CN107368789A - A kind of people flow rate statistical device and method based on Halcon vision algorithms - Google Patents
A kind of people flow rate statistical device and method based on Halcon vision algorithms Download PDFInfo
- Publication number
- CN107368789A CN107368789A CN201710469453.2A CN201710469453A CN107368789A CN 107368789 A CN107368789 A CN 107368789A CN 201710469453 A CN201710469453 A CN 201710469453A CN 107368789 A CN107368789 A CN 107368789A
- Authority
- CN
- China
- Prior art keywords
- people
- image
- halcon
- flow rate
- rate statistical
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 33
- 241001292396 Cirrhitidae Species 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000003287 optical effect Effects 0.000 claims abstract description 26
- 230000033001 locomotion Effects 0.000 claims abstract description 20
- 230000005540 biological transmission Effects 0.000 claims abstract description 5
- 230000000007 visual effect Effects 0.000 claims abstract description 5
- 238000007619 statistical method Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 3
- 230000014759 maintenance of location Effects 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 2
- 230000002045 lasting effect Effects 0.000 abstract description 3
- 238000005070 sampling Methods 0.000 abstract description 3
- 239000002699 waste material Substances 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
A kind of people flow rate statistical device based on Halcon vision algorithms disclosed by the invention, including image input module, computer, the display screen being sequentially connected；Wherein image input module includes real-time video input unit, video file input unit, by video data transmission to computer；Computer is detected and motion target tracking using the optical flow method of feature based and gradient to moving target；And vision algorithm is write by Halcon and handles image, flow of the people information is counted, then various functions are managed in the operation interface that Visual Studio are edited.The present invention can clap the number of the people in region by the camera in video data express statistic specified time, coordinated by multimachine and position relationship can directly calculate total flow of the people, error caused by sampling estimation totality can largely be avoided, realize being automatically brought into operation for machine, improve statistical efficiency, reduce manpower to waste, lasting statistics can be achieved.
Description
Technical field
The present invention relates to automation data to obtain field, more particularly to a kind of flow of the people system based on Halcon vision algorithms
Counter device and method.
Background technology
In the epoch of big data in length and breadth, who possesses data, and who just possesses first chance.People flow rate statistical data are to understand market letter
Breath, the one of developments is grasped sharp sword.The method of main flow statistics flow of the people is manpower collecting sample data, then passes through statistics
The overall data of method estimation.Require that sample can preferably reflect overall data, the estimation of use by statistical method estimation
Method is also required to scientific and reasonable, easily produces larger error.Market is fast changing simultaneously, and statistical condition is constantly all occurring
Change, needs to re-start statistics under new statistical condition, statistics is also required to exhaust substantial amounts of manpower and materials again.
The content of the invention
The shortcomings that it is an object of the invention to overcome prior art and deficiency, there is provided a kind of based on Halcon vision algorithms
People flow rate statistical device.
Another object of the present invention is to provide a kind of people flow rate statistical method based on Halcon vision algorithms.
The purpose of the present invention is realized by following technical scheme：
A kind of people flow rate statistical device based on Halcon vision algorithms, it is characterised in that：Including the image being sequentially connected
Input module, computer, display screen；Wherein
Image input module, including real-time video input unit, video file input unit, by video data transmission to meter
Calculation machine；
Computer, using feature based and the optical flow method of gradient, moving target is detected and motion target tracking；And
Vision algorithm is write by Halcon and handles image, counts flow of the people information, then the operation interface edited in Visual Studio
Middle management various functions；
Display screen, for display image and man-machine interaction.
The real-time video input unit includes monitoring camera.
The real-time video input unit also includes the polarizer on the camera lens of monitoring camera.Polarizer is used for
Eliminate reflective influence.
