CN112686226A - Big data management method and device based on gridding management and electronic equipment - Google Patents
Big data management method and device based on gridding management and electronic equipment Download PDFInfo
- Publication number
- CN112686226A CN112686226A CN202110271650.XA CN202110271650A CN112686226A CN 112686226 A CN112686226 A CN 112686226A CN 202110271650 A CN202110271650 A CN 202110271650A CN 112686226 A CN112686226 A CN 112686226A
- Authority
- CN
- China
- Prior art keywords
- target
- grid
- statistical
- information
- preset
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a big data management method, a device and electronic equipment based on grid management, wherein the method comprises the following steps: acquiring a video stream in a preset area, wherein the preset area comprises a plurality of grid areas, and a hierarchical relationship exists among the grid areas; performing frame-by-frame image extraction processing on the video stream to obtain an image extraction image, wherein the image extraction image comprises a monitoring target; carrying out target identification on a monitored target in the image-extracted image, and extracting target information of the monitored target, wherein the target information comprises target characteristic information, snapshot time information and snapshot place information of the monitored target; counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information; and sending the statistical data of the monitoring targets in all the grid areas to a front-end page for hierarchical visual display according to the hierarchical relation of the grid areas. The embodiment of the invention can improve the real reliability of the statistical data of the grid area.
Description
Technical Field
The invention relates to the technical field of security and protection, in particular to a big data management method and device based on grid management and electronic equipment.
Background
The traditional urban gridding visual data display mostly only stays in a community grid, the data of a smaller unit can not be counted and displayed, the data of a branch office can not be counted and displayed, the data relevance is not strong, the practicability is lacked, and only some basic statistical data of the community grid, such as camera information, data acquisition information and the like, exist. The traditional urban gridding visual data display only provides list-form display and only has basic community grid data statistics, so that the reality and reliability of grid statistical data are not high.
Disclosure of Invention
The embodiment of the invention provides a big data management method based on gridding management, which can solve the problem that the reality and reliability of grid statistical data in the prior art are not strong.
In a first aspect, an embodiment of the present invention provides a big data management method based on grid management, where the method includes:
acquiring a video stream in a preset area, wherein the preset area comprises a plurality of grid areas, and a hierarchical relationship exists among the grid areas;
performing frame-by-frame image extraction processing on the video stream to obtain an image extraction image, wherein the image extraction image comprises a monitoring target;
carrying out target identification on a monitored target in the image-drawing image, and extracting target information of the monitored target, wherein the target information comprises target characteristic information, snapshot time information and snapshot place information of the monitored target;
counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information;
sending the statistical data of the monitoring targets in all the grid areas to a front-end page for hierarchical visual display according to the hierarchical relation of the grid areas;
the preset statistical rule comprises a first statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information comprises the following steps:
calculating the occurrence frequency of the monitoring target appearing in each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target in each grid area;
comparing the occurrence times with a first preset time, and judging whether the monitored target is a frequent in-out target of the grid area;
and if the monitored target is the frequent access target of the grid area, recording the statistical data according to the first statistical rule.
Optionally, the preset statistical rule includes a second statistical rule and a third statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information further includes:
comparing the occurrence times with a second preset time, and judging whether the monitoring target is a resident target of the grid area;
if the monitoring target is a resident target of the grid area, recording the statistical data according to the second statistical rule;
and if the monitored target is the non-stationary target of the grid area, recording the statistical data according to the third statistical rule.
Optionally, the preset statistical rule includes a fourth statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information further includes:
judging whether the monitored target is a day and night target of each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target of each grid area;
and if the monitored target is the diurnal and nocturnal emission target of the grid area, recording the statistical data according to the fourth rule.
Optionally, the preset statistical rule further includes a fifth statistical rule and a sixth statistical rule, and the step of performing statistics on the statistical data of each grid region based on the preset statistical rule according to the target information further includes:
judging whether the monitored target is a known target of each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target of each grid area;
if the monitored target is a known target of the grid area, recording the statistical data according to the fifth statistical rule;
and if the monitored target is an unknown target of the grid area, recording statistical data according to a sixth statistical rule.
Optionally, the preset statistical rule further includes a seventh statistical rule, and the step of performing statistics on the statistical data of each grid region based on the preset statistical rule according to the target information further includes:
judging whether the monitoring target is a special target of each grid area according to the target characteristic information of the monitoring target of each grid area;
and if the monitored target is a special target of the grid area, recording the statistical data according to the seventh statistical rule.
Optionally, the method further includes:
and establishing activity data of each monitoring target according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target in each grid area, wherein the rule for establishing the activity data establishes an activity data for each activity target in each grid area.
In a second aspect, an embodiment of the present invention further provides a big data management apparatus based on grid management, where the apparatus includes:
the device comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring a video stream in a preset area, the preset area comprises a plurality of grid areas, and a hierarchical relationship exists among the grid areas;
the image extracting module is used for carrying out image extracting processing on the video stream frame by frame to obtain an image extracting image, and the image extracting image comprises a monitoring target;
the recognition module is used for carrying out target recognition on a monitored target in the image extraction image and extracting target information of the monitored target, wherein the target information comprises target characteristic information, snapshot time information and snapshot place information of the monitored target;
the statistical module is used for counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information;
the transmitting module is used for transmitting the statistical data of the monitoring targets in all the grid areas to a front-end page to carry out hierarchical visual display according to the hierarchical relation of the grid areas;
the preset statistical rule comprises a first statistical rule, and the statistical module comprises:
the appearance frequency calculation unit is used for calculating the appearance frequency of the monitoring target in each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target in the grid area;
the first judgment unit is used for comparing the occurrence times with a first preset time and judging whether the monitored target is a frequent access target of the grid area;
and the first recording unit is used for recording the statistical data according to the first statistical rule if the monitoring target is a frequent access target of the grid area.
Optionally, the preset statistical rule includes a second statistical rule and a third statistical rule, and the statistical module further includes:
the second judging unit is used for comparing the occurrence times with a second preset time and judging whether the monitoring target is a resident target of the grid area;
a second recording unit, configured to record the statistical data according to the second statistical rule if the monitored target is a resident target of the grid area;
and the third recording unit is used for recording the statistical data according to the third statistical rule if the monitoring target is the non-stationary target of the grid area.
In a third aspect, an embodiment of the present invention further provides an electronic device, including: the grid-based management method comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program to realize the steps of the grid-based management big data management method provided in the above embodiment.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the steps in the grid management-based big data management method provided in the foregoing embodiment.
In the embodiment of the invention, a video stream in a preset area is obtained, wherein the preset area comprises a plurality of grid areas, and a hierarchical relationship exists among the grid areas; performing frame-by-frame image extraction processing on the video stream to obtain an image extraction image, wherein the image extraction image comprises a monitoring target; carrying out target identification on a monitored target in the image-drawing image, and extracting target information of the monitored target, wherein the target information comprises target characteristic information, snapshot time information and snapshot place information of the monitored target; counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information; sending the statistical data of the monitoring targets in all the grid areas to a front-end page for hierarchical visual display according to the hierarchical relation of the grid areas; the preset statistical rule comprises a first statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information comprises the following steps: calculating the occurrence frequency of the monitoring target appearing in each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target in each grid area; comparing the occurrence times with a first preset time, and judging whether the monitored target is a frequent in-out target of the grid area; and if the monitored target is the frequent access target of the grid area, recording the statistical data according to the first statistical rule. Therefore, diversified statistics can be carried out on the monitoring targets of each grid region, the statistical data of each grid region can be displayed in a hierarchical mode, the intuition is stronger, and the real reliability of the statistical data of each grid region is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a big data management method based on grid management according to an embodiment of the present invention;
FIG. 2 is a flowchart of another big data management method based on grid management according to an embodiment of the present invention;
FIG. 3 is a flowchart of another big data management method based on grid management according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a big data management apparatus based on grid management according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of another big data management apparatus based on grid management according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of a big data management method based on grid management according to an embodiment of the present invention, and as shown in fig. 1, the big data management method based on grid management includes the following steps:
The preset area may include a plurality of grid areas, for example, the preset area may be a city, and the corresponding grid area may be divided into a plurality of blocks according to roads on the map, and of course, the preset area may also be a partial area of the city. The plurality of grid regions may be provided with a hierarchical relationship, for example, one of the grid regions is a certain city, and the other grid regions are other partial regions of the city or other grade cities, or still other partial grid regions are partial regions of the grade cities. For example, the multiple grid areas may divide cells, hospitals, supermarkets, and the like in the original community grid into smaller grid areas, then integrate the community grids into one branch grid, and finally integrate all the branch grids into the whole city grid. Therefore, the longitudinal hierarchical relations from top to bottom are achieved, namely from the city bureau to the branch bureau, then from the branch bureau to the community, and finally from the community to the cell. And the grid areas of each hierarchy are mutually related, and the upper grid area comprises the lower grid area.
The video stream includes a plurality of frames of images. In this embodiment, the video stream may be stored in the full-text search engine server, and after the camera captures the video stream of the monitoring target, the video stream is written into the full-text search engine server.
Specifically, the video stream is obtained by shooting with a camera at a specific position in each mesh region in a preset region. The video stream can be acquired in real time or acquired and stored in advance.
And 102, performing frame-by-frame image extraction processing on the video stream to obtain an image extraction image, wherein the image extraction image comprises a monitoring target.
The monitoring target may be a human being or a vehicle, or may be a specific animal, such as a wandering animal.
Specifically, the decimated image may be obtained by performing frame-by-frame decimation processing on the video stream by using a preset edge calculation engine. And the image extraction image obtained by image extraction contains the monitoring target. For example, each frame of a video stream is sliced to obtain a multi-frame image, and then an image including a monitoring target is extracted from the multi-frame image by an edge calculation engine to be used as an extracted image.
The target feature information may represent the identity of the monitored target, for example, the target feature information may refer to human face feature information of a person, and of course, the target feature information may further include one or more of main features of the monitored target, such as sex and age, head features of a wearer, wearing a mask, wearing glasses, etc., clothing features of an upper garment, a lower garment, a hat, and other feature information of whether there is a carried object, etc. Taking a vehicle as an example, the target feature information may be license plate number information, and of course, the target feature information may further include one or more of feature information such as a vehicle type, a vehicle logo (i.e., a brand), a sub-model (i.e., a vehicle series), a vehicle body color, vehicle local features (e.g., a decoration, a pendant, an annual inspection mark, etc.), a primary and secondary driver behavior (including whether a seat belt is fastened, whether a call is made, etc.), and the like.
The snapshot time information may be time information when the snapshot image is taken. Specifically, when a video stream is collected, corresponding snapshot time information is generated according to the collected time information, the video stream comprises multiple frames of images, and each frame of image has the own snapshot time information. And the drawing image is extracted from a plurality of frames of images, so that each drawing image containing the monitoring target also corresponds to the own snapshot time information.
The snapshot location information may be location information of a snapshot camera that extracts the image.
Specifically, after the extraction image is obtained, the extraction image can be identified through a preset neural network, and then corresponding target information can be obtained. Of course, the preset neural network may include a human face neural network, a vehicle neural network, or may be other animal neural networks. For example, the monitoring target is taken as a human, if the face characteristics of a person are identified by carrying out face recognition on the monitoring target through a preset face neural network, corresponding face characteristic information can be inquired in an archive information system of an authority according to the face characteristics, snapshot location information of the monitoring target can be obtained through the serial number or mark of a camera, and snapshot time information can be obtained through the generation time of a snapshot image containing a face in a video stream. Taking a vehicle as an example, the archive information of the vehicle can be identified through the identification of the number plate number, the snapshot location information of the vehicle can be obtained through the serial number or the mark of the camera, and the snapshot time information can be obtained through the generation time of the snapshot image containing the vehicle in the video stream.
In this embodiment, the target information of the monitoring target may also be stored in the full-text search engine server. Of course, multiple types of indexes can be created in the full-text search engine server in advance according to different monitored targets, for example, four types of indexes such as human faces, human figures, original drawings and vehicles can be set. This allows searching for target information based on different types of indices.
And 104, counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information.
In an embodiment of the present invention, as shown in fig. 2, the preset statistical rule includes a first statistical rule, and step 104 includes:
And 1043, if the monitored target is the frequent access target of the grid area, recording statistical data according to a first statistical rule.
The number of occurrences of the monitoring target is the number of times that the monitoring target is snapshotted. The first preset number is a preset number threshold value used for judging whether the monitored target is a condition value of the frequent access target of the grid area. The first statistical rule is used for a rule for counting frequent entrance targets, and all monitoring targets in the frequent entrance targets are unique. The frequent entering and exiting target may be a frequent entering and exiting person, a frequent entering and exiting vehicle, and the like.
Specifically, when the monitored target is shot once in the grid area, the occurrence of the monitored target is described once, and when the monitored target is snapshot in the grid area each time, the occurrence of the monitored target is accumulated by 1, so that the occurrence of the monitored target can be calculated according to the snapshot of the monitored target. For example, when a monitoring target is first captured in the mesh area, the number of occurrences of the monitoring target is 1, and when the same monitoring target is second captured in the mesh area, the number of occurrences of the monitoring target is increased by 1 to 2.
When the occurrence number of the monitoring target meets the first preset number, the monitoring target can be determined to be a frequent in-and-out target of the grid area. The number of targets frequently accessed may be incremented by 1 according to a first statistical rule. Therefore, frequent access targets of all monitored targets appearing in the grid area can be counted, and statistical data of the frequent access targets in the grid area can be obtained. For example, if the first preset number of times is set to 10 times and the number of times of occurrence of the monitoring target is 11 times, it may be determined that the monitoring target is a frequent access target in the grid area, that is, the number of frequent access targets in the grid area may be added up to 1. When the same monitoring target in the same grid area is judged to be the frequent in-and-out target for the first time, the monitoring target is recorded as the frequent in-and-out target, and when the monitoring target is judged to be the frequent in-and-out target for multiple times, the judgment after the first time is not accumulated in the number of the frequent in-and-out targets, so that the uniqueness of the frequent in-and-out target can be ensured, and the problem of repeated statistics is avoided. Of course, the statistical approach to frequent access targets may be the same for each grid area.
In an embodiment of the present invention, as shown in fig. 3, the preset statistical rules include a second statistical rule and a third statistical rule. Step 104 further comprises:
and comparing the occurrence times with a second preset time, and judging whether the monitored target is a resident target of the grid area.
And if the monitoring target is a resident target of the grid area, recording the statistical data according to a second statistical rule.
And if the monitored target is the non-stationary target of the grid area, recording the statistical data according to a third statistical rule.
The second preset number is a preset number threshold, and is used for determining whether the monitored target is a condition value of a resident target of the grid area. The second statistical rule may be a rule for performing statistics on the resident target. The resident target may be a resident person, a resident vehicle, or the like. The non-resident target (temporary target) may be a non-resident person (temporary person), a non-resident vehicle (temporary vehicle), or the like. The third statistical rule is a rule for counting the non-stationary targets.
Specifically, when the number of occurrences of the monitoring target satisfies the second preset number, it may be determined that the monitoring target is a resident target of the grid area. Then the target number of resident targets may be incremented by 1 according to a second statistical rule. Therefore, the resident targets of all the monitored targets appearing in the grid area can be counted to obtain the statistical data of the resident targets in the grid area.
Otherwise, when the number of occurrences of the monitoring target does not satisfy the second preset number, it may be determined that the monitoring target is a non-stationary target of the grid area. The target number of non-stationary targets may be accumulated by 1 according to a third statistical rule. Therefore, the non-resident targets of all the monitored targets appearing in the grid area can be counted, and the statistical data of the non-resident targets in the grid area can be obtained.
For example, if the second preset number is set to 5 times and the number of occurrences of the monitoring target is 6 times, it may be determined that the monitoring target is a resident target in the grid area, i.e., the number of resident targets in the grid area may be incremented by 1. When the same monitoring target in the same grid area is judged as the resident target for the first time, the monitoring target is recorded as the resident target, and when the monitoring target is judged as the resident target for a plurality of times, the judgment for the first time and the later judgment are not accumulated in the number of the resident targets, so that the uniqueness of the resident targets can be ensured, and the problem of repeated statistics is avoided. Of course, the statistical approach of the resident targets for each grid area may be the same.
If the number of occurrences of the monitored target is 4, it can be determined that the monitored target is a non-stationary target in the grid area, i.e. the number of non-stationary targets in the grid area is accumulated to 1. When the same monitoring target in the same grid area is judged as the non-resident target for the first time, the monitoring target is recorded as the non-resident target, and when the monitoring target is judged as the non-resident target for many times, the judgment after the first time is not accumulated in the quantity of the non-resident targets, so that the uniqueness of the non-resident targets can be ensured, and the problem of repeated statistics is avoided. Of course, the statistical approach of the non-stationary targets for each grid region may be the same.
In an embodiment of the present invention, as shown in fig. 3, the preset statistical rule includes a fourth statistical rule. Step 104 further comprises:
judging whether the monitored target is a day and night target of each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target of each grid area;
and if the monitored target is the daytime and nighttime output target of the grid area, recording statistical data according to a fourth rule.
The diurnal emission target is a monitored target whose snapshot time is evening, for example, the set evening time is an evening time period from 7 pm to 5 am, and then when the snapshot time of the monitored target is from 7 pm to 5 am, it can be determined that the monitored target is the diurnal emission target. The fourth statistical rule is a rule for counting the diurnal emission targets, and all the monitored targets are unique in the diurnal emission targets. The diurnal emission target may be a diurnal emission person, a diurnal emission vehicle, or the like.
Specifically, when the appearance time of the monitoring target is night, it may be determined that the monitoring target is a diurnal night appearance target in the grid area. The number of objects of the diurnal night appearance object may be accumulated by 1 according to a fourth statistical rule. Therefore, the diurnal and nocturnal emission targets of all monitoring targets appearing in the grid area can be counted, and the statistical data of the diurnal emission targets in the grid area can be obtained. When the same monitoring target in the same grid area is judged as the daytime and nighttime target for the first time in the same time period, the monitoring target is recorded as the daytime and nighttime target, and when the monitoring target is judged as the daytime and nighttime target for multiple times, the first and later judgments are not accumulated in the daytime and nighttime target, so that the uniqueness of the daytime and nighttime target can be ensured, and the problem of repeated statistics is avoided. Of course, the statistical method of the diurnal and nocturnal targets of each grid area may be the same.
In an embodiment of the present invention, as shown in fig. 3, the preset statistical rules further include a fifth statistical rule and a sixth statistical rule. Step 104 further comprises:
and judging whether the monitored target is a known target of each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target of each grid area.
And if the monitored target is a known target of the grid area, recording statistical data according to a fifth statistical rule.
And if the monitored target is an unknown target of the grid area, recording statistical data according to a sixth statistical rule.
The fifth statistical rule is used for a rule for performing statistics on a known target. The sixth statistical rule is a rule for performing statistics on unknown targets. The known targets are targets that exist in a library of known targets. The above-mentioned known target may be a known person, a known vehicle, or the like. The unknown object may be an unknown person, an unknown vehicle, or the like. The unknown object may be an unidentified object.
Specifically, when target feature information (such as face feature information or license plate number feature information) of the monitored target is obtained, a search comparison is performed based on the target feature information and target feature information existing in a known target library, and if the target feature information corresponding to the target feature information is searched in the known target library, the monitored target can be determined to be a known target of the grid area. The target number of known targets may be accumulated by 1 according to a fifth statistical rule. Therefore, the known targets of all the monitored targets in the grid area can be counted to obtain the statistical data of the known targets in the grid area.
Otherwise, if the target feature information corresponding to the target feature information of the monitored target is not searched and inquired in the known target library, the monitored target can be determined to be an unknown target, and the target number of the known target is accumulated by 1 according to the sixth statistical rule. Therefore, the unknown targets of all the monitored targets in the grid area can be counted to obtain the statistical data of the unknown targets in the grid area.
It should be noted that the known target and the unknown target in the grid area are unique. Of course, the statistical methods for known targets and unknown targets may be the same for each grid region.
The preset statistical rules further include seven statistical rules. Step 104 further comprises:
and judging whether the monitored target is a special target of each grid area according to the target characteristic information of the monitored target of each grid area.
And if the monitored target is the special target of the grid area, recording the statistical data according to a seventh statistical rule.
The special target can be a frequent in-and-out target, a daytime and nighttime emergence target, a target with a special identity and the like. The seventh statistical rule is a rule for performing statistics on a specific target. Specifically, when target feature information (such as face feature information or license plate number feature information) of a monitored target is obtained, a search comparison is performed based on the target feature information and special target feature information existing in a special target library of an authority, and if the special target feature information corresponding to the target feature information is searched in the special target library, the monitored target can be determined to be a special target of the grid area. The target number of the specific target may be accumulated by 1 according to a seventh statistical rule. Therefore, the special targets of all the monitored targets appearing in the grid area can be counted to obtain the statistical data of the special targets in the grid area.
It should be noted that the specific object in the grid area is unique. Of course, the statistical approach of the specific target for each grid region may be the same.
In an embodiment of the present invention, as shown in fig. 3, the preset statistical rules further include an eighth statistical rule and a ninth statistical rule. Step 104 further comprises:
and judging whether the monitored target is an entry target of each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target of each grid area.
And if the monitored target is the access target of the grid area, recording statistical data according to an eighth statistical rule.
And if the monitoring target is the access target of the grid area, recording statistical data according to a ninth statistical rule.
Specifically, the eighth statistical rule is a rule for performing statistics on the entry target. The ninth statistical rule is a rule for counting the access targets. This allows statistics to be made of the ingress and egress targets among all monitored targets in each grid area.
In the embodiment of the present invention, through the first statistical rule, the second statistical rule, the third statistical rule, the fourth statistical rule, the fifth statistical rule, the sixth statistical rule, the seventh statistical rule, the eighth statistical rule, and the ninth statistical rule, frequent target access, resident target, non-resident target, night-and-day exit target, known target, unknown target, special target, access target, and access target of all monitored targets in each grid area can be respectively counted, so as to obtain statistical data corresponding to each grid area.
It should be noted that all the frequent access targets, resident targets, non-resident targets, daytime and nighttime exit targets, known targets, unknown targets, special targets, access targets, and access target numbers of all the grid areas obtained through statistics are stored in the database of the full-text search engine.
And 105, sending the statistical data of the monitoring targets in all the grid areas to a front-end page for hierarchical visual display according to the hierarchical relation of the grid areas.
The front-end page may be a display page supported by a user end device (a computer, a mobile phone, etc.).
Specifically, statistics of all frequent access targets, resident targets, non-resident targets, daytime and nighttime exit targets, known targets, unknown targets, special targets, access targets and access targets in all grid areas are sent to a front-end page for display.
And displaying layout and displaying thought of grid region statistics. In layout, the front-end page adopts a left-side data overview, a middle department level and a right-side map display mode, the left-side data statistical overview can be directly seen only by clicking a middle department list, and the right-side map display can correspondingly display statistical data on a map in a three-dimensional mode according to the middle department list, so that the data are more three-dimensional; on the aspect of showing, the invention adopts hierarchical showing, and links the statistical data of each hierarchical grid region up and down layer by layer according to the intermediate department list, thereby ensuring the real reliability of the data.
The left data statistics overview click data can see the statistics personnel association information, so that relevant workers can conveniently and intuitively know the monitoring target data appearing in each grid area in real time. The target and the abnormal behavior of the target are focused, so that the target condition in the grid can be monitored in real time.
The presentation may be in the form of rendering the data through various charts, click effects, and animation effects. Therefore, the statistical data of each grid area can be displayed more intuitively.
In the embodiment of the invention, a video stream in a preset area is obtained, wherein the preset area comprises a plurality of grid areas, and a hierarchical relationship exists among the grid areas; performing frame-by-frame image extraction processing on the video stream to obtain an image extraction image, wherein the image extraction image comprises a monitoring target; carrying out target identification on a monitored target in the image-extracted image, and extracting target information of the monitored target, wherein the target information comprises target characteristic information, snapshot time information and snapshot place information of the monitored target; counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information; sending the statistical data of the monitoring targets in all the grid areas to a front-end page for hierarchical visual display according to the hierarchical relation of the grid areas; the preset statistical rule comprises a first statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information comprises the following steps: calculating the occurrence frequency of the monitored target in each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target in each grid area; comparing the occurrence times with a first preset time, and judging whether the monitored target is a frequent in-out target of the grid area; and if the monitored target is the frequent access target of the grid area, recording the statistical data according to a first statistical rule. Therefore, diversified statistics can be carried out on the monitoring targets of each grid region, the statistical data of each grid region can be displayed in a hierarchical mode, the intuition is stronger, and the real reliability of the statistical data of each grid region is improved.
In an embodiment of the present invention, the method further includes:
and establishing activity data of each monitoring target according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target in each grid area, wherein the rule for establishing the activity data establishes an activity data for each activity target in each grid area.
Specifically, each monitoring target corresponds to one piece of activity data in one grid area, that is, only one piece of activity data exists in one monitoring target in the same grid area. When the monitoring target moves to other grid areas, the monitoring target also correspondingly has an activity data corresponding to the other grid areas. And the activity data of the monitoring target can be displayed based on technologies such as a visual hierarchy chart, a Police Geographic Information System (PGIS) and the like.
According to the embodiment of the invention, related workers can conveniently know the activity data of each monitoring target in each grid area, and the activity data of each monitoring target can be conveniently analyzed and counted.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a big data management apparatus based on grid management according to an embodiment of the present invention, where the big data management apparatus 200 based on grid management includes:
the acquiring module 201 is configured to acquire a video stream in a preset area, where the preset area includes a plurality of grid areas, and a hierarchical relationship exists between the plurality of grid areas.
The drawing module 202 is configured to perform drawing processing on the video stream frame by frame to obtain a drawing image, where the drawing image includes a monitoring target.
The identification module 203 is configured to perform target identification on the monitored target in the snapshot image, and extract target information of the monitored target, where the target information includes target feature information, snapshot time information, and snapshot location information of the monitored target.
And the counting module 204 is used for counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information.
A sending module 205, configured to send statistical data of monitoring targets in all grid areas to a front-end page for hierarchical visualization display according to a hierarchical relationship of the grid areas;
the preset statistical rules comprise first statistical rules; as shown in fig. 5, the statistics module 204 includes:
an appearance frequency calculation unit 2041, configured to calculate the appearance frequency of the monitoring target appearing in each grid region according to the target feature information, the snapshot time information, and the snapshot location information of the monitoring target in the grid region;
the first judging unit 2042 is configured to compare the occurrence times with a first preset time, and judge whether the monitored target is a frequent in-out target of the grid area;
the first recording unit 2043 is configured to record statistical data according to a first statistical rule if the monitoring target belongs to a frequent-entering target in the grid area.
Optionally, the preset statistical rule includes a second statistical rule and a third statistical rule, and the statistical module 204 further includes:
the second judgment unit is used for comparing the occurrence times with a second preset time and judging whether the monitored target is a resident target of the grid area;
the second recording unit is used for recording statistical data according to a second statistical rule if the monitoring target is a resident target of the grid area;
and the third recording unit is used for recording the statistical data according to a third statistical rule if the monitoring target is the non-stationary target of the grid area.
Optionally, the preset statistical rule includes a fourth statistical rule, and the statistical module 204 further includes:
a third judging unit, configured to judge whether the monitored target is a diurnal and nocturnal target in each grid region according to the target feature information, the snapshot time information, and the snapshot location information of the monitored target in each grid region;
and the fourth recording unit is used for recording the statistical data according to a fourth rule if the monitored target is the diurnal and nocturnal target of the grid area.
Optionally, the preset statistical rules further include a fifth statistical rule and a sixth statistical rule, and the statistical module 204 further includes:
the fourth judging unit is used for judging whether the monitored target is a known target of each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target of each grid area;
a fifth recording unit, configured to record statistical data according to a fifth statistical rule if the monitored target is a known target of the grid area;
and the sixth recording unit is used for recording the statistical data according to a sixth statistical rule if the monitored target is an unknown target of the grid area.
Optionally, the preset statistical rule further includes a seventh statistical rule, and the statistical module 204 further includes:
a fifth judging unit, configured to judge whether the monitored target is a special target of each grid region according to the target feature information of the monitored target of the grid region;
and the seventh recording unit is used for recording the statistical data according to a seventh statistical rule if the monitored target is the special target of the grid area.
Optionally, the big data management apparatus 200 based on grid management further includes:
the establishing module is used for establishing activity data of each monitoring target according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target of each grid area, wherein the rule for establishing the activity data establishes an activity data for each activity target in each grid area.
The device 200 for big data management based on grid management according to the embodiment of the present invention can implement each implementation manner in the above method embodiments and corresponding beneficial effects, and is not described herein again to avoid repetition.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, where the electronic device 300 includes: a memory 302, a processor 301 and a computer program stored on the memory 302 and capable of running on the processor 301, wherein the processor 301 implements the steps of the grid management-based big data management method provided by the above-mentioned embodiments when executing the computer program,
the electronic device 300 provided in the embodiment of the present invention can implement each implementation manner in the above method embodiments and corresponding beneficial effects, and is not described herein again to avoid repetition.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the grid management-based big data management method provided in the embodiment of the present invention, and can achieve the same technical effect, and in order to avoid repetition, details are not described here again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, and the program can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (10)
1. A big data management method based on gridding management is characterized by comprising the following steps:
acquiring a video stream in a preset area, wherein the preset area comprises a plurality of grid areas, and a hierarchical relationship exists among the grid areas;
performing frame-by-frame image extraction processing on the video stream to obtain an image extraction image, wherein the image extraction image comprises a monitoring target;
carrying out target identification on a monitored target in the image-drawing image, and extracting target information of the monitored target, wherein the target information comprises target characteristic information, snapshot time information and snapshot place information of the monitored target;
counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information;
sending the statistical data of the monitoring targets in all the grid areas to a front-end page for hierarchical visual display according to the hierarchical relation of the grid areas;
the preset statistical rule comprises a first statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information comprises the following steps:
calculating the occurrence frequency of the monitoring target appearing in each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target in each grid area;
comparing the occurrence times with a first preset time, and judging whether the monitored target is a frequent in-out target of the grid area;
and if the monitored target is the frequent access target of the grid area, recording the statistical data according to the first statistical rule.
2. The big data management method based on grid management as claimed in claim 1, wherein the preset statistical rule comprises a second statistical rule and a third statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information further comprises:
comparing the occurrence times with a second preset time, and judging whether the monitoring target is a resident target of the grid area;
if the monitoring target is a resident target of the grid area, recording the statistical data according to the second statistical rule;
and if the monitored target is the non-stationary target of the grid area, recording the statistical data according to the third statistical rule.
3. The big data management method based on grid management as claimed in claim 2, wherein the preset statistical rule comprises a fourth statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information further comprises:
judging whether the monitored target is a day and night target of each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target of each grid area;
and if the monitored target is the diurnal and nocturnal emission target of the grid area, recording the statistical data according to the fourth rule.
4. The big data management method based on grid management as claimed in claim 3, wherein the preset statistical rules further include a fifth statistical rule and a sixth statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rules according to the target information further comprises:
judging whether the monitored target is a known target of each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitored target of each grid area;
if the monitored target is a known target of the grid area, recording the statistical data according to the fifth statistical rule;
and if the monitored target is an unknown target of the grid area, recording the statistical data according to the sixth statistical rule.
5. The big data management method based on grid management as claimed in claim 4, wherein the preset statistical rule further includes a seventh statistical rule, and the step of counting the statistical data of each grid region based on the preset statistical rule according to the target information further includes:
judging whether the monitoring target is a special target of each grid area according to the target characteristic information of the monitoring target of each grid area;
and if the monitored target is a special target of the grid area, recording the statistical data according to the seventh statistical rule.
6. The method for large data management based on grid management according to claim 1, wherein the method further comprises:
and establishing activity data of each monitoring target according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target in each grid area, wherein the rule for establishing the activity data establishes an activity data for each activity target in each grid area.
7. A big data management device based on gridding management, which is characterized in that the device comprises:
the device comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring a video stream in a preset area, the preset area comprises a plurality of grid areas, and a hierarchical relationship exists among the grid areas;
the image extracting module is used for carrying out image extracting processing on the video stream frame by frame to obtain an image extracting image, and the image extracting image comprises a monitoring target;
the recognition module is used for carrying out target recognition on a monitored target in the image extraction image and extracting target information of the monitored target, wherein the target information comprises target characteristic information, snapshot time information and snapshot place information of the monitored target;
the statistical module is used for counting the statistical data of the monitoring target in each grid area based on a preset statistical rule according to the target information;
the transmitting module is used for transmitting the statistical data of the monitoring targets in all the grid areas to a front-end page to carry out hierarchical visual display according to the hierarchical relation of the grid areas;
the preset statistical rule comprises a first statistical rule, and the statistical module comprises:
the appearance frequency calculation unit is used for calculating the appearance frequency of the monitoring target in each grid area according to the target characteristic information, the snapshot time information and the snapshot place information of the monitoring target in the grid area;
the first judgment unit is used for comparing the occurrence times with a first preset time and judging whether the monitored target is a frequent access target of the grid area;
and the first recording unit is used for recording the statistical data according to the first statistical rule if the monitoring target is a frequent access target of the grid area.
8. The big data management device based on grid management as claimed in claim 7, wherein the preset statistical rules comprise a second statistical rule and a third statistical rule, the statistical module further comprises:
the second judging unit is used for comparing the occurrence times with a second preset time and judging whether the monitoring target is a resident target of the grid area;
a second recording unit, configured to record the statistical data according to the second statistical rule if the monitored target is a resident target of the grid area;
and the third recording unit is used for recording the statistical data according to the third statistical rule if the monitoring target is the non-stationary target of the grid area.
9. An electronic device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the grid management based big data management method according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements the steps in the grid management-based big data management method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110271650.XA CN112686226A (en) | 2021-03-12 | 2021-03-12 | Big data management method and device based on gridding management and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110271650.XA CN112686226A (en) | 2021-03-12 | 2021-03-12 | Big data management method and device based on gridding management and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112686226A true CN112686226A (en) | 2021-04-20 |
Family
ID=75455522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110271650.XA Pending CN112686226A (en) | 2021-03-12 | 2021-03-12 | Big data management method and device based on gridding management and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686226A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114943936A (en) * | 2022-06-17 | 2022-08-26 | 北京百度网讯科技有限公司 | Target behavior identification method and device, electronic equipment and storage medium |
| CN117319611A (en) * | 2023-11-28 | 2023-12-29 | 重庆华悦生态环境工程研究院有限公司深圳分公司 | Monitoring image transmission method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040145658A1 (en) * | 2000-01-13 | 2004-07-29 | Ilan Lev-Ran | Video-based system and method for counting persons traversing areas being monitored |
| CN106341658A (en) * | 2016-08-31 | 2017-01-18 | 广州精点计算机科技有限公司 | Intelligent city security state monitoring system |
| CN107092680A (en) * | 2017-04-21 | 2017-08-25 | 中国测绘科学研究院 | A kind of government information resources integration method based on geographic grid |
| CN110390031A (en) * | 2019-06-28 | 2019-10-29 | 深圳市商汤科技有限公司 | Information processing method and device, vision facilities and storage medium |
| CN110705477A (en) * | 2019-09-30 | 2020-01-17 | 深圳市商汤科技有限公司 | Behavior analysis method and apparatus, electronic device, and computer storage medium |
| CN111258466A (en) * | 2020-01-03 | 2020-06-09 | 珠海市岭南大数据研究院 | Data visualization method and device, computer equipment and storage medium |
-
2021
- 2021-03-12 CN CN202110271650.XA patent/CN112686226A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040145658A1 (en) * | 2000-01-13 | 2004-07-29 | Ilan Lev-Ran | Video-based system and method for counting persons traversing areas being monitored |
| CN106341658A (en) * | 2016-08-31 | 2017-01-18 | 广州精点计算机科技有限公司 | Intelligent city security state monitoring system |
| CN107092680A (en) * | 2017-04-21 | 2017-08-25 | 中国测绘科学研究院 | A kind of government information resources integration method based on geographic grid |
| CN110390031A (en) * | 2019-06-28 | 2019-10-29 | 深圳市商汤科技有限公司 | Information processing method and device, vision facilities and storage medium |
| CN110705477A (en) * | 2019-09-30 | 2020-01-17 | 深圳市商汤科技有限公司 | Behavior analysis method and apparatus, electronic device, and computer storage medium |
| CN111258466A (en) * | 2020-01-03 | 2020-06-09 | 珠海市岭南大数据研究院 | Data visualization method and device, computer equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114943936A (en) * | 2022-06-17 | 2022-08-26 | 北京百度网讯科技有限公司 | Target behavior identification method and device, electronic equipment and storage medium |
| CN117319611A (en) * | 2023-11-28 | 2023-12-29 | 重庆华悦生态环境工程研究院有限公司深圳分公司 | Monitoring image transmission method and device |
| CN117319611B (en) * | 2023-11-28 | 2024-03-29 | 重庆华悦生态环境工程研究院有限公司深圳分公司 | Monitoring image transmission method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220092881A1 (en) | Method and apparatus for behavior analysis, electronic apparatus, storage medium, and computer program | |
| CN109766744B (en) | Pine wood nematode disease tree identification and positioning method and system | |
| TWI747341B (en) | File application method, device and storage medium | |
| CN108416985B (en) | Geological disaster monitoring and early warning system and method based on image recognition | |
| EP2219379A2 (en) | Social network construction based on data association | |
| CN106355154B (en) | Method for detecting frequent passing of people in surveillance video | |
| CN113065474B (en) | Behavior recognition method and device and computer equipment | |
| CN111222373B (en) | Personnel behavior analysis method and device and electronic equipment | |
| CN109544754B (en) | Access control method and system based on face recognition and computer equipment | |
| CN112686226A (en) | Big data management method and device based on gridding management and electronic equipment | |
| CN111241305A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| WO2020114138A1 (en) | Information associated analysis method and apparatus, and storage medium and electronic device | |
| CN103413330A (en) | Method for reliably generating video abstraction in complex scene | |
| CN102902960B (en) | Leave-behind object detection method based on Gaussian modelling and target contour | |
| CN111209446A (en) | Method and device for presenting personnel retrieval information and electronic equipment | |
| CN109033476A (en) | A kind of intelligent space-time data event analysis method based on event clue network | |
| Wang et al. | Video anomaly detection method based on future frame prediction and attention mechanism | |
| CN103888731A (en) | Structured description device and system for mixed video monitoring by means of gun-type camera and dome camera | |
| CN110019963B (en) | Method for searching suspect relation personnel | |
| CN109831634A (en) | The density information of target object determines method and device | |
| CN111435435A (en) | Method, device, server and system for identifying pedestrians | |
| CN111753642A (en) | Method and device for determining key frame | |
| CN112383751A (en) | Monitoring video data processing method and device, terminal equipment and storage medium | |
| CN112651992B (en) | Track tracking method and system | |
| CN111798356B (en) | Rail transit passenger flow abnormal pattern recognition method based on big data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210420 |
|
| RJ01 | Rejection of invention patent application after publication |