CN105279821A - Pedestrian counting method based on angle gray level information - Google Patents
Pedestrian counting method based on angle gray level information Download PDFInfo
- Publication number
- CN105279821A CN105279821A CN201410351238.9A CN201410351238A CN105279821A CN 105279821 A CN105279821 A CN 105279821A CN 201410351238 A CN201410351238 A CN 201410351238A CN 105279821 A CN105279821 A CN 105279821A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- optical flow
- angle
- input picture
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention belongs to the technical field of computer vision, and discloses a pedestrian counting method based on angle gray level information. The pedestrian counting method comprises the steps: a binary image R (x, y) and an optical flow field Gof (x, y) of an input image perform a collation operation, optical flow field angle information [theta]i of a pedestrian movement area is obtained, and angle gray level information fint (x, y) is calculated, and an angle gray level histogram is calculated through the angle gray level information fint (x, y); and finally the pedestrian movement direction of the moving pedestrian area is segmented through the angle gray level histogram, and the people numbers of moving pedestrians in all directions are counted by using a linear regression analysis method. By the method, the pedestrian movement area in a public area is divided into two categories of a 'coming-in' category and a 'going-out' category, so that the system overheads of a computer is significantly reduced, and the statistic efficiency and accuracy of the people number of the pedestrians in the public area are improved.
Description
Technical field
The invention belongs to technical field of computer vision, particularly a kind of pedestrian counting method based on angle half-tone information.
Background technology
In a lot of industry, people information can provide crucial foundation for people's flow management, resource management, management decision.Such as at subway station, stream of people's size of each website can be understood in real time by people counting, flexible dispatching subway train density, implement people's current control, the crowded regional information of real-time release, is conducive to reinforcement crowd conevying efficiency, guarantees that metro operation is steadily effective.
In market, flow of the people embodies the important evidence of its commercial value, to the accurate calculating of flow of the people, is conducive to the shopping preferences grasping guest, thus realizes better logistics arrangement, can also according to the crowd is dense in each region degree, effective coordination service personnel.Flow of the people is also related to the safety problem in crowded place, and crowd's quantity in effective controlling filed, in emergency circumstances can dredge rapidly crowd in fire alarm etc., avoids situation generations such as trampling, push.
In technical field of computer vision, be one of hot research direction wherein to the statistics of pedestrian's number.Pedestrian's number in public domain is effectively added up, important reference frame can be provided to multiple field such as business, security.In prior art, be generally the video streaming image comprising pedestrian obtained by video camera or camera in public domain, and the frame in video streaming image processed, to count pedestrian's number.Because video stream file is usually very huge, therefore cause to the Computing process more complicated in the statistic processes of pedestrian's number in public domain in prior art, system overhead when causing computing machine to process frame by frame the single-frame images in video stream file is larger.
In view of this, be necessary to be improved the demographic method in public domain in prior art, to solve above-mentioned technology flaw.
Summary of the invention
The object of the present invention is to provide a kind of pedestrian counting method based on angle half-tone information, reduce the system overhead carrying out counting computer-chronograph to the pedestrian in public domain, and improve efficiency and the accuracy of in public domain, pedestrian being carried out to demographics.
For achieving the above object, the invention provides a kind of pedestrian counting method based on angle half-tone information, the method comprises the following steps:
The video streaming image of S1, acquisition guarded region is as input picture;
S2, global optical flow method being combined with frame differential method acts on input picture, obtains the binary image R (x, y) comprising pedestrian movement region;
S3, by the optical flow field G of binary image R (x, y) and input picture
of(x, y) does and computing, obtains the optical flow field angle information θ in pedestrian movement region
i, obtain angle half-tone information f according to following formulae discovery
int(x, y) to calculate its angle grey level histogram,
S4, utilize angle grey level histogram to motion pedestrian region pedestrian movement direction split;
S5, linear regression analysis method statistic all directions are utilized to move the number of pedestrian.
As a further improvement on the present invention, " global optical flow method " in described step S2 is specially:
Utilize global optical flow method to carry out the calculating of global optical flow field to the input picture obtained in step S1, obtain the optical flow field G of input picture
of(x, y), and the Gaussian filter utilizing window size to be 5*5 carries out gaussian filtering process to the optical flow field of input picture, is then obtained the bianry image R of input picture optical flow field by Threshold segmentation
of(x, y).
As a further improvement on the present invention, the computing formula of described " Threshold segmentation " is specially:
Wherein, threshold value Th
of=0.05; The speed span of light stream is [0,1].
