CN117314077A - Channel gate data supervision method and system based on big data - Google Patents
Channel gate data supervision method and system based on big data Download PDFInfo
- Publication number
- CN117314077A CN117314077A CN202311247306.2A CN202311247306A CN117314077A CN 117314077 A CN117314077 A CN 117314077A CN 202311247306 A CN202311247306 A CN 202311247306A CN 117314077 A CN117314077 A CN 117314077A
- Authority
- CN
- China
- Prior art keywords
- gate
- data
- pedestrian
- target object
- monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims description 30
- 238000012544 monitoring process Methods 0.000 claims abstract description 108
- 238000007405 data analysis Methods 0.000 claims abstract description 17
- 230000006698 induction Effects 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 9
- 230000035945 sensitivity Effects 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000036632 reaction speed Effects 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Computer Security & Cryptography (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Emergency Management (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of gate supervision. The channel gate data monitoring system comprises a data acquisition module, a data analysis module, a gate monitoring module and an alarm reminding module, wherein the data acquisition module is used for acquiring a monitoring video in a target object range, and a historical time interval from a gate induction effective pass certificate to a gate complete opening and an actual switching time of the gate; the data analysis module is used for analyzing the area of the gate allowing passage and the exposed area of the package carried by the pedestrian according to the monitoring video within the range of the target object; the gate monitoring module monitors the gate and controls the switching time of the gate; and the warning reminding module carries out warning reminding when the accumulated number of times of mismatch between the switch time set by the gate and the actual switch time exceeds a preset threshold value. According to the invention, the gate switching time is limited according to the pedestrian information, so that the pedestrian delay is avoided, and the burden of staff is reduced.
Description
Technical Field
The invention relates to the technical field of gate monitoring, in particular to a channel gate data monitoring method and system based on big data.
Background
In the past place management, a manual management mode is generally adopted, and patrol and nursing are needed to be carried out on the place by security personnel, but a certain safety risk exists in the mode, and the place is difficult to monitor. With the development of society and the progress of science and technology, the demands of people for safety management are continuously increased, and effective management and monitoring of personnel entering and exiting can be expected to be realized through technical means, so that the safety and management efficiency of places are improved. The running state of the channel gate is collected through equipment such as a high-precision sensor, a camera and the like, raw data obtained by a mobile phone are preprocessed, and the service condition, the personnel flow, abnormal events and the like of the channel gate are analyzed and managed by utilizing a big data technology so as to improve the safety, the efficiency and the intellectualization of the channel gate; the channel gate is usually composed of an access control system, a face recognition system, an infrared detection system and the like, so that the automatic access of personnel can be realized, the safety of the field and the building is improved, the passing efficiency of the access is improved, and the burden of the staff is lightened.
Under the prior art, when a sensor arranged on the gate senses that a pedestrian passes through the gate, the gate is closed; however, in special places such as a station, the switching time of the gate is limited, and when pedestrians do not pass through the gate within a specified time limit, the pedestrians cannot pass through the gate again by means of the effective pass certificates, and the pedestrians need to resort to staff for manual security inspection, so that the operation may delay the travel and limit the switching time of the gate.
Disclosure of Invention
The invention aims to provide a channel gate data supervision method and system based on big data, which are used for solving the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: the channel gate data supervision method based on big data specifically comprises the following steps:
s100, acquiring a monitoring video in a target object range through a monitoring terminal, and analyzing pedestrian information in the target object range according to the monitoring video; the pedestrian information comprises package information of pedestrians and position information of pedestrians;
s200, acquiring historical data information of a gate in a target object range according to historical data, analyzing response sensitivity of the gate according to the historical data information of the gate in the target object range, and analyzing allowable traffic volume of the gate; resetting the initial switching time of the gate through the response sensitivity of the gate;
s300, limiting the passing time of pedestrians, namely the gate switching duration, in the range of the target object according to the pedestrian information and the gate allowed passing volume;
s400, constructing a matching model, and when the limited gate switch time length is not matched with the actual gate switch time length, indicating that a gate fails so as to give an alarm; the matching model is used for matching the passing time of all pedestrians in the target object range, namely the limit time of the gate switch, with the actual switch time of the gate.
Further, the specific method for analyzing the pedestrian information in the target range according to the monitoring video in S100 is as follows:
s101, acquiring map data of a target object from an open source map provider or sensor data, mapping the target object into a coordinate system according to the map data of the target object, extracting position information of a gate from the map data, and obtaining corresponding coordinates of the gate in the coordinate system according to the relative position of the gate on the target object map, wherein the corresponding coordinates are (x 0, yi), (x 0, y 0) and are expressed as a coordinate system origin; acquiring a monitoring video in a target object range from a monitoring terminal, wherein shielding conditions exist in a monitoring shooting process due to different angles of the monitoring video, the monitoring video is required to be integrated, and the integration of the monitoring video is completed through video calibration, splicing and synchronization; extracting the position information of pedestrians from map data according to the integrated monitoring video, avoiding that partial pedestrians are blocked and the complete pedestrian position information in the target object range cannot be obtained due to the angle problem of the monitoring video, and obtaining corresponding coordinates (xj, yi) of the pedestrians in a coordinate system according to the relative positions of the pedestrians on the target object map, wherein j=1, 2 and 3..J, J is expressed as the number of people arranged in front of each gate, i=1, 2 and 3..I, and I is expressed as the number of gates in the target range; the monitoring video is a video for monitoring the target object by cameras in different directions;
s102, positioning and marking any pedestrian in a monitoring video shot by a camera behind a gate, recording any pedestrian with a calibrated mark as a, extracting frames of the monitoring video shot by the camera behind the gate to obtain a monitoring image, detecting the edge of the pedestrian with the positioned mark in the monitoring image by a Canny edge detection operator, and detecting the continuous edge in a picture by the edge detection operator, wherein the pedestrian and the parcel to which the pedestrian belong have a connection relationship so as to obtain image information between the pedestrian with the positioned mark and the parcel to which the pedestrian with the positioned mark belongs; the Canny edge detection operator has low error rate, and can extract real edge points, and non-edge points are not extracted, so that the aim of high-position precision is fulfilled;
s103, recognizing the package information of any one located mark pedestrian by utilizing a three-dimensional convolution recognition algorithm, and respectively obtaining the exposed image area of the package of the located mark pedestrian as sa, wherein sa is expressed as the exposed image area of the package of the located mark pedestrian a behind a gate in the range of a target object; traversing the monitoring video to obtain the exposed image area of all pedestrian packages in the target object range as sij, wherein sij is expressed as the exposed image area of the package, obtained by a three-dimensional convolution recognition algorithm, of the jth pedestrian arranged in front of the ith gate and the camera behind the gate.
Further, the specific method for analyzing the response sensitivity of the gate and resetting the initial time of the gate switch according to the historical data information of the gate within the target range in S200 is as follows:
s201, obtaining the height of the gate in the monitoring image according to the monitoring video shot by the camera behind the gate in the target object range, and obtaining the interval between the gates as pi=y (i-1) -yi according to the formula by corresponding coordinates (x 0, yi) of the gate in the coordinate system: si=l×pi, calculating to obtain the maximum area allowed to pass by each gate in the target object range;
s202, obtaining historical time intervals from the effective pass certificate of gate induction to the complete opening of the gate in the range of a target object in the last unit time through historical data information, wherein ti represents the historical time interval from the effective pass certificate of the ith gate induction to the opening of the gate in the range of the target object, and the longer the historical time interval from the effective pass certificate of the gate induction to the opening of the gate is, the slower the reaction speed of the gate is; according to the fact that the gate senses the effective passing evidence and starts to count, when the reaction speed of the gate is slower, the time for allowing pedestrians to pass is shorter, and when the working time of the gate is longer, the reaction speed of the gate is slower due to ageing of internal parts of the gate or other reasons; therefore, the initial switching time of the gate in the reset target range needs to be ti=t0+ (k1×ti+c), where t0 is the initial switching time value set when all gates are shipped, k1 is a coefficient, and c is an error term.
Further, the specific method for analyzing the gate opening/closing time according to the passing time of the pedestrian in the target object range in S300 is as follows:
s301, because the position of the camera behind the gate is fixed, when a pedestrian gradually approaches the gate, the area of the exposed image of all the pedestrian packages in the acquired target object range is larger and larger, and the distance between the camera behind the gate and the gate is x according to the big data, and the formula is as follows: s' ij= [ (x+xij)/xij ]. Sij, calculating to obtain the exposed image area of the camera behind the gate, wrapping the jth pedestrian in front of the ith gate, in the range of the target object with the same proportion as the maximum area allowed to pass by each gate;
s302, when the exposed image area S' c > si of any pedestrian c wrapped on the camera behind the gate, the pedestrian wrapping area detected by the camera behind the gate is larger than the maximum area allowed to pass through each gate, but the monitored area is limited because the position of the camera behind the gate is fixed, the pedestrian wrapping larger than the maximum area allowed to pass through the gate needs to be re-detected by other cameras behind the gate, and the image area exposed by the wrapping of the pedestrian c in the z-th monitoring video is obtained by traversing the monitoring video shot by other cameras behind the gate, wherein scz is represented by scz; z=1, 2, 3..z, Z being the number of cameras within the target object; because of the distance problem of the cameras, the ratio of scz is different, and scz is required to be amplified or reduced according to the sizes of the lower gates of different cameras in the same ratio to obtain s' cz; sequencing s' cz according to the area from small to large;
s303, extracting that the minimum image area of the package exposure is S 'c (min), and when S' c (min) is less than or equal to si, enabling the duration of a pedestrian c needing to pass through a gate to be Tc=T (i) c )，T(i c ) The initial switching time is reset for the row of gates where the pedestrian c is located; when s' c (min) > si, the formula is followed: tc= { [ s' c (min)/si]+1}*T(i c ) Calculating the time length of the pedestrian c needing to pass through the gate; traversing the pedestrian information to obtain the time length Tij of the gate which all pedestrians need to pass through, wherein Tij is expressed as the time length of the jth pedestrian which is arranged in front of the ith gate in the range of the target object and needs to pass through the gate.
Further, the S400 includes: storing the time length of the gate which is required to be passed by all pedestrians into a gate database, and switching on and switching off the gate according to the time length of the gate which is required to be passed by the pedestrians in the database; the gate data monitoring system obtains the actual switching time length of the gate as T' ij; when Tij is not equal to T' ij, the ith gate is marked, and when the accumulated marking times are larger than a preset threshold value Q, the fault of the ith gate is indicated to perform early warning, and a worker is provided for maintaining the ith gate.
The channel gate data monitoring system based on big data comprises a data acquisition module, a data analysis module, a gate monitoring module and an alarm reminding module; the output end of the data acquisition module is connected with the input end of the data analysis module, the output end of the data analysis module is connected with the input end of the gate supervision module, and the output end of the gate supervision module is connected with the input end of the alarm reminding module; the data acquisition module acquires a monitoring video within the range of a target object, a historical time interval from the induction of an effective pass certificate by the gate to the complete opening of the gate and an actual switching time of the gate; the data analysis module is used for analyzing the area of the gate allowing passage and the exposed area of the package carried by the pedestrian according to the monitoring video within the range of the target object; the gate monitoring module monitors the gate and controls the switching time of the gate; and the warning reminding module carries out warning reminding when the accumulated number of times that the switch time length set by the gate is not matched with the actual switch time exceeds a preset threshold value.
Further, the data acquisition module comprises a monitoring video acquisition unit, an actual switch duration acquisition unit and a historical time interval acquisition unit; the monitoring video acquisition unit acquires monitoring videos shot by cameras with different angles in the range of the target object according to the monitoring terminal; the actual switch time length acquisition unit is used for acquiring the time switch time length of the gate, and when the actual switch time length of the gate is not consistent with the limited switch time length, the gate is required to be maintained due to the fact that the part of the gate is likely to be aged; the historical time interval acquisition unit acquires the historical time interval from the time when the gate senses the effective pass certificate to the time when the gate is completely opened through historical data, the time from the time when the gate senses the effective pass certificate to the time when the gate is completely opened reflects the reaction speed of the gate, and the shorter the time is, the faster the reaction speed of the gate is indicated.
Further, the data analysis module comprises a gate allowed passing area analysis unit and a package exposure area analysis unit; the gate allowed passage area analysis unit is used for analyzing the allowed passage area of the gate; the parcel display area analysis unit wraps areas displayed in cameras with different angles for pedestrians, and the sizes of the areas displayed in the parcel in the different cameras are different.
Further, the gate supervision module comprises an initial switch time length setting unit and a pass switch time length limiting unit; the initial switch time length setting unit is used for setting the initial switch time of the gate according to the preset initial switch time; the pass switch duration limiting unit is used for setting the pass time of different pedestrians, so as to avoid the situation that the reset initial switch duration is insufficient for passing pedestrians due to the fact that the number of the pedestrians is too large.
Further, the alarm reminding module comprises a matching model and an early warning reminding unit; the matching model is used for matching the actual switching time length of the gate with the passing switching time length limited by the gate, and accumulating the unmatched times of the same gate; the early warning and reminding unit performs early warning and reminding when the accumulated number of times of mismatch of the same gate exceeds a preset threshold value.
Compared with the prior art, the invention has the following beneficial effects: according to the invention, the image area exposed by the wrapping of the pedestrian is analyzed by utilizing the monitoring video, and the gate passing time is limited according to the pedestrian information, so that the running efficiency and the safety of the equipment are improved, and the burden of staff is reduced.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a channel gate data monitoring system based on big data according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions: the channel gate data supervision method based on big data specifically comprises the following steps:
s100, acquiring a monitoring video in a target object range through a monitoring terminal, and analyzing pedestrian information in the target object range according to the monitoring video; the pedestrian information comprises package information of pedestrians and position information of pedestrians;
s200, acquiring historical data information of a gate in a target object range according to historical data, analyzing response sensitivity of the gate according to the historical data information of the gate in the target object range, and analyzing allowable traffic volume of the gate; resetting the initial switching time of the gate through the response sensitivity of the gate;
s300, limiting the passing time of pedestrians, namely the gate switching duration, in the range of the target object according to the pedestrian information and the gate allowed passing volume; storing the passing time of pedestrians, namely the on-off time of the gate, into a database;
s400, constructing a matching model according to big data, and when the limited gate switch time length is not matched with the actual time length of the gate switch, indicating that the gate fails so as to give an alarm; the matching model is used for matching the passing time of all pedestrians in the target object range, namely the limit time of the gate switch, with the actual switch time of the gate.
Further, the specific method for analyzing the pedestrian information in the target range according to the monitoring video in S100 is as follows:
s101, acquiring map data of a target object from an open source map provider or sensor data, mapping the target object into a coordinate system according to the map data of the target object, extracting position information of a gate from the map data, and obtaining corresponding coordinates of the gate in the coordinate system according to the relative position of the gate on the target object map, wherein the corresponding coordinates are (x 0, yi), (x 0, y 0) and are expressed as a coordinate system origin; the monitoring video in the range of the target object is obtained through the monitoring terminal, and because the angles of the monitoring video are different, shielding conditions exist in the process of monitoring shooting, the monitoring video needs to be integrated, and the integration of the monitoring video is completed through video calibration, splicing and synchronization, wherein the video calibration means that under the condition that a camera is fixed, the video picture can be correctly mapped into a three-dimensional space by adjusting parameters such as the angle, the focal length and the like of the camera. Through video calibration, problems such as lens distortion and image distortion can be eliminated, and the accuracy of subsequent video processing is improved; video stitching refers to fusing a plurality of video streams with different angles to form a complete panoramic video. The video splicing needs to use a splicing algorithm to seamlessly splice overlapping areas in adjacent video streams, so that splicing marks are eliminated, and panoramic videos with wide angles and large fields of view are formed; video synchronization means that video streams of different angles can correspond to the same time-space point at the same time point, and the video synchronization can be realized through a time stamp or frame synchronization technology, so that the video streams of different angles can be aligned on the same time axis; extracting the position information of pedestrians from map data according to the integrated monitoring video, avoiding that partial pedestrians are blocked and the complete pedestrian position information in the target object range cannot be obtained due to the angle problem of the monitoring video, and obtaining corresponding coordinates (xj, yi) of the pedestrians in a coordinate system according to the relative positions of the pedestrians on the target object map, wherein j=1, 2 and 3..J, J is expressed as the number of people arranged in front of each gate, i=1, 2 and 3..I, and I is expressed as the number of gates in the target range; the monitoring video is a video for monitoring the target object by cameras in different directions;
s102, positioning and marking any pedestrian in a monitoring video shot by a camera behind a gate, recording any pedestrian with a calibrated mark as a, extracting frames of the monitoring video shot by the camera behind the gate to obtain a monitoring image, detecting the edge of the pedestrian with the positioned mark in the monitoring image by a Canny edge detection operator, and detecting the continuous edge in a picture by the edge detection operator, wherein the pedestrian and the parcel to which the pedestrian belong have a connection relationship so as to obtain image information between the pedestrian with the positioned mark and the parcel to which the pedestrian with the positioned mark belongs; the Canny edge detection operator has low error rate, and can extract real edge points, and non-edge points are not extracted, so that the aim of high-position precision is fulfilled;
s103, recognizing the package information of any one located mark pedestrian by utilizing a three-dimensional convolution recognition algorithm, and respectively obtaining the exposed image area of the package of the located mark pedestrian as sa, wherein sa is expressed as the exposed image area of the package of the located mark pedestrian a behind a gate in the range of a target object; traversing the monitoring video to obtain the exposed image area of all pedestrian packages in the target object range as sij, wherein sij is expressed as the exposed image area of the package, obtained by a three-dimensional convolution recognition algorithm, of the jth pedestrian arranged in front of the ith gate and the camera behind the gate.
Further, the specific method for analyzing the response sensitivity of the gate and resetting the initial time of the gate switch according to the historical data information of the gate within the target range in S200 is as follows:
s201, obtaining the height of the gate in the monitoring image according to the monitoring video shot by the camera behind the gate in the target object range, and obtaining the interval between the gates as pi=y (i-1) -yi according to the formula by corresponding coordinates (x 0, yi) of the gate in the coordinate system: si=l×pi, calculating to obtain the maximum area allowed to pass by each gate in the target object range;
s202, obtaining historical time intervals from the effective pass certificate of gate induction to the complete opening of the gate in the range of a target object in the last unit time through historical data information, wherein ti represents the historical time interval from the effective pass certificate of the ith gate induction to the opening of the gate in the range of the target object, and the longer the historical time interval from the effective pass certificate of the gate induction to the opening of the gate is, the slower the reaction speed of the gate is; according to the fact that the gate senses the effective passing evidence and starts to count, when the reaction speed of the gate is slower, the time for allowing pedestrians to pass is shorter, and when the working time of the gate is longer, the reaction speed of the gate is slower due to ageing of internal parts of the gate or other reasons; therefore, the initial switching time of the gate in the reset target range needs to be ti=t0+ (k1×ti+c), where t0 is the initial switching time value set when all gates are shipped, k1 is a coefficient, and c is an error term.
Further, the specific method for analyzing the gate opening/closing time according to the passing time of the pedestrian in the target object range in S300 is as follows:
s301, because the position of the camera behind the gate is fixed, when a pedestrian gradually approaches the gate, the area of the exposed image of all the pedestrian packages in the acquired target object range is larger and larger, and the distance between the camera behind the gate and the gate is x according to the big data, and the formula is as follows: s' ij= [ (x+xij)/xij ]. Sij, calculating to obtain the exposed image area of the camera behind the gate, wrapping the jth pedestrian in front of the ith gate, in the range of the target object with the same proportion as the maximum area allowed to pass by each gate;
s302, when the exposed image area S' c > si of any pedestrian c wrapped on the camera behind the gate, the pedestrian wrapping area detected by the camera behind the gate is larger than the maximum area allowed to pass through each gate, but the monitored area is limited because the position of the camera behind the gate is fixed, the pedestrian wrapping larger than the maximum area allowed to pass through the gate needs to be re-detected by other cameras behind the gate, and the image area exposed by the wrapping of the pedestrian c in the z-th monitoring video is obtained by traversing the monitoring video shot by other cameras behind the gate, wherein scz is represented by scz; z=1, 2, 3..z, Z being the number of cameras within the target object; because of the distance problem of the cameras, the ratio of scz is different, and scz is required to be amplified or reduced according to the sizes of the lower gates of different cameras in the same ratio to obtain s' cz; sequencing s' cz according to the area from small to large;
s303, extracting that the minimum image area of the package exposure is S 'c (min), and when S' c (min) is less than or equal to si, enabling the duration of a pedestrian c needing to pass through a gate to be Tc=T (i) c )，T(i c ) The initial switching time is reset for the row of gates where the pedestrian c is located; when s' c (min) > si, the formula is followed: tc= { [ s' c (min)/si]+1}*T(i c ) Calculating the time length of the pedestrian c needing to pass through the gate; traversing the pedestrian information to obtain the time length Tij of the gate which all pedestrians need to pass through, wherein Tij is expressed as the time length of the jth pedestrian which is arranged in front of the ith gate in the range of the target object and needs to pass through the gate.
Further, the S400 includes: storing the time length of the gate which is required to be passed by all pedestrians into a gate database, and switching on and switching off the gate according to the time length of the gate which is required to be passed by the pedestrians in the database; the gate data monitoring system obtains the actual switching time length of the gate as T' ij; when Tij is not equal to T' ij, the ith gate is marked, and when the accumulated marking times are larger than a preset threshold value Q, the fault of the ith gate is indicated to perform early warning, and a worker is provided for maintaining the ith gate.
The channel gate data monitoring system based on big data comprises a data acquisition module, a data analysis module, a gate monitoring module and an alarm reminding module; the output end of the data acquisition module is connected with the input end of the data analysis module, the output end of the data analysis module is connected with the input end of the gate supervision module, and the output end of the gate supervision module is connected with the input end of the alarm reminding module; the data acquisition module acquires a monitoring video within the range of a target object, a historical time interval from the induction of an effective pass certificate by the gate to the complete opening of the gate and an actual switching time of the gate; the data analysis module is used for analyzing the area of the gate allowing passage and the exposed area of the package carried by the pedestrian according to the monitoring video within the range of the target object; the gate monitoring module monitors the gate and controls the switching time of the gate; and the warning reminding module carries out warning reminding when the accumulated number of times that the switch time length set by the gate is not matched with the actual switch time exceeds a preset threshold value.
Further, the data acquisition module comprises a monitoring video acquisition unit, an actual switch duration acquisition unit and a historical time interval acquisition unit; the monitoring video acquisition unit acquires monitoring videos shot by cameras with different angles in the range of the target object according to the monitoring terminal; the actual switch time length acquisition unit is used for acquiring the time switch time length of the gate, and when the actual switch time length of the gate is not consistent with the limited switch time length, the gate is required to be maintained due to the fact that the part of the gate is likely to be aged; the historical time interval acquisition unit acquires the historical time interval from the time when the gate senses the effective pass certificate to the time when the gate is completely opened through historical data, the time from the time when the gate senses the effective pass certificate to the time when the gate is completely opened reflects the reaction speed of the gate, and the shorter the time is, the faster the reaction speed of the gate is indicated.
Further, the data analysis module comprises a gate allowed passing area analysis unit and a package exposure area analysis unit; the gate allowed passage area analysis unit is used for analyzing the allowed passage area of the gate; the parcel display area analysis unit wraps areas displayed in cameras with different angles for pedestrians, and the sizes of the areas displayed in the parcel in the different cameras are different.
Further, the gate supervision module comprises an initial switch time length setting unit and a pass switch time length limiting unit; the initial switch time length setting unit is used for setting the initial switch time of the gate according to the preset initial switch time; the pass switch duration limiting unit is used for setting the pass time of different pedestrians, so as to avoid the situation that the reset initial switch duration is insufficient for passing pedestrians due to the fact that the number of the pedestrians is too large.
Further, the alarm reminding module comprises a matching model and an early warning reminding unit; the matching model is used for matching the actual switching time length of the gate with the passing switching time length limited by the gate, and accumulating the unmatched times of the same gate; the early warning and reminding unit performs early warning and reminding when the accumulated number of times of mismatch of the same gate exceeds a preset threshold value.
In this embodiment:
setting a monitoring video shot by a camera behind a gate in a target object range to obtain a height of the gate in a monitoring image as l=5, respectively obtaining a distance between the gates as pi=4 by corresponding coordinates of the gate in a coordinate system as { (0, 4), (0, 8) and (0,12) }, and calculating to obtain a maximum area si=l×pi= 4*5 =20 allowed to pass by each gate in the target object range; according to the fact that the distance between the camera behind the big data acquisition gate and the gate is x=10, the corresponding coordinates of pedestrians in a coordinate system are set as follows: { (7, 4), (9, 4), (16, 4), (20, 4) }. Wherein the exposed areas of the pedestrian wrap are {20, 15, 7, 17. }, respectively
According to the formula: s' ij= [ (x+xij)/xij ]. Sij, calculating to obtain the exposed image areas of the pedestrian wrapped by the camera behind the gate in the target object range with the same proportion as the maximum area allowed to pass by each gate, wherein the exposed image areas are {48.6, 31.7, 11.4 and 25.5. };
when s' ij is less than or equal to si=20, the gate normally passes through according to the reset initial switching time of the gate, and the switching time of the gate is not required to be limited;
when s ' ij is more than si=20, the display area wrapped in other cameras except for the rear part of the gate is obtained, the smallest image area is set and selected as s ' c (min) =10, s ' c (min) < si=20, and the gate is normally passed according to the reset initial switching time of the gate without limiting the switching time of the gate;
setting and selecting the minimum image area as s 'c (min) =25, and s' c (min) > si=20 according to the formula:
Tc＝{[s’c(min)/si]+1}*T(i c )
＝(25/20+1)*15
＝33.75s
and calculating the time length of the pedestrian needing to pass through the gate.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A channel gate data supervision method based on big data is characterized in that: the channel gate data supervision method specifically comprises the following steps:
s100, acquiring a monitoring video in a target object range through a monitoring terminal, and analyzing pedestrian information in the target object range according to the monitoring video; the pedestrian information comprises package information of pedestrians and position information of pedestrians;
s200, acquiring historical data information of a gate in a target object range according to historical data, analyzing response sensitivity of the gate according to the historical data information of the gate in the target object range, and analyzing allowable traffic volume of the gate; resetting the initial switching time of the gate through the response sensitivity of the gate;
s300, limiting the passing time of pedestrians, namely the gate switching duration, in the range of the target object according to the pedestrian information and the gate allowed passing volume;
s400, constructing a matching model according to the big data, and alarming when the limited gate switch time length is not matched with the actual time length of the gate switch.
2. The method for monitoring and controlling the data of the channel gate based on big data as claimed in claim 1, wherein the method comprises the following steps: the specific method for analyzing the pedestrian information in the target range according to the monitoring video in the S100 is as follows:
s101, acquiring map data of a target object, mapping the target object into a coordinate system according to the map data of the target object, extracting position information of a gate from the map data, and obtaining corresponding coordinates of the gate in the coordinate system according to the relative position of the gate on the target object map, wherein the corresponding coordinates are (x 0, yi), (x 0, y 0) and are expressed as origin points of the coordinate system; acquiring a monitoring video in a target object range from a monitoring terminal, and integrating the monitoring video; extracting position information of pedestrians from map data according to the integrated monitoring video, and obtaining corresponding coordinates (xj, yi) of the pedestrians in a coordinate system according to the relative positions of the pedestrians on a target object map, wherein j=1, 2 and 3..J, J is expressed as the number of people arranged in front of each gate, i=1, 2 and 3..I, and I is expressed as the number of gates in a target range; the monitoring video is a video for monitoring the target object by cameras in different directions;
s102, positioning and marking any pedestrian in a monitoring video shot by a camera behind a gate, recording any pedestrian with a calibrated mark as a, extracting frames of the monitoring video shot by the camera behind the gate to obtain a monitoring image, and detecting edges of the pedestrian with the positioned mark in the monitoring image by an edge detection operator to obtain image information between the pedestrian with the positioned mark and a package to which the pedestrian with the positioned mark belongs;
s103, recognizing the package information of any one located mark pedestrian by utilizing a three-dimensional convolution recognition algorithm, and respectively obtaining the exposed image area of the package of the located mark pedestrian as sa, wherein sa is expressed as the exposed image area of the package of the located mark pedestrian a behind a gate in the range of a target object; traversing the monitoring video to obtain the exposed image area of all pedestrian packages in the target object range as sij, wherein sij is expressed as the exposed image area of the package, obtained by a three-dimensional convolution recognition algorithm, of the jth pedestrian arranged in front of the ith gate and the camera behind the gate.
3. The method for channel gate data supervision based on big data according to claim 2, wherein the method comprises the following steps: the specific method for analyzing the response sensitivity of the gate and resetting the initial time of the gate switch according to the historical data information of the gate in the target range in S200 is as follows:
s201, obtaining the height of the gate in the monitoring image according to the monitoring video shot by the camera behind the gate in the target object range, and obtaining the interval between the gates as pi=y (i-1) -yi according to the formula by corresponding coordinates (x 0, yi) of the gate in the coordinate system: si=l×pi, calculating to obtain the maximum area allowed to pass by each gate in the target object range;
s202, obtaining a historical time interval from a gate induction effective pass certificate to a gate complete opening in a target object range in the last unit time through historical data information, wherein Ti represents a historical time interval from an ith gate induction effective pass certificate to a gate opening in the target object range, the initial switching time of the gate in the target object range is reset to be Ti=t0+ (k 1. Ti+c), t0 represents an initial switching time value set when all gates leave the factory, k1 represents a coefficient, and c is an error item.
4. The method for channel gate data supervision based on big data according to claim 3, wherein: the specific method for analyzing the gate opening and closing time according to the passing time of the pedestrian in the target object range in S300 is as follows:
s301, acquiring the distance x from the shooting distance of a camera behind the gate to the gate according to big data, and according to the formula:
s' ij= [ (x+xij)/xij ]. Sij, calculating to obtain the exposed image area of the camera behind the gate, wrapping the jth pedestrian in front of the ith gate, in the range of the target object with the same proportion as the maximum area allowed to pass by each gate;
s302, when the exposed image area S' c > si of any pedestrian c wrapped on the camera behind the gate is existed, traversing the monitoring videos shot by the rest cameras behind the gate to obtain scz, wherein scz is represented as the exposed image area of the pedestrian c wrapped in the z-th monitoring video; z=1, 2, 3..z, Z being the number of cameras within the target object; amplifying or reducing scz according to the sizes of the lower gates of different cameras in the same proportion to obtain s' cz; sequencing s' cz according to the area from small to large;
s303, extracting that the minimum image area of the package exposure is S 'c (min), and when S' c (min) is less than or equal to si, enabling the duration of a pedestrian c needing to pass through a gate to be Tc=T (i) c )，T(i c ) The initial switching time is reset for the row of gates where the pedestrian c is located; when s' c (min) > si, the formula is followed: tc= { [ s' c (min)/si]+1}*T(i c ) Calculating the time length of the pedestrian c needing to pass through the gate; traversing the pedestrian information to obtain the time length Tij of the gate which all pedestrians need to pass through, wherein Tij is expressed as the time length of the jth pedestrian which is arranged in front of the ith gate in the range of the target object and needs to pass through the gate.
5. The method for channel gate data supervision based on big data according to claim 4, wherein: the S400 includes: storing the time length of the gate which is required to be passed by all pedestrians into a gate database, and switching on and switching off the gate according to the time length of the gate which is required to be passed by the pedestrians in the database; the gate data monitoring system obtains the actual switching time length of the gate as T' ij; when Tij is not equal to T' ij, the ith gate is marked, and early warning is carried out when the accumulated marking times are larger than a preset threshold value Q.
6. A channel gate data supervision system applying the big data based channel gate data supervision method as defined in any one of claims 1-5, wherein: the channel gate data monitoring system comprises a data acquisition module, a data analysis module, a gate monitoring module and an alarm reminding module; the output end of the data acquisition module is connected with the input end of the data analysis module, the output end of the data analysis module is connected with the input end of the gate supervision module, and the output end of the gate supervision module is connected with the input end of the alarm reminding module; the data acquisition module acquires a monitoring video within the range of a target object, a historical time interval from the induction of an effective pass certificate by the gate to the complete opening of the gate and an actual switching time of the gate; the data analysis module is used for analyzing the area of the gate allowing passage and the exposed area of the package carried by the pedestrian according to the monitoring video within the range of the target object; the gate monitoring module monitors the gate and controls the switching time of the gate; and the warning reminding module carries out warning reminding when the accumulated number of times that the switch time length set by the gate is not matched with the actual switch time exceeds a preset threshold value.
7. The aisle gate data supervisory system according to claim 6, wherein: the data acquisition module comprises a monitoring video acquisition unit, an actual switch duration acquisition unit and a historical time interval acquisition unit; the monitoring video acquisition unit acquires monitoring videos shot by cameras with different angles in the range of the target object according to the monitoring terminal; the actual switch time length acquisition unit is used for acquiring the time switch time length of the gate; the history time interval acquisition unit is used for acquiring a history time interval from the time when the gate senses the effective pass certificate to the time when the gate is completely opened through history data.
8. The aisle gate data supervisory system according to claim 7, wherein: the data analysis module comprises a gate allowed passing area analysis unit and a package exposure area analysis unit; the gate allowed passage area analysis unit is used for analyzing the allowed passage area of the gate; the package exposure area analysis unit is used for wrapping the area exposed by the cameras at different angles for pedestrians.
9. The aisle gate data supervisory system according to claim 8, wherein: the gate supervision module comprises an initial switch time length setting unit and a pass switch time length limiting unit; the initial switch time length setting unit resets the initial switch time of the gate; the pass switch duration limiting unit is used for setting the pass time of different pedestrians.
10. The aisle gate data supervisory system according to claim 9, wherein: the alarm reminding module comprises a matching model and an early warning reminding unit; the matching model is used for matching the actual switching time length of the gate with the passing switching time length limited by the gate, and accumulating the unmatched times of the same gate; the early warning and reminding unit performs early warning and reminding when the accumulated number of times of mismatch of the same gate exceeds a preset threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311247306.2A CN117314077A (en) | 2023-09-26 | 2023-09-26 | Channel gate data supervision method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311247306.2A CN117314077A (en) | 2023-09-26 | 2023-09-26 | Channel gate data supervision method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117314077A true CN117314077A (en) | 2023-12-29 |
Family
ID=89273149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311247306.2A Pending CN117314077A (en) | 2023-09-26 | 2023-09-26 | Channel gate data supervision method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314077A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109979059A (en) * | 2019-04-01 | 2019-07-05 | 日立楼宇技术（广州）有限公司 | A kind of method, apparatus, equipment and storage medium controlling gate |
| CN113393603A (en) * | 2020-03-11 | 2021-09-14 | 杭州海康威视数字技术股份有限公司 | Control method and system of channel gate |
| CN113960075A (en) * | 2021-10-14 | 2022-01-21 | 科大讯飞(苏州)科技有限公司 | Security check equipment, article size determination method, storage medium and equipment |
| CN114399862A (en) * | 2021-12-16 | 2022-04-26 | 金瑞致达（北京）科技股份有限公司 | Gate passing control method and system based on temperature detection and gate inhibition authorization |
| WO2022160616A1 (en) * | 2021-01-28 | 2022-08-04 | 深圳市商汤科技有限公司 | Passage detection method and apparatus, electronic device, and computer readable storage medium |
| CN114943932A (en) * | 2022-05-23 | 2022-08-26 | 北京声智科技有限公司 | Gate control method and device, electronic equipment, storage medium and product |
-
2023
- 2023-09-26 CN CN202311247306.2A patent/CN117314077A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109979059A (en) * | 2019-04-01 | 2019-07-05 | 日立楼宇技术（广州）有限公司 | A kind of method, apparatus, equipment and storage medium controlling gate |
| CN113393603A (en) * | 2020-03-11 | 2021-09-14 | 杭州海康威视数字技术股份有限公司 | Control method and system of channel gate |
| WO2022160616A1 (en) * | 2021-01-28 | 2022-08-04 | 深圳市商汤科技有限公司 | Passage detection method and apparatus, electronic device, and computer readable storage medium |
| CN113960075A (en) * | 2021-10-14 | 2022-01-21 | 科大讯飞(苏州)科技有限公司 | Security check equipment, article size determination method, storage medium and equipment |
| CN114399862A (en) * | 2021-12-16 | 2022-04-26 | 金瑞致达（北京）科技股份有限公司 | Gate passing control method and system based on temperature detection and gate inhibition authorization |
| CN114943932A (en) * | 2022-05-23 | 2022-08-26 | 北京声智科技有限公司 | Gate control method and device, electronic equipment, storage medium and product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103279949B (en) | Based on the multi-camera parameter automatic calibration system operation method of self-align robot | |
| CN110085029B (en) | Highway inspection system and method based on rail type inspection robot | |
| CN109375531B (en) | Intelligent storage management and control integrated system of granary | |
| CN108830390A (en) | A kind of intelligent operational system and method for charging station | |
| CN107331097A (en) | The periphery intrusion preventing apparatus and method merged based on target position information | |
| CN109353246A (en) | A kind of charging station intelligence operational system and method | |
| CN102147835A (en) | Driver body temperature automatic measurement system applied to port lanes and implementation method thereof | |
| CN109544946A (en) | Tunnel real-time monitoring and managing system and its implementation based on vehicle flowrate big data | |
| JPWO2017047687A1 (en) | Monitoring system | |
| KR101461184B1 (en) | Wether condition data extraction system using cctv image | |
| CN113139482A (en) | Method and device for detecting traffic abnormity | |
| CN110703760B (en) | Newly-added suspicious object detection method for security inspection robot | |
| JP4286074B2 (en) | Spatial information distribution device | |
| CN208207896U (en) | A kind of intelligent operational system for charging station | |
| CN113762766A (en) | Rail transit station transport pipe system, method and device | |
| CN110868568A (en) | Video monitoring method and device for station outside air pipe | |
| KR101499456B1 (en) | Facility anomaly detection System and Method using image | |
| KR101538592B1 (en) | Parking Management System with Aoutomatic Control for License Plate Misrecognition | |
| CN112163497A (en) | Construction site accident prediction method and device based on image recognition | |
| CN117314077A (en) | Channel gate data supervision method and system based on big data | |
| CN113052125B (en) | Construction site violation image recognition and alarm method | |
| KR102434154B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN109727348A (en) | A kind of electric power tunnel personnel monitoring method | |
| CN114399862A (en) | Gate passing control method and system based on temperature detection and gate inhibition authorization | |
| CN103726739B (en) | A kind of guard method of motor-driven folding door, protection system and motor-driven folding door |
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 |