CN111291216B - Method and system for analyzing foothold based on face structured data - Google Patents
Method and system for analyzing foothold based on face structured data Download PDFInfo
- Publication number
- CN111291216B CN111291216B CN202010131202.5A CN202010131202A CN111291216B CN 111291216 B CN111291216 B CN 111291216B CN 202010131202 A CN202010131202 A CN 202010131202A CN 111291216 B CN111291216 B CN 111291216B
- Authority
- CN
- China
- Prior art keywords
- score
- face
- data
- track data
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/75—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
- G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Abstract
The invention provides a method and a system for analyzing foothold based on face structural data, which comprises the steps of merging all monitoring equipment in an aggregation ring into a set to obtain monitoring data of the aggregation ring; acquiring a first face track data set with the face similarity of a person to be analyzed being larger than a first threshold value in monitoring data based on face recognition; filtering the face track data with the stay time less than a second threshold value in the first face track data set to obtain a second face track data set; and traversing the second face track data set, weighting and superposing the occurrence frequency score, the timeliness score, the time period score, the site coincidence score and the continuity score of the face track data to obtain a comprehensive score of the gathering circle, and acquiring the foothold of the person to be analyzed according to the ranking of the comprehensive score of the gathering circle. The position of the falling foot point of the personnel can be analyzed more accurately by acquiring the gathering circle data through multi-dimensional comprehensive analysis.
Description
Technical Field
The invention relates to the field of personnel trajectory analysis, in particular to a method and a system for analyzing foothold points based on face structured data.
Background
With the popularization of monitoring equipment installation and the continuous development of face recognition technology, face data becomes an important part of person trajectory data. After the face of a person is collected by the snapshot camera, the face of the person can be shot by the recognition engine and compared with the identification photo of the person, so that the person can be shot at a high probability, and the time and place of the person can be recorded. Therefore, the face snapshot track of the person can be formed for a long time. Based on the face snapshot track of the person, the activity rule of the person can be analyzed through a data mining technology.
In order to know the position situation of a specific person in a specified time period, the foothold analysis is carried out on the specific person, namely, the position situation that the specific person does not leave within a certain time is analyzed. At present, when the foothold analysis is performed, a user inputs a time range to be analyzed and a specific time period, for example, a travel time period and a return time period of one day, and because the time period in which a person appears can be set at will, the difficulty of preprocessing is increased. In the recording of a large amount of data, a user performs the analysis of the foothold in real time, and the amount of data to be processed is large, which takes a long time. On the other hand, the method counts all areas with cameras which a specific person passes in a specific time period within a certain time range, if the specific time period is not the time period of regular travel of the specific person, the final statistical result is only the statistics of the camera areas in the route, and the output result is a set of isolated camera positions which are arranged in descending order according to the passing times. The existing personnel trajectory analysis only simply counts the occurrence frequency of each device, then carries out sequencing and calculates the result, so that the analysis data is not accurate and error results are easy to generate, and users are misled.
Disclosure of Invention
In order to solve the problems that in the prior art, the number of times of occurrence of each device is simply counted, then sequencing is carried out, and a result is calculated, the invention provides a method and a system for analyzing foothold points based on face structured data, and the technical problems that the analysis data is inaccurate and wrong results are easy to generate are solved.
In one aspect, the present invention provides a method for analyzing foothold based on face structured data, including the following steps:
s1: merging all monitoring equipment in the gathering circle into a set to obtain monitoring data of the gathering circle;
s2: acquiring a first face track data set with the face similarity of a person to be analyzed being larger than a first threshold value in monitoring data based on face recognition;
s3: filtering the face track data with the stay time less than a second threshold value in the first face track data set to obtain a second face track data set;
s4: and traversing the second face track data set, weighting and superposing the occurrence frequency score, the timeliness score, the time period score, the site coincidence score and the continuity score of the face track data to obtain a comprehensive score of the gathering circle, and acquiring the foothold of the person to be analyzed according to the ranking of the comprehensive score of the gathering circle.
In particular embodiments, the focus circle includes stations, cells, intersections, and streets. Through the arrangement of the gathering ring, data of monitoring equipment in one area are unified and regular, and the foot falling track of personnel can be effectively obtained.
In a specific embodiment, the first threshold is 85%. By means of the setting of the first threshold value, people meeting the similarity of the faces can be screened out, and the accuracy of an analyst is ensured.
In a specific embodiment, the second threshold is 2 hours. By means of the setting of the second threshold value, the situation that the track information of the temporarily passing personnel is mistakenly regarded as the foothold can be avoided, the validity of the data is guaranteed, and meanwhile the analysis amount of the data can be reduced.
In a specific embodiment, step S3 specifically includes the following steps:
filtering face track data with the stay time less than a second threshold value in the first face track data set, grouping the filtered face track data according to days, and sequencing the data in the group according to time;
responding to the number of the data in the group which is more than or equal to 3, reserving head and tail data, filtering the intermediate data based on a preset filtering rule and then obtaining a second face track data set, wherein the filtering rule specifically comprises the following steps: and sequentially subtracting the snapshot time of the previous data from the snapshot time of the next data, filtering the previous data if the previous data is smaller than a preset time length threshold, and keeping the previous data if the previous data is larger than the preset time length threshold. The data are grouped according to the day, the data can be orderly arranged, and the effectiveness and the accuracy of the data can be further improved through the filtering of the data in the group.
In a specific embodiment, the calculation rule of the comprehensive score in step S4 is specifically:
taking the occurrence frequency of the person to be analyzed in the second face track data set as a basic score of the comprehensive score;
the timeliness score is the timeliness weight basis score, the time period score is the time period weight basis score, the site coincidence score is the site coincidence weight basis score, and the continuity score is specifically expressed as the continuous occurrence days with the largest aggregation circle, wherein the timeliness weight is 0.5, the time period weight is 0.2, and the site coincidence weight is 0.2;
the composite score is the timeliness score + the time period score + the site-anastomosis score + the continuity score. Through the calculation of each score and the statistics of the comprehensive scores, the scores of each landing point can be obtained through statistics, and data support is provided for a final result.
In a preferred embodiment, the timeliness is that the data recording time of the person to be analyzed is within a month, the time period includes the working hours and weekends of the working day, and the site coincidence specifically includes whether the first appearance site and the last appearance site are the same clustering circle. The timeliness, the time period and the place coincidence are used as scoring items, so that the final result has a reference meaning, and the foot placement point and track information of an analyst can be reflected.
In a preferred embodiment, step S4 further includes filtering the clustering circles with the composite score smaller than the third threshold, and determining the clustering circle with the top three of the composite score as the foothold of the person to be analyzed. The first three gathering circles are taken as the foothold of the person to be analyzed, and the result obtained through comprehensive analysis is more accurate and reasonable.
According to a second aspect of the present invention, a computer-readable storage medium is proposed, on which a computer program is stored, which computer program, when being executed by a computer processor, is adapted to carry out the above-mentioned method.
According to a third aspect of the present invention, a system for analyzing foothold based on face structured data is provided, the system comprising:
the gathering circle unit is configured to combine all monitoring devices in the gathering circle into a set to acquire monitoring data of the gathering circle;
the first face track data set generating unit is configured to acquire a first face track data set, of which the face similarity with a person to be analyzed is greater than a first threshold, from the monitoring data based on face recognition;
the second face track data set screening unit is configured to filter face track data of which the stay time is less than a second threshold value in the first face track data set to obtain a second face track data set;
and the foot-drop point analysis unit is configured for traversing the second face track data set, weighting and superposing the appearance frequency score, the timeliness score, the time period score, the site coincidence score and the continuity score of the face track data to obtain a comprehensive score of the gathering circle, and obtaining the foot-drop points of the personnel to be analyzed according to the ranking of the comprehensive score of the gathering circle.
The invention analyzes the position of the foot-falling point of the personnel in the gathering circle through the demarcation of the gathering circle, and finally obtains the grade of the personnel to be analyzed corresponding to each gathering circle through the multidimensional data analysis such as timeliness, time period, site coincidence and the like and the weighting of the data of each dimension, thereby obtaining the most accurate foot-falling point position. Compared with the traditional analysis method in which the frequency of occurrence of each device is simply counted and then the result calculated by sequencing is carried out, the method can obtain the possible foot-falling points of the person to be analyzed accurately according to the face track data.
Drawings
The accompanying drawings are included to provide a further understanding of the embodiments and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments and together with the description serve to explain the principles of the invention. Other embodiments and many of the intended advantages of embodiments will be readily appreciated as they become better understood by reference to the following detailed description. Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of a method for analyzing foothold based on face structured data according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating filtering rules for data within a group according to an embodiment of the present invention;
FIG. 3 is a block diagram of a system for analyzing foothold based on face structured data according to an embodiment of the present invention;
FIG. 4 is a block diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
In accordance with an embodiment of the present invention, a method for benchmarking data items, fig. 1 shows a method for analyzing foothold based on face structured data according to an embodiment of the present invention. As shown in fig. 1, the method comprises the steps of:
s101: and merging all the monitoring equipment in the gathering circle into a set to acquire the monitoring data of the gathering circle. Due to the arrangement of the gathering ring, monitoring data of a certain area can be structured and unified, and track analysis and foot drop point determination analysis are facilitated.
In a specific embodiment, all monitoring devices of a certain cell may be combined in a set, and divided into a cluster ring. The railway station, the subway station, the BRT, a plurality of devices at a certain intersection and the like can be divided into a gathering circle. Through the combination of the monitoring equipment in the gathering circle, the foot-falling point can be defined as a certain gathering circle, the analysis amount of data can be greatly reduced, and the analysis efficiency is improved. The monitoring equipment can be all monitoring devices which can acquire face information, such as a monitoring camera, a snapshot camera and the like in the gathering circle, and monitored data serve as a data base of subsequent analysis.
S102: and acquiring a first face track data set with the face similarity of the person to be analyzed being greater than a first threshold value in the monitoring data based on face recognition. The face recognition technology can be used for effectively recognizing the occurrence condition of the personnel needing to be analyzed in each gathering circle, and is the basis of data analysis.
In a specific embodiment, data of a person to be analyzed within a certain time period (for example, a near half year) may be obtained as an analysis database of the footfall point, and all face snapshot trajectory data sets whose face similarity of the person to be analyzed is greater than a first threshold are classified into a first face trajectory data set as an initial analysis database. Preferably, the first threshold is set to 85%, and by setting the first threshold, the accuracy of the identified face track snapshot data can be ensured, the occurrence of some recognition errors is avoided, and the noise of analysis is increased, it should be recognized that the value of the first threshold can be adjusted according to the actual analysis requirements besides 85%, the first threshold can be adjusted to a value greater than 85%, for example, 90% and the like in some analysis scenes with special requirements, and the first threshold can be adjusted to a value less than 85%, for example, 75% and the like in some analysis scenes with smaller requirements, so that the analysis data requirements in different scenes are met, and the technical effects of the present invention can also be achieved.
S103: and filtering the face track data with the stay time less than a second threshold value in the first face track data set to obtain a second face track data set. The retention time is an important parameter and can reflect the staying condition of a person in a certain gathering circle, if the retention time is shorter, the situation that the person appears in the gathering circle is only possible to pass by and is not a footfall point, and the retention time is used as a data condition for screening so as to further reduce the data volume and improve the analysis efficiency.
In a preferred embodiment, the second threshold is set to 2 hours, and the face track data with the dwell time longer than the second threshold is generated into a second face track data set. The data in the second face track data set has more analysis value of the footfall points. It should also be appreciated that the value of the second threshold can be adjusted according to different analysis requirements, and is set as data for more than 2 hours or less than 2 hours, which can also achieve the technical effects of the present invention.
In a specific embodiment, all the trajectory data in the second face trajectory data set are grouped by day, one group is formed in one day, and the trajectory data in the group is sorted in a positive sequence by time. And filtering the data in the group again by using a preset filtering rule. When the track data volume in the group is greater than or equal to 3, the data in the group needs to be filtered, and the specific filtering rule is as follows: and (3) sequentially subtracting the snapshot time of the previous track data from the snapshot time of the middle track data except the first track data and the last track data, and filtering the track data if the duration is less than a preset value X.
FIG. 2 is a diagram illustrating filtering rules for intra-group data according to a specific embodiment of the present invention, and as shown in FIG. 2, it is assumed that there is snapshot data A, B, C, D in a certain day, and their snapshot times are T1, T2, T3, T4, respectively, and are arranged in time. Removing A, D two data, not comparing, if the duration R1 of C's snapshot time T3 minus B's snapshot time T2 is less than a certain value X (for example 1 hour), filtering out snapshot record B; if the duration R2 of the snapshot time T4 of D minus the snapshot time T3 of C is greater than a certain value X (e.g., 1 hour), the snapshot record C is retained. By utilizing the filtering rule, data in the second face track data set can be further eliminated, track data without reference value are filtered, and the effectiveness of the data and the accuracy of analysis are improved.
S104: and traversing the second face track data set, weighting and superposing the occurrence frequency score, the timeliness score, the time period score, the site coincidence score and the continuity score of the face track data to obtain a comprehensive score of the gathering circle, and acquiring the foothold of the person to be analyzed according to the ranking of the comprehensive score of the gathering circle. The determined foot placement point is more accurate and error conditions can not occur by comprehensively evaluating and analyzing multiple dimensions of occurrence frequency, timeliness, time periods, site coincidence and continuity.
In a specific embodiment, a mapping relation between the monitoring equipment and the aggregation rings is obtained according to data of the aggregation rings, analysis is performed according to the dimensions of the aggregation rings, snapshot data of all equipment in the aggregation rings are counted, and if no data of the aggregation rings exists, analysis and counting are performed on one equipment according to one dimension. And (3) counting to obtain an aggregation circle score Y, wherein the specific calculation mode of the aggregation circle score is as follows: taking the occurrence frequency of the person to be analyzed in the second face track data set as a basic score of the comprehensive score; the timeliness score is the timeliness weight basis score, the time period score is the time period weight basis score, the site coincidence score is the site coincidence weight basis score, and the continuity score is specifically expressed as the continuous occurrence days with the largest aggregation circle, wherein the timeliness weight is 0.5, the time period weight is 0.2, and the site coincidence weight is 0.2; the composite score is the timeliness score + the time period score + the site-anastomosis score + the continuity score.
In a specific embodiment, all the snapshot data in the second face trajectory data set after the statistical filtering is circularly traversed, and the occurrence frequency scoring is performed: and when one record appears, counting 1 point, and when M records appear, counting M points, wherein the M points are used as the basis for subsequent scoring.
Evaluation of timeliness score: if the snapshot time of a record is nearly one month, the score of the record is 0.5M, and the score Y of the gathering circle is M + 0.5M. The timeliness of the snapshot time can reflect the recent occurrence condition of the trajectory data, and the method has strong analysis value.
Evaluation of time section score: if the snapshot time of the record occurs between 7 am and 9 pm on monday to friday or 18 pm and 20 pm on saturday and sunday, the score of the record is 0.2M, and the score Y of the gathering circle is M +0.5M + 0.2M. The time period can reflect certain behavior conditions of the person to be analyzed, such as the activities of going to work or on weekends, and the position and the time condition of a foot-falling point of the person to be analyzed, which may occur subsequently, can be deduced through the evaluation of the item.
Evaluation of site-matching score: when the last piece of data of the current day is traversed, if the first appearing place and the last appearing place are the same clustering circle, and the duration of the time interval between two appearances is greater than the preset duration value, the score of the record is counted as 0.2M, and the score Y of the clustering circle is equal to M +0.5M +0.2M + 0.2M. The daily trajectory of the person to be analyzed can be known by matching the first place of occurrence with the last place of occurrence, for example, from home and then finally back to home.
Evaluation of continuity score: counting the number of days of occurrence of each clustering circle in the filtered second face track data set, calculating the maximum number of continuous days of occurrence, and if the maximum number of continuous days of occurrence is P days, determining that the score Y of the clustering circle is M +0.5M +0.2M +0.2M + PM. For example, if the date of appearance of a certain circle of aggregation E is 10 months No. 1, 10 months No. 2, 10 months No. 5, 10 months No. 11, 10 months No. 12, 10 months No. 13, the maximum number of consecutive days of appearance of the circle of aggregation is 3, and 3M points are added to the circle of aggregation E. The continuous occurrence days have strong representativeness, can reflect the continuous occurrence condition of the person to be analyzed, and can provide a more valuable reference for the position of the next occurring foot drop point of the person to be analyzed.
In a specific embodiment, a comprehensive score of the aggregation circles is obtained through comprehensive evaluation of the items, the aggregation circles are sorted according to the score, data with the score smaller than a preset score (for example, 100 scores) are filtered, and the aggregation circle record with the top three is taken as a possible footfall point. It should be appreciated that the weighting factors of the items in the scoring process may be adjusted according to actual analysis conditions, for example, the score meeting the conditions in the timeliness evaluation may be counted as 0.6M, the score meeting the conditions in the time period score evaluation may be counted as 0.3M, and the like, and the technical effects of the present invention may also be achieved by specifically adjusting according to the importance degrees of the items in different analysis requirements.
With continued reference to FIG. 3, FIG. 3 is a block diagram of a system for analyzing foothold based on face structured data according to an embodiment of the present invention. The system comprises an aggregation ring unit 301, a first face track data set generation unit 302, a second face track data set generation unit 303 and a foothold analysis unit 304 which are connected in sequence.
In a specific embodiment, the colony unit 301 is configured to merge all monitoring devices in a colony into one set, and obtain monitoring data of the colony; the first face trajectory data set generating unit 302 is configured to obtain, based on face recognition, a first face trajectory data set in the monitoring data, where the similarity between the face and the person to be analyzed is greater than a first threshold; the second face trajectory data set generating unit 303 is configured to filter face trajectory data of which the staying time is less than a second threshold in the first face trajectory data set, and obtain a second face trajectory data set; the foothold analysis unit 304 is configured to traverse the second face trajectory data set, obtain a comprehensive score of the aggregation circle based on the occurrence frequency score, the timeliness score, the time period score, the location coincidence score, and the continuity score of the face trajectory data by weighted superposition, and obtain footholds of the person to be analyzed according to the ranking of the comprehensive score of the aggregation circle.
Referring now to FIG. 4, shown is a block diagram of a computer system 400 suitable for use in implementing the electronic device of an embodiment of the present application. The electronic device shown in fig. 4 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU)401 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the system 400 are also stored. The CPU 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
The following components are connected to the I/O interface 405: an input portion 406 including a keyboard, a mouse, and the like; an output section 407 including a display such as a Liquid Crystal Display (LCD) and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN card, a modem, or the like. The communication section 409 performs communication processing via a network such as the internet. A driver 410 is also connected to the I/O interface 405 as needed. A removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 410 as necessary, so that a computer program read out therefrom is mounted into the storage section 408 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer-readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 409, and/or installed from the removable medium 411. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 401. It should be noted that the computer readable storage medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable storage medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Sma l lta l k, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present application may be implemented by software or hardware.
As another aspect, the present application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable storage medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: merging all monitoring equipment in the gathering circle into a set to obtain monitoring data of the gathering circle; acquiring a first face track data set with the face similarity of a person to be analyzed being larger than a first threshold value in monitoring data based on face recognition; filtering the face track data with the stay time less than a second threshold value in the first face track data set to obtain a second face track data set; and traversing the second face track data set, weighting and superposing the occurrence frequency score, the timeliness score, the time period score, the site coincidence score and the continuity score of the face track data to obtain a comprehensive score of the gathering circle, and acquiring the foothold of the person to be analyzed according to the ranking of the comprehensive score of the gathering circle.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (8)
1. A method for analyzing foothold based on face structural data is characterized by comprising the following steps:
s1: merging all monitoring equipment in a gathering circle into a set to acquire monitoring data of the gathering circle;
s2: acquiring a first face track data set with the face similarity of the person to be analyzed being larger than a first threshold value in the monitoring data based on face recognition;
s3: filtering the face track data with the stay time less than a second threshold value in the first face track data set to obtain a second face track data set;
s4: traversing the second face track data set, weighting and superposing the occurrence frequency score, the timeliness score, the time period score, the place coincidence score and the continuity score of the second face track data to obtain a comprehensive score of the gathering circle, and obtaining the foot landing point of the person to be analyzed according to the ranking of the comprehensive score of the gathering circle;
wherein, the calculation rule of the comprehensive score specifically comprises the following steps:
taking the occurrence frequency of the person to be analyzed in the second face track data set as a basic score of the comprehensive score;
the timeliness score = timeliness weight basis score, the time period score = time period weight basis score, the place-coincidence score = place-coincidence weight basis score, and the continuity score is specifically represented by the largest consecutive days of occurrence of the gathering circle, wherein the timeliness weight is 0.5, the time period weight is 0.2, and the place-coincidence weight is 0.2;
the composite score = the timeliness score + the time period score + the location-compliance score + continuity score; the timeliness specifically means that the data recording time of the person to be analyzed is within nearly one month, the time period includes the working hours and weekends of a working day, and the site coincidence specifically includes whether the first occurrence site and the last occurrence site are the same aggregation circle.
2. The method of claim 1, wherein the colony comprises a station, a cell, an intersection, and a street.
3. The method of claim 1, wherein the first threshold is 85%.
4. The method of claim 1, wherein the second threshold is 2 hours.
5. The method for analyzing foothold based on face structured data according to claim 1, wherein the step S3 specifically comprises the following steps:
filtering face track data with the stay time less than a second threshold value in the first face track data set, grouping the filtered face track data according to days, and sequencing data in the group according to time;
responding to the number of the data in the group being more than or equal to 3, reserving head and tail data, filtering intermediate data based on a preset filtering rule, and then obtaining a second face track data set, wherein the filtering rule specifically is as follows: and sequentially subtracting the snapshot time of the previous data from the snapshot time of the next data, filtering the previous data if the previous data is smaller than a preset time length threshold, and keeping the previous data if the previous data is larger than the preset time length threshold.
6. The method for analyzing foothold based on face structured data of claim 1, wherein the step S4 further comprises filtering the aggregation circles with the composite score smaller than a third threshold, and determining the aggregation circle with the top three of the composite score as the foothold of the person to be analyzed.
7. A computer-readable storage medium having one or more computer programs stored thereon, which when executed by a computer processor perform the method of any one of claims 1 to 6.
8. A system for analyzing foothold based on face structured data, the system comprising:
the gathering circle unit is configured to combine all monitoring devices in a gathering circle into a set to acquire monitoring data of the gathering circle;
the first face track data set generating unit is configured to acquire a first face track data set, of which the face similarity with a person to be analyzed is greater than a first threshold, from the monitoring data based on face recognition;
the second face track data set screening unit is configured to filter face track data of which the stay time is less than a second threshold value in the first face track data set to obtain a second face track data set;
a foothold analysis unit configured to traverse the second face trajectory data set, obtain a comprehensive score of the aggregation circle based on a weighted superposition of an occurrence frequency score, a timeliness score, a time period score, a location coincidence score, and a continuity score of the second face trajectory data, and obtain footholds of the person to be analyzed according to a ranking of the comprehensive score of the aggregation circle;
wherein, the calculation rule of the comprehensive score specifically comprises the following steps:
taking the occurrence frequency of the person to be analyzed in the second face track data set as the basic score of the comprehensive score;
the timeliness score = timeliness weight basis score, the time period score = time period weight basis score, the site-coincidence score = site-coincidence weight basis score, the continuity score is specifically expressed as the number of consecutive days of occurrence of the largest aggregate circle, wherein the timeliness weight is 0.5, the time period weight is 0.2, and the site-coincidence weight is 0.2;
the composite score = the timeliness score + the time period score + the location-compliance score + continuity score; the timeliness specifically means that the data recording time of the personnel to be analyzed is within a month, the time period includes the working hours and weekends of a working day, and the place coincidence specifically includes whether the first place of occurrence and the last place of occurrence are the same gathering circle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010131202.5A CN111291216B (en) | 2020-02-28 | 2020-02-28 | Method and system for analyzing foothold based on face structured data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010131202.5A CN111291216B (en) | 2020-02-28 | 2020-02-28 | Method and system for analyzing foothold based on face structured data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111291216A CN111291216A (en) | 2020-06-16 |
| CN111291216B true CN111291216B (en) | 2022-06-14 |
Family
ID=71020574
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010131202.5A Active CN111291216B (en) | 2020-02-28 | 2020-02-28 | Method and system for analyzing foothold based on face structured data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111291216B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111883254A (en) * | 2020-07-20 | 2020-11-03 | 罗普特科技集团股份有限公司 | Method and system for analyzing risk degree of psychopath based on face track |
| CN113627719A (en) * | 2021-07-01 | 2021-11-09 | 广州云徙科技有限公司 | System and method for managing and controlling risk of local production channel |
| CN113626684B (en) * | 2021-07-07 | 2022-07-15 | 厦门市美亚柏科信息股份有限公司 | Method and device for analyzing advancing mode of object |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103246869A (en) * | 2013-04-19 | 2013-08-14 | 福建亿榕信息技术有限公司 | Crime monitoring method based on face recognition technology and behavior and sound recognition |
| CN106227889A (en) * | 2016-08-15 | 2016-12-14 | 华云科技有限公司 | A kind of track dwell point analyzes extracting method |
| CN106650652A (en) * | 2016-12-14 | 2017-05-10 | 黄先开 | Trajectory tracking system and method based on face recognition technology |
| CN107204114A (en) * | 2016-03-18 | 2017-09-26 | 中兴通讯股份有限公司 | A kind of recognition methods of vehicle abnormality behavior and device |
| KR101849327B1 (en) * | 2017-11-23 | 2018-04-17 | 주식회사 핀텔 | Method and apparatus for controlling door |
| CN109815878A (en) * | 2019-01-18 | 2019-05-28 | 深圳英飞拓智能技术有限公司 | Foothold analysis method and device based on recognition of face |
| CN110210276A (en) * | 2018-05-15 | 2019-09-06 | 腾讯科技（深圳）有限公司 | A kind of motion track acquisition methods and its equipment, storage medium, terminal |
-
2020
- 2020-02-28 CN CN202010131202.5A patent/CN111291216B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103246869A (en) * | 2013-04-19 | 2013-08-14 | 福建亿榕信息技术有限公司 | Crime monitoring method based on face recognition technology and behavior and sound recognition |
| CN107204114A (en) * | 2016-03-18 | 2017-09-26 | 中兴通讯股份有限公司 | A kind of recognition methods of vehicle abnormality behavior and device |
| CN106227889A (en) * | 2016-08-15 | 2016-12-14 | 华云科技有限公司 | A kind of track dwell point analyzes extracting method |
| CN106650652A (en) * | 2016-12-14 | 2017-05-10 | 黄先开 | Trajectory tracking system and method based on face recognition technology |
| KR101849327B1 (en) * | 2017-11-23 | 2018-04-17 | 주식회사 핀텔 | Method and apparatus for controlling door |
| CN110210276A (en) * | 2018-05-15 | 2019-09-06 | 腾讯科技（深圳）有限公司 | A kind of motion track acquisition methods and its equipment, storage medium, terminal |
| CN109815878A (en) * | 2019-01-18 | 2019-05-28 | 深圳英飞拓智能技术有限公司 | Foothold analysis method and device based on recognition of face |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111291216A (en) | 2020-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111291216B (en) | Method and system for analyzing foothold based on face structured data | |
| CN110245981B (en) | Crowd type identification method based on mobile phone signaling data | |
| CN108537544B (en) | Real-time monitoring method and monitoring system for transaction system | |
| CN108346292B (en) | Urban expressway real-time traffic index calculation method based on checkpoint data | |
| US20170286845A1 (en) | Automatic extraction of user mobility behaviors and interaction preferences using spatio-temporal data | |
| WO2022142042A1 (en) | Abnormal data detection method and apparatus, computer device and storage medium | |
| CN110298254A (en) | A kind of analysis method and system for personnel's abnormal behaviour | |
| WO2021126243A1 (en) | Systems and methods for detecting and responding to anomalous traffic conditions | |
| Zheng et al. | Investigation of model ensemble for fine-grained air quality prediction | |
| CN110276977B (en) | Bus station matching method, device, equipment and readable storage medium | |
| CN112232178A (en) | Region footfall point judgment method, system, device and medium based on portrait gathering | |
| CN111105628A (en) | Parking lot portrait construction method and device | |
| CN114428828A (en) | Method and device for digging new road based on driving track and electronic equipment | |
| WO2018141583A1 (en) | A method of predicting a traffic behaviour in a road system | |
| CN110889092A (en) | Short-time large-scale activity peripheral track station passenger flow volume prediction method based on track transaction data | |
| Ma et al. | Public transportation big data mining and analysis | |
| CN110021161A (en) | A kind of prediction technique and system of traffic direction | |
| CN108053646B (en) | Traffic characteristic obtaining method, traffic characteristic prediction method and traffic characteristic prediction system based on time sensitive characteristics | |
| CN107818415B (en) | General recognition method based on subway card swiping data | |
| Kwee et al. | Traffic-cascade: Mining and visualizing lifecycles of traffic congestion events using public bus trajectories | |
| Barkley et al. | Relating travel time reliability and nonrecurrent congestion with multistate models | |
| Salamanis et al. | Evaluating the effect of time series segmentation on STARIMA-based traffic prediction model | |
| CN111369394B (en) | Scenic spot passenger flow volume statistical evaluation system and method based on big data | |
| CN114611622A (en) | Method for identifying cross-city commuting crowd by utilizing mobile phone data | |
| CN114407661A (en) | Data-driven electric vehicle energy consumption prediction method, system, device and medium |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221027 Address after: 361000 unit 0006, No. 366, Chengyi street, phase III, software park, Jimei District, Xiamen City, Fujian Province Patentee after: ROPT TECHNOLOGY GROUP Co.,Ltd. Patentee after: ROPT (Shanghai) Technology Co.,Ltd. Address before: 361000 unit 0006, No. 366, Chengyi street, phase III, software park, Jimei District, Xiamen City, Fujian Province Patentee before: ROPT TECHNOLOGY GROUP Co.,Ltd. |