As a further improvement on the present invention, " frame differential method " in described step S2 is specially: the input picture obtained according to step S1, utilizes current frame image and previous frame image to make calculus of differences by following formula, to obtain difference image,
D
k(x，y)＝F
k(x，y)-F
k-1(x，y)
Wherein, F
k-1(x, y) is the gray-scale value of pixel in previous frame image, F
k(x, y) is the gray-scale value of pixel in current frame image, D
kthe difference image that (x, y) is the two.
As a further improvement on the present invention, described step S2 also comprises: the binary image R (x, y) comprising pedestrian movement region is made Morphological scale-space.
As a further improvement on the present invention, described Morphological scale-space is specially and first carries out dilation operation to the binary image R (x, y) in pedestrian movement region, after carry out erosion operation; Wherein, the expansion parameters in dilation operation is 7, and the corrosion parameter in erosion operation is 3.
As a further improvement on the present invention, described step S4 is specially: carry out derivative operation to determine two groups of extreme points in this curve to angle grey level histogram; Merge the gray scale point that extreme point middle distance is close, and the extreme value gray scale point that the difference of deleting different extreme point angle is less than 45 °, to determine cut-point; And pedestrian's region segmentation will be moved for " entering " and " going out " two classifications by described cut-point, thus obtain the direction of motion information of each pedestrian in motion pedestrian region.
Compared with prior art, the invention has the beneficial effects as follows: in the present invention, the pedestrian movement direction of angle grey level histogram to motion pedestrian region is utilized to split, and utilize pedestrian's quantity that linear regression analysis method statistic all directions are moved, thus the efficiency that have effectively achieved pedestrian's demographics in public domain and accuracy.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of a kind of pedestrian counting method based on angle half-tone information of the present invention;
Fig. 2 is the principle of work schematic diagram realizing step S1;
Fig. 3 is the testing result schematic diagram of global optical flow method;
Fig. 4 is global optical flow method combines to obtain motor area binary image logical flow chart with frame differential method;
Fig. 5 is the schematic diagram of angle gray histogram curve in invention.
Embodiment
Below in conjunction with each embodiment shown in the drawings, the present invention is described in detail; but should be noted that; these embodiments are not limitation of the present invention; those of ordinary skill in the art are according to these embodiment institute work energy, method or structural equivalent transformations or substitute, and all belong within protection scope of the present invention.
Shown in ginseng Fig. 1, Fig. 1 is the schematic flow sheet of a kind of pedestrian counting method based on angle half-tone information of the present invention.In the present embodiment, this pedestrian counting method comprises the following steps:
Step S1: obtain the video streaming image of guarded region as input picture.
Shown in concrete ginseng Fig. 2, a kind of pedestrian counting method based on angle half-tone information of the present invention is applicable to video camera 10 and vertically takes or adopt the situation being basically perpendicular to guarded region 30, and is applicable to outdoor environment and indoor environment.Concrete, this step S1 is specially: obtain the video streaming image of guarded region 30 as input picture by video camera 10, and described guarded region 30 is positioned at immediately below video camera 10.
Further, this video camera 10 is arranged on directly over gateway 20, and pedestrian can walk up and down on the direction of arrow 201 in gateway 20.The guarded region 30 that video camera 10 obtains can cover the Zone Full of gateway 20 completely.This gateway 20 can be arranged in the front door or corridor needing the market, garage, bank etc. added up pedestrian's number to need key monitoring place.
It should be noted that, the best results of the present invention when video camera 10 vertically faces guarded region 30, certainly can also by video camera 10 obliquely facing to needing the region of carrying out pedestrian's number counting statistics, to cover whole guarded region 30 by video camera 10.
In the present embodiment, this guarded region 30 is rectangle; Can certainly be square or circular or other shapes.Video camera 10 is positioned at directly over the central point 301 of guarded region 30, and now this guarded region 30 is positioned at immediately below video camera 10.
S2, global optical flow method being combined with frame differential method acts on input picture, obtains the binary image R (x, y) comprising pedestrian movement region.
Shown in ginseng Fig. 3, in the present embodiment, the specific implementation process of global optical flow method is: to input picture 40, and every 5*5 block of pixels draws a light stream line, and the length of light stream line represents the movement velocity of this point, and angle represents the direction of motion of this point.The unit length of light stream line is 10*2
1/2pixel, if the horizontal velocity of certain pixel light stream i.e. and vertical speed are all 1 pixel/frame, then the light stream line length of this point is 10*2
1/2pixel.Pixel movement velocity difference is not quite similar, and this is determined by the movement velocity of moving object.Global optical flow method can not only detect the movable information of moving object, also comprises movable information in background, as the information etc. of surrounding buildings surface reflection light.