Another object of the present invention is realized by following technical scheme：
A kind of people flow rate statistical method based on Halcon vision algorithms, comprises the following steps：
S1, import video data；
S2, statistics flow of the people：
(1) open_framegrabber operators are used, in loop body, read in image successively from video data, are started
When choose head two field pictures；The image of each retention time rearward backward, read in new images, cover time forward one
Image；
(2) create_bg_esti operators are used, the data set for assessing background is generated with kalman filter method；
(3) image is pre-processed, first with smooth class operators or mean class operator smoothed images, removes noise；
Then gray-scale map and binary map are converted picture into, remain below matching characteristic with being used during data processing；
(4) optical flow field is calculated using optical_flow_mg operators, and stores optical flow field information；Then threshold is used
Operator splits optical flow field, detects moving target；
(5) background and extraction prospect are estimated according to background data set using run_bg_esti operators, at morphology
Reason method, the region of foreground object is partitioned into, has various features in region；
(6) combining step (4), (5), screen and store the feature and characteristic point of moving target；
(7) for any two adjacent video frames, the motion vector field that is drawn according to optical flow field, find in previous frame
The optimum position of existing key feature points in the current frame, this feature point is searched near the position of present frame, realizes target
Tracking；
(8) detect moving target and follow the trail of target, when target disappears in vision periphery, corresponding counter adds 1；
(9) according to multimachine cooperation and positional information, total flow of the people in random time is calculated.
It is described to detect moving target in step S2 (4) step by step, be specially：
Assuming that two pictures of existing H (x, y) and I (x, y), will obtain the motion of respective pixel in H to I；When setting object
Carve t and be located at (x, y) point, after Δ t, object is in t+ time Δts positioned at (x+ Δs x, y+ Δ y) points, then have：
L (x+ Δs x, y+ Δ y, t+ Δ t)=L (x, y, t)；
Image constraint equation is deployed using one-level Taylor's formula, obtained:
L (x+ Δs x, y+ Δ y, t+ Δ t)=L (x, y, t)+Δ L/ Δ x+ Δ L/ Δ y+ Δ L/ Δs t；
Drawn from equation:
δ L/ δ x* Δ x+ δ L/ δ y* Δ y+ δ L/ δ t* Δs t=0
In a small neighbourhood of (x, y), brightness constancy, then using least square method to all pixels point in neighborhood
Solve basic optical flow equation and draw optical flow field information；In the position for having object of which movement, optical flow field and surrounding are different, are led to
The contrast with foreground information is crossed, that is, detects moving target.
Motion target tracking is realized in (5) step by step, (6) of the step S2 jointly, is specially：
Characteristic point is extracted respectively to H figures and I figures, in two adjacent frames, corresponding characteristic point can only move the one of very little
Segment distance；The position that is moved to (x+u, y+v) of the pixel (x, y) in I in H, offset are (u, v)；By preceding
The characteristic point position of one frame nearby searches for new characteristic point, to match object, realizes target following.
In step S2 (1) step by step, described image is coloured image.Generally coloured image, but it is not limited to cromogram
Picture.
In step S2 (6) step by step, the feature and characteristic point of the moving target are included in region classes.
In step S2 (5) step by step, the Morphological scale-space method includes opening and closing operation, gray scale two-value.
The present invention compared with prior art, has the following advantages that and beneficial effect：
1st, the present invention applies machine for more accurate, more efficiently this problem of the conceptual data of statistics flow of the people, consideration
The means of vision count total flow of the people, realize the video data that appliance computer processing captures, count special time inside-paint
Flow of the people in face, then by multimachine cooperation and site location relation, calculate the flow of the people for needing to try to achieve.In order to more smart
Really, it is more efficient, more easily count total flow of the people using machine vision means, design a kind of people based on Halcon vision algorithms
Flow statistic device.Because Halcon is emerging machine vision software, there is operator more, fast compared to other image processing softwares
The advantages that degree is fast, programming is easy, and easily with Visual Studio interfaces, the easily configuration operation under various system environments.Make
Efficiency, increase precision can be improved with Halcon vision algorithms.
2nd, the present invention can clap the number of the people in region by the camera in video data express statistic specified time, lead to
Total flow of the people can directly be calculated by crossing multimachine cooperation and position relationship, can largely avoid sampling estimation is overall from being brought
Error, realize being automatically brought into operation for machine, improve statistical efficiency, reduce manpower and waste, lasting statistics can be achieved.
