) * | 2008-08-29 | 2009-01-28 | 中兴通讯股份有限公司 | Omnidirection monitoring system and monitoring method without blind spot |
CN102300051A (en) * | 2010-06-28 | 2011-12-28 | 株式会社日立制作所 | Camera layout determination support device |
CN102932605A (en) * | 2012-11-26 | 2013-02-13 | 南京大学 | Method for selecting camera combination in visual perception network |
CN103822595A (en) * | 2012-11-19 | 2014-05-28 | 普乐福尼克·迪特·布什股份公司 | Device and method for determining the relative positions of two coupled shafts to each other |
CN104469322A (en) * | 2014-12-24 | 2015-03-25 | 重庆大学 | Camera layout optimization method for large-scale scene monitoring |
CN104717481A (en) * | 2013-12-13 | 2015-06-17 | 松下知识产权经营株式会社 | Image capturing apparatus, monitoring system, image processing apparatus, and image capturing method |
CN105282427A (en) * | 2014-05-26 | 2016-01-27 | 安讯士有限公司 | Automatic configuration of a replacement camera |
CN107111664A (en) * | 2016-08-09 | 2017-08-29 | 深圳市瑞立视多媒体科技有限公司 | A kind of video camera collocation method and device |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8514283B2 (en) * | 2010-09-20 | 2013-08-20 | Ajou University Industry Cooperation Foundation | Automatic vision sensor placement apparatus and method |
WO2013149340A1 (en) * | 2012-04-02 | 2013-10-10 | Mcmaster University | Optimal camera selection iν array of monitoring cameras |
-
2018
- 2018-02-13 CN CN201810151015.6A patent/CN108471496B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1561640A (en) * | 2001-09-27 | 2005-01-05 | 皇家飞利浦电子股份有限公司 | Optimal multi-camera setup for computer-based visual surveillance |
JP2006074260A (en) * | 2004-08-31 | 2006-03-16 | Sumitomo Electric Ind Ltd | Method for automatically determining camera setting condition in parking lot |
CN101251925A (en) * | 2007-12-29 | 2008-08-27 | 中国科学院计算技术研究所 | Virtual video camera planning and distributing method and system |
CN101355693A (en) * | 2008-08-29 | 2009-01-28 | 中兴通讯股份有限公司 | Omnidirection monitoring system and monitoring method without blind spot |
CN102300051A (en) * | 2010-06-28 | 2011-12-28 | 株式会社日立制作所 | Camera layout determination support device |
CN103822595A (en) * | 2012-11-19 | 2014-05-28 | 普乐福尼克·迪特·布什股份公司 | Device and method for determining the relative positions of two coupled shafts to each other |
CN102932605A (en) * | 2012-11-26 | 2013-02-13 | 南京大学 | Method for selecting camera combination in visual perception network |
CN104717481A (en) * | 2013-12-13 | 2015-06-17 | 松下知识产权经营株式会社 | Image capturing apparatus, monitoring system, image processing apparatus, and image capturing method |
CN105282427A (en) * | 2014-05-26 | 2016-01-27 | 安讯士有限公司 | Automatic configuration of a replacement camera |
CN104469322A (en) * | 2014-12-24 | 2015-03-25 | 重庆大学 | Camera layout optimization method for large-scale scene monitoring |
CN107111664A (en) * | 2016-08-09 | 2017-08-29 | 深圳市瑞立视多媒体科技有限公司 | A kind of video camera collocation method and device |
Also Published As
Publication number | Publication date |
---|---|
CN108471496A (en) | 2018-08-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110136082B (en) | Occlusion rejection method and device and computer equipment | |
KR101467663B1 (en) | Method and system of providing display in display monitoring system | |
CN109918977B (en) | Method, device and equipment for determining idle parking space | |
US20180197324A1 (en) | Virtual viewpoint setting apparatus, setting method, and storage medium | |
CN107920246B (en) | The gradient test method and device of camera module | |
CN112686877B (en) | Binocular camera-based three-dimensional house damage model construction and measurement method and system | |
WO2021129305A1 (en) | Calibration rod testing method for optical motion capture system, device, apparatus, and storage medium | |
JP2010165248A (en) | Image processor, image collation method, and program | |
US20180025247A1 (en) | Information processing apparatus, information processing method, and program | |
CN108074237B (en) | Image definition detection method and device, storage medium and electronic equipment | |
CN111462503A (en) | Vehicle speed measuring method and device and computer readable storage medium | |
CN110084797B (en) | Plane detection method, plane detection device, electronic equipment and storage medium | |
CN108460333B (en) | Ground detection method and device based on depth map | |
KR20190128110A (en) | Image processing apparatus, control method of image processing apparatus, and computer-readable storage medium | |
CN110263713A (en) | Method for detecting lane lines, device, electronic equipment and storage medium | |
CN110632582A (en) | Sound source positioning method, device and storage medium | |
JP2018113683A (en) | Image processing apparatus, image processing method, and program | |
CN105469387A (en) | Quantification method and quantification device for splicing quality | |
CN105791663A (en) | Distance estimating system and distance estimating method | |
JP6579727B1 (en) | Moving object detection device, moving object detection method, and moving object detection program | |
CN110008802B (en) | Method and device for selecting target face from multiple faces and comparing face recognition | |
CN104915948A (en) | System and method for selecting a two-dimensional region of interest using a range sensor | |
WO2020181522A1 (en) | Defective pixel detection method, image processing chip, and electronic device | |
CN108495057B (en) | Camera configuration method and device | |
CN108471496B (en) | Camera configuration method and device |
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 |