In the present embodiment, the algorithm specific implementation process that global optical flow method is combined with frame differential method for: join shown in Fig. 4, utilize global optical flow method to carry out the calculating of global optical flow field to the input picture obtained in step S1, obtain the optical flow field G of input picture
of(x, y).Owing to there will be the error of calculation, there is high frequency noise in the optical flow field of input picture, the smoothing process of the optical flow field of wave filter to input picture utilizing window size to be 5*5, then obtains the bianry image R of input picture optical flow field by Threshold segmentation
of(x, y).
Wherein, Threshold segmentation is specially:
Concrete, the optical flow field of input picture is carried out to the threshold value Th of Threshold segmentation
of=0.05, the speed span of optical flow field is [0,1].
The concrete implementation procedure of frame differential method is: the input picture obtained according to step S1, utilizes current frame image and previous frame image to make calculus of differences to obtain difference image.The computing formula of frame differential method is D
k(x, y)=F
k(x, y)-F
k-1(x, y);
Wherein, F
k-1(x, y) is the gray-scale value of pixel in previous frame image, F
k(x, y) is the gray-scale value of pixel in current frame image, D
kthe difference image that (x, y) is the two.
Then, to difference image D
k(x, y) carries out binary conversion treatment, and the operational formula of this binary conversion treatment is as follows:
Wherein, D
kthe difference image that (x, y) obtains after calculus of differences for current frame image and previous frame image, R
k(x, y) bianry image for obtaining after method of difference process, M is partition threshold.In the present embodiment, partition threshold M value is 70.Work as R
kwhen (x, y) is 0, this pixel is background dot; Work as R
kwhen (x, y) is 1, this pixel is foreground point and moving object.
Then, by two width bianry image R
of(x, y) and R
k(x, y) to do and computing, obtain bianry image R ' (x, y), finally utilize Morphological scale-space method, removal noise is carried out to bianry image R ' (x, y) and repairs cavity process, obtain the final binary image R (x, y) comprising pedestrian movement region.Concrete, the Morphological scale-space in present embodiment is specially: first carry out dilation operation, after carry out erosion operation.Wherein, the expansion parameters in dilation operation is 7, and the corrosion parameter in erosion operation is 3.
S3, by the optical flow field G of binary image R (x, y) and input picture
of(x, y) does and computing, obtains the optical flow field angle information θ in pedestrian movement region
i, calculate angle half-tone information f according to formula (1)
int(x, y) is to calculate its angle grey level histogram.
In the present embodiment, the binary image R (x, y) in motion pedestrian region obtained according to step S2 and the optical flow field G of input picture
of(x, y) does and computing, obtains the optical flow field angle information θ in pedestrian movement region
i, 1≤i≤N, wherein N is total number of the pixel in pedestrian movement region, θ
i∈ [0 °, 360 °).Then, by optical flow field angle information with the formula (1) be converted to angle half-tone information:
Utilize the conversion method of formula (1), the span of the pixel in pedestrian movement region be [0,250), the pixel value of background area is 255.
Utilize the method for image procossing, its angle grey level histogram is calculated to the angle half-tone information be converted to by formula (1).Further, the Gaussian smoothing template that window size can be utilized to be 5*5 carries out gaussian filtering process to angle grey level histogram.It should be noted that, the method for the Gaussian smoothing template using iterative discrete convolution of different windows size is obtained.Suppose that the smoothing parameter set is ω, corresponding smooth template is that f (ω) is calculated by formula (2):
f(ω)＝f(ω-2)*f(ω-2)，ω≥5(2)
Initial Gaussian smooth template is f (3)=[0.2261,0.5478,0.2261].Smoothing parameter ω may be selected to be 5,7 ... etc. odd-integral number.
When ω=3, the length of original template is 3, and along with the increase of smoothing parameter, the length lenf (w) of smooth template changes with the rule change of such as formula (3):
Concrete, when ω=11, template length is 33.Be 250 based on histogram length, preferably, in the present embodiment, these Gaussian smoothing template parameter ω=7.
S4, utilize angle grey level histogram to motion pedestrian region pedestrian movement direction split.