Brief description of the drawings
Fig. 1 is a kind of structural representation of the people flow rate statistical device based on Halcon vision algorithms of the present invention.
Fig. 2 is the flow chart of statistics flow of the people of the present invention.
Fig. 3 is target detection of the present invention and target tracking principle schematic.
Embodiment
With reference to embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are unlimited
In this.
Referring to Fig. 1, the present embodiment provides a kind of people flow rate statistical device based on halcon vision algorithms, including image is defeated
Enter module, computer and display screen.Image input module is responsible for image acquisition, is connected with computer；Display screen is responsible for man-machine friendship
Mutually and result is shown, be also connected with computer.
The image input module that the present embodiment provides supports real-time video input to be inputted with video file, can be by video data
It is transferred to computer.Wherein real-time video input unit is mainly monitoring camera, is aided with polarizer and eliminates reflective influence.
The core algorithm for the computer that the present embodiment provides is the optical flow method of feature based and gradient, is examined for moving target
Survey and motion target tracking.Other algorithms have：Image access transmission algorithm, Image Pretreatment Algorithm, feature extraction algorithm, gradient
Parser and managing data algorithm.
The display screen that the present embodiment provides is used for man-machine interaction and result is shown.
Referring to Fig. 2, the realization of people flow rate statistical is mainly made up of five parts：Image access transmission, image preprocessing, mesh
Mark detection, target tracking, data management.
Specifically implementation steps are：
(1) open_framegrabber operators are used, in loop body, are read in successively from camera or video file
Image (generally coloured image), head two field pictures are chosen during beginning.The image of each retention time rearward backward, read in
New images, a cover time forward image；
(2) create_bg_esti operators are used, the data set for assessing background is generated with kalman filter method.
(3) image is pre-processed, first with smooth class operators or mean class operator smoothed images, removes noise；
Then gray-scale map and binary map are converted picture into, remain below matching characteristic with being used during data processing.
(4) optical flow field is calculated using optical_flow_mg operators, and stores optical flow field information.Then threshold is used
Operator splits optical flow field, detects moving target.
(5) background and extraction prospect are estimated according to background data set using run_bg_esti operators, transported by being opened and closed
The Morphological scale-space methods such as calculation, gray scale two-value, the region of foreground object is partitioned into, has various features in region.
(6) comprehensive first two steps, screen and store the feature and characteristic point (being included in region classes) of moving target.
(7) for any two adjacent video frames, the motion vector field that is drawn according to optical flow field, find in previous frame
The optimum position of existing key feature points in the current frame, this feature point is searched near the position of present frame, realizes target
Tracking.
(8) detect moving target and follow the trail of target, when target disappears in vision periphery, corresponding counter adds 1.
(9) according to multimachine cooperation and positional information, total flow of the people in random time can be calculated.
Fig. 3 is target detection and target tracking principle schematic.
Its main method is optical flow method.Light stream is due to movement, the motion of camera of foreground target in itself in scene, or
It is the instantaneous velocity of pixel motion of the space motion object on observation imaging plane caused by both associated movements.Light
Stream method be using the correlation between change of the pixel in image sequence in time-domain and consecutive frame come find previous frame with
Existing corresponding relation between present frame, so as to calculate the movable information of object between consecutive frame.
Target detection：
Referring to Fig. 3, it is assumed that two pictures of existing H (x, y) and I (x, y), to obtain the motion of respective pixel in H to I.If
The earnest body moment, t was located at (x, y) point, and after Δ t, object is in t+ time Δts positioned at (x+ Δs x, y+ Δ y) points, then have：L(x+
Δ x, y+ Δ y, t+ Δ t)=L (x, y, t)
Image constraint equation is deployed using one-level Taylor's formula, we can obtain:
L (x+ Δs x, y+ Δ y, t+ Δ t)=L (x, y, t)+Δ L/ Δ x+ Δ L/ Δ y+ Δ L/ Δs t
It can be drawn from equation:
δ L/ δ x* Δ x+ δ L/ δ y* Δ y+ δ L/ δ t* Δs t=0
In a small neighbourhood of (x, y), brightness constancy, then can using least square method to all in neighborhood
Pixel solves basic optical flow equation and draws optical flow field information.In the position for having object of which movement, optical flow field and surrounding are to differ
Sample, pass through the contrast with foreground information, you can detect moving target.
Target tracking：
Referring to Fig. 3, we scheme to H and I figures extract characteristic point respectively.In two adjacent frames, corresponding characteristic point only can
One segment distance of mobile very little.As schemed, the position that is moved to (x+u, y+v) of the pixel (x, y) in I in H, offset
For (u, v).Can by searching for new characteristic point near the characteristic point position of former frame, to match object, realize target with
Track.
People flow rate statistical：
Pass through the algorithm of Object Detecting and Tracking, it is possible to achieve stream of people's total amount does not repeat in camera shooting picture
Calculate.Cooperation and place information further according to more cameras, can calculate total flow of the people by the flow of the people in each camera.
The present invention is the people flow rate statistical device based on Halcon vision algorithms, and people flow rate statistical is write by Halcon
Vision algorithm handles image, counts flow of the people information, then every work(is managed in the operation interface that Visual Studio are edited
Energy.The number of the people in region can be clapped by the camera in video data express statistic specified time using the present invention, is passed through
Multimachine coordinates and position relationship can directly calculate total flow of the people, can largely avoid caused by sampling estimation totality
Error.Being automatically brought into operation for machine is realized, improves statistical efficiency, manpower is reduced and wastes, lasting statistics can be achieved.
Above-described embodiment is the preferable embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, other any Spirit Essences without departing from the present invention with made under principle change, modification, replacement, combine, simplification,
Equivalent substitute mode is should be, is included within protection scope of the present invention.
Claims (9)
- A kind of 1. people flow rate statistical device based on Halcon vision algorithms, it is characterised in that：Image including being sequentially connected is defeated Enter module, computer, display screen；WhereinImage input module, including real-time video input unit, video file input unit, by video data transmission to calculating Machine；Computer, using feature based and the optical flow method of gradient, moving target is detected and motion target tracking；And pass through Halcon writes vision algorithm processing image, counts flow of the people information, then the operation interface middle pipe edited in Visual Studio Manage various functions；Display screen, for display image and man-machine interaction.
- 2. the people flow rate statistical device based on Halcon vision algorithms according to claim 1, it is characterised in that：It is described real-time Video input device includes monitoring camera.
- 3. the people flow rate statistical device based on Halcon vision algorithms according to claim 2, it is characterised in that：It is described real-time Video input device also includes the polarizer on the camera lens of monitoring camera.
- A kind of 4. people flow rate statistical method based on Halcon vision algorithms, it is characterised in that comprise the following steps：S1, import video data；S2, statistics flow of the people：(1) open_framegrabber operators are used, in loop body, read in image successively from video data, are selected during beginning Take a two field pictures；The image of each retention time rearward backward, read in new images, forward one figure of cover time Picture；(2) create_bg_esti operators are used, the data set for assessing background is generated with kalman filter method；(3) image is pre-processed, first with smooth class operators or mean class operator smoothed images, removes noise；Then Convert picture into gray-scale map and binary map, remain below matching characteristic with being used during data processing；(4) optical flow field is calculated using optical_flow_mg operators, and stores optical flow field information；Then threshold operators are used Split optical flow field, detect moving target；(5) background and extraction prospect are estimated according to background data set using run_bg_esti operators, by Morphological scale-space side Method, the region of foreground object is partitioned into, has various features in region；(6) combining step (4), (5), screen and store the feature and characteristic point of moving target；(7) for any two adjacent video frames, the motion vector field that is drawn according to optical flow field, find what is occurred in previous frame The optimum position of key feature points in the current frame, this feature point is searched near the position of present frame, realizes target tracking；(8) detect moving target and follow the trail of target, when target disappears in vision periphery, corresponding counter adds 1；(9) according to multimachine cooperation and positional information, total flow of the people in random time is calculated.
- 5. the people flow rate statistical method based on Halcon vision algorithms according to claim 4, it is characterised in that step S2's It is described to detect moving target step by step in (4), be specially：Assuming that two pictures of existing H (x, y) and I (x, y), will obtain the motion of respective pixel in H to I；Set object moment t positions In (x, y) point, after Δ t, object is in t+ time Δts positioned at (x+ Δs x, y+ Δ y) points, then have：L (x+ Δs x, y+ Δ y, t+ Δ t)=L (x, y, t)；Image constraint equation is deployed using one-level Taylor's formula, obtained:L (x+ Δs x, y+ Δ y, t+ Δ t)=L (x, y, t)+Δ L/ Δ x+ Δ L/ Δ y+ Δ L/ Δs t；Drawn from equation:δ L/ δ x* Δ x+ δ L/ δ y* Δ y+ δ L/ δ t* Δs t=0In a small neighbourhood of (x, y), brightness constancy, then all pixels point in neighborhood is solved using least square method Basic optical flow equation draws optical flow field information；In the position for having object of which movement, optical flow field and surrounding be it is different, by with The contrast of foreground information, that is, detect moving target.
- 6. the people flow rate statistical method based on Halcon vision algorithms according to claim 5, it is characterised in that the step Motion target tracking is realized in S2 (5) step by step, (6) jointly, is specially：Characteristic point is extracted respectively to H figures and I figures, in two adjacent frames, corresponding characteristic point can only move one section of very little away from From；The position that is moved to (x+u, y+v) of the pixel (x, y) in I in H, offset are (u, v)；By in former frame Characteristic point position nearby search for new characteristic point, to match object, realize target following.
- 7. the people flow rate statistical method based on Halcon vision algorithms according to claim 4, it is characterised in that step S2's Step by step in (1), described image is coloured image.
- 8. the people flow rate statistical method based on Halcon vision algorithms according to claim 4, it is characterised in that step S2's Step by step in (6), the feature and characteristic point of the moving target are included in region classes.
- 9. the people flow rate statistical method based on Halcon vision algorithms according to claim 4, it is characterised in that step S2's Step by step in (5), the Morphological scale-space method includes opening and closing operation, gray scale two-value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710469453.2A CN107368789B (en) | 2017-06-20 | 2017-06-20 | People flow statistical device and method based on Halcon visual algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710469453.2A CN107368789B (en) | 2017-06-20 | 2017-06-20 | People flow statistical device and method based on Halcon visual algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107368789A true CN107368789A (en) | 2017-11-21 |
| CN107368789B CN107368789B (en) | 2021-01-19 |
Family
ID=60305383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710469453.2A Expired - Fee Related CN107368789B (en) | 2017-06-20 | 2017-06-20 | People flow statistical device and method based on Halcon visual algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107368789B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921072A (en) * | 2018-06-25 | 2018-11-30 | 苏州欧普照明有限公司 | A kind of the people flow rate statistical method, apparatus and system of view-based access control model sensor |
| CN110191554A (en) * | 2019-05-21 | 2019-08-30 | 安徽理工大学 | A kind of road lamp system based on PLC gradual change light modulation and machine vision |
| CN111369596A (en) * | 2020-02-26 | 2020-07-03 | 华南理工大学 | Escalator passenger flow volume statistical method based on video monitoring |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093198A (en) * | 2013-01-15 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Crowd density monitoring method and device |
| CN104036301A (en) * | 2014-06-11 | 2014-09-10 | 北京中慧煌技术有限公司 | Optical flow block feature based violence incident recognition method and system |
| US20150178570A1 (en) * | 2012-06-28 | 2015-06-25 | International Business Machines Corporation | Detection of static object on thoroughfare crossings |
| CN105632170A (en) * | 2014-11-26 | 2016-06-01 | 安徽中杰信息科技有限公司 | Mean shift tracking algorithm-based traffic flow detection method |
| CN106611157A (en) * | 2016-11-17 | 2017-05-03 | 中国石油大学(华东) | Multi-people posture recognition method based on optical flow positioning and sliding window detection |
-
2017
- 2017-06-20 CN CN201710469453.2A patent/CN107368789B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150178570A1 (en) * | 2012-06-28 | 2015-06-25 | International Business Machines Corporation | Detection of static object on thoroughfare crossings |
| CN103093198A (en) * | 2013-01-15 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Crowd density monitoring method and device |
| CN104036301A (en) * | 2014-06-11 | 2014-09-10 | 北京中慧煌技术有限公司 | Optical flow block feature based violence incident recognition method and system |
| CN105632170A (en) * | 2014-11-26 | 2016-06-01 | 安徽中杰信息科技有限公司 | Mean shift tracking algorithm-based traffic flow detection method |
| CN106611157A (en) * | 2016-11-17 | 2017-05-03 | 中国石油大学(华东) | Multi-people posture recognition method based on optical flow positioning and sliding window detection |
Non-Patent Citations (5)
| Title |
|---|
| 张水发等: "双模型背景建模与目标检测研究", 《计算机研究与发展》 * |
| 徐正洲: "基于计算机视觉的目标跟踪预测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 朱志宇: "《流形粒子滤波算法及其在视频目标跟踪中的应用》", 31 May 2015, 国防工业出版 * |
| 汤石晨: "基于光流法的视频人数统计方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 雷帮军等: "《视频目标跟踪系统分步详解》", 31 December 2015, 国防工业出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921072A (en) * | 2018-06-25 | 2018-11-30 | 苏州欧普照明有限公司 | A kind of the people flow rate statistical method, apparatus and system of view-based access control model sensor |
| CN108921072B (en) * | 2018-06-25 | 2021-10-15 | 苏州欧普照明有限公司 | People flow statistical method, device and system based on visual sensor |
| CN110191554A (en) * | 2019-05-21 | 2019-08-30 | 安徽理工大学 | A kind of road lamp system based on PLC gradual change light modulation and machine vision |
| CN111369596A (en) * | 2020-02-26 | 2020-07-03 | 华南理工大学 | Escalator passenger flow volume statistical method based on video monitoring |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107368789B (en) | 2021-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106096577B (en) | A kind of target tracking method in camera distribution map | |
| Song et al. | Real-time tunnel crack analysis system via deep learning | |
| CN104361327B (en) | A kind of pedestrian detection method and system | |
| CN104270570B (en) | Binocular camera and its image processing method | |
| JP5213105B2 (en) | Video network system and video data management method | |
| CN103268480B (en) | A kind of Visual Tracking System and method | |
| CN102915432B (en) | A kind of vehicle-mounted microcomputer image/video data extraction method and device | |
| CN107368789A (en) | A kind of people flow rate statistical device and method based on Halcon vision algorithms | |
| CN104978567B (en) | Vehicle checking method based on scene classification | |
| CN103024281A (en) | Infrared and visible video integration system | |
| CN102043953A (en) | Real-time-robust pedestrian detection method aiming at specific scene | |
| CN107660039A (en) | A kind of lamp control system for identifying dynamic gesture | |
| CN110084243A (en) | It is a kind of based on the archives of two dimensional code and monocular camera identification and localization method | |
| CN108363482A (en) | A method of the three-dimension gesture based on binocular structure light controls smart television | |
| CN107784838A (en) | A kind of traffic offence dynamic identifying method and system | |
| CN103942843A (en) | Fairway and ship three-dimensional model dynamic presenting method based on video | |
| US11003963B2 (en) | Method and system for identifying targets in scenes shot by a camera | |
| CN102307297A (en) | Intelligent monitoring system for multi-azimuth tracking and detecting on video object | |
| CN107909599A (en) | A kind of object detecting and tracking system | |
| CN110087042A (en) | A kind of face snap method and system of real-time synchronization video flowing and metadata | |
| CN102538759B (en) | Method for fully-automatically catching near earth and medium and high orbit space targets in real time | |
| CN202231803U (en) | Intelligent monitoring system for multi-aspect video object tracking detection | |
| CN117824624B (en) | Indoor tracking and positioning method, system and storage medium based on face recognition | |
| CN108009491A (en) | A kind of object recognition methods solved in fast background movement and system | |
| CN103006332B (en) | Scalpel tracking method and device and digital stereoscopic microscope system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210119 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |