CN109656973B - Target object association analysis method and device - Google Patents
Target object association analysis method and device Download PDFInfo
- Publication number
- CN109656973B CN109656973B CN201811452014.1A CN201811452014A CN109656973B CN 109656973 B CN109656973 B CN 109656973B CN 201811452014 A CN201811452014 A CN 201811452014A CN 109656973 B CN109656973 B CN 109656973B
- Authority
- CN
- China
- Prior art keywords
- target
- track
- track point
- association
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012097 association analysis method Methods 0.000 title claims description 11
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000012098 association analyses Methods 0.000 claims abstract description 19
- 230000008447 perception Effects 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 23
- 230000003993 interaction Effects 0.000 claims description 17
- 238000012795 verification Methods 0.000 claims description 15
- 238000010219 correlation analysis Methods 0.000 abstract description 6
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a target object correlation analysis method and a target object correlation analysis device, wherein the method comprises the following steps: obtaining a target object to be analyzed; searching a multi-dimensional sensing data set to obtain a target track of the target object; wherein the target track is formed by target track points; the multi-dimensional perception dataset is used for storing a track; obtaining the associated information; searching the multi-dimensional sensing data set based on the associated information and each target track point, and determining the associated track point near each target track point; for each target track point, determining a target associated track point from associated track points near the target track point; determining each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining a target associated object according to the association level of each associated object, and completing the association analysis of the target object. By applying the embodiment of the invention, the efficiency and the accuracy of the correlation analysis are improved.
Description
Technical Field
The invention relates to the field of intelligent security, in particular to a target object association analysis method and device.
Background
In order to strengthen the safety protection of cities, some target objects are generally required to be analyzed to determine associated objects associated with the target objects, and the target objects and the associated objects of the target objects are usually frequently gathered together.
At present, the existing target object association analysis method mainly adopts a manual analysis method or a video analysis method, the former mainly depends on the analysis capability of workers, and a great amount of time and energy are consumed due to the need of carrying out a great amount of investigation and statistics, so that the efficiency is low; the latter needs to analyze and identify the human face in the video, and because the video data volume is large, the analysis time is long, and the efficiency is low.
Therefore, it is necessary to design a new target object association analysis method to overcome the above problems. .
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a target object association analysis method and device so as to improve the efficiency and accuracy of association analysis.
The invention is realized in the following way:
in a first aspect, the present invention provides a target object association analysis method, where the method includes:
obtaining a target object to be analyzed; searching a multi-dimensional sensing data set to obtain a target track of the target object; wherein the target track is formed by target track points; the multi-dimensional perception dataset is used for storing a track;
obtaining the associated information; searching the multi-dimensional sensing data set based on the associated information and each target track point, and determining the associated track point near each target track point;
for each target track point, determining a target associated track point from associated track points near the target track point;
determining each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining a target associated object according to the association level of each associated object, and completing the association analysis of the target object.
Optionally, calculating the association level of each association object includes:
and regarding each associated object, taking the number of target associated track points belonging to the associated object as the association level of the associated object.
Optionally, the association information includes a preset association level; determining a target associated object according to the association level of each associated object, wherein the method comprises the following steps:
and taking the associated object with the association level larger than the preset association level as a target associated object.
Optionally, the association information includes a time threshold and an association type, the track point includes an object type, a time point and a place, based on the association information and each target track point, the multidimensional sensing dataset is searched, and the association track point near each target track point is determined, including:
and searching the multidimensional sensing data set aiming at each target track point, and determining the track point, of which the object type belongs to the correlation type, the absolute value of the difference between the time point and the time point of the target track point is not more than the time threshold value, and the point is the same as the point of the target track point, as the correlation track point near the target track point.
Optionally, for each target track point, determining a target associated track point from associated track points near the target track point, including:
and aiming at each target track point, determining the associated track point with the earliest time point from the associated track points near the target track point to serve as the target associated track point.
Optionally, after determining the target associated object, the method further includes:
and when a secondary analysis instruction is detected, taking the target associated object as the target object, and returning to execute the step of searching the multidimensional sensing data set to obtain the target track of the target object.
Optionally, obtaining a target object to be analyzed includes:
and acquiring a target object input by a user through a human-computer interaction interface.
Optionally, after obtaining the target object to be analyzed, the method further includes:
carrying out format verification on the obtained target object;
if the target object passes the format verification, executing a step of searching a multi-dimensional sensing data set to obtain a target track of the target object;
and if the format check fails, generating prompt information for prompting the target object to be input again, and displaying the prompt information.
In a second aspect, the present invention provides a target object association analysis apparatus, including:
the first obtaining module is used for obtaining a target object to be analyzed; searching a multi-dimensional sensing data set to obtain a target track of the target object; wherein the target track is formed by target track points; the multi-dimensional perception dataset is used for storing a track;
a second obtaining module, configured to obtain the association information; searching the multi-dimensional sensing data set based on the associated information and each target track point, and determining the associated track point near each target track point;
the first determining module is used for determining a target associated track point from associated track points near the target track point aiming at each target track point;
the second determining module is used for determining each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining a target associated object according to the association level of each associated object, and completing association analysis of the target object.
Optionally, the second determining module calculates the association level of each associated object, specifically:
and regarding each associated object, taking the number of target associated track points belonging to the associated object as the association level of the associated object.
Optionally, the association information includes a preset association level; the second determining module determines the target associated object according to the association level of each associated object, and comprises the following steps:
and taking the associated object with the association level larger than the preset association level as a target associated object.
Optionally, the associated information includes a time threshold and an associated type, the track points include an object type, a time point, and a location, the second obtaining module searches the multidimensional sensing dataset based on the associated information and each target track point, and determines the associated track points near each target track point, specifically:
and searching the multidimensional sensing data set aiming at each target track point, and determining the track point, of which the object type belongs to the correlation type, the absolute value of the difference between the time point and the time point of the target track point is not more than the time threshold value, and the point is the same as the point of the target track point, as the correlation track point near the target track point.
Optionally, the first determining module determines, for each target track point, one target associated track point from associated track points near the target track point, specifically:
and aiming at each target track point, determining the associated track point with the earliest time point from the associated track points near the target track point to serve as the target associated track point.
Optionally, the apparatus further includes a secondary analysis module, configured to:
after the target associated object is determined, when a secondary analysis instruction is detected, the target associated object is used as the target object, and the multidimensional sensing data set is returned to be searched, so that the target track of the target object is obtained.
Optionally, the first obtaining module obtains a target object to be analyzed, specifically:
and acquiring a target object input by a user through a human-computer interaction interface.
Optionally, the apparatus further includes a format checking module, configured to:
after a target object to be analyzed is obtained, carrying out format verification on the obtained target object;
if the target object passes the format verification, searching a multi-dimensional sensing data set to obtain a target track of the target object;
and if the format check fails, generating prompt information for prompting the target object to be input again, and displaying the prompt information.
The invention has the following beneficial effects: by applying the embodiment of the invention, the multi-dimensional sensing data set can be searched, the associated track points near each target track point are determined, and for each target track point, a target associated track point can be determined from the associated track points near the target track point; determining each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining the target associated object according to the association level of each associated object. Compared with the existing target object association analysis mode, the association analysis efficiency is improved, only one target association track point is determined for each target track point, repeated statistics of the target association track points is avoided, and therefore the accuracy of association analysis is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a target object association analysis method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a target object association analysis apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the target object association analysis method provided by the present invention can be applied to electronic devices, wherein in a specific application, the electronic device can be a computer, a personal computer, a tablet, a mobile phone, and the like, which is reasonable.
Referring to fig. 1, an embodiment of the present invention provides a target object association analysis method, including the following steps:
s101, obtaining a target object to be analyzed; searching a multi-dimensional sensing data set to obtain a target track of the target object; wherein the target track is formed by each target track point; the multi-dimensional perception dataset is used for storing a track;
the target object may be an object to be analyzed, and may be one of a license plate Number, a face picture, an Identification Number, a Radio Frequency Identification (RFID) tag, a Media Access Control (MAC) Address, an International Mobile Subscriber Identity (IMSI), an International Mobile Equipment Identity (IMEI), and the like, for example, and one or more target objects may be provided.
Obtaining a target object to be analyzed may include:
and acquiring a target object input by a user through a human-computer interaction interface.
The human-computer interaction interface can provide an input box, a user can input target objects such as identification numbers, face images, license plate numbers and the like through the input box, and the electronic equipment can obtain the target objects through the human-computer interaction interface. The terminal where the electronic device and the human-computer interaction interface are located may exist independently or may be integrated with each other, which is not limited in the present invention.
