CN105959639B - Pedestrian's monitoring method in avenue region based on ground calibration - Google Patents
Pedestrian's monitoring method in avenue region based on ground calibration Download PDFInfo
- Publication number
- CN105959639B CN105959639B CN201610395781.8A CN201610395781A CN105959639B CN 105959639 B CN105959639 B CN 105959639B CN 201610395781 A CN201610395781 A CN 201610395781A CN 105959639 B CN105959639 B CN 105959639B
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- region
- avenue
- activity
- target area
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Abstract
The present invention provide it is a kind of based on ground calibration avenue region in pedestrian's monitoring method, the following steps are included: step 1, segmentation object region: to the ground areas for being partitioned into pedestrian activity in the monitoring scene in avenue region, ground calibration is carried out as target area；Step 2 is monitored target area: the camera for being used to photographic subjects region being connected with background server, server is equipped with positioning device, recording device, analytical equipment and control device, and positioning device is for positioning target area；Recording device is used to record pedestrian activity's situation in target area, including shape color, motion state and azimuth information；Analytical equipment is used to analyze the feature of pedestrian, including shape, color, motion state and azimuth information.
Description
Technical field
It the present invention relates to the use of the technology that camera is monitored pedestrian in avenue region, it is specifically a kind of to be based on
Pedestrian's monitoring method in the avenue region of ground calibration.
Background technique
With the development of information technology and universal, camera in avenue region in obtained large-scale laying.
The monitoring carried out using these cameras plays the guarantee of the safety of daily life in avenue region more and more important
Effect.In specific monitoring, the monitoring to pedestrian in avenue region is one piece of wherein mostly important content.But
Because more complicated to the image analysis of the monitoring of pedestrian in avenue region, it is difficult to accomplish to handle in real time.At present to camera shooting
The utilization of head monitoring often has thing that access has occurred to use, do so efficiency sometimes and effect and be not it is obvious that
The effect of processing and accident prevention in time is not achieved.The operating rate and effect of pedestrian's monitoring in avenue region are improved at present
Rate makes it have more the development trend that real-time is monitoring work in avenue region.
By taking Fig. 1 as an example, we can have found that the range monitored is very big in entire avenue region in monitored picture,
But the movable region (such as black line institute target area in figure) of pedestrian institute energy only accounts for very small part therein.If in city
A large amount of resource and time can be wasted by carrying out analysis and target pedestrian searching to whole region when monitoring in city, region, street,
Pedestrian's monitoring system is set to lose the effect of real-time.But if our monitor videos in avenue region divide
When analysis, the range being only likely to occur to monitored picture pedestrian is calculated, and can largely improve work in this way
Efficiency improves the real-time of system.
In view of discussed above, it is proposed that pedestrian monitoring technology side in a kind of avenue region based on ground calibration
Case.
Summary of the invention
The present invention provides a kind of based on ground calibration to solve drawbacks described above and deficiency existing in the prior art
Pedestrian's monitoring method in avenue region, this method monitoring efficiency is high and result precision is high, and effectively reduces to money
The waste in source, real-time are high.
In order to solve the above technical problems, the present invention provide it is a kind of based on ground calibration avenue region in pedestrian monitoring
Method, comprising the following steps:
Step 1, segmentation object region: to the ground for being partitioned into pedestrian activity in the monitoring scene in avenue region
Range carries out ground calibration as target area；
Step 2 is monitored target area: the camera for being used to photographic subjects region is connected with background server,
Server is equipped with positioning device, recording device, analytical equipment and control device, and positioning device is for positioning target area；Record
Device is used to record pedestrian activity's situation in target area, including shape color, motion state and azimuth information；Analysis dress
Set the feature for analyzing pedestrian, including shape, color, motion state and azimuth information.
Wherein, living to the pedestrian in monitoring scene using Algorithms for Automatic Classification when segmentation object region in the step 1
Dynamic ground areas is demarcated, and target area need to meet two conditions: one, target area is in the effective monitoring region of camera
It is interior；Two, the scope of activities region of all pedestrians is covered in target area.
The division methods of pedestrian activity range areas the following steps are included:
A. the shade of the monitoring scene video in avenue region is eliminated, forms the background in original video region
Interface；
B. the background interface to the monitoring scene video in avenue region and the video clip with pedestrian activity into
Row analysis, determines the activity trail of pedestrian；
C. the scope of activities of pedestrian in the monitoring scene in avenue region is determined by the activity trail of pedestrian, and is carried out
Ground calibration, the region of calibration are the target area of pedestrian activity.
Step a is specifically, the monitoring background video first in one section of avenue region of acquisition includes as original video
There is n frame background picture, wherein n is the number of frame in the monitoring background video obtained；Then again with n frame background picture pixel
Average value replaces each color vector of pixel in each background picture, forms new pixel, reaches the mesh for eliminating shade
, to form original background interface.
Step b is specifically, have the set S:{ s of the frame of pedestrian activity in setting video1,s2,s3...sm, then the work of pedestrian
The set A of dynamic trace, calculation formula are as follows:
A:{a1,a2,a3...am}=b-S:{ s1,s2,s3...sm}
Wherein, b is the background interface of video.
Step c specifically, firstly, by with pedestrian activity's trace video clip color space conversion be the space HSL,
Conversion formula is as follows:
Wherein, three components in the space HSL: h is form and aspect, and s is saturation degree, and l is brightness；Three points in colored rgb space
Amount: r represents red；G represents green；B represents blue；
Then, average value H, S and L of the space pedestrian trace HSL three components of pixel are found out, and by the pixel at background interface
Operation is carried out with the average value and obtains ground calibration, and operational formula is as follows:
abs(H-h)<1and abs(S-s)<1and abs(L-l)<10
Operation result is the target area of pedestrian activity's trace.
Present invention advantageous effects achieved: the present invention is provided in a kind of avenue region based on ground calibration
Pedestrian's monitoring method, this method monitoring efficiency is high and result precision is high, and effectively reduces the waste to resource, real-time
It is high.
Detailed description of the invention
Fig. 1 flow diagram of the present invention；
Fig. 2 embodiments of the present invention original background frame；
Fig. 3 embodiments of the present invention pedestrian activity's frame；
Shadow removing is carried out to original background frame in Fig. 4 embodiments of the present invention and does not carry out shadow removing comparison diagram；
The pedestrian activity's trace figure extracted in Fig. 5 embodiments of the present invention.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
As shown in Figure 1, the present invention provide it is a kind of based on ground calibration avenue region in pedestrian's monitoring method, including
Following steps:
Step 1, segmentation object region: to the ground for being partitioned into pedestrian activity in the monitoring scene in avenue region
Range carries out ground calibration as target area；
When segmentation object region, marked using ground areas of the Algorithms for Automatic Classification to the pedestrian activity in monitoring scene
Fixed, target area need to meet two conditions: one, target area is in the effective monitoring region of camera；Two, target area is covered
The scope of activities region of all pedestrians.
The division methods of pedestrian activity range areas the following steps are included:
A. the shade of the monitoring scene video in avenue region is eliminated, forms the background in original video region
Interface, shade not only influence ground calibration, can also bring difficulty to the monitoring analysis of pedestrian；As the embodiment of the present invention,
As shown in Fig. 2, being the original background frame of a certain street monitor video.
The monitoring background video in one section of avenue region is obtained first as original video, includes n frame Background
Piece；Then each color vector of pixel in each background picture is replaced with the average value of n frame background picture pixel again, is formed
New pixel achievees the purpose that eliminate shade, to form original background interface.Eradicating efficacy is as shown in Figure 4, wherein M
For the background interface for not eliminating shade, N is the background interface eliminated after shade.
B. the background interface to the monitoring scene video in avenue region and the video clip with pedestrian activity into
Row analysis, determines the activity trail of pedestrian, as shown in Figure 3；
The set S:{ s of frame in setting video with pedestrian activity1,s2,s3...sm, then the set of the activity trail of pedestrian
A, calculation formula are as follows:
A:{a1,a2,a3...am}=b-S:{ s1,s2,s3...sm}
Wherein, b is the background interface of video.
C. the scope of activities of pedestrian in the monitoring scene in avenue region is determined by the activity trail of pedestrian, and is carried out
Ground calibration, the region of calibration are the target area of pedestrian activity, as shown in Figure 5；
Firstly, being the space HSL by the color space conversion of the video clip with pedestrian activity's trace, conversion formula is such as
Under:
Wherein, three components in the space HSL: h is form and aspect, and s is saturation degree, and l is brightness；Three points in colored rgb space
Amount: r represents red；G represents green；B represents blue；
Then, average value H, S and L of the space pedestrian trace HSL three components of pixel are found out, and by the pixel at background interface
Operation is carried out with the average value and obtains ground calibration, and operational formula is as follows:
abs(H-h)<1and abs(S-s)<1and abs(L-l)<10
Operation result is the target area of pedestrian activity's trace.
Step 2 is monitored target area: the camera for being used to photographic subjects region is connected with background server,
Server is equipped with positioning device, recording device, analytical equipment and control device, and positioning device is for positioning target area；Record
Device is used to record pedestrian activity's situation in target area, including shape color, motion state and azimuth information；Analysis dress
Set the feature for analyzing pedestrian, including shape, color, motion state and azimuth information.
Advantageous effects in order to better illustrate the present invention, scene in conjunction with the embodiments as shown in Figure 2-5 carry out more
Detailed description:
Fig. 2 is the original background frame of a certain street monitor video, carries out shadow removing to the picture of Fig. 2 and does not carry out shade
The comparison of elimination is as shown in figure 4, by extracting pedestrian activity's trace shown in Fig. 3 with pedestrian activity after carrying out shadow removing
Mark, as shown in Figure 5.The results show that this method monitoring efficiency is high and result precision height, picture are clear.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (3)
1. pedestrian's monitoring method in the avenue region based on ground calibration, which comprises the following steps:
Step 1, segmentation object region: to the ground areas for being partitioned into pedestrian activity in the monitoring scene in avenue region,
Ground calibration is carried out as target area；
Step 2 is monitored target area: the camera for being used to photographic subjects region being connected with background server, is serviced
Device is equipped with positioning device, recording device, analytical equipment and control device, and positioning device is for positioning target area；Recording device
For recording pedestrian activity's situation in target area, including shape color, motion state and azimuth information；Analytical equipment is used
In the feature of analysis pedestrian, including shape, color, motion state and azimuth information；
In the step 1, when segmentation object region, using Algorithms for Automatic Classification to the ground of the pedestrian activity in monitoring scene
Range is demarcated, and target area need to meet two conditions: one, target area is in the effective monitoring region of camera；Two, mesh
Cover the scope of activities region of all pedestrians in mark region；
The division methods of pedestrian activity range areas the following steps are included:
A. the shade of the monitoring scene video in avenue region is eliminated, forms background circle in original video region
Face；
B. the background interface to the monitoring scene video in avenue region and the video clip with pedestrian activity are divided
Analysis, determines the activity trail of pedestrian；
C. the scope of activities of pedestrian in the monitoring scene in avenue region is determined by the activity trail of pedestrian, and carries out ground
Calibration, the region of calibration are the target area of pedestrian activity；
Step c specifically, firstly, the colored rgb space of video clip with pedestrian activity's trace is converted to the space HSL,
Conversion formula is as follows:
Wherein, three components in the space HSL: h is form and aspect, and s is saturation degree, and l is brightness；Three components in colored rgb space: r
Represent red；G represents green；B represents blue；
Then, average value H, S and L of the space pedestrian activity trace HSL three components of pixel are found out, and by each of background interface
A pixel and the average value carry out operation and obtain ground calibration, and operational formula is as follows:
abs(H-h)<1and abs(S-s)<1and abs(L-l)<10
Operation result meets the target area that above-mentioned operational formula is pedestrian activity's trace in background interface.
2. pedestrian's monitoring method in the avenue region according to claim 1 based on ground calibration, it is characterised in that: step
Rapid a is specifically, the monitoring background video first in one section of avenue region of acquisition includes n frame background as original video
Picture, wherein n is the number of frame in the monitoring background video obtained；Then it is replaced again with the average value of n frame background picture pixel
Each color vector of pixel, forms new pixel in each background picture, achievees the purpose that eliminate shade, to be formed
Original background interface.
3. pedestrian's monitoring method in the avenue region according to claim 1 based on ground calibration, it is characterised in that: step
Rapid b is specifically, have the set S:{ s of the frame of pedestrian activity in setting video1,s2,s3...sm, then the collection of the activity trail of pedestrian
A is closed, calculation formula is as follows:
A:{a1,a2,a3...am}=b-S:{ s1,s2,s3...sm}
Wherein, b is the background interface of video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610395781.8A CN105959639B (en) | 2016-06-06 | 2016-06-06 | Pedestrian's monitoring method in avenue region based on ground calibration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610395781.8A CN105959639B (en) | 2016-06-06 | 2016-06-06 | Pedestrian's monitoring method in avenue region based on ground calibration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105959639A CN105959639A (en) | 2016-09-21 |
| CN105959639B true CN105959639B (en) | 2019-06-14 |
Family
ID=56908781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610395781.8A Active CN105959639B (en) | 2016-06-06 | 2016-06-06 | Pedestrian's monitoring method in avenue region based on ground calibration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105959639B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108491818B (en) * | 2018-03-30 | 2019-07-05 | 北京三快在线科技有限公司 | Detection method, device and the electronic equipment of target object |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201059A (en) * | 2011-05-20 | 2011-09-28 | 北京大学深圳研究生院 | Pedestrian detection method and device |
| CN102332157A (en) * | 2011-06-15 | 2012-01-25 | 夏东 | Method for eliminating shadow |
| JP2012242993A (en) * | 2011-05-18 | 2012-12-10 | Nissan Motor Co Ltd | Moving body monitoring device and moving body monitoring method |
| CN102930719A (en) * | 2012-10-09 | 2013-02-13 | 北京航空航天大学 | Video image foreground detection method for traffic intersection scene and based on network physical system |
| CN103324913A (en) * | 2013-05-29 | 2013-09-25 | 长安大学 | Pedestrian event detection method based on shape features and trajectory analysis |
| CN103400371A (en) * | 2013-07-09 | 2013-11-20 | 河海大学 | Multi-camera synergistic monitoring equipment and method |
-
2016
- 2016-06-06 CN CN201610395781.8A patent/CN105959639B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012242993A (en) * | 2011-05-18 | 2012-12-10 | Nissan Motor Co Ltd | Moving body monitoring device and moving body monitoring method |
| CN102201059A (en) * | 2011-05-20 | 2011-09-28 | 北京大学深圳研究生院 | Pedestrian detection method and device |
| CN102332157A (en) * | 2011-06-15 | 2012-01-25 | 夏东 | Method for eliminating shadow |
| CN102930719A (en) * | 2012-10-09 | 2013-02-13 | 北京航空航天大学 | Video image foreground detection method for traffic intersection scene and based on network physical system |
| CN103324913A (en) * | 2013-05-29 | 2013-09-25 | 长安大学 | Pedestrian event detection method based on shape features and trajectory analysis |
| CN103400371A (en) * | 2013-07-09 | 2013-11-20 | 河海大学 | Multi-camera synergistic monitoring equipment and method |
Non-Patent Citations (1)
| Title |
|---|
| 场景信息估计与遮挡条件下目标跟踪问题研究;朱琳;《中国博士学位论文全文数据库 信息科技辑》;20100215(第2期);全文 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105959639A (en) | 2016-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070033B (en) | Method for detecting wearing state of safety helmet in dangerous working area in power field | |
| CN109657575B (en) | Intelligent video tracking algorithm for outdoor constructors | |
| CN106650620B (en) | A kind of target person identification method for tracing using unmanned plane monitoring | |
| WO2020029921A1 (en) | Monitoring method and device | |
| CN101236606B (en) | Shadow cancelling method and system in vision frequency monitoring | |
| CN108419014A (en) | The method for capturing face using panoramic camera and the linkage of Duo Tai candid cameras | |
| CN109918971B (en) | Method and device for detecting number of people in monitoring video | |
| KR20140095333A (en) | Method and apparratus of tracing object on image | |
| CN112149513A (en) | Industrial manufacturing site safety helmet wearing identification system and method based on deep learning | |
| CN103942539B (en) | A kind of oval accurate high efficiency extraction of head part and masking method for detecting human face | |
| CN104050480A (en) | Cigarette smoke detection method based on computer vision | |
| CN103258232A (en) | Method for estimating number of people in public place based on two cameras | |
| CN106682596A (en) | Violation fishing monitoring method based on video image analysis | |
| CN103996203A (en) | Method and device for detecting whether face in image is sheltered | |
| CN112347814A (en) | Passenger flow estimation and display method, system and computer readable storage medium | |
| CN103226860A (en) | Passage passenger traffic density estimation method | |
| CN110544259B (en) | Method for detecting disguised human body target under complex background based on computer vision | |
| CN105635696A (en) | Statistical method and device | |
| CN111242025A (en) | Action real-time monitoring method based on YOLO | |
| CN110288623A (en) | The data compression method of unmanned plane marine cage culture inspection image | |
| CN112287823A (en) | Facial mask identification method based on video monitoring | |
| CN115035088A (en) | Helmet wearing detection method based on yolov5 and posture estimation | |
| CN106599880A (en) | Discrimination method of the same person facing examination without monitor | |
| Chen et al. | Robust license plate detection in nighttime scenes using multiple intensity IR-illuminator | |
| CN104318240A (en) | Flower bud discriminating method based on computer vision |
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 |
Effective date of registration: 20211229 Address after: 214191 unit 3, jinhuwan Shijia, Dongbei Tang, Xishan District, Wuxi City, Jiangsu Province Patentee after: WUXI XIELIAN INFORMATION TECHNOLOGY CO.,LTD. Address before: 1 No. 211167 Jiangsu city of Nanjing province Jiangning Science Park Hongjing Road Patentee before: NANJING INSTITUTE OF TECHNOLOGY |
|
| TR01 | Transfer of patent right |