CN106161968B - A kind of method of cell monitoring platform courses camera shooting - Google Patents
A kind of method of cell monitoring platform courses camera shooting Download PDFInfo
- Publication number
- CN106161968B CN106161968B CN201610835194.6A CN201610835194A CN106161968B CN 106161968 B CN106161968 B CN 106161968B CN 201610835194 A CN201610835194 A CN 201610835194A CN 106161968 B CN106161968 B CN 106161968B
- Authority
- CN
- China
- Prior art keywords
- target object
- image
- camera
- clarity
- shooting
- 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
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
- H04N23/67—Focus control based on electronic image sensor signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a kind of methods for controlling the object clear image of cell monitoring camera photographic subjects, a method of control cell monitoring camera photographic subjects object clear image, including monitoring system, the monitoring system includes the camera set on the cell and the characteristic information for being stored with target object, the step of this method includes: the first image of shooting, when monitoring system searches target object image according to the characteristic information in the first image, judge the clarity of target object image, target object clear image is stored in monitoring system when clarity is more than or equal to first threshold, otherwise the first position of target object is recorded;Shoot the second image after shooting for the first image △ t1 time, monitoring system according to the characteristic information rope is to target object image in the second image is searched when, judge the clarity of target object image.The present invention can fast and effectively take target object clear image.
Description
Technical field
The present invention relates to the methods that a kind of control camera shooting moving object of control platform is accurately focused.
Background technique
During control platform control camera is monitored, shoots, it is sometimes desirable to continuous to the object of certain movement
It is shot, but because moving object focusing is inaccurate, the photo of shooting is often very fuzzy, even if in control platform using artificial
Focusing shooting, under the limitation of a variety of factors, focusing success rate is still relatively low.
Summary of the invention
To solve the above problems, the present invention provides a kind of side for controlling the object clear image of cell monitoring camera photographic subjects
Method, including monitoring system, the monitoring system include the camera set on the cell and the characteristic information for being stored with target object, the party
The step of method includes:
S1: the first image of shooting, monitoring system search target object figure according to the characteristic information in the first image
When picture, the clarity of target object image is judged, jump to S9 when clarity is more than or equal to first threshold, otherwise record target
The first position of object simultaneously enters S2;
S2: the second image is shot after the time in shooting the first image △ t1 (0s < △ t1 < 1s), monitoring system is according to institute
When stating characteristic information rope is to target object image in the second image is searched, judges the clarity of target object image, work as clarity
S9 is jumped to when more than or equal to first threshold, otherwise records the second position of target object and enters S3;
S3: according to the first position of target object and second position prediction in shooting the second image △ t2 (0s < △ t2 <
The third place of target object when 1s) shooting third image after time, the camera of control shooting third image is at the third place
Focusing;Third image is shot after shooting for the second image △ t2 time, monitoring system is according to the characteristic information in third image
In when searching target object image, judge the clarity of target object image, jumped when clarity is more than or equal to first threshold
Go to S9;
S9: target object clear image is stored in monitoring system.
In some embodiments of the present invention, the camera is one;
S3 further include: the first, second, and third image including shooting, the camera shoot m-1 width target object image altogether,
M value is the integer more than or equal to 4, and the clarity of those target object images is both less than first threshold, according to target object
In the first position of the first image, the position m-1 of the second position ... the m-1 image of the second image, the target object is established
First action prediction module, prediction shooting m-1 image △ tm-1M of target object when shooting m image after the time
It sets, the camera of control shooting m image is focused at the position m;Monitoring system is searched in m image according to the characteristic information
When rope is to target object image, the clarity of target object image is judged, jump to S9 when clarity is greater than first threshold.
In some embodiments of the present invention, which includes n platform camera (2 >=n >=50), which also deposits
The 3D model in the cell monitoring section is contained, which includes the distribution of road and camera;Wherein, by the n platform camera
In first camera execute S1 and S2;Step S3 further includes S4: according to the characteristic information of the target object, cell monitoring section
The first action prediction module of the target object is established in 3D model and first position and the second position;According to the of target object
One action prediction module, the third place that prediction target object occurs after the △ t2 time is in magazine second phase of the n platform
On first estimation range of machine, monitoring system is issued to second camera and is instructed, and second camera is after the △ t2 time to second camera
The first estimation range carry out focusing shooting to obtain third image, and judge the clear of target object image in the second image
Degree jumps to S9 when clarity is more than or equal to first threshold;Otherwise, S6 is entered step;
S6: setting the first estimation range of second camera is side length as the square of r (10 pixels≤r≤30 pixels), with this
Point centered on the midpoint of first estimation range of two cameras, establish side length be 2r square area as second camera second
Estimation range is scanned for according to the characteristic information in second estimation range, to the mesh if searching the target object
Mark object carries out focusing shooting;If search is built less than the target object by the point centered on the midpoint of second estimation range
Third estimation range of the square area of a length of 4r of stile as second camera, using the characteristic information stored in monitoring system
It is scanned in the third estimation range of the second camera, if searching the target object, focusing bat is carried out to the target object
It takes the photograph, and records the 4th position of target object;
If search less than the target object, continues to expand region of search, until side length that pth time is established be 2pr just
Pth estimation range of the square region as the second camera, the edge of the pth estimation range exceed the image side of camera shooting
Step S7 is jumped to when edge and still search are less than the target object;
S7: the position of second camera is searched from the 3D model in cell monitoring section in monitoring system, by remaining n-1 platform phase
Machine is ranked up from the near to the distant with the distance apart from the second camera, with the collating sequence, with the characteristic information of the target object
The image of those cameras shooting is successively scanned for, the target object is searched and appears in the shooting image of third camera
When, judge the clarity of target object image in the image, jumps to S9 when clarity is greater than first threshold;Record third phase
The third place information of target object in the image of machine shooting is simultaneously transferred to step S8;
S8: monitoring system is according to the characteristic information of the target object, the 3D model in cell monitoring section and first position,
The second Motion prediction template is established in two positions, the third place and the 4th position;According to the second Motion prediction template of target object,
Predict target object in t2Time appears on the first estimation range of third camera, and monitoring system refers to third camera sending
It enables, third camera is in t2Time carries out focusing shooting to the first estimation range of third camera to obtain the figure of third camera shooting
Picture, and judge the clarity of target object image in the image, S9 is jumped to when clarity is greater than first threshold;Otherwise, into
Enter step S6.
In the method, it is first scanned for using the characteristic information of target object, it is carried out after searching out target object
Focusing shooting, largely can be improved the speed of focusing, the present invention provides a kind of monitoring cameras quickly to clap in this way
The method for taking the photograph specific objective object clear image.
Specific embodiment
For the ease of the understanding of those skilled in the art, the present invention will be further described with reference to the examples below.
To solve the above problems, the present invention provides a kind of side for controlling the object clear image of cell monitoring camera photographic subjects
Method, including monitoring system, the monitoring system include the camera set on the cell and the characteristic information for being stored with target object, the party
The step of method includes:
S1: the first image of shooting, monitoring system search target object figure according to the characteristic information in the first image
When picture, the clarity of target object image is judged, jump to S9 when clarity is more than or equal to first threshold, otherwise record target
The first position of object simultaneously enters S2;
S2: the second image is shot after shooting the first image 0.1s, monitoring system is according to the characteristic information in the second figure
When as searching middle rope to target object image, the clarity of target object image is judged, when clarity is more than or equal to first threshold
S9 is jumped to, the second position of target object is otherwise recorded and enters S3;
S3: third is shot after shooting the second image 0.15s according to the first position of target object and second position prediction
The camera of the third place of target object when image, control shooting third image is focused at the third place;Shooting the second figure
As shooting third image after 0.15s, monitoring system searches target object image according to the characteristic information in third image
When, judge the clarity of target object image, jumps to S9 when clarity is more than or equal to first threshold;
S9: target object clear image is stored in monitoring system.
In some embodiments of the present invention, the camera is one;
S3 further include: the first, second, and third image including shooting, the camera shoot 5 width target object images altogether, and
The clarity of those target object images is both less than first threshold, according to target object the first image first position, second
5th position of the 5th image of the second position ... of image, establishes the first action prediction module of the target object, and prediction is being clapped
6th position of target object when shooting six images is taken the photograph after the 5th image 0.2s, and the camera of control the 6th image of shooting is the 6th
It focuses at position;When monitoring system searches target object image in the 6th image according to the characteristic information, target is judged
The clarity of object images jumps to S9 when clarity is greater than first threshold.
In some embodiments of the present invention, which includes 10 cameras, and it is small which is also stored with this
Area monitors the 3D model in section, which includes the distribution of road and camera;Wherein, by described 10 magazine first
Camera executes S1 and S2;Step S3 further includes S4: according to the 3D model in the characteristic information of the target object, cell monitoring section with
And the first action prediction module of the target object is established in first position and the second position;It is pre- according to the first action of target object
Survey template, the third place that occurs after the 0.15s time of prediction target object in 10 magazine second cameras the
On one estimation range, monitoring system is issued to second camera and is instructed, and second camera is after 0.15s to the first prediction of second camera
Region carries out focusing shooting to obtain third image, and judges the clarity of target object image in the second image, works as clarity
S9 is jumped to when more than or equal to first threshold;Otherwise, S6 is entered step;
S6: setting the first estimation range of second camera is side length as the square of 15 pixels, pre- with the first of the second camera
Point centered on the midpoint in region is surveyed, second estimation range of the square area as second camera that side length is 30 pixels is established,
It is scanned for according to the characteristic information in second estimation range, the target object is carried out if searching the target object
Focusing shooting;If search is less than the target object, by the point centered on the midpoint of second estimation range, establishing side length is 60
Third estimation range of the square area of pixel as second camera, using the characteristic information stored in monitoring system this
The third estimation range of two cameras scans for, if searching the target object, carries out focusing shooting to the target object, and remember
Record the 4th position of target object;
If search less than the target object, continues to expand region of search, until side length that pth time is established be 30p just
Pth estimation range of the square region as the second camera, the edge of the pth estimation range exceed the image side of camera shooting
Step S7 is jumped to when edge and still search are less than the target object;
S7: the position of second camera is searched from the 3D model in cell monitoring section in monitoring system, by remaining 9 cameras
It is ranked up from the near to the distant with the distance apart from the second camera, with the collating sequence, with the characteristic information pair of the target object
The image of those cameras shooting successively scans for, when searching the target object and appearing in the shooting image of third camera,
The clarity for judging target object image in the image jumps to S9 when clarity is greater than first threshold;Record third camera
The third place information of target object in the image of shooting is simultaneously transferred to step S8;
S8: monitoring system is according to the characteristic information of the target object, the 3D model in cell monitoring section and first position,
The second Motion prediction template is established in two positions, the third place and the 4th position;According to the second Motion prediction template of target object,
Predict target object in t2Time appears on the first estimation range of third camera, and monitoring system refers to third camera sending
It enables, third camera is in t2Time carries out focusing shooting to the first estimation range of third camera to obtain the figure of third camera shooting
Picture, and judge the clarity of target object image in the image, S9 is jumped to when clarity is greater than first threshold;Otherwise, into
Enter step S6.
The above, the only preferred embodiment of this practical invention, cannot limit this practical invention practical range with this;It is all
According to simple equivalent changes and modifications made by scope of the present invention patent and creation description, the present invention should still belong to
In the range of patent covers.
Claims (1)
1. a kind of method for controlling the object clear image of cell monitoring camera photographic subjects, including a kind of monitoring system is provided, it should
The step of monitoring system includes the camera set on the cell and is stored with the characteristic information of target object, this method include:
S1: the first image of shooting, when monitoring system searches target object image according to the characteristic information in the first image,
The clarity for judging target object image jumps to S9 when clarity is more than or equal to first threshold, otherwise records target object
First position and enter S2;
S2: the second image is shot after shooting for the first image △ t1 time, monitoring system is according to the characteristic information in the second figure
When searching target object image as in, the clarity of target object image is judged, when clarity is more than or equal to first threshold
S9 is jumped to, the second position of target object is otherwise recorded and enters S3;
S3: third figure is shot after shooting for the second image △ t2 time according to the first position of target object and second position prediction
As when target object the third place, control shooting third image camera focus at the third place;Shooting the second image
Third image is shot after the △ t2 time, monitoring system searches target object image according to the characteristic information in third image
When, judge the clarity of target object image, jumps to S9 when clarity is more than or equal to first threshold;
S9: target object clear image is stored in monitoring system;
Wherein, which includes n platform camera, which is also stored with the 3D model in the cell monitoring section, the 3D
Model includes the distribution of road and camera;
Wherein, S1 and S2 is executed by the magazine first camera of the n platform;
Step S3 further includes S4: according to the characteristic information of the target object, the 3D model in cell monitoring section and first position
The first action prediction module of the target object is established with the second position;According to the first action prediction module of target object, in advance
The third place that survey target object occurs after the △ t2 time is in the first estimation range of the magazine second camera of n platform
On, monitoring system to second camera issue instruct, second camera after the △ t2 time to the first estimation range of second camera into
Row focusing shooting and judge the clarity of target object image in the second image to obtain third image, when clarity greater than etc.
S9 is jumped to when first threshold;Otherwise, S6 is entered step;
S6: setting the first estimation range of second camera is side length as the square of r, in the first estimation range of the second camera
Point centered on point establishes second estimation range of the square area as second camera that side length is 2r, according to feature letter
Breath is scanned in second estimation range, carries out focusing shooting to the target object if searching the target object;If searching
Rope is less than the target object, then by the point centered on the midpoint of second estimation range, establishes the square area that side length is 4r
As the third estimation range of second camera, the third using the characteristic information stored in monitoring system in the second camera is predicted
Region scans for, if searching the target object, carries out focusing shooting to the target object, and record the 4th of target object the
Position;
If search less than the target object, continues to expand region of search, until the secondary side length established of pth is the square of 2pr
Pth estimation range of the region as the second camera, the edge of the pth estimation range exceed the image border of camera shooting simultaneously
And step S7 is jumped to when still searching for less than the target object;
S7: from the 3D model in cell monitoring section in monitoring system search second camera position, by remaining n-1 platform camera with
Distance apart from the second camera is ranked up from the near to the distant, with the collating sequence, with the characteristic information of the target object to this
The image of a little cameras shootings successively scans for, and when searching the target object and appearing in the shooting image of third camera, sentences
Break the clarity of target object image in the image, jumps to S9 when clarity is greater than first threshold;Third camera is recorded to clap
The third place information for the target object in image taken the photograph simultaneously is transferred to step S8;
S8: monitoring system is according to the characteristic information of the target object, the 3D model in cell monitoring section and first position, second
It sets, the third place and the 4th position establish the second Motion prediction template;According to the second Motion prediction template of target object, prediction
Target object is in t2Time appears on the first estimation range of third camera, and monitoring system is issued to third camera and instructed, the
Three cameras are in t2Time carries out focusing shooting to the first estimation range of third camera to obtain the image of third camera shooting, and
The clarity for judging target object image in the image jumps to S9 when clarity is greater than first threshold;Otherwise, it enters step
S6。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610835194.6A CN106161968B (en) | 2016-09-20 | 2016-09-20 | A kind of method of cell monitoring platform courses camera shooting |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610835194.6A CN106161968B (en) | 2016-09-20 | 2016-09-20 | A kind of method of cell monitoring platform courses camera shooting |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106161968A CN106161968A (en) | 2016-11-23 |
CN106161968B true CN106161968B (en) | 2018-12-11 |
Family
ID=57341078
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610835194.6A Active CN106161968B (en) | 2016-09-20 | 2016-09-20 | A kind of method of cell monitoring platform courses camera shooting |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106161968B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110930340B (en) * | 2019-10-11 | 2023-09-29 | 成都华为技术有限公司 | Image processing method and device |
CN116468254B (en) * | 2023-06-14 | 2023-09-26 | 佳都科技集团股份有限公司 | Method and system for processing in-station emergency task data for rail transit |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103795909A (en) * | 2012-10-29 | 2014-05-14 | 株式会社日立制作所 | Shooting optimization device, image-pickup device and shooting optimization method |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1201803C (en) * | 2003-04-01 | 2005-05-18 | 方太祥 | Nasosinusitis treating Chinese medicine powder |
JP2014106732A (en) * | 2012-11-27 | 2014-06-09 | Sony Computer Entertainment Inc | Information processor and information processing method |
-
2016
- 2016-09-20 CN CN201610835194.6A patent/CN106161968B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103795909A (en) * | 2012-10-29 | 2014-05-14 | 株式会社日立制作所 | Shooting optimization device, image-pickup device and shooting optimization method |
Also Published As
Publication number | Publication date |
---|---|
CN106161968A (en) | 2016-11-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8736689B2 (en) | Imaging apparatus and image processing method | |
CN100550989C (en) | Self focusing device, image capture apparatus and auto-focus method | |
US8605942B2 (en) | Subject tracking apparatus, imaging apparatus and subject tracking method | |
EP1764622B1 (en) | Image pickup apparatus | |
CN103747179B (en) | A kind of zoom tracking and system based on focusing evaluation of estimate feedback regulation | |
CN105763795A (en) | Focusing method and apparatus, cameras and camera system | |
CN102209197A (en) | Imaging apparatus and imaging method | |
CN106161968B (en) | A kind of method of cell monitoring platform courses camera shooting | |
CN109886995B (en) | Multi-target tracking method in complex environment | |
CN101593353A (en) | Image processing method and equipment and video system | |
CN105430277B (en) | Autofocus control method and device | |
CN102023460B (en) | Quick focusing method for digital camera | |
CN106210548B (en) | A kind of method and device of rapid focus | |
CN105812649A (en) | Photographing method and device | |
CN107038686A (en) | A kind of method and apparatus of image mosaic processing | |
RU2005115276A (en) | DEVICE FOR TRACKING MOBILE ROBOT MOVEMENT AND METHOD FOR THIS | |
JP5665512B2 (en) | Imaging apparatus and main subject detection method | |
JP2017204795A (en) | Tracking apparatus | |
JP5127692B2 (en) | Imaging apparatus and tracking method thereof | |
CN103581553A (en) | Object ranging apparatus, imaging apparatus and object ranging method | |
JP2021057660A (en) | Image control device, imaging apparatus, and image control method | |
JP5858658B2 (en) | Imaging device | |
JP2008287648A (en) | Mobile body detection method and device, and monitoring device | |
JP6071561B2 (en) | Focus adjustment apparatus and method | |
JP5446660B2 (en) | Image recognition apparatus and imaging apparatus |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20200429 Address after: 200433 16th Floor, 127 Guodao Road, Yangpu District, Shanghai (Centralized Registration Place) Patentee after: Shanghai Xitu Information Technology Co., Ltd Address before: 200233, room 6, building 333, 802 Guiping Road, Shanghai, Xuhui District Patentee before: ZHAOKUANG TECHNOLOGY (SHANGHAI) Co.,Ltd. |