When the electronic equipment and the terminal where the human-computer interaction interface is located exist independently, the terminal where the human-computer interaction interface is located can send the target object to the electronic equipment after the target object is obtained, and therefore the electronic equipment can obtain the target object; when the electronic equipment and the terminal where the human-computer interaction interface is located are integrated, the electronic equipment can directly read a target object obtained by the human-computer interaction interface.
In yet another implementation, after obtaining the target object to be analyzed, the method further includes:
carrying out format verification on the obtained target object;
if the target object passes the format verification, executing a step of searching a multi-dimensional sensing data set to obtain a target track of the target object;
and if the format check fails, generating prompt information for prompting the target object to be input again, and displaying the prompt information.
The format check may check whether the target object meets a preset format requirement, for example, when the target object is a face picture, the format check may be performed on an image type and a size of the face picture, if the face picture conforms to the preset image type and the preset size, the face picture may pass the format check, otherwise, the face picture does not pass the format check. In practical application, the method for checking the specific format of the target objects of different types can be designed according to requirements, and the method is not limited in this respect.
In addition, in other embodiments, in addition to acquiring the target object, a target time range and a target location range may be acquired, so that the obtained target trajectory is a trajectory whose time point belongs to the target time range and whose location belongs to the target location range.
When the electronic equipment and the terminal where the human-computer interaction interface is located independently exist, after the prompt information is generated, the prompt information can be sent to the terminal where the human-computer interaction interface is located.
S102, obtaining associated information; searching the multi-dimensional sensing data set based on the associated information and each target track point, and determining the associated track point near each target track point; wherein the association information comprises a preset association level;
the association information input by the user through the human-computer interaction interface can be obtained, the association information can include a preset association level, a time threshold, an association type and the like, the preset association level can be a numerical type, the higher the numerical value is, the higher the association degree of the associated object and the target object is represented, the time threshold can be used for reflecting the deviation degree of the time point of the track point of the associated object and the track point of the target object, and the time threshold can be 30 seconds, 20 seconds, 10 seconds and the like. The association type may include one or more types, for example, may include a face image type, an identification card type, a license plate type, and the like.
After the associated information is obtained, format verification may also be performed on the associated information, for example, format verification is performed on the time threshold, the preset association level, and the association type, respectively, and if the time threshold is less than 30 seconds, it is determined that the time threshold passes the format verification; if the preset association level belongs to the numerical type, judging that the preset association level passes the format verification; and if the association type belongs to the preset object type set, judging that the association type passes format verification.
Each track point is used for recording the time point and the place of the object, and all track points of a certain object are connected to form the track of the object. Each trace point may include an object type, an object identifier, a time point, and a location, the object type may be one of a face image type, an identity card type, a license plate type, an MAC address type, an IMSI type, an IMEI type, and the like, and the object identifier may be a specific face picture, an identity card number, a license plate number, an MAC address, an IMSI, or a specific value of an IMEI. The object identification can uniquely identify the object, and the object represented by the track points is as follows: the object with the object identification in the track point.
Based on the associated information and each target track point, searching the multidimensional sensing data set, and determining the associated track point near each target track point, including:
and searching the multidimensional sensing data set aiming at each target track point, and determining the track point, of which the object type belongs to the correlation type, the absolute value of the difference between the time point and the time point of the target track point is not more than the time threshold value, and the point is the same as the point of the target track point, as the correlation track point near the target track point.
The association type may include multiple types, and when the object type is a certain type included in the association type, the object type may be considered to belong to the association type, for example, the association type includes a face image class, an identity card class, and a license plate class, and when the object type is the face image class, the identity card class, or the license plate class, the object type all belongs to the association type.
Assuming that the time threshold is 30 seconds, when the absolute value of the difference between the time point of a certain object and the time point of the target track point is not more than 30 seconds, it indicates that the time difference between the object and the target object meets the time range requirement.
Illustratively, the time threshold is RT, the time point of the kth target track point is pk, the location is tk, the association type is a face image class, and then the association track points near the kth target track point include: the object type is a face image type, the time point is in the time range from pk-RT to pk + RT, and the position is the track point of tk.
The multidimensional sensing data set is used for storing the track, the multidimensional sensing data set can be stored in the electronic equipment, or stored in a storage server or a storage server cluster independent of the electronic equipment, and the track in the multidimensional sensing data set is derived from the track data collected by the collecting equipment.
The acquisition devices may include one or more of, for example, a vehicle mount camera, a data acquisition server, a base station, and the like, and each acquisition device may acquire one or more types of trajectory data, for example, trajectory data that may be acquired by the vehicle mount camera includes: license plate number track data, face image track data and the like, and the track data which can be collected by the data collection server comprises the following components: ID card number track data, face image track data, bank card number track data, etc. the track data that the base station can gather include: the system comprises identity card number track data, mobile phone number track data, license plate number track data, face image track data, bank card number track data, MAC address track data, IMSI track data, IMEI track data and the like.
By acquiring the trajectory data acquired by the plurality of acquisition devices and storing the acquired various trajectory data in the form of the multi-dimensional sensing data set, a more comprehensive basic data source can be acquired, more comprehensive correlation analysis on the target object is facilitated, and the accuracy of the method is improved.
In other embodiments, based on the association information and each target track point, searching the multidimensional sensing dataset, and determining an associated track point near each target track point, includes:
and searching the multidimensional sensing data set aiming at each target track point, and determining the track point of which the object type belongs to the association type, the absolute value of the difference between the time point and the time point of the target track point is not more than the time threshold and the location belongs to the location range of the target track point as the association track point near the target track point, wherein the location range of the target track point is an area taking the location of the target track point as the center and taking a preset value as the radius. The association information may include the preset value.
S103, determining a target associated track point from associated track points near the target track point for each target track point;
specifically, for each target track point, determining a target associated track point from associated track points near the target track point includes:
and aiming at each target track point, determining the associated track point with the earliest time point from the associated track points near the target track point to serve as the target associated track point.
Because the acquisition device may acquire data for the same object several times in a certain place and time range, multiple associated trace points near one target trace point may belong to the same object, and it can be understood that, in order to avoid repeated association, the trace point of the same object should be recorded as one time near the target trace point.
Assume that the associated trace points near the 1 st target trace point include: rt1, rt2, rt3.. rtn, and rt1 to rtn are sorted in ascending order of time, the time point of the 1 st target track point is p1, and the location point is t1, then the associated track point near the 1 st target track point and belonging to the same object b1 can be represented by the following expression:
wherein m represents the number of associated track points which are near the 1 st target track point and belong to the same object b1, rti (ai, ci, bi, di) represents the ith associated track point near the 1 st target track point, and ai, ci, bi, di respectively represent the object type, time point, object identification and location of the ith associated track point; RO represents an association type; RT denotes a time threshold.
Based on the above example, the target associated trace points of the 1 st target trace point are:
assuming that there are n target track points in total, the associated track formed by all target associated track points can be expressed as:
in other embodiments, for each target track point, the associated track point with the smallest time difference value is determined from the associated track points near the target track point, and the determined associated track point is used as the target associated track point, where the time difference value of a certain track point is: the absolute value of the difference between the time point of the track point and the time point of the target track point. Or, the associated track point with the smallest time difference may be determined from the associated track points with time points earlier than the target track point, and the determined associated track point is used as the target associated track point.
S104, determining each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining a target associated object according to the association level of each associated object, and completing the association analysis of the target object.
Specifically, calculating the association level of each association object includes:
and regarding each associated object, taking the number of target associated track points belonging to the associated object as the association level of the associated object.
It can be understood that each target track point corresponds to one target associated track point, different target associated track points may belong to one associated object, and if the number of the target associated track points of the associated object is larger, it indicates that the possibility that the associated object and the target object appear at the same time is higher, so that the associated object may be used as the target associated object.
In other embodiments, the association level of each associated object may also be calculated in other manners, for example, each target associated track point may correspond to a weight factor, and the weight factors of the target associated track points belonging to the same associated object may be added to serve as the association level of the associated object. Wherein, each target track point can be preset with a weight factor, and the weight factor corresponding to each target associated track point is: and the weight factor of the target track point corresponding to the target associated track point.
In one implementation manner, determining a target associated object according to an association level of each associated object includes: taking the associated object with the maximum association level as a target associated object; alternatively, the first and second electrodes may be,
in another implementation manner, the determining the target associated object according to the association level of each associated object includes: and taking the associated object with the association level larger than the preset association level as a target associated object.
Therefore, by applying the technical scheme provided by the embodiment of the invention, the correlation analysis of the target object is realized, and the efficiency and the accuracy of the correlation analysis are improved.
In one implementation, after determining the target associated object, the method further comprises:
and when a secondary analysis instruction is detected, taking the target associated object as the target object, and returning to execute the step of searching the multidimensional sensing data set to obtain the target track of the target object.
When the terminal where the human-computer interaction interface is located is electronic equipment, when the electronic equipment detects that a user clicks a secondary analysis button, a secondary analysis instruction can be determined to be detected; alternatively, when the electronic device detects that the user clicks on the secondary analysis selection box and detects the confirm analysis button, it may be determined that the secondary analysis instruction is detected.
When the terminal where the human-computer interaction interface is located is another communication device, when the communication device detects that a user clicks a secondary analysis button, a secondary analysis instruction can be generated and sent to the electronic device, and when the electronic device receives the secondary analysis instruction, the secondary analysis instruction can be considered to be detected.
When the user cannot determine the real target object, the target object input for the first time may be only the alternative object, so the target associated object obtained for the first time may be the alternative associated object, and further, the alternative associated object may be used as the target object to be analyzed to continue the analysis, thereby obtaining a new target associated object, achieving the purpose of obtaining the target associated object under the condition that the target object is uncertain, and further improving the universality and flexibility of the method.
After the target associated object is determined, the collision analysis can be performed on the target associated object and the identity data of the target object, and the collision analysis result is displayed in the form of a graph and a track, so that the relationship between the target object and the target associated object is more clearly and intuitively reflected.
Corresponding to the above method embodiment, the embodiment of the present invention further provides a target object association analysis apparatus.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a target object association analysis apparatus according to an embodiment of the present invention, where the apparatus includes:
a first obtaining module 201, configured to obtain a target object to be analyzed; searching a multi-dimensional sensing data set to obtain a target track of the target object; wherein the target track is formed by target track points; the multi-dimensional perception dataset is used for storing a track;
a second obtaining module 202, configured to obtain association information; searching the multi-dimensional sensing data set based on the associated information and each target track point, and determining the associated track point near each target track point;
the first determining module 203 is configured to determine, for each target track point, one target associated track point from associated track points near the target track point;
the second determining module 204 is configured to determine each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining a target associated object according to the association level of each associated object, and completing the association analysis of the target object.
Therefore, by applying the embodiment of the invention, the multi-dimensional sensing data set can be searched, the associated track points near each target track point can be determined, and for each target track point, one target associated track point can be determined from the associated track points near the target track point; determining each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining the target associated object according to the association level of each associated object. Compared with the existing target object association analysis mode, the association analysis efficiency is improved, only one target association track point is determined for each target track point, repeated statistics of the target association track points is avoided, and therefore the accuracy of association analysis is improved.
Optionally, the second determining module 204 calculates the association level of each associated object, specifically:
and regarding each associated object, taking the number of target associated track points belonging to the associated object as the association level of the associated object.
Optionally, the association information includes a preset association level; the second determining module 204 determines the target associated object according to the association level of each associated object, including:
and taking the associated object with the association level larger than the preset association level as a target associated object.
Optionally, the associated information includes a time threshold and an associated type, the track points include an object type, a time point, and a location, the second obtaining module 202 searches the multidimensional sensing dataset based on the associated information and each target track point, and determines the associated track points near each target track point, specifically:
and searching the multidimensional sensing data set aiming at each target track point, and determining the track point, of which the object type belongs to the correlation type, the absolute value of the difference between the time point and the time point of the target track point is not more than the time threshold value, and the point is the same as the point of the target track point, as the correlation track point near the target track point.
Optionally, for each target track point, the first determining module 203 determines a target associated track point from associated track points near the target track point, specifically:
and aiming at each target track point, determining the associated track point with the earliest time point from the associated track points near the target track point to serve as the target associated track point.
Optionally, the apparatus further includes a secondary analysis module, configured to:
after the target associated object is determined, when a secondary analysis instruction is detected, the target associated object is used as the target object, and the multidimensional sensing data set is returned to be searched, so that the target track of the target object is obtained.
Optionally, the first obtaining module 201 obtains a target object to be analyzed, specifically:
and acquiring a target object input by a user through a human-computer interaction interface.
Optionally, the apparatus further includes a format checking module, configured to:
after a target object to be analyzed is obtained, carrying out format verification on the obtained target object;
if the target object passes the format verification, searching a multi-dimensional sensing data set to obtain a target track of the target object;
and if the format check fails, generating prompt information for prompting the target object to be input again, and displaying the prompt information.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A target object association analysis method, the method comprising:
obtaining a target object to be analyzed; searching a multi-dimensional sensing data set to obtain a target track of the target object; wherein the target track is formed by target track points; the multi-dimensional perception dataset is used for storing a track;
obtaining the associated information; searching the multi-dimensional sensing data set based on the associated information and each target track point, and determining the associated track point near each target track point;
for each target track point, determining a target associated track point from associated track points near the target track point;
determining each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining a target associated object according to the association level of each associated object, and completing the association analysis of the target object.
2. The method of claim 1, wherein calculating the relevance level for each relevance object comprises:
and regarding each associated object, taking the number of target associated track points belonging to the associated object as the association level of the associated object.
3. The method according to claim 1 or 2, wherein the association information comprises a preset association level; determining a target associated object according to the association level of each associated object, wherein the method comprises the following steps:
and taking the associated object with the association level larger than the preset association level as a target associated object.
4. The method according to claim 1, wherein the association information includes a time threshold and an association type, the track points include an object type, a time point and a place, the multidimensional sensing dataset is searched based on the association information and each target track point, and the association track points near each target track point are determined, including:
and searching the multidimensional sensing data set aiming at each target track point, and determining the track point, of which the object type belongs to the correlation type, the absolute value of the difference between the time point and the time point of the target track point is not more than the time threshold value, and the point is the same as the point of the target track point, as the correlation track point near the target track point.
5. The method of claim 1, wherein for each target track point, determining a target associated track point from associated track points in the vicinity of the target track point comprises:
and aiming at each target track point, determining the associated track point with the earliest time point from the associated track points near the target track point to serve as the target associated track point.
6. The method of claim 1, wherein after determining the target associated object, the method further comprises:
and when a secondary analysis instruction is detected, taking the target associated object as the target object, and returning to execute the step of searching the multidimensional sensing data set to obtain the target track of the target object.
7. The method of claim 1, wherein obtaining a target object to be analyzed comprises:
and acquiring a target object input by a user through a human-computer interaction interface.
8. The method of claim 7, wherein after obtaining the target object to be analyzed, the method further comprises:
carrying out format verification on the obtained target object;
if the target object passes the format verification, executing a step of searching a multi-dimensional sensing data set to obtain a target track of the target object;
and if the format check fails, generating prompt information for prompting the target object to be input again, and displaying the prompt information.
9. A target object association analysis apparatus, characterized in that the apparatus comprises:
the first obtaining module is used for obtaining a target object to be analyzed; searching a multi-dimensional sensing data set to obtain a target track of the target object; wherein the target track is formed by target track points; the multi-dimensional perception dataset is used for storing a track;
a second obtaining module, configured to obtain the association information; searching the multi-dimensional sensing data set based on the associated information and each target track point, and determining the associated track point near each target track point;
the first determining module is used for determining a target associated track point from associated track points near the target track point aiming at each target track point;
the second determining module is used for determining each associated object to which each target associated track point belongs; calculating the association level of each association object; and determining a target associated object according to the association level of each associated object, and completing the association analysis of the target object.
10. The apparatus according to claim 9, wherein the second determining module calculates the association level of each associated object, specifically:
and regarding each associated object, taking the number of target associated track points belonging to the associated object as the association level of the associated object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811452014.1A CN109656973B (en) | 2018-11-30 | 2018-11-30 | Target object association analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811452014.1A CN109656973B (en) | 2018-11-30 | 2018-11-30 | Target object association analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109656973A CN109656973A (en) | 2019-04-19 |
| CN109656973B true CN109656973B (en) | 2022-07-08 |
Family
ID=66112084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811452014.1A Active CN109656973B (en) | 2018-11-30 | 2018-11-30 | Target object association analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109656973B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110334111B (en) * | 2019-06-13 | 2023-06-02 | 武汉市公安局视频侦查支队 | Multidimensional track analysis method and device |
| CN110618997B (en) * | 2019-08-13 | 2022-07-26 | 深圳市天彦通信股份有限公司 | Identity data unifying method and related device |
| CN110750589B (en) * | 2019-09-04 | 2022-08-16 | 武汉烽火众智数字技术有限责任公司 | Data analysis method and device and computer storage medium |
| CN110674236A (en) * | 2019-09-23 | 2020-01-10 | 浙江省北大信息技术高等研究院 | Moving target association method, device and equipment based on space-time trajectory matching and storage medium |
| CN110837606A (en) * | 2019-11-04 | 2020-02-25 | 北京明略软件系统有限公司 | Spatio-temporal data fusion query method, device, server and storage medium |
| CN113326410B (en) * | 2020-02-28 | 2024-02-13 | 拓尔思天行网安信息技术有限责任公司 | Method and device for analyzing behavior track of relatives based on space-time association |
| CN112218046B (en) * | 2020-09-27 | 2023-10-24 | 杭州海康威视系统技术有限公司 | Object monitoring method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923549A (en) * | 2009-07-29 | 2010-12-22 | 北京航天理想科技有限公司 | User-defined visual intelligent track clue analytical system and establishing method |
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN108694216A (en) * | 2017-04-12 | 2018-10-23 | 杭州海康威视数字技术股份有限公司 | A kind of multi-source method of mapping and device |
-
2018
- 2018-11-30 CN CN201811452014.1A patent/CN109656973B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923549A (en) * | 2009-07-29 | 2010-12-22 | 北京航天理想科技有限公司 | User-defined visual intelligent track clue analytical system and establishing method |
| CN103593361A (en) * | 2012-08-14 | 2014-02-19 | 中国科学院沈阳自动化研究所 | Movement space-time trajectory analysis method in sense network environment |
| CN108694216A (en) * | 2017-04-12 | 2018-10-23 | 杭州海康威视数字技术股份有限公司 | A kind of multi-source method of mapping and device |
Non-Patent Citations (1)
| Title |
|---|
| 基于时空标签轨迹的k近邻模式匹配查询;许建秋等;《通信学报》;20180425(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109656973A (en) | 2019-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109656973B (en) | Target object association analysis method and device | |
| CN107590439B (en) | Target person identification and tracking method and device based on monitoring video | |
| CN110363076B (en) | Personnel information association method and device and terminal equipment | |
| CN110334111B (en) | Multidimensional track analysis method and device | |
| CN110837582B (en) | Data association method and device, electronic equipment and computer-readable storage medium | |
| CN108668233B (en) | Building entrance detection method and system | |
| CN107909668B (en) | Sign-in method and terminal equipment | |
| EP3296975A1 (en) | Collection and provision method, device, system and server for vehicle image data | |
| CN103942811A (en) | Method and system for determining motion trajectory of characteristic object in distributed and parallel mode | |
| CN109559336B (en) | Object tracking method, device and storage medium | |
| CN111078512B (en) | Alarm record generation method and device, alarm equipment and storage medium | |
| CN112770265B (en) | Pedestrian identity information acquisition method, system, server and storage medium | |
| CN105279496A (en) | Human face recognition method and apparatus | |
| CN108540755A (en) | Personal identification method and device | |
| CN105426862A (en) | Analysis method and system based on RFID (Radio Frequency Identification Devices), positioning technology and video technology | |
| CN111126288B (en) | Target object attention calculation method, target object attention calculation device, storage medium and server | |
| CN115205883A (en) | Data auditing method, device, equipment and storage medium based on OCR (optical character recognition) and NLP (non-line language) | |
| CN114743132A (en) | Target algorithm selection method and device, electronic equipment and storage medium | |
| CN113807342A (en) | Method and related device for acquiring equipment information based on image | |
| CN110766101A (en) | Method and device for determining movement track | |
| CN115668989B (en) | Scene recognition method and electronic equipment | |
| CN103546900B (en) | Electronic characteristic acquisition method based on authentication | |
| CN114373209A (en) | Video-based face recognition method and device, electronic equipment and storage medium | |
| CN111107139A (en) | Information pushing method and related product | |
| CN111783786A (en) | Picture identification method and system, electronic equipment 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |