CN110852148A - Visitor destination verification method and system based on target tracking - Google Patents
Visitor destination verification method and system based on target tracking Download PDFInfo
- Publication number
- CN110852148A CN110852148A CN201910901106.1A CN201910901106A CN110852148A CN 110852148 A CN110852148 A CN 110852148A CN 201910901106 A CN201910901106 A CN 201910901106A CN 110852148 A CN110852148 A CN 110852148A
- Authority
- CN
- China
- Prior art keywords
- visitor
- track
- points
- real
- destination
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Alarm Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a visitor destination verification method and a visitor destination verification system based on target tracking, wherein the method comprises the following steps: acquiring a face image and destination information of a visitor; generating a reasonable prediction track of the visitor according to the face image and the destination information of the visitor; acquiring the face characteristics of a person target according to a monitoring video picture shot by a camera; identifying the same character target belonging to the visitor by matching the face image of the visitor with the face characteristics of the character target; setting the position points of the shot cameras of the same character target as the path track points of the visitor; connecting the passing track points of the visitors in series according to time to generate a real-time track of the visitors; calculating the goodness of fit of the real-time track of the visitor and the reasonable prediction track, and judging whether the real-time track of the visitor is abnormal or not according to the goodness of fit. The method realizes the real-time monitoring and management of the visitor and improves the management efficiency and the safety of the visitor.
Description
Technical Field
The invention relates to the field of target tracking for intelligent communities, in particular to a visitor destination verification method and a visitor destination verification system based on target tracking.
Background
General communities, office buildings and the like have functions of visitor identity verification and registration, and after visitors in a foreground or a guard room indicate identities and describe destinations of visitors, the visitors are opened to allow the visitors to enter the communities or the office buildings.
However, the situation after visitors enter the community, inside an office building, is now lacking in necessary monitoring and management: it can not be verified whether the user really goes to the destination or not, whether the action track of the user in the community or the office building is normal or not, and whether unreasonable action tracks exist or not.
Therefore, the existing visitor registration management method has a leak, for example, a person who enters a community or an office building under the name of a visitor visits and shops around to promote and paste small advertisements, and even illegal activities are possible.
Therefore, it is an urgent need to solve the problem of monitoring and managing the action trajectory of the visitor after entering the community or the office building.
Disclosure of Invention
In view of the above problems, the present invention is directed to solving the problem that security in a community or an office building cannot be guaranteed due to lack of necessary monitoring and management for the situation after visitors enter the community or the office building.
The embodiment of the invention provides a target tracking-based visitor destination verification method, which comprises the following steps:
acquiring a face image and destination information of a visitor;
generating a reasonable predicted track of the visitor according to the destination information of the visitor;
acquiring the face characteristics of a person target according to a monitoring video picture shot by a camera;
identifying the same character target belonging to the visitor by matching the face image of the visitor with the face characteristics of the character target;
setting the position points of the shot cameras of the same character target as the path track points of the visitor;
connecting the passing track points of the visitors in series according to time to generate a real-time track of the visitors;
calculating the coincidence degree of the real-time track of the visitor and the reasonable prediction track;
judging whether the real-time track of the visitor is abnormal or not according to the goodness of fit; and if the abnormality exists, sending alarm information to the control device.
In one embodiment, acquiring a face image and destination information of a visitor comprises: determining an accessed owner according to the destination information of the visitor;
sending the facial image of the acquired visitor and destination information to the visited owner;
the visited owner judges whether to accept the visit according to the face image;
and after the visited owner accepts the visit, granting the visitor access authority to generate a reasonable predicted track of the visitor.
In one embodiment, generating a reasonable predicted trajectory of the visitor according to the face image and the destination information of the visitor comprises:
according to the destination information of the visitor, obtaining the passing probability of each camera position point from the entrance guard room to the destination;
segmenting the camera position points to generate a plurality of segments of camera position points;
according to the route probability, selecting a camera position point with the route probability higher than a threshold value from each camera position point as an anchor point;
and connecting the anchor points in the plurality of camera position points in series to generate the reasonable prediction track.
In one embodiment, calculating the goodness of fit of the real-time trajectory of the visitor to the reasonably predicted trajectory comprises:
the goodness of fit is represented by the coincidence rate of the passing track point of the visitor and the anchor point of each reasonable prediction path;
the positions of the via track points coincide with the positions of the anchor points, the via direction of the visitor at the via track points coincides with the via direction set by the anchor points, the via track points coincide with the anchor points, and the ratio of the via track points of the visitor coinciding with the anchor points to all the via track points of the visitor is used as the coincidence rate.
In one embodiment, the alert information includes:
face image, destination, and real-time location of the character target.
In a second aspect, the present invention is also directed to a system for checking a visitor destination based on target tracking, comprising:
the acquisition module is used for acquiring a face image and destination information of the visitor;
the reasonable prediction track generation module is used for generating a reasonable prediction track of the visitor according to the destination information of the visitor;
the acquisition module is used for acquiring the face characteristics of the person target according to the monitoring video picture shot by the camera;
the identification module is used for identifying the same character target belonging to the visitor by matching the face image of the visitor with the face characteristics of the character target;
the setting module is used for setting the shot position points of the cameras of the same character target as the passing track points of the visitor;
the visitor real-time track generation module is used for connecting the passing track points of the visitors in series according to time to generate a visitor real-time track;
the calculation module is used for calculating the coincidence degree of the real-time track of the visitor and the reasonable prediction track;
the judging module is used for judging whether the real-time track of the visitor is abnormal according to the goodness of fit; and if the abnormality exists, sending alarm information to the control device.
In one embodiment, the acquisition module includes:
the determining submodule is used for determining the visited owner according to the destination information of the visitor;
the sending submodule is used for sending the facial image of the acquired visitor and the destination information to the visited owner;
the judging submodule is used for judging whether the visited owner accepts the visit or not according to the face image;
and the granting submodule is used for granting the visitor access authority after the visited owner accepts the access.
In one embodiment, the reasonable prediction trajectory generation module includes:
the obtaining submodule is used for obtaining the passing probability of each camera position point from a guard room to a destination according to the destination information of the visitor;
the segmentation submodule is used for segmenting the camera position points to generate a plurality of segments of camera position points;
the selecting submodule is used for selecting a camera position point with the passing probability higher than a threshold value from each section as an anchor point according to the passing probability;
and the generation submodule is used for serially connecting all anchor points in the plurality of sections of camera position points to generate the reasonable prediction track.
In one embodiment, the calculation module includes:
the goodness of fit is represented by the coincidence rate of the passing track point of the visitor and the anchor point of each reasonable prediction path;
the positions of the via track points coincide with the positions of the anchor points, the via direction of the visitor at the via track points coincides with the via direction set by the anchor points, the via track points coincide with the anchor points, and the ratio of the via track points of the visitor coinciding with the anchor points to all the via track points of the visitor is used as the coincidence rate.
In one embodiment, the determining module is configured to, in,
the alarm information includes: face image, destination, and real-time location of the character target.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
according to the visitor destination verification method based on the target tracking, provided by the embodiment of the invention, whether the visitor is abnormal or not is judged according to the coincidence degree of the reasonable predicted track and the actual track of the visitor, so that the real-time monitoring and management of the visitor are realized, the management quality and efficiency of the visitor are improved, and the method has great significance for improving the safety of communities and office buildings.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
In the drawings:
fig. 1 is a flowchart of a guest destination verification method based on target tracking according to an embodiment of the present invention;
fig. 2 is a flowchart of step S101 according to an embodiment of the present invention;
fig. 3 is a flowchart of step S102 according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a reasonable predicted trajectory and a real-time trajectory of a visitor according to embodiment 1 of the present invention;
FIG. 5 is a block diagram of a guest destination verification system based on target tracking according to an embodiment of the present invention;
fig. 6 is a block diagram of an acquisition module S501 provided in an embodiment of the present invention;
fig. 7 is a block diagram of a reasonable predicted trajectory module S502 according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Referring to fig. 1, a guest destination verification method based on target tracking according to an embodiment of the present invention includes: s101 to S108;
s101, acquiring a face image and destination information of a visitor;
s102, generating a reasonable predicted track of the visitor according to the destination information of the visitor;
s103, acquiring the face characteristics of the person target according to the monitoring video picture shot by the camera;
s104, identifying the same character target by matching the face image of the visitor with the face characteristics of the character target;
s105, setting the position points of the shot cameras of the same character target as the passing track points of the visitor;
s106, connecting the passing track points of the visitors in series according to time to generate a real-time track of the visitors;
s107, calculating the coincidence degree of the real-time track and the reasonable prediction track of the visitor;
s108, judging whether the real-time track of the visitor is abnormal or not according to the goodness of fit; if the abnormality exists, sending alarm information to the control device; the alarm information includes: face image, destination, and real-time location of the character target.
In the embodiment, whether the visitor is abnormal or not is judged according to the coincidence degree of the reasonable prediction track and the actual track of the visitor, so that the visitor is monitored and managed in real time, the management quality and efficiency of the visitor are improved, and the method has great significance for improving the safety of communities and office buildings.
In step S107, the goodness of fit is represented by a coincidence rate of a passing trajectory point of the visitor and an anchor point of each reasonable prediction path;
the positions of the via track points coincide with the positions of the anchor points, the via direction of the visitor at the via track points coincides with the via direction set by the anchor points, the via track points coincide with the anchor points, and the ratio of the via track points of the visitor coinciding with the anchor points to all the via track points of the visitor is used as the coincidence rate.
In one embodiment, referring to fig. 2, acquiring a face image and destination information of a visitor includes:
s1011, determining an accessed owner according to the destination information of the visitor;
s1012, sending the face image of the acquired visitor and destination information to the visited owner;
s1013, the visited owner judges whether to accept the visit according to the face image;
and S1014, after the visited owner accepts the visit, granting the visitor access authority.
In the embodiment, the information of the visitor is disclosed to the interviewee, so that the access right of the interviewee is controlled, the visitor is further screened, and the safety of communities and office buildings is further improved.
In one embodiment, referring to fig. 3, generating a reasonable predicted trajectory of the visitor according to the facial image and the destination information of the visitor includes:
s1021, obtaining the passing probability of each camera position point from the entrance guard room to the destination according to the destination information of the visitor;
s1022, segmenting the camera position points to generate a plurality of segments of camera position points;
s1023, according to the route probability, selecting a camera position point with the route probability higher than a threshold value from each camera position point as an anchor point;
and S1024, connecting the anchor points in the camera position points in the plurality of sections in series to generate the reasonable prediction track.
A method for target tracking based guest destination verification is provided by a complete embodiment.
Example 1:
for example, referring to fig. 4, a visitor visits building a of the community, where a solid line represents a reasonably predicted track generated from a guard room to building a and an anchor point thereof, and a dotted line represents a real-time track of the visitor and a track point thereof.
Specifically, the visitor destination verification based on target tracking comprises the following steps:
1. in the process of handling identity verification registration by a visitor in a foreground or a entrance guard room, a camera and a computer of the foreground or the entrance guard room are used for executing a step S101, namely, a face image of the visitor is collected by the camera, destination information of the visitor is recorded, for example, the destination information is A building, and the face image and the destination information are registered in a visitor management server;
2. the visitor management server executes step S102, namely, generates a reasonable predicted track of the visitor according to the destination information registered by the visitor; the reasonable predicted trajectory may be generated based on statistics of historical big data.
For example, if 100 persons go from the entrance guard room to the building a on average, 100 person movement tracks can be generated; if one week is taken as a history analysis period, 700 character movement tracks exist; in order to expand the statistical range, the 100 persons are not limited to visitors, but also comprise owners and the like, namely all persons from the guard room to the A-building are included in historical big data; the 700 character moving tracks are counted, and the passing probability of each camera position point from a entrance guard room to a building A is determined; for example, each black point in fig. 4 is a camera position, and the percentage of the black points is the route probability of the camera position point; segmenting the camera position points, for example, each segment of the path can be used as one segment according to the road path in the community, and one segment comprises one or more camera position points; then, according to the route probability, selecting a camera position point with the route probability higher than a threshold value from each section as an anchor point, for example, by using 20% as the threshold value in fig. 4, selecting an anchor point with the route probability higher than 20%, and then connecting each anchor point in series according to the sections to generate the reasonable prediction track, such as three reasonable prediction tracks shown by solid lines in fig. 4;
3. executing step S103 by cameras arranged at various places in the community or office building, namely shooting monitoring video pictures and sending the pictures to the visitor management server; the visitor management server continues to execute steps S104 and S105, extracts a present character target from the monitoring video picture, compares the extracted character target face features with the features of the face image of the visitor registered in advance by using the character target face features, if matching, identifies the same character target belonging to the visitor, shoots the position points of the cameras of the same character target as the passing track points of the character target, and further executes step S106, connects the passing track points of the same character target in series according to the time sequence to generate the visitor real-time track of the visitor, as shown by the dotted line in fig. 4;
4. the visitor management server executes the step S107, and calculates the goodness of fit between the real-time track of the visitor and the reasonable prediction track, wherein the goodness of fit is expressed by the coincidence rate of the passing track point of the visitor and the anchor point of each reasonable prediction path (the coincidence rate comprises two aspects, namely the coincidence rate of the passing track point and the anchor point, and the passing direction accords with the passing direction set by the anchor point);
5. the visitor management server executes step S108, and when the matching degree is lower than the threshold value, the visitor management server considers that the real-time trajectory of the visitor does not match the destination of the visitor and there is an abnormality, and may send an alarm message to a control device of a community or office building property security to prompt the property security to intervene or assist the visitor (for example, the visitor gets lost).
In the embodiment, the reasonable prediction track is formed according to the historical big data, so that the reasonable prediction track is more accurate, and the coincidence degree of the reasonable prediction track and the real-time track is calculated, so that the judgment on the abnormal condition is more accurate, the management efficiency of the visitors is improved, the condition that the visitors enter the community or the office building can be clearly monitored, and the reasonable prediction track has great significance for improving the safety of the community and the office building.
Based on the same inventive concept, the embodiment of the invention also provides a guest destination verification system based on target tracking, and as the principle of the problem solved by the system is similar to the guest destination verification method based on target tracking, the implementation of the system can refer to the implementation of the method, and repeated details are not repeated.
An embodiment of the present invention provides a target tracking based visitor destination verification system, which is shown in fig. 5 and includes:
the acquisition module S501 is used for acquiring a face image and destination information of a visitor;
a reasonable prediction track generation module S502, configured to generate a reasonable prediction track of the visitor according to the destination information of the visitor;
an obtaining module S503, configured to obtain a face feature of the person target according to a monitoring video image captured by the camera;
a recognition module S504, configured to recognize the same character target belonging to the visitor by matching a face image of the visitor with a face feature of the character target;
the setting module S505 is used for setting the position points of the shot cameras of the same character target as the passing track points of the visitor;
a visitor real-time track generation module S506, configured to connect the passing track points of the visitors in series according to time to generate a visitor real-time track;
a calculating module S507, configured to calculate an agreement degree between the real-time trajectory of the visitor and the reasonable prediction trajectory;
a judging module S508, configured to judge whether the real-time trajectory of the visitor is abnormal according to the goodness of fit; and if the abnormality exists, sending alarm information to the control device.
In one embodiment, referring to fig. 6, the acquisition module S501 includes:
the determining submodule S5011 is used for determining an accessed owner according to the destination information of the visitor;
the sending submodule S5012 is used for sending the face image of the acquired visitor and the destination information to the visited owner;
the judgment submodule S5013 is used for judging whether to accept the access or not by the accessed owner according to the face image;
and the granting submodule S5014 is used for granting the visitor access right after the visited owner accepts the visit.
In one embodiment, the reasonable prediction trajectory generation submodule S502 includes:
the obtaining submodule S5021 is used for obtaining the passing probability of each camera position point from a entrance guard room to a destination according to the destination information of the visitor;
the segmentation submodule S5022 is used for segmenting the camera position points to generate a plurality of segments of camera position points;
the selecting submodule S5023 is used for selecting a camera position point with the passing probability higher than a threshold value from each segment as an anchor point according to the passing probability;
and the generation submodule S5024 is used for connecting anchor points in the position points of the plurality of segments of cameras in series to generate the reasonable prediction track.
In one embodiment, the calculating module S507 includes:
the goodness of fit is represented by the coincidence rate of the passing track point of the visitor and the anchor point of each reasonable prediction path;
the positions of the via track points coincide with the positions of the anchor points, the via direction of the visitor at the via track points coincides with the via direction set by the anchor points, the via track points coincide with the anchor points, and the ratio of the via track points of the visitor coinciding with the anchor points to all the via track points of the visitor is used as the coincidence rate.
In an embodiment, in the determining module S508, the alarm information includes:
face images, destinations and real-time locations of character targets;
specifically, the visitor management server is provided with a reasonable prediction track generation module, an identification module, a setting module, a visitor real-time track generation module, a calculation module and a judgment module; the entrance guard room is provided with an acquisition module; each deployed camera in the community or office building is provided with an acquisition module; the visitor management server is connected with cameras arranged in the guard room and the community or the office building.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A visitor destination verification method based on target tracking is characterized by comprising the following steps:
acquiring a face image and destination information of a visitor;
generating a reasonable predicted track of the visitor according to the destination information of the visitor;
acquiring the face characteristics of a person target according to a monitoring video picture shot by a camera;
identifying the same character target belonging to the visitor by matching the face image of the visitor with the face characteristics of the character target;
setting the position points of the shot cameras of the same character target as the path track points of the visitor;
connecting the passing track points of the visitors in series according to time to generate a real-time track of the visitors;
calculating the coincidence degree of the real-time track of the visitor and the reasonable prediction track;
judging whether the real-time track of the visitor is abnormal or not according to the goodness of fit; and if the abnormality exists, the control device sends alarm information.
2. The method of claim 1, wherein collecting the facial image of the visitor and the destination information comprises:
determining an accessed owner according to the destination information of the visitor;
sending the facial image of the acquired visitor and destination information to the visited owner;
the visited owner judges whether to accept the visit according to the face image;
and after the visited owner accepts the visit, granting the visitor the visit authority.
3. The method of claim 1, wherein generating a reasonable predicted trajectory of the visitor based on the facial image of the visitor and the destination information comprises:
according to the destination information of the visitor, obtaining the passing probability of each camera position point from the entrance guard room to the destination;
segmenting the camera position points to generate a plurality of segments of camera position points;
according to the route probability, selecting a camera position point with the route probability higher than a threshold value from each camera position point as an anchor point;
and connecting the anchor points in the plurality of camera position points in series to generate the reasonable prediction track.
4. The method of claim 1, wherein calculating a goodness of fit of the guest real-time trajectory to the reasonable predicted trajectory comprises:
the goodness of fit is represented by the coincidence rate of the passing track point of the visitor and the anchor point of each reasonable prediction path;
the positions of the via track points coincide with the positions of the anchor points, the via direction of the visitor at the via track points coincides with the via direction set by the anchor points, the via track points coincide with the anchor points, and the ratio of the via track points of the visitor coinciding with the anchor points to all the via track points of the visitor is used as the coincidence rate.
5. The method of claim 1, wherein the alert information comprises:
face image, destination, and real-time location of the character target.
6. A guest destination verification system based on target tracking, comprising:
the acquisition module is used for acquiring a face image and destination information of the visitor;
the reasonable prediction track generation module is used for generating a reasonable prediction track of the visitor according to the destination information of the visitor;
the acquisition module is used for acquiring the face characteristics of the person target according to the monitoring video picture shot by the camera;
the identification module is used for identifying the same character target belonging to the visitor by matching the face image of the visitor with the face characteristics of the character target;
the setting module is used for setting the shot position points of the cameras of the same character target as the passing track points of the visitor;
the visitor real-time track generation module is used for connecting the passing track points of the visitors in series according to time to generate a visitor real-time track;
the calculation module is used for calculating the coincidence degree of the real-time track of the visitor and the reasonable prediction track;
the judging module is used for judging whether the real-time track of the visitor is abnormal according to the goodness of fit; and if the abnormality exists, sending alarm information to the control device.
7. The system of claim 6, wherein the acquisition module comprises:
the determining submodule is used for determining the visited owner according to the destination information of the visitor;
the sending submodule is used for sending the facial image of the acquired visitor and the destination information to the visited owner;
the judging submodule is used for judging whether the visited owner accepts the visit or not according to the face image;
and the granting submodule is used for granting the visitor access authority after the visited owner accepts the access.
8. The system of claim 6, wherein the reasonable predicted trajectory generation module comprises:
the obtaining submodule is used for obtaining the passing probability of each camera position point from a guard room to a destination according to the destination information of the visitor;
the segmentation submodule is used for segmenting the camera position points to generate a plurality of segments of camera position points;
the selecting submodule is used for selecting a camera position point with the passing probability higher than a threshold value from each section as an anchor point according to the passing probability;
and the generation submodule is used for serially connecting all anchor points in the plurality of sections of camera position points to generate the reasonable prediction track.
9. The system of claim 6, wherein the computation module comprises:
the goodness of fit is represented by the coincidence rate of the passing track point of the visitor and the anchor point of each reasonable prediction path;
the positions of the via track points coincide with the positions of the anchor points, the via direction of the visitor at the via track points coincides with the via direction set by the anchor points, the via track points coincide with the anchor points, and the ratio of the via track points of the visitor coinciding with the anchor points to all the via track points of the visitor is used as the coincidence rate.
10. The system of claim 6, wherein in the determination module,
the alarm information includes: face image, destination, and real-time location of the character target.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910901106.1A CN110852148B (en) | 2019-09-23 | 2019-09-23 | Visitor destination verification method and system based on target tracking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910901106.1A CN110852148B (en) | 2019-09-23 | 2019-09-23 | Visitor destination verification method and system based on target tracking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110852148A true CN110852148A (en) | 2020-02-28 |
| CN110852148B CN110852148B (en) | 2023-01-24 |
Family
ID=69596010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910901106.1A Active CN110852148B (en) | 2019-09-23 | 2019-09-23 | Visitor destination verification method and system based on target tracking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110852148B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950470A (en) * | 2020-08-14 | 2020-11-17 | 深圳市万物云科技有限公司 | Intelligent monitoring method and device, computer equipment and storage medium |
| CN113284282A (en) * | 2021-05-24 | 2021-08-20 | 深圳崎点数据有限公司 | Intelligent pass management method, system, terminal and storage medium for intelligent park |
| CN113592919A (en) * | 2021-08-02 | 2021-11-02 | 金茂智慧科技(广州)有限公司 | Security control method and related device |
| CN114449228A (en) * | 2022-04-07 | 2022-05-06 | 深圳市亚联讯网络科技有限公司 | Safety monitoring method, monitoring server and storage medium for community visitors |
| CN114639216A (en) * | 2022-02-18 | 2022-06-17 | 国政通科技有限公司 | Specific personnel track area analysis early warning system and method |
| CN116485321A (en) * | 2023-03-01 | 2023-07-25 | 深圳市一应科技有限公司 | Property management platform based on big data |
| CN116956960A (en) * | 2023-07-28 | 2023-10-27 | 武汉市万睿数字运营有限公司 | Community visitor visit path restoration method and system based on cloud edge end collaboration |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090327148A1 (en) * | 2008-06-27 | 2009-12-31 | Microsoft Corporation | Mechanisms and architecture for mobile opportunistic commerce |
| CN102735237A (en) * | 2012-06-29 | 2012-10-17 | 安科智慧城市技术（中国）有限公司 | Visitor path planning method, apparatus and system |
| CN103325245A (en) * | 2013-06-25 | 2013-09-25 | 中国科学院信息工程研究所 | Method for predicting space-time traveling track of blacklisted vehicle |
| CN107331003A (en) * | 2017-06-22 | 2017-11-07 | 厦门劢联科技有限公司 | A kind of school dormitory's management system based on recognition of face |
| CN108153867A (en) * | 2017-12-25 | 2018-06-12 | 山东大学 | User trajectory Forecasting Methodology and device based on temporal regularity |
| CN108877141A (en) * | 2017-05-09 | 2018-11-23 | 同方威视科技江苏有限公司 | Safety zone monitoring system and method |
| CN109360314A (en) * | 2018-10-24 | 2019-02-19 | 平安科技（深圳）有限公司 | Reserve access method, system, computer equipment and storage medium |
| CN109741498A (en) * | 2018-12-28 | 2019-05-10 | 金威建设集团有限公司 | A method of intelligence registration community visitor |
| US20190145779A1 (en) * | 2017-11-10 | 2019-05-16 | Bayerische Motoren Werke Aktiengesellschaft | Methods and Apparatuses for Predicting a Destination of a User's Current Travel Path |
-
2019
- 2019-09-23 CN CN201910901106.1A patent/CN110852148B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090327148A1 (en) * | 2008-06-27 | 2009-12-31 | Microsoft Corporation | Mechanisms and architecture for mobile opportunistic commerce |
| CN102735237A (en) * | 2012-06-29 | 2012-10-17 | 安科智慧城市技术（中国）有限公司 | Visitor path planning method, apparatus and system |
| CN103325245A (en) * | 2013-06-25 | 2013-09-25 | 中国科学院信息工程研究所 | Method for predicting space-time traveling track of blacklisted vehicle |
| CN108877141A (en) * | 2017-05-09 | 2018-11-23 | 同方威视科技江苏有限公司 | Safety zone monitoring system and method |
| CN107331003A (en) * | 2017-06-22 | 2017-11-07 | 厦门劢联科技有限公司 | A kind of school dormitory's management system based on recognition of face |
| US20190145779A1 (en) * | 2017-11-10 | 2019-05-16 | Bayerische Motoren Werke Aktiengesellschaft | Methods and Apparatuses for Predicting a Destination of a User's Current Travel Path |
| CN108153867A (en) * | 2017-12-25 | 2018-06-12 | 山东大学 | User trajectory Forecasting Methodology and device based on temporal regularity |
| CN109360314A (en) * | 2018-10-24 | 2019-02-19 | 平安科技（深圳）有限公司 | Reserve access method, system, computer equipment and storage medium |
| CN109741498A (en) * | 2018-12-28 | 2019-05-10 | 金威建设集团有限公司 | A method of intelligence registration community visitor |
Non-Patent Citations (4)
| Title |
|---|
| ELENA VILDJIOUNAITE 等: "Predicting Consumers" Locations in Dynamic Environments via 3D Sensor-Based Tracking", 《2014 EIGHTH INTERNATIONAL CONFERENCE ON NEXT GENERATION MOBILE APPS, SERVICES AND TECHNOLOGIES》 * |
| NYOMAN JUNIARTA 等: "Sequence Mining within Formal Concept Analysis for Analyzing Visitor Trajectories", 《2018 13TH INTERNATIONAL WORKSHOP ON SEMANTIC AND SOCIAL MEDIA ADAPTATION AND PERSONALIZATION (SMAP)》 * |
| 罗平: "办公区域定位与跟随信息系统设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈强: "基于轨迹运行理念下终端空域航迹管理研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950470A (en) * | 2020-08-14 | 2020-11-17 | 深圳市万物云科技有限公司 | Intelligent monitoring method and device, computer equipment and storage medium |
| CN113284282A (en) * | 2021-05-24 | 2021-08-20 | 深圳崎点数据有限公司 | Intelligent pass management method, system, terminal and storage medium for intelligent park |
| CN113592919A (en) * | 2021-08-02 | 2021-11-02 | 金茂智慧科技(广州)有限公司 | Security control method and related device |
| CN114639216A (en) * | 2022-02-18 | 2022-06-17 | 国政通科技有限公司 | Specific personnel track area analysis early warning system and method |
| CN114449228A (en) * | 2022-04-07 | 2022-05-06 | 深圳市亚联讯网络科技有限公司 | Safety monitoring method, monitoring server and storage medium for community visitors |
| CN116485321A (en) * | 2023-03-01 | 2023-07-25 | 深圳市一应科技有限公司 | Property management platform based on big data |
| CN116485321B (en) * | 2023-03-01 | 2023-10-20 | 深圳市一应科技有限公司 | Property management platform system based on big data |
| CN116956960A (en) * | 2023-07-28 | 2023-10-27 | 武汉市万睿数字运营有限公司 | Community visitor visit path restoration method and system based on cloud edge end collaboration |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110852148B (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852148B (en) | Visitor destination verification method and system based on target tracking | |
| JP6905850B2 (en) | Image processing system, imaging device, learning model creation method, information processing device | |
| CN109410401B (en) | Face recognition access control system suitable for smart community | |
| CN110222640B (en) | Method, device and method for identifying suspect in monitoring site and storage medium | |
| US20190087464A1 (en) | Regional population management system and method | |
| CN112132045B (en) | Community personnel abnormal behavior monitoring scheme based on computer vision | |
| WO2003003721A1 (en) | Surveillance system and methods regarding same | |
| EP1399889A1 (en) | Method for monitoring a moving object and system regarding same | |
| EP1410333A1 (en) | Moving object assessment system and method | |
| CN108710827B (en) | A kind of micro- police service inspection in community and information automatic analysis system and method | |
| CN110738178A (en) | Garden construction safety detection method and device, computer equipment and storage medium | |
| CN110942580A (en) | Intelligent building visitor management method and system and storage medium | |
| CN112132048A (en) | Community patrol analysis method and system based on computer vision | |
| CN112349016A (en) | Intelligent access control system based on big data analysis | |
| US10586130B2 (en) | Method, system and apparatus for providing access to videos | |
| CN114358980A (en) | Intelligent community property management system and method based on Internet of things | |
| CN116546438B (en) | Building monitoring system based on Bluetooth MESH network | |
| CN112330742A (en) | Method and device for recording activity routes of key personnel in public area | |
| CN112258707A (en) | Intelligent access control system based on face recognition | |
| JP2019159377A (en) | Monitoring system, server device, monitoring method, and monitoring program | |
| CN110929590A (en) | Community archive management system | |
| CN116343419B (en) | Intelligent video monitoring alarm management system | |
| CN116823892B (en) | Identity determination method, device, equipment and medium based on building management and control | |
| CN117830960B (en) | Smart community-based risk identification method, device, equipment and medium | |
| CN118116048A (en) | Face recognition method, device, equipment and storage medium applied to access control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |