CN113344649A - Social investigation big data construction system - Google Patents

Social investigation big data construction system Download PDF

Info

Publication number
CN113344649A
CN113344649A CN202110895985.9A CN202110895985A CN113344649A CN 113344649 A CN113344649 A CN 113344649A CN 202110895985 A CN202110895985 A CN 202110895985A CN 113344649 A CN113344649 A CN 113344649A
Authority
CN
China
Prior art keywords
unit
mapping
vector
pixel point
data
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.)
Withdrawn
Application number
CN202110895985.9A
Other languages
Chinese (zh)
Inventor
余芳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangxi Heyi Cloud Data Technology Co ltd
Original Assignee
Jiangxi Heyi Cloud Data Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangxi Heyi Cloud Data Technology Co ltd filed Critical Jiangxi Heyi Cloud Data Technology Co ltd
Priority to CN202110895985.9A priority Critical patent/CN113344649A/en
Publication of CN113344649A publication Critical patent/CN113344649A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data

Landscapes

  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Finance (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a social big data construction system which comprises an investigation region, wherein the investigation region is provided with a port and a channel connected with the port. The port is provided with a counting unit, a plurality of service units are arranged in the channel, a first camera unit is arranged on one side of the channel, and a second camera unit is arranged on the other side of the channel. The social investigation big data construction system further comprises a first processing unit, a first extraction unit, a second processing unit, a second extraction unit and a mapping construction unit. The system can rapidly distinguish the moving surveyor from the non-moving fixture, count the surveyor more accurately and construct the large mapping data related to the consumption capacity. And the user can conveniently make corresponding decisions according to the big data.

Description

Social investigation big data construction system
Technical Field
The invention relates to a consumption data analysis technology, in particular to a social investigation big data construction system.
Background
The efficiency of social research can be improved by means of computer technology, such as the determination method of consumption peak time period of CN109658125B, which mainly adopts the online data analysis mode to determine the network congestion and the reservation quantity. In some cases, it is necessary to look up some data under the line. The offline flow survey employs, for example, a regional flow monitoring method of CN112699109A or a road flow detection method of CN 101710448B. These flow measurements can be used to determine the occurrence of events (consumption events of people) in an area or road, and then analyze the relationship between the occurrence of events and flow. Furthermore, visual inspection of images may be used to analyze the consumption propensity of a panelist, see US20120271785a 1. However, this document is mainly directed to single consumption behaviors and does not disclose how to utilize the analysis consumption ability of the population. In the prior art, the system construction is lacked for investigating the investigation object population, and the data capturing and analyzing capability is poor. In view of this, there is a need for further improvements in the prior art.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a social investigation big data construction system. The system can acquire the relation with consumption data through data acquisition and analysis of the investigation objects in the investigation region, is used for constructing the consumption investigation, and can improve the accuracy of the investigation compared with the prior art.
A social survey big data construction system comprises a survey area, wherein the survey area is provided with a port and a channel connected with the port, a plurality of surveyors are positioned in the survey area, the port is provided with a counting unit, the channel is internally provided with a plurality of service units, one side of the channel is provided with a first camera unit, the other side of the channel is provided with a second camera unit, wherein,
the counting unit collects the net inflow data S of the surveyor in the survey area at the time ttGenerating a first contrast set;
the service unit provides a consumption service to the surveyor and collects consumption data C of the surveyor at time ttGenerating a second contrast set;
the first camera unit collects a first instantaneous image at a moment t, and a pixel point of a coordinate (x, y) in the first instantaneous image is I (x, y);
the second camera unit collects a second instantaneous image at a moment t, and a pixel point of a coordinate (x, y) in the second instantaneous image is O (x, y);
it is characterized in that the social investigation big data construction system also comprises a first processing unit, a first extraction unit, a second processing unit, a second extraction unit and a mapping construction unit,
the first processing unit is used for processing the image according to the pixel point I (x) of the adjacent first transient imageY) obtaining first vector data, the velocity vector of pixel point I (x, y) in the first vector data is (u)xy，vxy)，uxyIs the vector of pixel point I (x, y) in the x-axis direction, vxyThe vector of the pixel point I (x, y) in the y-axis direction is shown;
the first extraction unit extracts uxy 2+vxy 2Multiple velocity vectors (u) of ≧ Δxy，vxy) Generating a first reference set, wherein delta is a preset speed threshold value;
the second processing unit obtains second vector data according to the pixel point O (x, y) of the adjacent second instantaneous image, and the speed vector of the pixel point O (x, y) in the second vector data is (h)xy，kxy)，hxyIs the vector, k, of pixel point O (x, y) in the x-axis directionxyThe vector of the pixel point O (x, y) in the y-axis direction is shown;
second extraction unit extracts hxy 2+kxy 2Multiple velocity vectors (h) of ≧ Δxy，kxy) Generating a second reference set;
the mapping construction unit fits a first mapping of the first reference set, the second reference set and the first contrast set and a second mapping of the first reference set, the second reference set, the first contrast set and the second contrast set.
In the present invention, the first and second imaging units acquire image data every period T.
In the present invention, the period T is 0.1 s.
In the invention, the investigation area is a market, and the consumption data is the consumption amount.
In the present invention, the first mapping is St=f1(r1，r2T), the second mapping being Ct=f2(St，r1，r2，t)，f1() Is StAnd r1、r2T, f2() Is CtAnd St、r1、r2T, where r1，r2Average moving speed of pixel points in the first reference set and the second reference set respectively。
In the invention, a first processing unit and a second processing unit determine a velocity vector (u) from an optical flow algorithmxy，vxy)。
In the present invention, the mapping construction unit constructs a third mapping of the first contrast set and the second contrast set, the third mapping being g1(St，t)=g2 (Ct，t)，g1()、g2() Is StT and CtAnd t.
The social survey big data construction system determines the moving condition of the surveyor according to the optical flow data captured by the first camera unit, can quickly distinguish the moving surveyor from the non-moving fixture, and can count the surveyor more accurately. Meanwhile, the net inflow data of the surveyor is combined to construct a mapping related to consumption, so that a user can make corresponding decisions according to the existing consumption big data.
Drawings
FIG. 1 is a schematic diagram of a preferred configuration of an investigation region according to the present invention;
FIG. 2 is a block diagram of a social survey big data construction system of the present invention;
FIG. 3 is a schematic representation of the net inflow data of the present invention over time;
FIG. 4 is a schematic representation of consumption data over time in accordance with the present invention;
FIG. 5 is a schematic diagram of the average moving speed of the first processing unit according to the present invention;
FIG. 6 is a diagram illustrating the variation of the average moving speed in the second processing unit according to the present invention;
FIG. 7 is a schematic diagram of the preferred implementation steps of the social survey big data construction system of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention.
As shown in fig. 1 and 2, the social survey big data construction system of the invention includes a survey area and a plurality of unit modules located in the survey area, which are respectively a first camera unit, a second camera unit, a counting unit (e.g., an entrance guard counter), and a service unit (e.g., pos consumption equipment). The survey area in this embodiment is a mall and has a plurality of ports and channels, a plurality of survey objects are located in the survey area, the ports are provided with counting units, a plurality of service units are arranged in the channels, one side of each channel is provided with a first camera unit, and the other side of each channel is provided with a second camera unit. The first camera unit and the second camera unit can utilize existing monitoring equipment in a shopping mall. In order to realize big data analysis, the invention also comprises a first processing unit, a first extraction unit, a second processing unit, a second extraction unit, a mapping construction unit and an output unit. The first and second processing units determine the moving state of the surveyor according to the optical flow data captured by the first and second imaging units, so that the moving surveyor and the non-moving fixture can be rapidly distinguished, and the surveyor can be more accurately analyzed. The mapping construction unit combines the total number of the surveyors and the movement condition to construct large mapping data related to consumption capacity.
In particular, the counting unit collects the net inflow data S of the investigation object in the investigation region at the time ttAnd generating a first contrast set. In the invention, the first contrast set is a set of a plurality of net inflow data which change along with the time t and is an input parameter of big data analysis. The net inflow data is the total daily inflow data minus the total daily outflow data for the population. The net inflow data over time is shown, for example, with reference to fig. 3. The service unit provides consumption service for the surveyor and collects consumption data C of the surveyor at time ttA second contrast set is generated. The second contrast set is a second input parameter for big data analysis, and the change of consumption data with time is shown, for example, with reference to fig. 4.
The first camera unit collects a first instantaneous image at a time T, wherein the time T is a time point corresponding to each period T in a preset investigation time. the pixel point of the coordinate (x, y) in the first transient image at the time t is I (x, y). The first processing unit obtains first vector data according to pixel points I (x, y) of adjacent first transient images, and the first vector data comprises velocity vectors (u) of the pixel points I (x, y)xy，vxy). In the present invention, a velocity vector (u) is determinedxy，vxy) And adopting an optical flow algorithm, and detailed later. The first extraction unit extracts uxy 2+vxy 2Multiple velocity vectors (u) of ≧ Δxy，vxy) A first reference set is generated. Δ is a preset threshold value of the velocity vector composition, for example 0.05m/s, above which a moving surveyor object can be considered. Similarly, the second camera unit acquires a second instantaneous image at a time T, which is a time point corresponding to each period T within a preset investigation time (for example, 9 to 21 points). the pixel point of the coordinate (x, y) in the first transient image at the time t is I (x, y). The second processing unit obtains second vector data according to the pixel point O (x, y) of the adjacent second instantaneous image, and the second vector data comprises a speed vector (h) of the pixel point O (x, y)xy，kxy). Second extraction unit extracts hxy 2+kxy 2Multiple velocity vectors (h) of ≧ Δxy，kxy) And generating a second reference set. u. ofxyIs the vector of pixel point I (x, y) in the x-axis direction, vxyThe vector of the pixel point I (x, y) in the y-axis direction is shown. h isxyIs the vector, k, of pixel point O (x, y) in the x-axis directionxyThe vector of the pixel point O (x, y) in the y-axis direction is shown.
The mapping construction unit fits a first mapping of the first reference set, the second reference set and the first contrast set and a second mapping of the first reference set, the second reference set, the first contrast set and the second contrast set. The intermediate parameters are first calculated. Intermediate parameter r1，r2The average moving speed of the pixel points in the first reference set or the second reference set is respectively.
Figure 27920DEST_PATH_IMAGE001
、
Figure 132011DEST_PATH_IMAGE002
The velocity vector of the pixel point I (x, y) and the velocity vector of the pixel point O (x, y) on the x axis and the y axis are synthesized, namely the moving velocity of the pixel point. The average moving speed r can be determined according to the moving speeds of a plurality of pixel points1，r2。r1，r2The variation with time t is shown in fig. 5 and 6. It is expected that the average moving speed is higher when the number of persons is small; when the number of people is large, the average moving speed is low, and the change is in a nonlinear relation. Fitting the mapping may be by using a general numerical analysis method or MATLAB analysis software, i.e. establishing a numerical relationship between a plurality of parameters, such as interpolation, function approximation, curve fitting, etc. Different analysis methods can obtain different mapping relations, part of abnormal values are removed in the fitting process, and the number of the removed abnormal values can influence the result of numerical analysis. The first mapping S may be approximated, for example, by means of a function approximationt=f1(r1，r2T), i.e. the net inflow data investigated in the investigation region has a certain relation to time and the moving speed of the investigation object, in some embodiments f1() Typically a piecewise quartile function. The second mapping is Ct=f2(St，r1，r2T). Consumption data in the survey area has a certain relationship with the net inflow data of the survey subject and the moving speed. It is expected that the consumption data will be lower when the number of people is small and the average moving speed is high; when the number of people is large and the average moving speed is low, the consumption data is high, and the change is in a nonlinear relation. In addition, the data extracted by the user according to the present invention can be analyzed for other investigation, for example, the mapping construction unit can try to construct a third mapping between the first contrast set and the second contrast set, where the third mapping is g1(St，t)=g2 (CtT). The output unit outputs different data analysis results according to needs.
Referring to fig. 7, the social survey big data construction system of the invention is implemented in more detail.
And (5) setting a system. The shopping mall is used as a survey area, and the crowd in the shopping mall is a survey object. Install entrance guard's inductor in market entrance and exit, the number of people is counted in to the inductor, calculates investigation region net inflow data through the difference of the number of people of cominging in and going out
Figure 380590DEST_PATH_IMAGE003
(number of remaining people) as the first comparison set. Cameras are arranged on two sides of a channel in a market, the cameras are respectively a first camera unit and a second camera unit, people flow data in an image acquisition channel is shot by taking T as a period in time T, generally, T is set to be 12h (10: 00-22: 00), and T is set to be 0.1 s. The camera typically captures two-dimensional color information about the crowd, i.e. color images that we typically see, e.g. the first temporal image captured by the first camera element, and the size of the image can be set to be: 640 x 480, 2048 x 1536, and larger image sizes. In the image, several panelists are included, and further processing is required to perform status analysis on the panelists.
And (6) data acquisition. The first transient image acquired by the first camera unit is sent to a first processing unit of a foreground and background segmentation model based on optical flow analysis, and the optical flow method is generally used for analyzing moving objects and targets. In order to carry out statistical analysis on people stream data, the first transient image shot by the first camera shooting unit and the first transient image which follows the first transient image are adopted, and the images are different by T. Based on the following assumptions: the brightness in the channel needs to be kept constant, which is satisfactory for images taken at intervals of T, and the brightness of the images does not change basically; the consumer group needs to be in continuous motion in time, which also coincides with the characteristics of the consumer group itself.
Therefore, based on these two preconditions, L (x, y, t) = L (x + dx, y + dy, t + dt) can be obtained from the optical flow model. The left side L (x, y, t) represents the intensity of light at the original position, and the variation values of x, y, t, the intensity of light obtained by varying the occurring position and time, is L (x + dx, y + dy, t + dt). The velocity vector of the light stream along the x-axis in the image is uxyVelocity vector along the y-axis is vxyIs defined as
Figure 244641DEST_PATH_IMAGE004
，
Figure 527854DEST_PATH_IMAGE005
The definitional formula is in derivative form. To obtain the pixel point I (x,y) optical flow vector (u)xy，vxy) Satisfies the following conditions:
Figure 71356DEST_PATH_IMAGE006
。
Figure 10493DEST_PATH_IMAGE007
、
Figure 678235DEST_PATH_IMAGE008
and
Figure 65222DEST_PATH_IMAGE009
the partial differential of the illumination intensity L with respect to x, y, and t can be obtained from the image data, and the optical flow algorithm in the prior art is specifically referred to and will not be described herein. In the Horn-Schunck optical flow algorithm, the velocity of motion of a pixel is similar or identical to the velocity of its neighboring pixels, and the velocity variation everywhere in the optical flow field is smooth. And (4) smooth constraint:
Figure 527428DEST_PATH_IMAGE010
、
Figure 750599DEST_PATH_IMAGE011
。
Figure 956452DEST_PATH_IMAGE012
. Wherein the content of the first and second substances,
Figure 197946DEST_PATH_IMAGE013
and
Figure 96632DEST_PATH_IMAGE014
it can be calculated from neighboring pixels, and the invention uses the values of the neighboring (3 x 3) pixels around this pixel.
Figure 807099DEST_PATH_IMAGE016
Figure 551064DEST_PATH_IMAGE018
Therefore, the velocity vector (u) of the pixel point I (x, y) can be obtainedxy，vxy). Similarly, the second camera unit transmits the people stream image shot in the T period within the time T to the second processing unit of the foreground and background segmentation model based on the optical flow analysis in the same method, the pixel point in the image is O (x, y), and a velocity vector (h) is obtainedxy，kxy)。
And (6) data extraction. Screening the speed vectors collected by the first camera unit and the second camera unit in the period of T within the time T, and extracting the speed vectors u on the x axis and the y axis obtained by the first processing unit by the first extraction unitxy 2+vxy 2A plurality of velocity vectors ≧ Δ generate a first reference set. By passing
Figure 912645DEST_PATH_IMAGE001
Calculating the moving speed of the pixel points, and determining the average moving speed of the pixel points in the first reference set
Figure 513390DEST_PATH_IMAGE019
. The second extraction unit extracts the velocity vector h on the x-axis and the y-axis obtained by the second processing unitxy 2+kxy 2Generating a second reference set by a plurality of velocity vectors ≧ Δ
Figure 711153DEST_PATH_IMAGE002
And calculating the moving speed of the pixel points, and then determining the average moving speed of the pixel points in the second reference set. And Δ is a variable customized by the user, taking 0.05m/s in the present embodiment. The service unit provides consumption service to the surveyor by connecting with the cashier system in the survey area and collects consumption data of the surveyor at the moment t
Figure 993230DEST_PATH_IMAGE020
A second contrast set is generated.
And (6) analyzing the data. The first reference set, the second reference set, the first contrast set and the second contrast set are transmitted into a mappingAnd constructing a unit. The mapping construction unit fits the first mapping St=f1(r1，r2T), second mapping Ct=f2(St，r1，r2T) and a third mapping g1(St，t)=g2(CtT). More data relationships can also be obtained as needed.
And (6) outputting the data. And outputting the relation obtained by fitting the mapping construction unit to a user.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principles of the present invention are intended to be included within the scope of the present invention.

Claims (7)

1. A social survey big data construction system comprises a survey area, wherein the survey area is provided with a port and a channel connected with the port, a plurality of surveyors are positioned in the survey area, the port is provided with a counting unit, the channel is internally provided with a plurality of service units, one side of the channel is provided with a first camera unit, the other side of the channel is provided with a second camera unit, wherein,
the counting unit collects the net inflow data S of the surveyor in the survey area at the time ttGenerating a first contrast set;
the service unit provides a consumption service to the surveyor and collects consumption data C of the surveyor at time ttGenerating a second contrast set;
the first camera unit collects a first instantaneous image at a moment t, and a pixel point of a coordinate (x, y) in the first instantaneous image is I (x, y);
the second camera unit collects a second instantaneous image at a moment t, and a pixel point of a coordinate (x, y) in the second instantaneous image is O (x, y);
it is characterized in that the social investigation big data construction system also comprises a first processing unit, a first extraction unit, a second processing unit, a second extraction unit and a mapping construction unit,
root of first processing unitObtaining first vector data according to the pixel point I (x, y) of the adjacent first transient image, wherein the velocity vector of the pixel point I (x, y) in the first vector data is (u)xy，vxy)，uxyIs the vector of pixel point I (x, y) in the x-axis direction, vxyThe vector of the pixel point I (x, y) in the y-axis direction is shown;
the first extraction unit extracts uxy 2+vxy 2Multiple velocity vectors (u) of ≧ Δxy，vxy) Generating a first reference set, wherein delta is a preset speed threshold value;
the second processing unit obtains second vector data according to the pixel point O (x, y) of the adjacent second instantaneous image, and the speed vector of the pixel point O (x, y) in the second vector data is (h)xy，kxy)，hxyIs the vector, k, of pixel point O (x, y) in the x-axis directionxyThe vector of the pixel point O (x, y) in the y-axis direction is shown;
second extraction unit extracts hxy 2+kxy 2Multiple velocity vectors (h) of ≧ Δxy，kxy) Generating a second reference set;
the mapping construction unit fits a first mapping of the first reference set, the second reference set and the first contrast set and a second mapping of the first reference set, the second reference set, the first contrast set and the second contrast set.
2. The social survey big data construction system of claim 1, wherein the first camera unit and the second camera unit collect image data every period T.
3. The social survey big data construction system of claim 2, wherein the period T is 0.1 s.
4. The social survey big data construction system of claim 1, wherein the survey area is a shopping mall and the consumption data is a consumption amount.
5. The social survey of claim 1Data construction system characterized in that the first mapping is St=f1(r1，r2T), the second mapping being Ct=f2(St，r1，r2，t)，f1() Is StAnd r1、r2T, f2() Is CtAnd St、r1、r2T, where r1，r2The average moving speed of the pixel points in the first reference set and the second reference set is respectively.
6. The social survey big data construction system of claim 1, wherein the first processing unit and the second processing unit determine velocity vectors (u) according to an optical flow algorithmxy，vxy)。
7. The social survey big data construction system of claim 1, wherein the mapping construction unit constructs a third mapping of the first contrast set and the second contrast set, the third mapping being g1(St，t)=g2 (Ct，t)，g1()、g2() Is StT and CtAnd t.
CN202110895985.9A 2021-08-05 2021-08-05 Social investigation big data construction system Withdrawn CN113344649A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110895985.9A CN113344649A (en) 2021-08-05 2021-08-05 Social investigation big data construction system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110895985.9A CN113344649A (en) 2021-08-05 2021-08-05 Social investigation big data construction system

Publications (1)

Publication Number Publication Date
CN113344649A true CN113344649A (en) 2021-09-03

Family

ID=77480826

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110895985.9A Withdrawn CN113344649A (en) 2021-08-05 2021-08-05 Social investigation big data construction system

Country Status (1)

