CN107016696A - A kind of passenger flow density detection method and device - Google Patents
A kind of passenger flow density detection method and device Download PDFInfo
- Publication number
- CN107016696A CN107016696A CN201710208108.3A CN201710208108A CN107016696A CN 107016696 A CN107016696 A CN 107016696A CN 201710208108 A CN201710208108 A CN 201710208108A CN 107016696 A CN107016696 A CN 107016696A
- Authority
- CN
- China
- Prior art keywords
- image
- passenger flow
- gray level
- video sequence
- intensity
- 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.)
- Pending
Links
Classifications
-
- 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
- G06T2207/30196—Human being; Person
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to the technical field of intensity of passenger flow detection, more particularly to the passenger flow density detection method based on image procossing, the step in this method, functional module can be set up, functional module construction is combined into, is mainly realized by storing computer program in a computer-readable storage medium.Video sequence image is obtained in the real-time video that the present invention was photographed from default monitored area, gray processing processing is carried out to the video sequence image, obtain corresponding gray level image, so as to highlight the difference of crowd's image and background image, in order to distinguish, gray level image is generated corresponding gray level co-occurrence matrixes, the textural characteristics of gray level co-occurrence matrixes are then calculated, classified finally according to textural characteristics, to obtain intensity of passenger flow grade so as to realize that real-time, clear, accurate intensity of passenger flow is detected.
Description
Technical field
The present invention relates to the technical field of intensity of passenger flow detection, more particularly to the intensity of passenger flow detection side based on image procossing
Step in method, this method, can set up functional module, be combined into functional module construction, mainly can by being stored in computer
The computer program in storage medium is read to realize.
Background technology
In recent years, the increasing with government to intelligent bus cause investment, China's intelligent Public Transportation System is first
Show an inkling, the important component that intensity of passenger flow detecting system is.
The detection of existing intensity of passenger flow is generally based on relation that number is directly proportional to pixel count to estimate crowd density
Method.Specific practice has two kinds, and a kind of is the background that the method subtracted first with background removes each image, is then calculated remaining
Total pixel number shared by crowd's image.It is another be the background that the method subtracted with background removes each image after, examined by edge
Survey method extracts the edge of single people, and edge is refined, and calculates the total pixel number at edge.But both approaches are due to people
Group's image is not easy clearly to distinguish sometimes with Background so that detection is likely to occur error.
The content of the invention
It is an object of the invention to provide a kind of fast and effectively passenger flow density detection method.
It is achieved through the following technical solutions foregoing invention purpose：
The present invention provides a kind of passenger flow density detection method, it is characterised in that comprise the following steps：
Step A1. obtains the real-time video of default monitored area, and obtains video sequence image from the real-time video, to described
Video sequence image carries out gray processing processing, obtains corresponding gray level image；
The gray level image is generated corresponding gray level co-occurrence matrixes by step A2.；
Step A3. calculates the characteristic value of the gray level co-occurrence matrixes, and this feature value is the textural characteristics of the video sequence image；
Step A4. is classified according to the textural characteristics, to obtain intensity of passenger flow grade.
Wherein, in step A1 specifically, median filter process is carried out to the video sequence image, to remove noise and do
Disturb.
Wherein, video capture is carried out using binocular camera.
Step in the passenger flow density detection method provided for the present invention, can set up functional module, be combined into function
Module frame, is mainly realized by storing computer program in a computer-readable storage medium.
Beneficial effect：Video sequence image is obtained in the real-time video that the present invention was photographed from default monitored area, to institute
State video sequence image and carry out gray processing processing, obtain corresponding gray level image, so as to highlight crowd's image and background image
Gray level image, in order to distinguish, is generated corresponding gray level co-occurrence matrixes by difference, and the texture for then calculating gray level co-occurrence matrixes is special
Levy, classified finally according to textural characteristics, to obtain intensity of passenger flow grade so as to realize that real-time, clear, accurate passenger flow is close
Degree detection.
Embodiment
The invention will be further described with the following Examples.
Video acquisition module is provided with passenger entrance AT STATION, it can monitor that passenger enters the stream of people at station, video
The real-time video real-time monitored is delivered to server by acquisition module, and server obtains video sequence figure according to time sequence accordingly
Picture, and gray processing processing is carried out to the video sequence image, corresponding gray level image is obtained, so as to highlight crowd's image and background
The difference of image, in order to distinguish, overcomes being not easy for traditional passenger flow density detection method crowd image and background image
Gray level image is generated corresponding gray level co-occurrence matrixes by the problem of difference, server, then calculates the texture of gray level co-occurrence matrixes
Feature（Such as local stationary characteristic value, contrast metric value, angular second moment characteristic value, degree of correlation characteristic value）, different densities
The corresponding textural characteristics of crowd's image are different：Highdensity crowd shows as thin pattern on textural characteristics；The crowd of low-density
Image shows as roughcast formula when background image is also low frequency on textural characteristics, can thus be divided according to textural characteristics
Class, is 5 classes by intensity of passenger flow grade classification to obtain intensity of passenger flow grade（Seldom, less, normally, it is many, a lot）.
In the present embodiment, median filter process is carried out to video sequence image, to remove noise and interference, so as to improve figure
The recognition effect of picture.
In the present embodiment, video acquisition module uses binocular camera stereoscopic vision（CCD）Design, compared to existing list
Camera video analytical technology precision and the degree of accuracy are higher；Binocular camera carries out integrated on same circuit board, and passes through phase
Same clock is synchronized, to ensure the uniformity of video acquisition；Binocular camera also includes being provided between lens mount, lens mount
Fixed metal fittings, to ensure the stability of camera, and can provide auxiliary for the radiating of camera lens.
Step in the passenger flow density detection method provided for the present invention, can set up functional module, be combined into function
Module frame, is mainly realized by storing computer program in a computer-readable storage medium.
Finally it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than to present invention guarantor
The limitation of scope is protected, although being explained with reference to preferred embodiment to the present invention, one of ordinary skill in the art should
Work as understanding, technical scheme can be modified or equivalent substitution, without departing from the reality of technical solution of the present invention
Matter and scope.
Claims (6)
1. a kind of passenger flow density detection method, it is characterised in that comprise the following steps：
Step A1. obtains the real-time video of default monitored area, and obtains video sequence image from the real-time video, to described
Video sequence image carries out gray processing processing, obtains corresponding gray level image；
The gray level image is generated corresponding gray level co-occurrence matrixes by step A2.；
Step A3. calculates the characteristic value of the gray level co-occurrence matrixes, and this feature value is the textural characteristics of the video sequence image；
Step A4. is classified according to the textural characteristics, to obtain intensity of passenger flow grade.
2. a kind of passenger flow density detection method according to claim 1, it is characterised in that, to institute in step A1 specifically
State video sequence image and carry out median filter process, to remove noise and interference.
3. a kind of passenger flow density detection method according to claim 1, it is characterised in that regarded using binocular camera
Frequency is shot.
4. a kind of intensity of passenger flow detection means, it is characterised in that including following device：
It obtains the real-time video of default monitored area to device A1., and obtains video sequence image from the real-time video, to institute
State video sequence image and carry out gray processing processing, obtain corresponding gray level image；
Its described gray level image of device A2. generates corresponding gray level co-occurrence matrixes；
The characteristic value of its calculating gray level co-occurrence matrixes of device A3., this feature value is special for the texture of the video sequence image
Levy；
Device A4. is classified according to the textural characteristics, to obtain intensity of passenger flow grade.
5. a kind of intensity of passenger flow detection means according to claim 4, it is characterised in that device A1 operations have image filtering
It carries out median filter process to device to the video sequence image, to remove noise and interference.
6. a kind of intensity of passenger flow detection means according to claim 4, it is characterised in that regarded using binocular camera
Frequency is shot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710208108.3A CN107016696A (en) | 2017-03-31 | 2017-03-31 | A kind of passenger flow density detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710208108.3A CN107016696A (en) | 2017-03-31 | 2017-03-31 | A kind of passenger flow density detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107016696A true CN107016696A (en) | 2017-08-04 |
Family
ID=59446645
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710208108.3A Pending CN107016696A (en) | 2017-03-31 | 2017-03-31 | A kind of passenger flow density detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107016696A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822893A (en) * | 2021-11-24 | 2021-12-21 | 中导光电设备股份有限公司 | Liquid crystal panel peripheral circuit detection method and system based on texture features |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102044073A (en) * | 2009-10-09 | 2011-05-04 | 汉王科技股份有限公司 | Method and system for judging crowd density in image |
| CN102496058A (en) * | 2011-11-11 | 2012-06-13 | 北京声迅电子股份有限公司 | Passenger flow density detection method |
| CN103839085A (en) * | 2014-03-14 | 2014-06-04 | 中国科学院自动化研究所 | Train carriage abnormal crowd density detection method |
| CN104077613A (en) * | 2014-07-16 | 2014-10-01 | 电子科技大学 | Crowd density estimation method based on cascaded multilevel convolution neural network |
| CN104268898A (en) * | 2014-09-15 | 2015-01-07 | 郑州天迈科技股份有限公司 | Method for detecting density of passengers in bus on basis of image analysis |
| CN104463121A (en) * | 2014-12-08 | 2015-03-25 | 北京市新技术应用研究所 | Crowd density information obtaining method |
-
2017
- 2017-03-31 CN CN201710208108.3A patent/CN107016696A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102044073A (en) * | 2009-10-09 | 2011-05-04 | 汉王科技股份有限公司 | Method and system for judging crowd density in image |
| CN102496058A (en) * | 2011-11-11 | 2012-06-13 | 北京声迅电子股份有限公司 | Passenger flow density detection method |
| CN103839085A (en) * | 2014-03-14 | 2014-06-04 | 中国科学院自动化研究所 | Train carriage abnormal crowd density detection method |
| CN104077613A (en) * | 2014-07-16 | 2014-10-01 | 电子科技大学 | Crowd density estimation method based on cascaded multilevel convolution neural network |
| CN104268898A (en) * | 2014-09-15 | 2015-01-07 | 郑州天迈科技股份有限公司 | Method for detecting density of passengers in bus on basis of image analysis |
| CN104463121A (en) * | 2014-12-08 | 2015-03-25 | 北京市新技术应用研究所 | Crowd density information obtaining method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822893A (en) * | 2021-11-24 | 2021-12-21 | 中导光电设备股份有限公司 | Liquid crystal panel peripheral circuit detection method and system based on texture features |
| CN113822893B (en) * | 2021-11-24 | 2022-03-11 | 中导光电设备股份有限公司 | Liquid crystal panel peripheral circuit detection method and system based on texture features |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9916646B2 (en) | System and method for processing input images before generating a high dynamic range image | |
| US9307134B2 (en) | Automatic setting of zoom, aperture and shutter speed based on scene depth map | |
| WO2019233264A1 (en) | Image processing method, computer readable storage medium, and electronic device | |
| US9686463B2 (en) | Systems and methods for continuous auto focus (CAF) | |
| CN112514373B (en) | Image processing apparatus and method for feature extraction | |
| CN108510540B (en) | Stereoscopic vision camera and height acquisition method thereof | |
| CN103279956B (en) | A kind of method detecting chip mounter components and parts positioning precision | |
| US10410368B1 (en) | Hybrid depth processing | |
| WO2013132951A1 (en) | Distance calculation device and distance calculation method | |
| JP6261266B2 (en) | Moving body detection device | |
| EP2591593A1 (en) | System and method for shot change detection in a video sequence | |
| CN106375706A (en) | Method and apparatus for velocity measurement of moving object by use of double pick-up heads, and terminal | |
| CN103763458B (en) | A kind of scene-change detecting method and device | |
| CN104349039A (en) | Video anti-jittering method and apparatus | |
| CN105046719A (en) | Method and system for video monitoring | |
| WO2020143499A1 (en) | Corner detection method based on dynamic vision sensor | |
| CN110689565B (en) | Depth map determination method and device and electronic equipment | |
| TWI496115B (en) | Video frame stabilization method for the moving camera | |
| CN107016696A (en) | A kind of passenger flow density detection method and device | |
| CN102034243B (en) | Method and device for acquiring crowd density map from video image | |
| CN115035168B (en) | Multi-constraint-based photovoltaic panel multi-source image registration method, device and system | |
| CN106101485A (en) | A kind of prospect track decision method based on feedback and device | |
| JP2011009857A (en) | Noise level measuring apparatus and image processor | |
| CN103841312B (en) | Object detecting apparatus and method | |
| KR20180125278A (en) | Apparatus and method for detecting pedestrian |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170804 |