CN105635657A - Camera holder omnibearing interaction method and device based on face detection - Google Patents
Camera holder omnibearing interaction method and device based on face detection Download PDFInfo
- Publication number
- CN105635657A CN105635657A CN201410608706.6A CN201410608706A CN105635657A CN 105635657 A CN105635657 A CN 105635657A CN 201410608706 A CN201410608706 A CN 201410608706A CN 105635657 A CN105635657 A CN 105635657A
- Authority
- CN
- China
- Prior art keywords
- coordinate
- image
- human face
- current
- face region
- 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
Abstract
Embodiments of the invention provide a camera holder omnibearing interaction method and device based on face detection. The method mainly comprises the steps of: positioning a face area in a current image collected by a camera by means of face detection and a tracking algorithm; according to image coordinates of a central point of the face area, calculating current correction plane coordinates through an interpolation mapping algorithm based on a preset coordinate model; according to the area of the face area, calculating current correction distance coordinates; and according to the current correction plane coordinates and the correction distance coordinates, calculating current horizontal and vertical object rotation angles of a holder of the camera, and calculating the current zooming number of a lens of the camera. According to the embodiments, a video monitoring worker can move the head of himself up and down, left and right and back and forth, and the object rotation angles of the holder and the zooming of the lens are controlled, so that the current view field area of the camera is changed, and the effect of first view angle field monitoring simulation is realized.
Description
Technical field
The present invention relates to technical field of video monitoring, particularly relate to a kind of video camera PTZ based on Face datection (Pan/Tilt/Zoom, The Cloud Terrace is comprehensive) exchange method.
Background technology
In traditional video monitoring system, the automatic cradle head of video camera is usually the mounting platform of two alternating current generator compositions, it is possible to rotating horizontally and vertically, the direction of its rotation and angle remotely can be controlled by human-computer interaction interface. The contracting clicked in camera control menu in human-computer interaction interface on DVR or other-end, put, upper and lower, left and right option, or directly click to forward to target direction, angle, region etc., be video camera PTZ interactive mode common at present.
The shortcoming of above-mentioned common video camera PTZ interactive mode is: which uses mouse, action bars etc. as mutual medium, inadequate simple, intuitive.
Summary of the invention
The embodiment provides a kind of video camera PTZ exchange method based on Face datection and device, to provide one video camera PTZ exchange method simply and intuitively.
The invention provides following scheme:
A kind of comprehensive exchange method of the camera pan-tilt based on Face datection, including:
By the human face region in the present image that persona face detection algorithm positioning shooting head collects;
The image coordinate of the central point according to described human face region, calculates current correcting plane coordinate based on coordinate model set in advance by interpolation mapping algorithm; Areal calculation according to described human face region goes out current correction distance coordinate;
Calculate the current level of The Cloud Terrace of video camera, vertical target rotational angle according to described current correcting plane coordinate, correction distance coordinate, calculate the current zoom multiple of the camera lens of video camera.
Before human face region in the described present image collected by persona face detection algorithm positioning shooting head, including:
After the head of monitoring personnel moves to the most upper left position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the position of most lower left of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most top-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most bottom-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
The image coordinate of the 4 of described record central points is surrounded a tetragon, by homography matrix, described tetragon is mapped to a square, this square is called coordinate model.
The image coordinate of the described central point according to described human face region, calculates current correcting plane coordinate based on coordinate model set in advance by interpolation mapping algorithm, including:
Newly set a correcting plane coordinate system, in this correcting plane coordinate system, with described foursquare center for zero, described foursquare upper left, lower-left, upper right, lower right corner coordinate be (-1,1) respectively, (-1,-1), (1,1), (1 ,-1);
If the image coordinate that the central point of the human face region in described present image is in described tetragon is (xa,ya), the central point of the human face region in described present image respective coordinates in correcting plane coordinate system is (xb,yb), (xb,yb) computing formula as follows:
Wherein H is the homography matrix set, and w is the proportionality coefficient set, by described (xb,yb) as current correcting plane coordinate.
The described areal calculation according to described human face region goes out current correction distance coordinate, including:
After the head of monitoring personnel moves to an off the position that screen is farthest, in the image of photographic head shooting, orient human face region by persona face detection algorithm, record the area a of this human face region; After the head of monitoring personnel moves to an off the position that screen is nearest, in the image of photographic head shooting, orient human face region by persona face detection algorithm, record the area b of this human face region;
Record described camera collection to present image in the area x of human face region, then current correction distance coordinate is:
Described calculates the current level of The Cloud Terrace of video camera, vertical target rotational angle according to described current correcting plane coordinate, correction distance coordinate, including:
If described correcting plane coordinate be (u, v), the The Cloud Terrace of described video camera be comprehensive rotatably, if u is just, then the current horizontal target rotational angle of described The Cloud Terrace is leftDegree, if u is negative, the current horizontal target rotational angle of described The Cloud Terrace is rightDegree; If v is just, then under the current vertical target rotational angle of described The Cloud Terrace isDegree, if v is negative, then the current vertical target rotational angle of described The Cloud Terrace is upperDegree.
The current zoom multiple of the described camera lens calculating video camera, including:
If correction distance coordinate is x, and the maximum zoom multiple of the camera lens of video camera is N, then the current zoom multiple of the camera lens of described video camera is
A kind of comprehensive interactive device of the camera pan-tilt based on Face datection, including:
Human face region locating module, for the human face region in the present image that collected by persona face detection algorithm positioning shooting head;
Correcting plane coordinate calculation module, for the image coordinate of the central point according to described human face region, calculates current correcting plane coordinate based on coordinate model set in advance by interpolation mapping algorithm;
Correction distance coordinate calculation module, goes out current correction distance coordinate for the areal calculation according to described human face region;
Cloud platform rotation angle calculation module, for calculating the current level of The Cloud Terrace of video camera, vertical target rotational angle according to described current correcting plane coordinate, correction distance coordinate;
Camera lens zoom multiple computing module, for calculating the current zoom multiple of the camera lens of video camera.
Described device also includes:
Coordinate model sets up module, for after the head of monitoring personnel moves to the most upper left position of screen, in the image of photographic head shooting, is oriented the central point of human face region by persona face detection algorithm, records the image coordinate of this central point;
After the head of monitoring personnel moves to the position of most lower left of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most top-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most bottom-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
The image coordinate of the 4 of described record central points is surrounded a tetragon, by homography matrix, described tetragon is mapped to a square, this square is called coordinate model.
Described correcting plane coordinate calculation module, for newly setting a correcting plane coordinate system, in this correcting plane coordinate system, with described foursquare center for zero, described foursquare upper left, lower-left, upper right, lower right corner coordinate respectively (-1,1), (-1 ,-1), (1,1), (1 ,-1);
If the image coordinate that the central point of the human face region in described present image is in described tetragon is (xa,ya), the central point of the human face region in described present image respective coordinates in correcting plane coordinate system is (xb,yb), (xb,yb) computing formula as follows:
Wherein H is the homography matrix set, and w is the proportionality coefficient set, by described (xb,yb) as current correcting plane coordinate.
Described correction distance coordinate calculation module, for after the head of monitoring personnel moves to an off the position that screen is farthest, in the image of photographic head shooting, orients human face region by persona face detection algorithm, records the area a of this human face region; After the head of monitoring personnel moves to an off the position that screen is nearest, in the image of photographic head shooting, orient human face region by persona face detection algorithm, record the area b of this human face region;
Record described camera collection to present image in the area x of human face region, then current correction distance coordinate is:
Described cloud platform rotation angle calculation module, be used for setting described correcting plane coordinate as (u, v), the The Cloud Terrace of described video camera be comprehensive rotatably, if u is just, then the current horizontal target rotational angle of described The Cloud Terrace is leftDegree, if u is negative, the current horizontal target rotational angle of described The Cloud Terrace is rightDegree; If v is just, then under the current vertical target rotational angle of described The Cloud Terrace isDegree, if v is negative, then the current vertical target rotational angle of described The Cloud Terrace is upperDegree.
Described camera lens zoom multiple computing module, is used for setting correction distance coordinate as x, and the maximum zoom multiple of the camera lens of video camera is N, then the current zoom multiple of the camera lens of described video camera is
The technical scheme provided by embodiments of the invention described above can be seen that, the video camera PTZ exchange method based on persona face detection that the embodiment of the present invention provides, video monitoring staff can move the head of oneself by up, down, left, right, before and after, control the target direction angle of cloud platform rotation and the zoom of camera lens, thus changing the field of view of current photographic head, it is achieved simulate the effect that the first visual angle is monitored on the spot. Which does not rely on the mutual medium such as mouse, action bars, it is achieved simple, intuitive of getting up.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below the accompanying drawing used required during embodiment is described is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the premise not paying creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The process chart of a kind of video camera PTZ exchange method based on Face datection that Fig. 1 provides for the embodiment of the present invention one;
A kind of comprehensive interactive device of the camera pan-tilt based on Face datection that Fig. 2 provides for the embodiment of the present invention two implement structure chart, in figure, human face region locating module 21, correcting plane coordinate calculation module 22, correction distance coordinate calculation module 23, cloud platform rotation angle calculation module 24, camera lens zoom multiple computing module 25, coordinate model sets up module 26.
Detailed description of the invention
For ease of the understanding to the embodiment of the present invention, it is further explained explanation below in conjunction with accompanying drawing for several specific embodiments, and each embodiment is not intended that the restriction to the embodiment of the present invention.
Embodiment one
This embodiment offers the handling process of a kind of video camera PTZ exchange method based on Face datection as it is shown in figure 1, include following process step:
Step S110, video monitoring system include the equipment such as video camera, server, screen, the embodiment of the present invention needs optional position near screen to install a photographic head, this photographic head is preferably mounted at surface or the underface of screen, the horizontal direction parallel of its horizontal direction and screen, shooting direction is parallel with the normal direction of screen plane, for the face of monitoring personnel is positioned.
Step S120, the embodiment of the present invention arrange three modules in the server: correction module, persona face detection module and video camera PTZ interactive module.
Above-mentioned correction module determines the head moving range of monitoring personnel, obtains the transformational relation of face location and cloud platform rotation, camera lens zoom. Monitoring personnel face screen, are moved to the upper left side of screen by head, it is determined that a position the most upper left, and in the image of photographic head shooting, detection or manual point select the central point of human face region automatically, record the image coordinate of this central point. Same,
After the head of monitoring personnel moves to the position of most lower left of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most top-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most bottom-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
The image coordinate of the 4 of described record central points is surrounded a tetragon, and this tetragon illustrates face moving range in the picture. The coordinate of a point in tetragon is called 4 summit image coordinate of tetragon.
Training the homography matrix H of 3 �� 3, the tetragon that these 4 image coordinate surround is mapped to a square, this square is properly termed as a coordinate model. Newly setting a correcting plane coordinate system, with foursquare center for zero, foursquare upper left, lower-left, upper right, lower right corner coordinate be (-1,1) respectively, (-1 ,-1), (1,1), (1 ,-1).
For any point in the tetragon that above-mentioned 4 image coordinate surround, its coordinate in tetragon might as well be set as (xa,ya), this respective coordinates in correcting plane coordinate system is (xb,yb),
Its corresponding relation formula is:
Wherein w is proportionality coefficient, and H and w can be solved by known methods such as ransac.
Above-mentioned corresponding relation formula reflects the corresponding relation between 4 summit image coordinate of tetragon and 4 summit correcting plane coordinates of square, in subsequent module, it is possible to by above-mentioned corresponding relation formula, the arbitrfary point interpolation in tetragon in image is mapped in correcting plane coordinate system.
Step S130, monitoring personnel face screen, being moved to the direction away from screen by head, it is determined that the position that an off screen curtain is farthest, by persona face detection algorithm, in the image that photographic head shoots, detection or manual point select human face region automatically, record the area of this human face region, be set to a. Same, by head to the direction near screen, when record off screen curtain is nearest, the area of the human face region in image, is set to b, obtains the computation model of correction distance coordinate according to area a and the b of 2 human face regions.
If correction distance coordinate is the one-dimensional coordinate on the normal of screen plane, the correction distance coordinate that (position that off screen curtain is farthest) is corresponding if area is a is 0, and the correction distance coordinate that when area is b, (position that off screen curtain is nearest) is corresponding is set to 1. In subsequent module, the computation model of the correction distance coordinate that area x, the x of the human face region in any one image given are corresponding is:
Before screen, up, down, left, right, before and after moves the head of oneself as required for step S140, video monitoring staff. Persona face detection module in above-mentioned server passes through known persona face detection algorithm, the human face region in the present image that positioning shooting head collects.
Video camera PTZ interactive module in step S150, above-mentioned server obtains the image coordinate of the central point of the human face region in above-mentioned present image, the image coordinate interpolation of above-mentioned central point is mapped to a coordinate in above-mentioned square by interpolation mapping algorithm, and this coordinate is current correcting plane coordinate.
Above-mentioned video camera PTZ interactive module obtains the area x of the human face region in above-mentioned present image, and calculating current correction distance coordinate is:
Step S160, calculate the current level of The Cloud Terrace of video camera, vertical target rotational angle according to above-mentioned correcting plane coordinate, correction distance coordinate, calculate the current zoom multiple of the camera lens of video camera.
The central point of the human face region in present image image coordinate in described tetragon is substituted into above-mentioned (xa,ya) and (xb,yb) between corresponding relation formula: Obtain current correcting plane coordinate for (u, v).
The target direction angle of cloud platform rotation is contrary relative to the orientation of zero with correcting plane coordinate. If current correcting plane coordinate be (u, v), The Cloud Terrace be comprehensive rotatably, namely left and right up and down maximum rotation angle is 180 degree. If u is just, then the current horizontal target rotational angle of described The Cloud Terrace is leftDegree, if u is negative, the current horizontal target rotational angle of described The Cloud Terrace is rightDegree; If v is just, then under the current vertical target rotational angle of described The Cloud Terrace isDegree, if v is negative, then the current vertical target rotational angle of described The Cloud Terrace is upperDegree.
If correction distance coordinate is x, and the maximum zoom multiple of the camera lens of video camera is N, then the current zoom multiple of camera lens is
PTZ instruction is sent to camera pan-tilt by the mode such as RS-485 or Ethernet, this PTZ instruction is carried the current level of the The Cloud Terrace of above-mentioned video camera, vertical target rotational angle, the current zoom multiple of the camera lens of video camera, above-mentioned current level, vertical target rotational angle is adjusted at camera pan-tilt, after the camera lens of video camera adjusts above-mentioned current zoom multiple, then complete the PTZ to current face position and control. In actual applications, rotational angle and zoom multiple can be adjusted according to factors such as the rotatable scope of The Cloud Terrace and practical field of view need.
Embodiment two
This embodiment offers a kind of comprehensive interactive device of the camera pan-tilt based on Face datection, it implements structure as in figure 2 it is shown, specifically can include following module:
Human face region locating module 21, for the human face region in the present image that collected by persona face detection algorithm positioning shooting head;
Correcting plane coordinate calculation module 22, for the image coordinate of the central point according to described human face region, calculates current correcting plane coordinate based on coordinate model set in advance by interpolation mapping algorithm;
Correction distance coordinate calculation module 23, goes out current correction distance coordinate for the areal calculation according to described human face region;
Cloud platform rotation angle calculation module 24, for calculating the current level of The Cloud Terrace of video camera, vertical target rotational angle according to described current correcting plane coordinate, correction distance coordinate;
Camera lens zoom multiple computing module 25, for calculating the current zoom multiple of the camera lens of video camera.
Further, described device also includes:
Coordinate model sets up module 26, for after the head of monitoring personnel moves to the most upper left position of screen, in the image of photographic head shooting, is oriented the central point of human face region by persona face detection algorithm, records the image coordinate of this central point;
After the head of monitoring personnel moves to the position of most lower left of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most top-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most bottom-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
The image coordinate of the 4 of described record central points is surrounded a tetragon, by homography matrix, described tetragon is mapped to a square, this square is called coordinate model.
Further, described correcting plane coordinate calculation module 22, for newly setting a correcting plane coordinate system, in this correcting plane coordinate system, with described foursquare center for zero, described foursquare upper left, lower-left, upper right, lower right corner coordinate be (-1,1) respectively, (-1,-1), (1,1), (1 ,-1);
If the image coordinate that the central point of the human face region in described present image is in described tetragon is (xa,ya), the central point of the human face region in described present image respective coordinates in correcting plane coordinate system is (xb,yb), (xb,yb) computing formula as follows:
Wherein H is the homography matrix set, and w is the proportionality coefficient set, by described (xb,yb) as current correcting plane coordinate.
Further, described correction distance coordinate calculation module 23, for after the head of monitoring personnel moves to an off the position that screen is farthest, in the image of photographic head shooting, orient human face region by persona face detection algorithm, record the area a of this human face region; After the head of monitoring personnel moves to an off the position that screen is nearest, in the image of photographic head shooting, orient human face region by persona face detection algorithm, record the area b of this human face region;
Record described camera collection to present image in the area x of human face region, then current correction distance coordinate is:
Further, described cloud platform rotation angle calculation module 24, be used for setting described correcting plane coordinate as (u, v), the The Cloud Terrace of described video camera be comprehensive rotatably, if u is just, then the current horizontal target rotational angle of described The Cloud Terrace is leftDegree, if u is negative, the current horizontal target rotational angle of described The Cloud Terrace is rightDegree; If v is just, then under the current vertical target rotational angle of described The Cloud Terrace isDegree, if v is negative, then the current vertical target rotational angle of described The Cloud Terrace is upperDegree.
Further, described camera lens zoom multiple computing module 25, be used for setting correction distance coordinate as x, and the maximum zoom multiple of the camera lens of video camera is N, then the current zoom multiple of the camera lens of described video camera is
Carry out the comprehensive mutual detailed process of the camera pan-tilt based on Face datection with the device of the embodiment of the present invention similar with preceding method embodiment, repeat no more herein.
In sum, the video camera PTZ exchange method based on persona face detection that the embodiment of the present invention provides, video monitoring staff can move the head of oneself by up, down, left, right, before and after, control the target direction angle of cloud platform rotation and the zoom of camera lens, thus changing the field of view of current photographic head, it is achieved simulate the effect that the first visual angle is monitored on the spot. Which does not rely on the mutual medium such as mouse, action bars, it is achieved simple, intuitive of getting up.
Embodiments providing the PTZ interactive mode of a kind of simple, intuitive, monitoring staff does not need any training and technological know-how can complete associative operation. Fix in background, persona face detection algorithm comparative maturity under the scene of uniform illumination, the probability of mistake is very low, this guarantees mutual correctness.
One of ordinary skill in the art will appreciate that: accompanying drawing is the schematic diagram of an embodiment, module or flow process in accompanying drawing are not necessarily implemented necessary to the present invention.
As seen through the above description of the embodiments, those skilled in the art is it can be understood that can add the mode of required general hardware platform by software to the present invention and realize. Based on such understanding, the part that prior art is contributed by technical scheme substantially in other words can embody with the form of software product, this computer software product can be stored in storage medium, such as ROM/RAM, magnetic disc, CD etc., including some instructions with so that a computer equipment (can be personal computer, server, or the network equipment etc.) perform the method described in some part of each embodiment of the present invention or embodiment.
Each embodiment in this specification all adopts the mode gone forward one by one to describe, between each embodiment identical similar part mutually referring to, what each embodiment stressed is the difference with other embodiments. Especially for device or system embodiment, owing to it is substantially similar to embodiment of the method, so describing fairly simple, relevant part illustrates referring to the part of embodiment of the method. Apparatus and system embodiment described above is merely schematic, the wherein said unit illustrated as separating component can be or may not be physically separate, the parts shown as unit can be or may not be physical location, namely may be located at a place, or can also be distributed on multiple NE. Some or all of module therein can be selected according to the actual needs to realize the purpose of the present embodiment scheme. Those of ordinary skill in the art, when not paying creative work, are namely appreciated that and implement.
The above; being only the present invention preferably detailed description of the invention, but protection scope of the present invention is not limited thereto, any those familiar with the art is in the technical scope that the invention discloses; the change that can readily occur in or replacement, all should be encompassed within protection scope of the present invention. Therefore, protection scope of the present invention should be as the criterion with scope of the claims.
Claims (12)
1. the comprehensive exchange method of the camera pan-tilt based on Face datection, it is characterised in that including:
By the human face region in the present image that persona face detection algorithm positioning shooting head collects;
The image coordinate of the central point according to described human face region, calculates current correcting plane coordinate based on coordinate model set in advance by interpolation mapping algorithm; Areal calculation according to described human face region goes out current correction distance coordinate;
Calculate the current level of The Cloud Terrace of video camera, vertical target rotational angle according to described current correcting plane coordinate, correction distance coordinate, calculate the current zoom multiple of the camera lens of video camera.
2. the comprehensive exchange method of the camera pan-tilt based on Face datection according to claim 1, it is characterised in that before the human face region in the described present image collected by persona face detection algorithm positioning shooting head, including:
After the head of monitoring personnel moves to the most upper left position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the position of most lower left of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most top-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most bottom-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
The image coordinate of the 4 of described record central points is surrounded a tetragon, by homography matrix, described tetragon is mapped to a square, this square is called coordinate model.
3. the comprehensive exchange method of the camera pan-tilt based on Face datection according to claim 2, it is characterized in that, the image coordinate of the described central point according to described human face region, current correcting plane coordinate is calculated by interpolation mapping algorithm based on coordinate model set in advance, including:
Newly set a correcting plane coordinate system, in this correcting plane coordinate system, with described foursquare center for zero, described foursquare upper left, lower-left, upper right, lower right corner coordinate be (-1,1) respectively, (-1,-1), (1,1), (1 ,-1);
If the image coordinate that the central point of the human face region in described present image is in described tetragon is (xa,ya), the central point of the human face region in described present image respective coordinates in correcting plane coordinate system is (xb,yb), (xb,yb) computing formula as follows:
Wherein H is the homography matrix set, and w is the proportionality coefficient set, by described (xb,yb) as current correcting plane coordinate.
4. the comprehensive exchange method of the camera pan-tilt based on Face datection according to claim 1, it is characterised in that the described areal calculation according to described human face region goes out current correction distance coordinate, including:
After the head of monitoring personnel moves to an off the position that screen is farthest, in the image of photographic head shooting, orient human face region by persona face detection algorithm, record the area a of this human face region; After the head of monitoring personnel moves to an off the position that screen is nearest, in the image of photographic head shooting, orient human face region by persona face detection algorithm, record the area b of this human face region;
Record described camera collection to present image in the area x of human face region, then current correction distance coordinate is:
5. the comprehensive exchange method of the camera pan-tilt based on Face datection according to claim 1 or 2 or 3 or 4, it is characterized in that, described calculates the current level of The Cloud Terrace of video camera, vertical target rotational angle according to described current correcting plane coordinate, correction distance coordinate, including:
If described correcting plane coordinate be (u, v), the The Cloud Terrace of described video camera be comprehensive rotatably, if u is just, then the current horizontal target rotational angle of described The Cloud Terrace is leftDegree, if u is negative, the current horizontal target rotational angle of described The Cloud Terrace is rightDegree; If v is just, then under the current vertical target rotational angle of described The Cloud Terrace isDegree, if v is negative, then the current vertical target rotational angle of described The Cloud Terrace is upperDegree.
6. the comprehensive exchange method of the camera pan-tilt based on Face datection according to claim 1 or 2 or 3 or 4, it is characterised in that the current zoom multiple of the described camera lens calculating video camera, including:
If correction distance coordinate is x, and the maximum zoom multiple of the camera lens of video camera is N, then the current zoom multiple of the camera lens of described video camera is
7. the comprehensive interactive device of the camera pan-tilt based on Face datection, it is characterised in that including:
Human face region locating module, for the human face region in the present image that collected by persona face detection algorithm positioning shooting head;
Correcting plane coordinate calculation module, for the image coordinate of the central point according to described human face region, calculates current correcting plane coordinate based on coordinate model set in advance by interpolation mapping algorithm;
Correction distance coordinate calculation module, goes out current correction distance coordinate for the areal calculation according to described human face region;
Cloud platform rotation angle calculation module, for calculating the current level of The Cloud Terrace of video camera, vertical target rotational angle according to described current correcting plane coordinate, correction distance coordinate;
Camera lens zoom multiple computing module, for calculating the current zoom multiple of the camera lens of video camera.
8. the comprehensive interactive device of the camera pan-tilt based on Face datection according to claim 7, it is characterised in that described device also includes:
Coordinate model sets up module, for after the head of monitoring personnel moves to the most upper left position of screen, in the image of photographic head shooting, is oriented the central point of human face region by persona face detection algorithm, records the image coordinate of this central point;
After the head of monitoring personnel moves to the position of most lower left of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most top-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
After the head of monitoring personnel moves to the most bottom-right position of screen, in the image of photographic head shooting, oriented the central point of human face region by persona face detection algorithm, record the image coordinate of this central point;
The image coordinate of the 4 of described record central points is surrounded a tetragon, by homography matrix, described tetragon is mapped to a square, this square is called coordinate model.
9. the comprehensive interactive device of the camera pan-tilt based on Face datection according to claim 6, it is characterised in that:
Described correcting plane coordinate calculation module, for newly setting a correcting plane coordinate system, in this correcting plane coordinate system, with described foursquare center for zero, described foursquare upper left, lower-left, upper right, lower right corner coordinate respectively (-1,1), (-1 ,-1), (1,1), (1 ,-1);
If the image coordinate that the central point of the human face region in described present image is in described tetragon is (xa,ya), the central point of the human face region in described present image respective coordinates in correcting plane coordinate system is (xb,yb), (xb,yb) computing formula as follows:
Wherein H is the homography matrix set, and w is the proportionality coefficient set, by described (xb,yb) as current correcting plane coordinate.
10. the comprehensive interactive device of the camera pan-tilt based on Face datection according to claim 6, it is characterised in that:
Described correction distance coordinate calculation module, for after the head of monitoring personnel moves to an off the position that screen is farthest, in the image of photographic head shooting, orients human face region by persona face detection algorithm, records the area a of this human face region; After the head of monitoring personnel moves to an off the position that screen is nearest, in the image of photographic head shooting, orient human face region by persona face detection algorithm, record the area b of this human face region;
Record described camera collection to present image in the area x of human face region, then current correction distance coordinate is:
11. according to the comprehensive interactive device of the camera pan-tilt based on Face datection described in claim 6 or 7 or 8 or 9 or 10, it is characterised in that:
Described cloud platform rotation angle calculation module, be used for setting described correcting plane coordinate as (u, v), the The Cloud Terrace of described video camera be comprehensive rotatably, if u is just, then the current horizontal target rotational angle of described The Cloud Terrace is leftDegree, if u is negative, the current horizontal target rotational angle of described The Cloud Terrace is rightDegree; If v is just, then under the current vertical target rotational angle of described The Cloud Terrace isDegree, if v is negative, then the current vertical target rotational angle of described The Cloud Terrace is upperDegree.
12. according to the comprehensive interactive device of the camera pan-tilt based on Face datection described in claim 6 or 7 or 8 or 9 or 10, it is characterised in that:
Described camera lens zoom multiple computing module, is used for setting correction distance coordinate as x, and the maximum zoom multiple of the camera lens of video camera is N, then the current zoom multiple of the camera lens of described video camera is
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410608706.6A CN105635657B (en) | 2014-11-03 | 2014-11-03 | The comprehensive exchange method of camera pan-tilt and device based on Face datection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410608706.6A CN105635657B (en) | 2014-11-03 | 2014-11-03 | The comprehensive exchange method of camera pan-tilt and device based on Face datection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105635657A true CN105635657A (en) | 2016-06-01 |
| CN105635657B CN105635657B (en) | 2019-04-23 |
Family
ID=56050095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410608706.6A Active CN105635657B (en) | 2014-11-03 | 2014-11-03 | The comprehensive exchange method of camera pan-tilt and device based on Face datection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105635657B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598078A (en) * | 2016-11-04 | 2017-04-26 | 浙江宇视科技有限公司 | Image processing method and apparatus for pan-tilt-zoom (PTZ) camera |
| CN108073873A (en) * | 2016-11-15 | 2018-05-25 | 上海宝信软件股份有限公司 | Human face detection and tracing system based on high-definition intelligent video camera |
| CN108632569A (en) * | 2017-03-20 | 2018-10-09 | 华为技术有限公司 | Video frequency monitoring method and device based on the linkage of rifle ball |
| CN108965694A (en) * | 2018-06-26 | 2018-12-07 | 深圳岚锋创视网络科技有限公司 | The acquisition methods and portable terminal of gyroscope information for camera rectification |
| CN110099254A (en) * | 2019-05-21 | 2019-08-06 | 浙江师范大学 | A kind of driver's face tracking device and method |
| CN110809880A (en) * | 2018-10-31 | 2020-02-18 | 深圳市大疆创新科技有限公司 | Adjusting method of monitoring equipment, monitoring equipment and holder equipment |
| CN111526335A (en) * | 2020-05-03 | 2020-08-11 | 杭州晶一智能科技有限公司 | Target tracking algorithm for suspended track type omnidirectional pan-tilt camera |
| CN111526334A (en) * | 2020-05-03 | 2020-08-11 | 杭州晶一智能科技有限公司 | Imaging target position servo control strategy based on PID algorithm |
| CN111650968A (en) * | 2020-07-28 | 2020-09-11 | 南京天创电子技术有限公司 | Method for measuring positioning error of holder |
| CN111914739A (en) * | 2020-07-30 | 2020-11-10 | 深圳创维－Rgb电子有限公司 | Intelligent following method and device, terminal equipment and readable storage medium |
| CN112153270A (en) * | 2019-06-27 | 2020-12-29 | 浙江宇视科技有限公司 | Cloud deck zero point detection method and device, camera and storage medium |
| CN112995566A (en) * | 2019-12-17 | 2021-06-18 | 佛山市云米电器科技有限公司 | Sound source positioning method based on display equipment, display equipment and storage medium |
| CN113112668A (en) * | 2021-04-15 | 2021-07-13 | 新疆爱华盈通信息技术有限公司 | Face recognition-based holder tracking method, holder and entrance guard recognition machine |
| CN114509168A (en) * | 2020-10-29 | 2022-05-17 | 中移物联网有限公司 | Infrared temperature measurement method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102043410A (en) * | 2010-09-30 | 2011-05-04 | 清华大学 | Servo system for instructing pan-tilt system of unmanned aerial vehicle (UAV) by adopting head movement of operator |
| CN102088552A (en) * | 2009-12-03 | 2011-06-08 | 鸿富锦精密工业（深圳）有限公司 | Adjusting system and method for PTZ (Pan/Tilt/Zoom) camera |
| CN102143316A (en) * | 2010-02-02 | 2011-08-03 | 鸿富锦精密工业（深圳）有限公司 | Pan/tilt/zoom (PTZ) camera control system and method and adjusting device with control system |
| US20120069223A1 (en) * | 2009-05-28 | 2012-03-22 | Panasonic Corporation | Camera device with rotary base |
| CN103049007A (en) * | 2012-12-29 | 2013-04-17 | 安科智慧城市技术（中国）有限公司 | System and method for operating mobile platform based on head movement of operator |
-
2014
- 2014-11-03 CN CN201410608706.6A patent/CN105635657B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120069223A1 (en) * | 2009-05-28 | 2012-03-22 | Panasonic Corporation | Camera device with rotary base |
| CN102088552A (en) * | 2009-12-03 | 2011-06-08 | 鸿富锦精密工业（深圳）有限公司 | Adjusting system and method for PTZ (Pan/Tilt/Zoom) camera |
| CN102143316A (en) * | 2010-02-02 | 2011-08-03 | 鸿富锦精密工业（深圳）有限公司 | Pan/tilt/zoom (PTZ) camera control system and method and adjusting device with control system |
| CN102043410A (en) * | 2010-09-30 | 2011-05-04 | 清华大学 | Servo system for instructing pan-tilt system of unmanned aerial vehicle (UAV) by adopting head movement of operator |
| CN103049007A (en) * | 2012-12-29 | 2013-04-17 | 安科智慧城市技术（中国）有限公司 | System and method for operating mobile platform based on head movement of operator |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106598078B (en) * | 2016-11-04 | 2020-09-01 | 浙江宇视科技有限公司 | Image processing method and device for pan-tilt camera |
| CN106598078A (en) * | 2016-11-04 | 2017-04-26 | 浙江宇视科技有限公司 | Image processing method and apparatus for pan-tilt-zoom (PTZ) camera |
| CN108073873A (en) * | 2016-11-15 | 2018-05-25 | 上海宝信软件股份有限公司 | Human face detection and tracing system based on high-definition intelligent video camera |
| CN108632569A (en) * | 2017-03-20 | 2018-10-09 | 华为技术有限公司 | Video frequency monitoring method and device based on the linkage of rifle ball |
| CN108632569B (en) * | 2017-03-20 | 2020-09-29 | 华为技术有限公司 | Video monitoring method and device based on gun and ball linkage |
| CN108965694A (en) * | 2018-06-26 | 2018-12-07 | 深圳岚锋创视网络科技有限公司 | The acquisition methods and portable terminal of gyroscope information for camera rectification |
| CN108965694B (en) * | 2018-06-26 | 2020-11-03 | 影石创新科技股份有限公司 | Method for acquiring gyroscope information for camera level correction and portable terminal |
| CN110809880A (en) * | 2018-10-31 | 2020-02-18 | 深圳市大疆创新科技有限公司 | Adjusting method of monitoring equipment, monitoring equipment and holder equipment |
| CN110099254B (en) * | 2019-05-21 | 2023-08-25 | 浙江师范大学 | Driver face tracking device and method |
| CN110099254A (en) * | 2019-05-21 | 2019-08-06 | 浙江师范大学 | A kind of driver's face tracking device and method |
| CN112153270A (en) * | 2019-06-27 | 2020-12-29 | 浙江宇视科技有限公司 | Cloud deck zero point detection method and device, camera and storage medium |
| CN112153270B (en) * | 2019-06-27 | 2022-02-18 | 浙江宇视科技有限公司 | Cloud deck zero point detection method and device, camera and storage medium |
| CN112995566A (en) * | 2019-12-17 | 2021-06-18 | 佛山市云米电器科技有限公司 | Sound source positioning method based on display equipment, display equipment and storage medium |
| CN112995566B (en) * | 2019-12-17 | 2024-04-05 | 佛山市云米电器科技有限公司 | Sound source positioning method based on display device, display device and storage medium |
| CN111526334A (en) * | 2020-05-03 | 2020-08-11 | 杭州晶一智能科技有限公司 | Imaging target position servo control strategy based on PID algorithm |
| CN111526334B (en) * | 2020-05-03 | 2021-08-20 | 上海弈山实业有限公司 | Imaging target position servo control method based on PID algorithm |
| CN111526335B (en) * | 2020-05-03 | 2021-08-27 | 金华精研机电股份有限公司 | Target tracking method for suspended track type omnidirectional pan-tilt camera |
| CN111526335A (en) * | 2020-05-03 | 2020-08-11 | 杭州晶一智能科技有限公司 | Target tracking algorithm for suspended track type omnidirectional pan-tilt camera |
| CN111650968A (en) * | 2020-07-28 | 2020-09-11 | 南京天创电子技术有限公司 | Method for measuring positioning error of holder |
| CN111914739A (en) * | 2020-07-30 | 2020-11-10 | 深圳创维－Rgb电子有限公司 | Intelligent following method and device, terminal equipment and readable storage medium |
| CN114509168A (en) * | 2020-10-29 | 2022-05-17 | 中移物联网有限公司 | Infrared temperature measurement method and device and electronic equipment |
| CN113112668A (en) * | 2021-04-15 | 2021-07-13 | 新疆爱华盈通信息技术有限公司 | Face recognition-based holder tracking method, holder and entrance guard recognition machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105635657B (en) | 2019-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105635657A (en) | Camera holder omnibearing interaction method and device based on face detection | |
| US11863857B2 (en) | Photographing control method, apparatus, and control device | |
| CN105120242B (en) | A kind of panoramic camera and high-speed ball-forming machine intelligent linkage method and device | |
| CN112164015B (en) | Monocular vision autonomous inspection image acquisition method and device and power inspection unmanned aerial vehicle | |
| CN106161953A (en) | A kind of track up method and apparatus | |
| CN103198488B (en) | PTZ surveillance camera realtime posture rapid estimation | |
| CN103188434B (en) | Method and device of image collection | |
| CN105554447B (en) | A kind of coal working face real-time video splicing system based on image processing techniques | |
| CN104320587A (en) | Method for automatically obtaining shooting range of outdoor pan-tilt camera | |
| CN110062205A (en) | Motion estimate, tracking device and method | |
| CN102902884A (en) | PTZ (pan/tilt/zoom) camera automatic positioning and angle calculating method | |
| WO2021098453A1 (en) | Target tracking method and unmanned aerial vehicle | |
| CN105744226A (en) | 1+N gun-type camera and dome camera cooperation method based on camera coordinate system | |
| US20200267309A1 (en) | Focusing method and device, and readable storage medium | |
| CN103167270B (en) | Personnel's head image pickup method, system and server | |
| CN106331639B (en) | A kind of method and device automatically determining camera position | |
| KR101347450B1 (en) | Image sensing method using dual camera and apparatus thereof | |
| CN106060452A (en) | Method and apparatus for controlling a surveillance system | |
| CN106506955A (en) | A kind of transformer substation video polling path planing method based on GIS map | |
| CN107509055A (en) | A kind of rotary panorama focus identification optronic tracker and its implementation | |
| CN107995408A (en) | A kind of 360 ° of panoramic shooting systems and method | |
| CN110757462A (en) | Robot hand-eye calibration method, system and storage medium | |
| CN109327656A (en) | The image-pickup method and system of full-view image | |
| US20120287160A1 (en) | Display device and rotation method of same | |
| CN104168407A (en) | Panorama photographing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |