CN113362376A - Target tracking method - Google Patents
Target tracking method Download PDFInfo
- Publication number
- CN113362376A CN113362376A CN202110705333.4A CN202110705333A CN113362376A CN 113362376 A CN113362376 A CN 113362376A CN 202110705333 A CN202110705333 A CN 202110705333A CN 113362376 A CN113362376 A CN 113362376A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- area point
- point location
- blind area
- bright area
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Abstract
The invention provides a target tracking method, which comprises the following steps: acquiring a monitoring bright area point location according to the query information; matching the monitoring bright area point and the monitoring blind area point by combining an association rule to obtain an associated monitoring blind area point; and arranging and connecting the monitoring bright area point locations and the associated monitoring blind area point locations according to a time sequence to obtain the moving path of the target. The existing software and hardware facilities in the area are utilized to the maximum extent, the association rules of the monitoring open areas and the monitoring blind areas are used for automatically calculating the staying position and time of the user in the monitoring blind areas according to the monitoring open area point location information and the monitoring blind area point location information and combining the association rules after the personnel information is input, so that the tracking and the troubleshooting in the user blind areas are realized, the personnel action paths are presented, and the close contact personnel are found more efficiently.
Description
Technical Field
The invention relates to the technical field of information of the Internet of things, in particular to a target tracking method.
Background
With the development of technology and the requirements of related security and epidemic prevention regulations, higher requirements are put forward on video monitoring and target tracking systems in various industrial parks and public buildings. Especially in the work of epidemic prevention and control, it is very important to acquire the movement track of the personnel in a small range in order to control the spread of the epidemic situation.
At present, once high-risk people are found in people, people can be quickly positioned to close-connected people of the high-risk people for epidemic prevention risk prevention and control through safety control cameras distributed all over the street. However, when the person enters a blind area without video monitoring, such as an office, a factory, a public transport vehicle, etc., the position of the person is basically in a state that the person cannot be tracked by free actions, and the action range of the person is often uncertain, so that it is difficult to find the whereabouts of the person in the monitoring blind area and to closely contact the person. Even if partial behaviors of the personnel in the monitoring blind area are obtained through investigation, technical means for linking data of monitoring equipment with the behaviors of the personnel in the monitoring blind area are lacked.
Therefore, a method is needed to acquire the trace of the person in the monitoring blind area and track the behavior of the person in the monitoring blind area in relation to the behavior in the monitoring range.
Disclosure of Invention
To solve the problems in the prior art, an embodiment of the present invention provides a target tracking method, including:
in a first aspect, the present invention provides a target tracking method, including:
acquiring a monitoring bright area point location according to the query information; matching the monitoring bright area point and the monitoring blind area point by combining an association rule to obtain an associated monitoring blind area point; and arranging and connecting the monitoring bright area point locations and the associated monitoring blind area point locations according to a time sequence to obtain the moving path of the target.
According to a target tracking method provided by the invention, the query information comprises: identity information and time range of the target.
According to the target tracking method provided by the invention, the monitoring bright area point location is obtained according to the query information, and the method comprises the following steps:
adding the monitoring bright area point location into a point location list;
and the monitoring bright area point position is the position and time of the target in the monitoring bright area in the time range.
According to the target tracking method provided by the invention, the monitoring bright area point location and the monitoring blind area point location are matched by combining the association rule, and the method further comprises the following steps:
if the associated monitoring blind area point locations are obtained in a matching mode, adding the associated monitoring blind area point locations into the point location list;
and the monitoring blind area point position is the position and the time of the target in the monitoring blind area within the time range.
According to the target tracking method provided by the invention, if the associated monitoring blind area point location is obtained in a matching manner, the associated monitoring blind area point location is added into the point location list, and the method further comprises the following steps:
judging whether other monitoring bright area points exist or not; if the other monitoring bright area points exist, matching the other monitoring bright area points with the monitoring blind area points by combining an association rule; and if the other monitoring bright area point locations do not exist, outputting the point location list.
According to the target tracking method provided by the invention, the monitoring bright area point location and the monitoring blind area point location are matched by combining the association rule, and the method further comprises the following steps:
if the associated monitoring blind area point location cannot be obtained, judging whether other monitoring open area point locations exist or not; if the other monitoring open area point locations exist, continuously matching the other monitoring open area point locations with the monitoring blind area point locations; and if the other monitoring bright area point locations do not exist, outputting the point location list.
According to the target tracking method provided by the invention, the monitoring bright area point locations and the associated monitoring blind area point locations are arranged and connected according to the time sequence to obtain the target activity path, and the method comprises the following steps:
arranging the point location list according to the time sequence;
acquiring the positions of the monitoring bright area point and the associated monitoring blind area point according to the point position list;
and identifying the positions on the map and sequentially connecting the positions according to the time sequence to obtain the target activity path.
According to the target tracking method provided by the invention, the monitoring bright area point location and the monitoring blind area point location are matched by combining the association rule, and the method comprises the following steps:
defining a support threshold; defining a confidence threshold;
obtaining the support degree and the confidence degree of the association rule;
if the support degree of the association rule is higher than the support degree threshold value and the confidence degree of the association rule is higher than the confidence degree threshold value;
outputting the association rule as an optimal association rule;
and matching the monitoring bright area point location and the monitoring blind area point location according to the optimal association rule to obtain the associated monitoring blind area point location.
In a second aspect, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the target tracking method according to any one of the above aspects.
In a third aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the object tracking method as described in any one of the above.
Therefore, the invention provides a target tracking method, which matches the corresponding relation between the monitoring bright area point and the monitoring blind area point through an association rule, arranges and connects the monitoring bright area point and the association monitoring blind area point according to the time sequence, and obtains the moving path of the target. The existing software and hardware facilities in the area are utilized to the maximum extent, the use records of designated personnel are obtained by calling the system inquiry function through accessing a background system of the software and hardware facilities, after personnel information is input through the association rules of the monitoring open area and the monitoring blind area, the staying position and time of a user in the monitoring blind area are calculated automatically according to the point location information of the monitoring open area and the point location information of the monitoring blind area and combined with the association rules, tracking and troubleshooting in the user blind area are realized, the action path of the personnel is presented, the close contact personnel are found more efficiently, and the software and hardware equipment is particularly suitable for relatively closed environments such as various industrial parks, schools and the like.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a target tracking method according to an embodiment of the present invention;
FIG. 2 is a second schematic flowchart of a target tracking method according to an embodiment of the present invention;
FIG. 3 is a flow chart illustrating the extraction of association rules according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. 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.
The embodiment of the invention discloses a target tracking method, which specifically comprises the following steps as shown in figures 1-2:
acquiring a monitoring bright area point location according to the query information;
after the monitoring bright area point locations are obtained, adding all the monitoring bright area point locations into a point location list;
matching the monitoring bright area point and the monitoring blind area point by combining an association rule to obtain an associated monitoring blind area point, and adding the screened monitoring blind area point into a point list;
and arranging and connecting the monitoring bright area point locations and the associated monitoring blind area point locations according to a time sequence, thereby obtaining an active path of the target.
Wherein the query information comprises: target identity information and time range;
optionally, the target identity information may be one or more of a name, an identity card, a job number, a two-dimensional code and a license plate number;
optionally, the time range is at least 1 hour, such as 9: 00-10: in the time interval of 00, the invention does not limit the end point of the time range;
the monitoring bright area point location or the monitoring blind area point location is an activity record respectively generated by a tracked target in the monitoring bright area or the monitoring blind area within the query time range;
wherein, monitoring the activity record of the bright area includes but is not limited to: a park entrance monitoring camera, a street monitoring camera, a building entrance health code swiping record and a parking lot entrance record;
in one embodiment, the time of a tracking target entering a park can be obtained and the entrance position can be determined through a park entrance monitoring camera; the walking time and the route of the tracked target entering the park can be obtained through the street monitoring camera; the time and the specific position of a tracking target reaching an office place can be obtained through a monitoring camera and health code swiping records at an entrance of a building, and health data is obtained through health codes; according to the parking lot entrance record, the time of a tracking target entering a parking lot and a potential path from the parking lot to an office place can be acquired;
wherein, the record of the activity of the monitoring blind area includes but is not limited to: the method comprises the following steps of (1) carrying out access card swiping record, fingerprint/facial recognition attendance machine, IC card, meeting room electronic sign-in, indoor health code swiping record, bus card swiping record and code swiping shopping consumption record; the collected point location information is used as supplementary information of a video monitoring bright area, so that the action path of the appointed person in the limited area is perfected, and a complete time line of the action line of the person in the limited area is formed.
In one embodiment, through the card swiping record of the entrance guard card, the record of the card swiping entering place and time after the tracked target enters the monitoring blind area can be obtained; the attendance machine can acquire the place and time of the card punching action after the tracking target enters the monitoring blind area; through IC card/code swiping shopping consumption records, such as canteen consumption card swiping records or living area consumption card swiping records, the place and time of consumption behavior of a tracking target entering a monitoring blind area can be obtained; through the conference room electronic check-in record, the position and time of the check-in behavior of the tracking target in the monitoring blind area conference room can be obtained; through the indoor health code swiping record, the specific department position and time of the tracking target entering the monitoring blind area can be obtained; through the card swiping record of the bus card, the serial number of the public transport means taken by the tracking target can be obtained, and the travel route and time of the tracking target are obtained;
in one embodiment, before tracking the targets, behavior records and corresponding time of a plurality of targets occurring in a monitoring bright area and a monitoring blind area are obtained, the behavior records and the corresponding time in the monitoring bright area are recorded as a monitoring bright area point location library, and the behavior records and the corresponding time in the monitoring blind area are recorded as a monitoring blind area point location library;
further, according to query conditions, acquiring a monitoring bright area meeting the conditions from a monitoring bright area point database, adding the screened monitoring bright area into a point location list, and acquiring behaviors and time of the monitoring bright area from the point location list;
optionally, the acquired time in the monitoring bright area may be a time point or a time interval, for example { building gate 1 snapshot camera record, 8:35}, where the duration is less than 1 minute, and the duration is recorded as 1 minute, where 8:35 belongs to time interval 8: 00-9: 00;
in an embodiment, as shown in fig. 2, matching the monitoring bright area point and the monitoring blind area point in combination with an association rule, further includes:
if the associated monitoring blind area point locations are obtained in a matching mode, adding the associated monitoring blind area point locations into the point location list;
and the monitoring blind area point position is the position and the time of the target in the monitoring blind area within the time range.
Optionally, the acquired time in the dead zone may be a time point or a time interval, for example {3 th fingerprint punched-card machine record, 8:50}, where the duration is less than 1 minute, and the duration is recorded as 1 minute, where 8:50 belongs to time interval 8: 00-9: 00;
optionally, the point location list may be one of an Excel worksheet or a flowchart.
In one embodiment, if the associated blind monitoring area point location is obtained in a matching manner, the associated blind monitoring area point location is added to the point location list, specifically including:
adding the monitoring bright area point location into a point location list;
if the monitoring open area point location is matched with the monitoring blind area point location library through the association rule to obtain the monitoring blind area point location, adding the monitoring blind area point location into the same point location list;
further, searching a monitoring open area point position library, and judging whether other monitoring open area points exist or not, so that all monitoring open area points are traversed, omission is avoided, and monitoring blind area points with higher mining confidence degrees possibly existing are avoided being omitted;
if other monitoring open area point locations exist, matching the new monitoring open area point location with the monitoring blind area point location library through the association rule, and repeatedly executing all the previous steps;
if no other monitoring bright area points exist in the searching, the calculation is performed by traversing all the monitoring bright area points in the monitoring bright area point library, and an accumulated point list is output;
specifically, if the matching of the monitoring open area point location and the monitoring blind area point location library fails through the association rule, the monitoring blind area point location is not obtained, and whether other monitoring open area points exist is continuously judged, so that all monitoring open area points are traversed;
if other monitoring open area point locations exist, matching the new monitoring open area point location with the monitoring blind area point location library through the association rule, and repeatedly executing all the previous steps;
if no other monitoring bright area points exist, it is indicated that all monitoring bright area points in the monitoring bright area point position library have been traversed in the calculation, and an accumulated point position list is output.
In one embodiment, the chronologically arranging and connecting the monitoring bright zone points and the associated monitoring blind zone points to obtain a target activity path includes:
calling a map in an area range generated by map software;
optionally, the map may be one of a Baidu map, a Gade map, and the like.
Alternatively, the area may be an industrial park, an office park, or a school.
Optionally, the regional scope may also include a main artery connecting the garden with the garden.
Arranging the obtained point location lists according to the time sequence, and obtaining the positions of the monitoring bright area point locations and the positions of the associated monitoring blind area point locations;
identifying the positions on a map and sequentially connecting the positions according to a time sequence to obtain the target activity path;
preferably, the position of the point location is identified on the map, the area size of the identification point can be changed to represent the staying time of the target at the specific point location, and the larger the area is, the longer the staying time is identified;
preferably, the positions of the point locations are identified on the map, the colors of the identification points can be changed to identify the behavior types of the targets at the specific point locations, for example, the camera capture identification is blue, the face recognition attendance identification is black, the health code scanning identification is green, and the garden consumption behavior identification is white.
Preferably, for an object identified as being of high risk, the active path of the object is identified as red.
In one embodiment, assume that an office building has a gate snapshot camera a, a 3 rd face recognition access control machine B, a 3 rd fingerprint punched-card machine C, and a-1 rd dining-room card machine D. A, B belongs to a monitoring bright area, and C, D belongs to a monitoring blind area. Face recognition by monitoring bright areas A, B based on daily behavior patterns, some behavior sets can be generalized, including 8:35 entering a building, 8: breakfast 40, 8: 45 upstairs and 8:50, punching a card:
| collection | Behavior |
| {A,B,C} | { enter building 8:35, going upstairs 8: 45, card punching 8:50} |
| {A,D,B,C} | { enter building 8:35, eating breakfast 8: 40, going upstairs 8: 45, card punching 8:50} |
| {A,D} | { enter building 8:35, eating breakfast 8: 40} |
Specifically, as shown in fig. 3, the extracting step of the rule set includes:
s301, inputting a data set; the data set comprises a monitoring bright area point position library and a monitoring blind area point position library;
s302, defining a minimum support degree;
s303 sets an iteration round K to 1;
s304, acquiring data in the monitoring bright area point position library and the monitoring blind area point position library, wherein the data comprises position, identity information and time intervals, and forming K item sets;
S305K item set support degree calculation;
s306, analyzing the calculation result of each item set, if the support degree is smaller than the minimum support degree, executing a step S307 to abandon the data, otherwise, obtaining a frequent item set and executing a step 208;
s307 abandoning the data, namely abandoning the item set, wherein the relation of the item set cannot be used as an association rule because the minimum support degree is not met;
s308 further judges whether the frequent item set in the calculation result is empty, if so, S309 is executed to take the K-1 th item set of the previous calculation result as the frequent item set, and S313 is skipped to finish the process; if not, executing S310 to judge whether the frequent item set is unique, if so, executing S314 to take the Kth item set as the frequent item set and skipping to S315 to finish the process, otherwise, executing S313 to perform the next round of calculation;
s311 sets K to K +1, returns the K +1 th item set to step S304 as a new data set, and executes the subsequent steps;
s312, taking the K item set as a frequent item set;
s313 ends the flow.
Through the iteration process, all item sets are iterated and traversed, and frequent item sets meeting the requirement of the support degree are obtained from the item sets.
It should be noted that, an item set is a set containing specified items, which is called an item set, and includes records in a plurality of monitoring bright areas, records in a monitoring blind area, and an item set valid time interval;
it should be noted that, the support count is the number of transactions containing a specific item set, that is, every time a record in the monitoring bright area in the valid time of an item set is generated, the support count of the item set is added by 1;
it should be noted that the frequent item set is a frequent item set when the relative support of a certain item set meets a predefined minimum support threshold. If the support degree threshold of the item set is set to be 95%, after 100 employees enter the gate of the No. 1 building and the face recognition entrance guard of the No. 3 building is recorded, 2 employees forget to punch the card, the relative support degree of the item set is 98%, and the threshold requirement is met.
It should be noted that the support is used to determine how often a rule can be used for a given data set:
it should be noted that the confidence level is used to determine how frequently Y occurs in the transaction containing X:
it should be noted that a strong rule, i.e., an association rule satisfying both the minimum support threshold and the minimum confidence threshold, is called a strong rule.
Specifically, for example, association rules { building 1 gate snapshot camera a record, building 13 face recognition entrance guard B record, fingerprint punched-card machine C record, 08:00-09:00}, 100 records in the item set valid time interval 08:00-09:00 on this day, the support degree count is 98, and the support degree count is 98 and the transaction total number is 100, so the rule set support degree is 0.98.
It should be noted that the confidence is the quotient of the support count of the item set and all the support counts containing the item set.
Preferably, the optimal range of the support degree threshold is 80% -90%;
preferably, the confidence threshold is 65%.
Specifically, according to the optimal association rule, matching the monitoring bright area point location and the monitoring blind area point location to obtain the associated monitoring blind area point location, specifically including the steps of:
step S1: inquiring records of the personnel in the monitoring bright area, wherein the records comprise a gate snapshot camera snapshot record a extracted from a security system and a 3 rd floor face recognition access control machine recognition record b, and adding the gate snapshot camera snapshot record a and the 3 rd floor face recognition access control machine recognition record b to a behavior list;
step S2: and inquiring the behavior records of the personnel in the monitoring blind area, wherein the behavior records comprise a card punching record c of a 3-floor fingerprint card punching machine and a card punching record d of a-1-floor canteen card punching machine which occur in the same time interval.
Step S3: respectively using association rules R1And R2And calculating the support degree and the confidence degree of the monitoring blind area behavior records c and d. In this example, the association rule R1Is higher than R2Rule of association of failure recovery R1Blind spot behavior record c.
Step S4: adding the blind area behavior record c to a point location list;
step S5: and sequencing and outputting the point location list according to time, and performing point marking and line connecting on the map.
It should be noted that the above steps are only an example of one embodiment.
And repeating the steps S1-S4 for multiple times to obtain the blind area point with the highest confidence and support degree and screen out the optimal association rule.
Because the behavior trace of the personnel in the blind area comes from a plurality of different systems, the content recorded by each system is inconsistent in time and space, and the conflict situation is avoided through the steps.
In one embodiment, rules are considered
Since the support of { going upstairs, and getting up with a card } is 2 and the total number of transactions is 3, the support is 2/3-67%, and since all transactions including { going upstairs, going upstairs } include { getting up with a card }, the confidence is 2/2-100%. Thus, from table 1, it can be extracted:
the rule shows that strong connection exists between the 3-floor face recognition entrance guard machine and the 3-floor fingerprint card punch;
consider a rule
Since the support of { going upstairs, eating breakfast } is 1 and the total number of affairs is 3, the support is 1/3 ═33%, since the number of transactions including { going upstairs, going upstairs } and transactions including { eating breakfast } is 1, its confidence is 1/2 ═ 50%;
the monitoring blind area point position obtained by screening is required to be { punch card }, and association rules are adopted
To be closer.
Through the association rule, the monitoring blind area point meeting the association rule is found from the monitoring blind area point library in the same time interval, so that the condition that the content recorded by each system is inconsistent in time and space to generate conflict is avoided.
On the other hand, an embodiment of the present invention provides an electronic device, which is shown as a schematic entity structure diagram of the electronic device as shown in fig. 4, where the electronic device may include: a processor (processor)410, a communication interface (communication interface)420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may call logic instructions in the memory 430 to perform a target tracking method, the method comprising: acquiring a monitoring bright area point location according to the query information; matching the monitoring bright area point and the monitoring blind area point by combining an association rule to obtain an associated monitoring blind area point; and arranging and connecting the monitoring bright area point locations and the associated monitoring blind area point locations according to a time sequence to obtain the moving path of the target.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform a method of object tracking provided by the above methods, the method comprising: acquiring a monitoring bright area point location according to the query information; matching the monitoring bright area point and the monitoring blind area point by combining an association rule to obtain an associated monitoring blind area point; and arranging and connecting the monitoring bright area point locations and the associated monitoring blind area point locations according to a time sequence to obtain the moving path of the target.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform a method of object tracking provided in the above aspects, the method comprising: acquiring a monitoring bright area point location according to the query information; matching the monitoring bright area point and the monitoring blind area point by combining an association rule to obtain an associated monitoring blind area point; and arranging and connecting the monitoring bright area point locations and the associated monitoring blind area point locations according to a time sequence to obtain the moving path of the target.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A target tracking method, comprising:
acquiring a monitoring bright area point location according to the query information;
matching the monitoring bright area point and the monitoring blind area point by combining an association rule to obtain an associated monitoring blind area point;
and arranging and connecting the monitoring bright area point locations and the associated monitoring blind area point locations according to a time sequence to obtain the moving path of the target.
2. The method of claim 1, wherein the query information comprises: identity information and time range of the target.
3. The target tracking method according to claim 1, wherein obtaining the monitoring bright area point location according to the query information comprises:
adding the monitoring bright area point location into a point location list;
and the monitoring bright area point position is the position and time of the target in the monitoring bright area in the time range.
4. The target tracking method according to claim 3, wherein the monitoring bright area point location and the monitoring blind area point location are matched in combination with an association rule, and further comprising:
if the associated monitoring blind area point locations are obtained in a matching mode, adding the associated monitoring blind area point locations into the point location list;
and the monitoring blind area point position is the position and the time of the target in the monitoring blind area within the time range.
5. The target tracking method according to claim 4, wherein if the associated dead zone point location is obtained by matching, adding the associated dead zone point location to the point location list, further comprising:
judging whether other monitoring bright area points exist or not;
if the other monitoring bright area points exist, matching the other monitoring bright area points with the monitoring blind area points by combining the association rule;
and if the other monitoring bright area point locations do not exist, outputting the point location list.
6. The target tracking method according to claim 4, wherein the monitoring bright area point location and the monitoring blind area point location are matched in combination with an association rule, and further comprising:
if the associated monitoring blind area point location cannot be obtained, judging whether other monitoring open area point locations exist or not;
if the other monitoring open area point locations exist, continuously matching the other monitoring open area point locations with the monitoring blind area point locations;
and if the other monitoring bright area point locations do not exist, outputting the point location list.
7. The method according to claim 6, wherein the obtaining a target activity path by connecting the monitoring bright zone point and the associated monitoring blind zone point in a time sequence comprises:
arranging the point location list according to the time sequence;
acquiring the positions of the monitoring bright area point and the associated monitoring blind area point according to the point position list;
and identifying the positions on the map and sequentially connecting the positions according to the time sequence to obtain the target activity path.
8. The target tracking method according to claim 1, wherein matching the monitoring bright area point location and the monitoring blind area point location in combination with an association rule comprises:
defining a support threshold; defining a confidence threshold;
obtaining the support degree and the confidence degree of the association rule;
if the support degree of the association rule is higher than the support degree threshold value and the confidence degree of the association rule is higher than the confidence degree threshold value;
outputting the association rule as an optimal association rule;
and matching the monitoring bright area point location and the monitoring blind area point location according to the optimal association rule to obtain the associated monitoring blind area point location.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of a method of object tracking as claimed in any one of claims 1 to 8 are implemented when the program is executed by the processor.
10. A non-transitory computer readable storage medium, having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of a target tracking method as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110705333.4A CN113362376A (en) | 2021-06-24 | 2021-06-24 | Target tracking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110705333.4A CN113362376A (en) | 2021-06-24 | 2021-06-24 | Target tracking method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113362376A true CN113362376A (en) | 2021-09-07 |
Family
ID=77536215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110705333.4A Pending CN113362376A (en) | 2021-06-24 | 2021-06-24 | Target tracking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113362376A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115116164A (en) * | 2022-06-08 | 2022-09-27 | 武汉虹信技术服务有限责任公司 | Dynamic management method, system and medium for park access control permission |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030048926A1 (en) * | 2001-09-07 | 2003-03-13 | Takahiro Watanabe | Surveillance system, surveillance method and surveillance program |
| AU2008264230A1 (en) * | 2008-11-24 | 2010-06-10 | Canon Kabushiki Kaisha | Rule-based network surveillance system |
| CN102638675A (en) * | 2012-04-01 | 2012-08-15 | 安科智慧城市技术（中国）有限公司 | Method and system for target tracking by using multi-view videos |
| CN106651916A (en) * | 2016-12-29 | 2017-05-10 | 深圳市深网视界科技有限公司 | Target positioning tracking method and device |
| CN109977730A (en) * | 2017-12-27 | 2019-07-05 | 深圳市优必选科技有限公司 | A kind of personnel's path following method, system and terminal device |
| CN110175583A (en) * | 2019-05-30 | 2019-08-27 | 重庆跃途科技有限公司 | It is a kind of in the campus universe security monitoring analysis method based on video AI |
| CN110443828A (en) * | 2019-07-31 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Method for tracing object and device, storage medium and electronic device |
| CN111915671A (en) * | 2020-07-15 | 2020-11-10 | 安徽清新互联信息科技有限公司 | Personnel trajectory tracking method and system for working area |
-
2021
- 2021-06-24 CN CN202110705333.4A patent/CN113362376A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030048926A1 (en) * | 2001-09-07 | 2003-03-13 | Takahiro Watanabe | Surveillance system, surveillance method and surveillance program |
| AU2008264230A1 (en) * | 2008-11-24 | 2010-06-10 | Canon Kabushiki Kaisha | Rule-based network surveillance system |
| CN102638675A (en) * | 2012-04-01 | 2012-08-15 | 安科智慧城市技术（中国）有限公司 | Method and system for target tracking by using multi-view videos |
| CN106651916A (en) * | 2016-12-29 | 2017-05-10 | 深圳市深网视界科技有限公司 | Target positioning tracking method and device |
| CN109977730A (en) * | 2017-12-27 | 2019-07-05 | 深圳市优必选科技有限公司 | A kind of personnel's path following method, system and terminal device |
| CN110175583A (en) * | 2019-05-30 | 2019-08-27 | 重庆跃途科技有限公司 | It is a kind of in the campus universe security monitoring analysis method based on video AI |
| CN110443828A (en) * | 2019-07-31 | 2019-11-12 | 腾讯科技（深圳）有限公司 | Method for tracing object and device, storage medium and electronic device |
| CN111915671A (en) * | 2020-07-15 | 2020-11-10 | 安徽清新互联信息科技有限公司 | Personnel trajectory tracking method and system for working area |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115116164A (en) * | 2022-06-08 | 2022-09-27 | 武汉虹信技术服务有限责任公司 | Dynamic management method, system and medium for park access control permission |
| CN115116164B (en) * | 2022-06-08 | 2023-12-19 | 武汉虹信技术服务有限责任公司 | Method, system and medium for dynamically managing park entrance guard permission |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6905850B2 (en) | Image processing system, imaging device, learning model creation method, information processing device | |
| Bernardini et al. | Towards creating a combined database for earthquake pedestrians’ evacuation models | |
| EP2219379B1 (en) | Social network construction based on data association | |
| JP2003087771A (en) | Monitoring system and monitoring method | |
| CN108846911A (en) | A kind of Work attendance method and device | |
| CN110096606B (en) | Foreign roll personnel management method and device and electronic equipment | |
| CN105913507A (en) | Attendance checking method and system | |
| US20180158063A1 (en) | Point-of-sale fraud detection using video data and statistical evaluations of human behavior | |
| CN110717885A (en) | Customer number counting method and device, electronic equipment and readable storage medium | |
| CN113362376A (en) | Target tracking method | |
| Gupta et al. | Twitter usage across industry: A spatiotemporal analysis | |
| CN113343913A (en) | Target determination method, target determination device, storage medium and computer equipment | |
| CN110717358A (en) | Visitor number counting method and device, electronic equipment and storage medium | |
| CN110519324B (en) | Person tracking method and system based on network track big data | |
| EP3570207B1 (en) | Video cookies | |
| JP2007172422A (en) | Meeting detection device and method | |
| Zhou et al. | Variability in individual home-work activity patterns | |
| Hamdy et al. | Criminal act detection and identification model | |
| CN109871456B (en) | Method and device for analyzing relationship between watchmen and electronic equipment | |
| CN111402105A (en) | Community management system | |
| CN116775747A (en) | Personnel early warning method and system based on Apriori algorithm | |
| JP5223404B2 (en) | Organization activity analysis apparatus and program | |
| McClain | The horizons of technological control: automated surveillance in the New York subway | |
| Naini et al. | Opportunistic sampling for joint population size and density estimation | |
| CN113689613A (en) | Access control system, access control method, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |