CN114648056A - Association method, electronic device and computer-readable storage medium - Google Patents

Association method, electronic device and computer-readable storage medium Download PDF

Info

Publication number
CN114648056A
CN114648056A CN202210141708.3A CN202210141708A CN114648056A CN 114648056 A CN114648056 A CN 114648056A CN 202210141708 A CN202210141708 A CN 202210141708A CN 114648056 A CN114648056 A CN 114648056A
Authority
CN
China
Prior art keywords
target
sub
time period
equipment
determining
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210141708.3A
Other languages
Chinese (zh)
Inventor
王凯垚
陈立力
周明伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Dahua Technology Co Ltd
Original Assignee
Zhejiang Dahua Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Dahua Technology Co Ltd filed Critical Zhejiang Dahua Technology Co Ltd
Priority to CN202210141708.3A priority Critical patent/CN114648056A/en
Publication of CN114648056A publication Critical patent/CN114648056A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/10—Small scale networks; Flat hierarchical networks
    • H04W84/12—WLAN [Wireless Local Area Networks]

Abstract

The application discloses an association method, an electronic device and a computer readable storage medium, wherein the association method comprises the following steps: acquiring a target file, wherein the target file comprises a target image corresponding to the same target object and captured by capturing equipment in a target area; searching for a device detector bound by the capturing device corresponding to each of at least one target image, and detecting the target device in a first time period corresponding to the target image, wherein the intervals between the starting time point and the ending time point of the first time period corresponding to the target image and the capturing time corresponding to the target image are all larger than the preset time interval; and determining target equipment associated with the target archive according to the searched target equipment, wherein the target equipment associated with the target archive and the target archive correspond to the same target object. The method provided by the application can efficiently determine the target equipment of the same target object corresponding to the target archive.

Description

Association method, electronic device and computer-readable storage medium
Technical Field
The present application relates to the field of image processing technologies, and in particular, to an association method, an electronic device, and a computer-readable storage medium.
Background
With the continuous popularization of smart cities, target track data of each object can be formed according to data captured by a camera, so that a target file is formed, and important information can be provided for population distribution, point area monitoring and the like in a city according to the formed target file.
Most of the existing target clustering means are based on a deep learning technology, object features in a snapshot image are extracted, similarity comparison is carried out, and therefore object clustering is carried out.
Disclosure of Invention
The application provides an association method, an electronic device and a computer readable storage medium, which can efficiently determine a target device corresponding to the same target object with a target archive.
A first aspect of an embodiment of the present application provides an association method, where the method includes: acquiring a target file, wherein the target file comprises a target image corresponding to the same target object and captured by capturing equipment in a target area; searching for a device detector bound to at least one piece of capturing device corresponding to each target image, and detecting the target device in a first time period corresponding to the target image, wherein intervals of a starting time point and an ending time point of the first time period corresponding to the target image and capturing time corresponding to the target image are all larger than a preset time interval; determining the target equipment associated with the target archive according to the searched target equipment, wherein the target equipment associated with the target archive and the target archive correspond to the same target object; and binding the snapshot equipment and the equipment detector in response to that the snapshot equipment takes a snapshot of the target object and the time interval of the equipment detector for acquiring information of the target equipment carried by the target object does not exceed the preset time interval in advance.
A second aspect of the embodiments of the present application provides an electronic device, which includes a processor, a memory, and a communication circuit, where the processor is respectively coupled to the memory and the communication circuit, the memory stores program data, and the processor implements the steps in the above method by executing the program data in the memory.
A third aspect of embodiments of the present application provides a computer-readable storage medium, which stores a computer program, the computer program being executable by a processor to implement the steps in the above method.
The beneficial effects are that: the method and the device respond to that the snapshot device takes a snapshot of the target object, the time interval of the device detector for collecting information of the target device carried by the target object does not exceed the preset time interval, the snapshot device and the device detector are bound, the target device carried by the target object corresponding to the target file can only be located, the device detector bound by the snapshot device corresponding to the target image is detected in the target device detected in the first time period corresponding to the target image, the range of searching for the target device associated with the target file can be reduced, and the target device corresponding to the same target object with the target file is determined efficiently.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts. Wherein:
FIG. 1 is a schematic flow chart diagram of one embodiment of a method associated with the present application;
FIG. 2 is a schematic flow chart of step S120 in FIG. 1;
FIG. 3 is a schematic flow chart of step S130 in FIG. 1;
FIG. 4 is a schematic flowchart of step S131 in FIG. 3;
FIG. 5 is a schematic structural diagram of an embodiment of an electronic device of the present application;
FIG. 6 is a schematic block diagram of another embodiment of an electronic device of the present application;
FIG. 7 is a schematic structural diagram of an embodiment of a computer-readable storage medium according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all 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 application.
Referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a method associated with the present application, the method including:
s110: and acquiring a target file.
The target archive comprises target images corresponding to the same target object and captured by the capturing equipment in the target area, namely the target images in the target archive are images of the same target object. Specifically, clustering is performed on a plurality of images to be clustered captured by capturing equipment in a target area in advance, and images corresponding to the same target object are classified into one file, so that target files corresponding to different target objects are obtained. The target object may be any object capable of moving, and is not limited in particular herein.
The method comprises the steps of clustering a plurality of images to be clustered based on a preset clustering threshold value in the process of clustering the images to be clustered, and particularly, classifying two images to be clustered, the similarity of which exceeds the clustering threshold value, into the same archive.
S120: and searching for the equipment detector bound by the capturing equipment corresponding to at least one target image, and detecting the target equipment in the first time period corresponding to the target image.
For each target image in the target archive, corresponding capturing equipment and capturing time exist, wherein the capturing time corresponding to the target image can be a capturing time point or a capturing time period.
Wherein, equipment detector is used for gathering target device's equipment information, and target device can be equipment such as cell-phone, computer, and in this embodiment, equipment detector is WIFI acquisition probe, and it can gather the MAC information that gets into target device such as cell-phone, computer of its collection scope.
The method comprises the steps of acquiring all snapshot devices and all device detectors in a target area in advance, responding to the fact that the snapshot devices and the device detectors meet preset requirements, and establishing a binding relationship between the snapshot devices and the device detectors, wherein the preset requirements are as follows: the time interval for capturing the target object by the capturing equipment and acquiring the information of the target equipment carried by the target object by the equipment detector does not exceed the preset time interval.
Specifically, if the snapshot device a takes a snapshot of the object C and the interval between the snapshot device a and the device detector B for acquiring information of the target device carried by the object C is smaller than the preset time interval, the snapshot device a and the device detector B are bound.
It will be appreciated that the number of device detectors bound for a single capture device may be zero, one, or more.
When the snapshot time corresponding to the target image is a snapshot time point, the intervals between the starting time point, the ending time point and the snapshot time point of the first time period are all larger than a preset time interval; when the snapshot time corresponding to the target image is the snapshot time period, the interval between the starting time point of the first time period and the starting time point of the snapshot time period and the interval between the ending time point of the first time period and the ending time point of the snapshot time period are both larger than the preset time interval.
In step S120, an operation may be performed on each target image in the target archive, or may be performed on a part of the target image. For a target image needing to be operated, the corresponding snapshot device and the snapshot time of the target image are searched first, then the device detectors bound to the snapshot device are determined, and finally the target devices detected by the device detectors in the first time period corresponding to the snapshot time are determined.
S130: and determining the target equipment associated with the target file according to the searched target equipment.
The target device associated with the target archive and the target archive correspond to the same target object, namely, the target device associated with the target archive is the target device carried by the target object corresponding to the target archive.
For a better understanding, the scheme is explained in connection with the examples:
the capturing device a and the device detector B are in a binding relationship, and the time when the capturing device a captures the object C is a time point T1, so that the time point when the device detector B acquires information of the target device carried by the object C is inevitably between T1-T and T1+ T, and is not in other time periods, where T is a preset time interval.
Therefore, the target device carried by the object C only needs to be searched in the target devices detected by the device detector B between T1-T and T1+ T, the searching range can be shortened, and the searching efficiency can be improved.
Therefore, the target device carried by the target object corresponding to the target file may only be located in the target device detected by the device detector bound to the capturing device corresponding to the target image in the first time period corresponding to the target image, so that the step 130 searches the target device corresponding to the same target object as the target file from the target devices searched in the step S120, and can narrow the search range and efficiently determine the target device corresponding to the same target object as the target file.
Wherein the number of target devices associated with a target profile may be zero, one, or more.
In this embodiment, whether the snapshot device and the device detector can be bound is determined by detecting the distance between the snapshot device and the device detector, and specifically, in response to that the distance between the snapshot device and the device detector does not exceed a corresponding distance threshold value in advance, it is determined that the time interval between the snapshot device taking a snapshot of the target object and the information acquisition of the target device carried by the target object by the device detector does not exceed a preset time interval.
Specifically, the positions of all the capturing devices and all the device detectors in the target area are obtained, specifically, latitude and longitude information can be obtained, then, for each capturing device, the distance between each capturing device and each device detector is calculated, if the distance between a certain capturing device and a certain device detector is smaller than a corresponding distance threshold value, it is determined that the capturing device captures an object a, and the time for the device detector to acquire information of the target device carried by the object a does not exceed a preset time interval, so that the capturing device and the device detectors are bound.
In an application scenario, the corresponding distance threshold dmaxThe calculation formula of (2) is as follows: dmax＝d1+d2+d3X t, wherein d1Is the maximum snapping distance of the snapping device, i.e. the distance between only the target object and the snapping device is less than or equal to d1Can be snap shot by snap shot equipment, d2Is the maximum detection distance of the device detector, i.e. the distance between the target device and the device detector is less than or equal to d2The device detector can acquire information of the target device, t is a detection time interval of the device detector, namely, the time interval of two adjacent target device detections of the device detector is t, d3As the maximum moving distance of the target object per unit time, it can be understood that d3And x t is the maximum moving distance of the target object in the detection time interval of the equipment detector. Wherein, the maximum moving distance d of the target object in unit time can be obtained in advance through a large number of experiments3。
In the application scenario, the distance threshold is related to the types of the capturing devices and the device detectors, the capturing devices or the device detectors are different, and the corresponding distance thresholds may be different.
In other application scenarios, the corresponding distance threshold may also be a fixed value preset by a designer, regardless of the types of the capturing device and the device detector.
In order to reduce the calculation amount, referring to fig. 2, step S120 specifically includes:
s121: and determining a target image with corresponding snapshot time within a second time period in the target file to form a first sub-file.
S122: and searching the equipment detector bound by the snapshot equipment corresponding to at least one target image in the first sub-file, and detecting the target equipment in the corresponding first time period.
Specifically, a target image with the capturing time within the second time period is searched from the target file, and then a device detector bound to the capturing device corresponding to each of at least one target image and the target device detected within the corresponding first time period are determined from the part of the target image.
In the present embodiment, the second time period is the time period closest to the present time, and in other embodiments, the second time period may be a time period in a day before that, in short, it is sufficient if there is a target image whose capturing time is within the second time period.
Step S122 may be performed on a part of the target images in the first sub-archive, or step S122 may be performed on each target image in the first sub-archive.
It should be noted that, in another embodiment, in step S120, several target images may also be randomly selected from the target file, and then the device detectors bound to the capturing devices corresponding to the target images are determined, so as to determine the target devices detected in the corresponding first time period.
The process of forming a target profile generally includes: clustering images captured by all capturing devices in the target area on the day: the two images with the similarity exceeding the clustering threshold are classified into the same file, so that a plurality of target files corresponding to different target objects are formed, and then the target files obtained on the same day are subjected to file falling processing, wherein the file falling processing process comprises the following steps: and determining the similarity between each target file obtained on the current day and each existing target file, if the similarity exceeds a clustering threshold, merging the target files obtained on the current day into the corresponding existing target files, and if the similarity does not meet the requirement, taking the target files obtained on the current day as a newly-built file.
In view of the above, the present embodiment may perform division of the second period in units of days, specifically, the second period is the latest day, two days, three days, or the like. Of course, in other embodiments, the second time period may be the last 2 hours, 5 hours, 20 hours, or the like.
Referring to fig. 3, in the present embodiment, the process of determining the target device associated with the target profile in step S130 includes:
s131: and determining a coincidence degree evaluation value corresponding to each target device according to at least one target image in the first sub-file.
And the contact ratio evaluation value corresponding to the target equipment represents the contact ratio of the target equipment and the motion trail of the target object corresponding to the target file in a second time period.
The at least one target image in the first sub-archive shows the motion trajectory of the target object corresponding to the target archive in the second time period, for example, the at least one target image is arranged according to the sequence of the snapshot time from front to back, then the snapshot device corresponding to each of the at least one target image is obtained, and the motion trajectory of the target object corresponding to the target archive in the second time period can be shown according to the position corresponding to the snapshot device from front to back.
For each target device found, the device detector for detecting the target device in the target area in the second time period can be found, the position of each device detector is obtained according to the sequence of the detection time from front to back, and the motion track of the target device in the second time period can be displayed according to the position obtained from front to back.
It can be understood that, the higher the coincidence degree of the motion trajectories of the target object corresponding to the target profile in the second time period, the higher the probability that the target object corresponds to the same target object as the target profile.
S132: and determining the target equipment associated with the target file according to the contact ratio evaluation value corresponding to each target equipment.
In an application scenario, the contact ratio evaluation value corresponding to the target device is in direct proportion to the contact ratio of the motion trajectories of the target object corresponding to the target device and the target file in the second time period, that is, the higher the contact ratio evaluation value corresponding to the target device is, the higher the contact ratio of the motion trajectories of the target object corresponding to the target device and the target file in the second time period is represented.
In this application scenario, step S132 may be: if the evaluation value of the degree of coincidence corresponding to the target device is greater than the threshold value of the evaluation value, then it is determined that the target device corresponds to the same target object as the target profile, and at this time, it is possible that the evaluation values of the degree of coincidence corresponding to a plurality of target devices are all greater than the threshold value of the evaluation value, so that it is finally determined that the target device associated with the target profile may be zero, one, or multiple, or step S132 may also be: and determining a maximum contact ratio evaluation value in the determined contact ratio evaluation values, and if the maximum contact ratio evaluation value is larger than the evaluation value threshold value, determining that the target device corresponding to the maximum contact ratio evaluation value corresponds to the same target object as the target file, wherein the target device associated with the target file is finally determined to be either zero or one.
In other application scenarios, the overlap ratio evaluation value corresponding to the target device may also be inversely proportional to the overlap ratio of the motion trajectories of the target device and the target object corresponding to the target profile in the second time period, and step S132 is the reverse of the process of step S132 in the above application scenarios, and will not be described in detail here.
It is understood that the longer the second time period determined in step S121, the higher the accuracy of finally determining the target device corresponding to the same target object as the target profile.
Referring to fig. 4, in the present embodiment, step S131 specifically includes:
s1311: and determining a first evaluation value and a second evaluation value corresponding to each target device according to at least one target image in the first sub-file.
The first evaluation value corresponding to the target device represents the coincidence degree of the snapshot device bound to the device detector which detects the target device in the target area in the second time period and the snapshot device of the target object corresponding to the target file in the second time period.
It can be understood that, if the target device and the target file correspond to the same target object, the snapshot device bound to the device detector that detects the target device can take a snapshot of the user of the target device, and the coincidence degree of the snapshot device bound to the device detector that detects the target device and the snapshot device corresponding to the target image in the target file is higher.
If the target device and the target file do not correspond to the same target object, the snapshot device bound to the device detector of the target device is detected, the user of the target device is not necessarily snapshot, and the contact ratio of the snapshot device bound to the device detector of the target device and the snapshot device corresponding to the target image in the target file is lower.
The second evaluation value corresponding to the target device represents the ratio of the path length traveled by the target object corresponding to the target archive in the second time period to the path length traveled by the target device in the second time period.
It can be understood that, if the target device and the target archive correspond to the same target object, the path length traveled by the target object corresponding to the target archive in the second time period should be equal or almost equal to the path length traveled by the target device in the second time period.
If the target device and the target archive do not correspond to the same target object, the path length of the target object corresponding to the target archive in the second time period is different from the path length of the target device in the second time period.
S1312: and determining a coincidence degree evaluation value corresponding to each target device according to at least one of the first evaluation value and the second evaluation value corresponding to each target device.
The coincidence degree evaluation value corresponding to the target device may be determined based on only one of the first evaluation value and the second evaluation value, or may be determined based on both the first evaluation value and the second evaluation value.
In an application scenario, the process of determining the first evaluation value corresponding to the target device includes:
(a1) a first number of at least one target image in the first sub-archive is determined.
(b1) And determining a second number of first target images in at least one target image in the first sub-file, wherein the device detector bound to the capturing device corresponding to the first target image detects the target device within the corresponding first time period.
(c1) And determining a first ratio of the second quantity to a third quantity to obtain a first evaluation value corresponding to the target device, wherein the third quantity is equal to the sum of the first quantity and the first positive number.
The process of determining the first evaluation value is explained in connection with an example:
it is assumed that at least one target image in the first sub-archive is sequentially arranged from front to back according to the capturing time: c1, C2, C3, C4 and C5, corresponding snapshot equipment is: n1, N2, N3, N4 and N5, and the corresponding first time periods are T1, T2, T3, T4 and T5 in sequence. The first number is now determined to be 5.
The device detector bound to the capturing device N1 acquires device information of the target device in the corresponding first time period T1, the device detector bound to the capturing device N3 acquires device information of the target device in the corresponding first time period T3, the device detector bound to the capturing device N2 does not acquire device information of the target device in the corresponding first time period T2, the device detector bound to the capturing device N4 does not acquire device information of the target device in the corresponding first time period T4, and the device detector bound to the capturing device N5 does not acquire device information of the target device in the corresponding first time period T5. At this time, the target images C1 and C2 are determined as the first target images, and the second number is 2.
And further calculating a first ratio of 2 to a third number to obtain a first evaluation value corresponding to the target device, wherein the third number is equal to the sum of 5 and the first positive number.
Where the first positive number may be any positive number, such as 1, 5, or other number.
Wherein calculating the ratio of the second number to the third number instead of the ratio of the second number to the first number is to avoid the first ratio being equal to 1, and to avoid the first ratio being equal to 1 is to distinguish the following cases:
it is assumed that there are two first sub-files, one first sub-file includes 100 target images, and the other includes 5 target images, wherein in the two first sub-files, the device detector bound to the capturing device corresponding to each target image detects the target device in the corresponding first time period, that is, the target images in the two first sub-files are the first target images.
If the ratio of the second number to the first number is directly determined as the first evaluation value corresponding to the target device, the first evaluation values corresponding to the target device in both of the two first sub-files are 1, but in reality, the probability that the target device corresponds to the same target object as the first sub-file including 100 target images is greater than the probability that the target device corresponds to the same target object as the first sub-file including 5 target images.
If the ratio of the second number to the third number is calculated, taking the first positive number as 1, one is
Figure BDA0003507296090000101
Approximately equal to 0.99, the other is
Figure BDA0003507296090000102
Approximately equal to 0.83, which is in fact true.
That is, the range of the first ratio determined through the above method is [0, 1 ].
In other embodiments, the ratio of the second number to the first number may be directly used as the first evaluation value corresponding to the target device.
In an application scenario, the process of determining the second evaluation value corresponding to the target device includes:
(a2) and searching a first equipment detector in the equipment detectors bound to the snapping equipment corresponding to the at least one target image, wherein the first equipment detector detects the target equipment in the corresponding first time period.
(b2) First distances of any two first equipment detectors are determined, and the largest first distance is found.
(c2) A second device detector is determined that detects a target device within the target area during a second time period.
(d2) And determining the second distance between any two second target equipment detectors, and searching the maximum second distance.
(e2) And determining a second ratio of the maximum first distance to a third distance to obtain a second evaluation value corresponding to the target device, wherein the third distance is equal to the sum of the maximum second distance and a second positive number.
The process of determining the second evaluation value is explained in connection with an example:
it is assumed that at least one target image in the first sub-archive is sequentially arranged from front to back according to the capturing time: c1, C2, C3, C4 and C5, corresponding snapshot equipment is: n1, N2, N3, N4 and N5, and the corresponding first time periods are T1, T2, T3, T4 and T5 in sequence. And the device detectors bound by the snapshot device N1 are W1 and W2, the device detectors bound by the snapshot device N2 are W1 and W3, the device detectors bound by the snapshot device N3 are W4 and W5, the device detectors bound by the snapshot device N4 are W2 and W4, and the device detector bound by the snapshot device N5 is W2.
The device probes W1 and W2 acquire device information of the target device in a first time period T1, the device probes W1 and W3 do not acquire device information of the target device in a second time period T2, the device probes W4 and W5 do not acquire device information of the target device in the second time period T3, the device probes W2 and W4 acquire device information of the target device in a second time period T4, and the device probe W2 does not acquire device information of the target device in the second time period T5.
The device probes W1, W2, W4 are determined as the first device probes and the first distance between each two is determined and then the largest first distance is determined.
All second device detectors that detected the target device within the target area during the second time period are simultaneously located, then a first distance between any two second device detectors is determined, and then a maximum second distance is determined.
And finally, determining a second ratio of the maximum first distance to a third distance, wherein the second ratio is a second evaluation value corresponding to the target device, and the third distance is equal to the sum of the maximum second distance and a second positive number.
The second positive number may be any positive number, for example, the second positive number is 1 or 10, and in an application scenario, the second positive number is the distance threshold.
The principle of setting the second positive number is the same as the principle of setting the first positive number, and the second ratio is avoided to be equal to 1 in combination with the actual situation, that is, the range of the second ratio is [0, 1 ].