Country Link
CN (1) CN113344649A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101739653A (en) * 2008-11-13 2010-06-16 上海汇纳网络信息科技有限公司 Passenger flow analysis system
EP2426642A1 (en) * 2009-04-28 2012-03-07 Hisense State Key Laboratory Of Digital Multi-Media Technology Co., Ltd. Method, device and system for motion detection
CN105023019A (en) * 2014-04-17 2015-11-04 复旦大学 Characteristic description method used for monitoring and automatically detecting group abnormity behavior through video
CN107133825A (en) * 2017-05-19 2017-09-05 上海斐讯数据通信技术有限公司 The Forecasting Methodology and device of a kind of businessman's volume of the flow of passengers
CN108537184A (en) * 2018-04-13 2018-09-14 郑俊杰 A kind of stream of people's statistical system being applicable in market survey
CN109782014A (en) * 2019-03-11 2019-05-21 南京理工大学泰州科技学院 A kind of unmanned plane method for determining speed and device
CN111652161A (en) * 2020-06-08 2020-09-11 上海商汤智能科技有限公司 Crowd excess density prediction method and device, electronic equipment and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101739653A (en) * 2008-11-13 2010-06-16 上海汇纳网络信息科技有限公司 Passenger flow analysis system
EP2426642A1 (en) * 2009-04-28 2012-03-07 Hisense State Key Laboratory Of Digital Multi-Media Technology Co., Ltd. Method, device and system for motion detection
CN105023019A (en) * 2014-04-17 2015-11-04 复旦大学 Characteristic description method used for monitoring and automatically detecting group abnormity behavior through video
CN107133825A (en) * 2017-05-19 2017-09-05 上海斐讯数据通信技术有限公司 The Forecasting Methodology and device of a kind of businessman's volume of the flow of passengers
CN108537184A (en) * 2018-04-13 2018-09-14 郑俊杰 A kind of stream of people's statistical system being applicable in market survey
CN109782014A (en) * 2019-03-11 2019-05-21 南京理工大学泰州科技学院 A kind of unmanned plane method for determining speed and device
CN111652161A (en) * 2020-06-08 2020-09-11 上海商汤智能科技有限公司 Crowd excess density prediction method and device, electronic equipment and storage medium

Similar Documents

Publication Publication Date Title
JP7036863B2 (en) Systems and methods for activity monitoring using video data
KR101723073B1 (en) Ine dust concentration measuring apparatus and fine dust concentration measuring system
WO2017122258A1 (en) Congestion-state-monitoring system
CN104394377B (en) A kind of fuzzy abnormal recognition methods of monitoring image and device
CN106650584B (en) Flame detecting method and system
WO2016114134A1 (en) Motion condition estimation device, motion condition estimation method and program recording medium
CN105791774A (en) Surveillance video transmission method based on video content analysis
CN103179350B (en) The camera and method of the exposure of picture frame in picture frame sequence based on the sports level optimization capturing scenes in scene
CN103258232B (en) A kind of public place crowd estimate's method based on dual camera
CN101431664A (en) Automatic detection method and system for intensity of passenger flow based on video image
CN106570449B (en) A kind of flow of the people defined based on region and popularity detection method and detection system
JP2015186202A (en) Residence condition analysis device, residence condition analysis system and residence condition analysis method
Srivastava et al. Crowd flow estimation using multiple visual features for scenes with changing crowd densities
CN103226860B (en) Passage passenger traffic density estimation method
JP2014006586A (en) Information processor, and control method and computer program thereof
CN107240092A (en) A kind of image blur detection method and device
CN110187142A (en) Flow monitoring method and system
CN110880184A (en) Method and device for carrying out automatic camera inspection based on optical flow field
KR20100093797A (en) Method and system for vision-based people counting in cctv
CN112906590A (en) FairMOT-based multi-target tracking pedestrian flow monitoring method
Ua-Areemitr et al. Low-cost road traffic state estimation system using time-spatial image processing
CN109711313B (en) Real-time video monitoring method for identifying sewage poured into river channel
CN112714308B (en) Method and device for detecting video rolling stripes
KR101640527B1 (en) Method and Apparatus for Monitoring Video for Estimating Size of Single Object
CN113344649A (en) Social investigation big data construction 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
WW01 Invention patent application withdrawn after publication
WW01 Invention patent application withdrawn after publication

Application publication date: 20210903