Shown in concrete ginseng Fig. 5, the Wave crest and wave trough of angle gray histogram curve is obvious, the curve distribution in " M " shape substantially.By to the differentiate of angle gray histogram curve, to determine maximum value and the minimal value (namely the zero crossing of angle grey level histogram derivative curve is exactly the extreme point of angle grey level histogram) of this angle gray histogram curve.
Concrete, the computing formula as formula (4) can be taked, by the zero crossing in angle grey level histogram derivative curve, find the extreme point of angle gray histogram curve:
Wherein, the gray-scale value of p corresponding to the zero crossing in angle grey level histogram derivative curve, { maxi}{mini} is maximum value vector sum minimal value vector respectively.
The two groups of extreme points obtained by angle grey level histogram derivative curve, outside removing background pixel point, present man-to-man state.Namely there is a minimal value between two maximum value, between two minimal values, there is a maximum value, and the direction of motion of adjacent two extreme points representative is similar.
Based on this, point close for extreme point middle distance is merged.In the present embodiment, the extreme value gray scale point difference of the angle of different extreme point being less than 45 ° is cast out.It is Th that this angle threshold changes into gray-scale value by formula (1)
cbm=31, and merge extreme point with following steps, and determine final cut-point:
First, the maximum point 255 representing background is cast out.
Then, gray scale point close in maximum value is merged according to the following rules:
if|maxi-maxj|≤31
ifN(maxi)≥N(maxj)
maxj＝255；
elsemaxi＝255；
Wherein, maxi, maxj are two adjacent maximum points, and N (maxi), N (maxj) are respectively the gray scale point number of these two maximum point representatives.By gray scale point assignment 255, represent and this point of gray scale is cast out, because 255 represent background pixel point.Due in angle grey level histogram, gray-scale value by 0 with 255 the direction of sign pedestrian movement be consistent, therefore the maximum point at these angle grey level histogram two ends also should merge, and merges rule as follows:
ifmaxi＜31&&maxj＞219&&|maxi-maxj+250|≤31
ifN(maxi)≥N(maxj)
maxj＝255；
elsemaxi＝255；
Through above-mentioned process, { maxi} is updated to maximum value set { maxi ' } in maximum value set.
Finally, according to two groups of extreme values relation one to one, { select some minimum points mini} to be inserted in the middle of minimal value combination { maxi ' } numerical value from minimal value set.Picking rule is as follows: suppose that an adjacent maximum point maxi ' and maxj ' has k minimum point min1, min2 ..., mink, and only retain minimum point minimum in an above-mentioned k minimum point, then remaining k-1 minimum point is deleted.{ the minimal value set after mini} renewal is { mini ' } in this minimal value set.
Suppose that the two groups of extreme points initially obtained become after merging and upgrading:
A
2, b
2as the cut-point between different motion stream, a
1, b
1as the direction of motion of different motion stream.
The present embodiment is mainly used in adds up the volume of the flow of passengers of turnover guarded region 30 as shown in Figure 2.So in the present embodiment, angle half-tone information histogram pedestrian's region segmentation of moving is utilized to be " entering " and " going out " two classifications.Wherein, " enter " classification representative to enter along the direction of arrow 201 and by the pedestrian of guarded region 30; " go out " classification representative to leave along the direction of arrow 201 and by the pedestrian of guarded region 30.
S5, linear regression analysis method statistic all directions are utilized to move the number of pedestrian.
In the present embodiment, motion pedestrian region can not be all single pedestrian, is also likely two even multiple people of people, needs to calculate the number of moving in pedestrian region by carrying out analysis meter to motion pedestrian region.
In the present embodiment, utilize linear regression algorithm, add up the number of the pedestrian moved to " entering " respectively, with the number of the pedestrian moved to " going out ", thus the total number of persons obtained by the pedestrian in this guarded region 30, also can calculate separately the total number of persons entering this guarded region 30 simultaneously and calculate separately the total number of persons leaving this guarded region 30.
A series of detailed description listed is above only illustrating for feasibility embodiment of the present invention; they are also not used to limit the scope of the invention, all do not depart from the skill of the present invention equivalent implementations done of spirit or change all should be included within protection scope of the present invention.
In addition, be to be understood that, although this instructions is described according to embodiment, but not each embodiment only comprises an independently technical scheme, this narrating mode of instructions is only for clarity sake, those skilled in the art should by instructions integrally, and the technical scheme in each embodiment also through appropriately combined, can form other embodiments that it will be appreciated by those skilled in the art that.
Claims (7)
1. based on a pedestrian counting method for angle half-tone information, it is characterized in that, the method comprises the following steps:
The video streaming image of S1, acquisition guarded region is as input picture;
S2, global optical flow method being combined with frame differential method acts on input picture, obtains the binary image R (x, y) comprising pedestrian movement region;
S3, by the optical flow field G of binary image R (x, y) and input picture
of(x, y) does and computing, obtains the optical flow field angle information θ in pedestrian movement region
i, obtain angle half-tone information f according to following formulae discovery
int(x, y) to calculate its angle grey level histogram,
S4, utilize angle grey level histogram to motion pedestrian region pedestrian movement direction split;
S5, linear regression analysis method statistic all directions are utilized to move the number of pedestrian.
2. pedestrian counting method according to claim 1, is characterized in that, " global optical flow method " in described step S2 is specially:
Utilize global optical flow method to carry out the calculating of global optical flow field to the input picture obtained in step S1, obtain the optical flow field G of input picture
of(x, y), and the Gaussian filter utilizing window size to be 5*5 carries out gaussian filtering process to the optical flow field of input picture, is then obtained the bianry image R of input picture optical flow field by Threshold segmentation
of(x, y).
3. pedestrian counting method according to claim 2, is characterized in that, the computing formula of described " Threshold segmentation " is specially:
Wherein, threshold value Th
of=0.05; The speed span of light stream is [0,1].
4. pedestrian counting method according to claim 1, it is characterized in that, " frame differential method " in described step S2 is specially: the input picture obtained according to step S1, utilizes current frame image and previous frame image to make calculus of differences by following formula, to obtain difference image
D
k(x，y)＝F
k(x，y)-F
k-1(x，y)
Wherein, F
k-1(x, y) is the gray-scale value of pixel in previous frame image, F
k(x, y) is the gray-scale value of pixel in current frame image, D
kthe difference image that (x, y) is the two.
5. the pedestrian counting method according to any one of claim 2 to 4, is characterized in that, described step S2 also comprises: the binary image R (x, y) comprising pedestrian movement region is made Morphological scale-space.
6. pedestrian counting method according to claim 5, is characterized in that, described Morphological scale-space is specially and first carries out dilation operation to the binary image R (x, y) in pedestrian movement region, after carry out erosion operation; Wherein, the expansion parameters in dilation operation is 7, and the corrosion parameter in erosion operation is 3.
7. pedestrian counting method according to claim 1, is characterized in that, described step S4 is specially: carry out derivative operation to determine two groups of extreme points in this curve to angle grey level histogram; Merge the gray scale point that extreme point middle distance is close, and the extreme value gray scale point that the difference of deleting different extreme point angle is less than 45 °, to determine cut-point; And pedestrian's region segmentation will be moved for " entering " and " going out " two classifications by described cut-point, thus obtain the direction of motion information of each pedestrian in motion pedestrian region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410351238.9A CN105279821B (en) | 2014-07-22 | 2014-07-22 | A kind of pedestrian counting method based on angle half-tone information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410351238.9A CN105279821B (en) | 2014-07-22 | 2014-07-22 | A kind of pedestrian counting method based on angle half-tone information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105279821A true CN105279821A (en) | 2016-01-27 |
| CN105279821B CN105279821B (en) | 2018-01-09 |
Family
ID=55148767
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410351238.9A Active CN105279821B (en) | 2014-07-22 | 2014-07-22 | A kind of pedestrian counting method based on angle half-tone information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105279821B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779043A (en) * | 2016-12-28 | 2017-05-31 | 南京沃顿物联网科技有限公司 | A kind of method of counting based on number of people detection |
| CN108038432A (en) * | 2017-11-30 | 2018-05-15 | 中国人民解放军国防科技大学 | Bus pedestrian flow statistical method and system based on optical flow counting |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08161453A (en) * | 1994-12-02 | 1996-06-21 | Tokai Rika Co Ltd | Counter for number of persons |
| EP0747865A2 (en) * | 1995-06-08 | 1996-12-11 | ABBPATENT GmbH | Apparatus to determine the sense of movement of a person |
| CN102855465A (en) * | 2012-04-12 | 2013-01-02 | 无锡慧眼电子科技有限公司 | Tracking method of moving object |
| CN102867177A (en) * | 2012-09-19 | 2013-01-09 | 无锡慧眼电子科技有限公司 | People number counting method based on image grey level matching |
-
2014
- 2014-07-22 CN CN201410351238.9A patent/CN105279821B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08161453A (en) * | 1994-12-02 | 1996-06-21 | Tokai Rika Co Ltd | Counter for number of persons |
| EP0747865A2 (en) * | 1995-06-08 | 1996-12-11 | ABBPATENT GmbH | Apparatus to determine the sense of movement of a person |
| CN102855465A (en) * | 2012-04-12 | 2013-01-02 | 无锡慧眼电子科技有限公司 | Tracking method of moving object |
| CN102867177A (en) * | 2012-09-19 | 2013-01-09 | 无锡慧眼电子科技有限公司 | People number counting method based on image grey level matching |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779043A (en) * | 2016-12-28 | 2017-05-31 | 南京沃顿物联网科技有限公司 | A kind of method of counting based on number of people detection |
| CN106779043B (en) * | 2016-12-28 | 2019-08-09 | 南京艾伯瑞电子科技有限公司 | A kind of method of counting based on number of people detection |
| CN108038432A (en) * | 2017-11-30 | 2018-05-15 | 中国人民解放军国防科技大学 | Bus pedestrian flow statistical method and system based on optical flow counting |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105279821B (en) | 2018-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022126669A1 (en) | Subway pedestrian flow network fusion method based on video pedestrian recognition, and pedestrian flow prediction method | |
| Ren et al. | Detecting and positioning of traffic incidents via video‐based analysis of traffic states in a road segment | |
| CN103577875B (en) | A kind of area of computer aided CAD demographic method based on FAST | |
| Teknomo et al. | Tracking system to automate data collection of microscopic pedestrian traffic flow | |
| CN103049787A (en) | People counting method and system based on head and shoulder features | |
| CN104933710A (en) | Intelligent analysis method of store people stream track on the basis of surveillance video | |
| JP2016027490A (en) | Method, system, product and computer program for multi-cue object detection and analysis (multi-cue object detection and analysis) | |
| US20150350608A1 (en) | System and method for activity monitoring using video data | |
| CN101800890A (en) | Multiple vehicle video tracking method in expressway monitoring scene | |
| CN105321187A (en) | Pedestrian counting method based on head detection | |
| CN103488993A (en) | Crowd abnormal behavior identification method based on FAST | |
| CN103984937A (en) | Pedestrian counting method based on optical flow method | |
| Khan et al. | PASSENGER DETECTION AND COUNTING FOR PUBLIC TRANSPORT SYSTEM. | |
| CN104091351B (en) | Number method of counting based on clustering procedure | |
| Lumentut et al. | Evaluation of recursive background subtraction algorithms for real-time passenger counting at bus rapid transit system | |
| CN105279821A (en) | Pedestrian counting method based on angle gray level information | |
| CN103824074A (en) | Crowd density estimation method based on background subtraction and texture features and system | |
| Guerrieri et al. | Traffic flow variables estimation: An automated procedure based on moving observer method. potential application for autonomous vehicles | |
| Zhang et al. | Image-based approach for parking-spot detection with occlusion handling | |
| Ha et al. | Improved Optical Flow Estimation In Wrong Way Vehicle Detection. | |
| Liu et al. | Metro passenger flow statistics based on yolov3 | |
| Chen et al. | Estimation of people movement in video based on optical flow block method and motion maps | |
| Salmane et al. | A novel evidence based model for detecting dangerous situations in level crossing environments | |
| Trivedi et al. | Vehicle counting module design in small scale for traffic management in smart city | |
| Hu et al. | A high efficient system for traffic mean speed estimation from mpeg video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 214000 Jiangsu, Huishan Economic Development Zone, wisdom road, No. 1, Tsinghua innovation building, A1501-A1509, Applicant after: ABD SMART EYE ELECTRONICS CO., LTD. Address before: 214000, Jiangsu, Huishan Economic Development Zone, Wuxi, 1, wisdom road, Jiangsu Digital Information Industry Park, Tsinghua innovation building, block A, 15F Applicant before: Wuxi Eye Technology Co., Ltd. |
|
| COR | Change of bibliographic data | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191220 Address after: 214174 Tsinghua innovation building a1511, No.1, wisdom road, Huishan Economic Development Zone, Wuxi, Jiangsu Province Patentee after: Wuxi Huiyan Artificial Intelligence Technology Co., Ltd Address before: 214000 Tsinghua innovation building, No. 1, wisdom road, Huishan Economic Development Zone, Jiangsu, Wuxi province A1501-A1509 Patentee before: ABD SMART EYE ELECTRONICS CO., LTD. |
|
| TR01 | Transfer of patent right |