In an application scenario, step S1312 specifically includes: and determining the product of the square value of the first evaluation value corresponding to each target device and the square root of the corresponding second evaluation value to obtain the coincidence degree evaluation value corresponding to each target device.
In order to amplify the difference of the first evaluation values corresponding to the large number and the small number of the target images in the first sub-archive, the first evaluation values are squared. Specifically, if there are two first sub-files for the same target device and the target device has the same or almost the same first evaluation value corresponding to the two first sub-files, but if one first sub-file includes a larger number of target images than the other first sub-file, the probability that the target device and the two first sub-files correspond to the same target object should be different from each other in practice, so in order to amplify the difference, the first evaluation value is squared.
Considering that the similarity of two target images of the same target object may be low due to factors such as the capturing device and the image definition, and the two target images may not be included in the same file in the clustering process, a part of target images may be omitted from the target file, and if the target images are omitted, the capturing device capturing the target object corresponding to the target file in the second time period may also be omitted, and the second evaluation value may be too small, so that the second evaluation value is developed to avoid the phenomenon that the second evaluation value is too small.
In other embodiments, the product of the first evaluation value and the second evaluation value may also be directly determined as the coincidence degree evaluation value corresponding to the target device.
In this embodiment, the determination of the goodness-of-overlap evaluation value corresponding to each target device may also be performed in a segmented manner, where step S131 includes:
(a3) the second time period is divided into a plurality of first sub-time periods.
The length of the second time period is greater than one day (24 hours), and the second time period may be divided by 24 hours, that is, the length of the first sub-time periods is 24 hours, and the starting time point of each first sub-time period is the zero point of the day.
Of course, the application does not limit the length of the first sub-period.
(b3) And determining target images with corresponding capturing time in each first sub-time period in at least one target image in the first sub-files, and forming second sub-files corresponding to the first sub-time periods.
It can be understood that, if there is no target image in a first sub-period, the number of target images in the second sub-archive corresponding to the first sub-period is zero, indicating that the target object corresponding to the target archive has not been moved during the period.
(c3) And determining a sub-contact ratio evaluation value corresponding to each target device and each first sub-time period according to each second sub-file, wherein the sub-contact ratio evaluation value corresponding to the target device and the first sub-time period represents the contact ratio of the target device and the target object corresponding to the target file in the motion track of the target device in the first sub-time period.
And determining an evaluation value of the motion track coincidence degree of each target device and the target object corresponding to the target archive in each first sub-time period, namely a sub-coincidence evaluation value.
The process of determining the evaluation value of degree of overlap is similar to the process of determining the evaluation value of degree of overlap, and is equivalent to replacing the second time period with the first sub-time period and replacing the first sub-file with the second sub-file.
(d3) And determining the ratio of the sum of the sub-contact ratio evaluation values corresponding to the target devices to the number of the target first sub-time periods to obtain the contact ratio evaluation value corresponding to each target device, wherein the number of the target images with corresponding capturing time in the target first sub-time periods is at least one.
In response to the number of target images corresponding to the first sub-period not being zero, the first sub-period is defined as a target first sub-period, and it is understood that the target first sub-period is a period when the user is out.
For each target device, calculating the sum of the corresponding sub-contact ratio evaluation values, and then determining the sum and the number of the target first sub-time periods to obtain the contact ratio evaluation value corresponding to the target device.
In this embodiment, in order to reduce the amount of computation, the first sub-file is also subjected to deduplication processing in advance, and the deduplication process includes: dividing the second time period into a plurality of second sub-time periods; and carrying out duplication elimination processing on the first sub-files, so that the number of target images corresponding to the same snapshot device in the duplicated first sub-files in the same second sub-time period is at most one.
The second sub-period is smaller than the first sub-period, and the length of the second sub-period may be 1 second, 30 seconds, 1 minute, or the like.
In the duplicate removal process, if a plurality of target images corresponding to the same snapshot device exist in a second sub-time period, the target images are subjected to duplicate removal, and only one target image is reserved.
In an application scenario, the length of the second sub-period is greater than the preset time interval, and the specific process of searching for the first period corresponding to the target image may be as follows: and determining a second sub-time period where the snapshot time point of the target image is located, and then taking a time period formed by three second sub-time periods, namely a previous second sub-time period adjacent to the second sub-time period, the second sub-time period and a next second sub-time period adjacent to the second sub-time period, as the first time period corresponding to the target image.
In the present embodiment, also in order to reduce the amount of calculation, step S122 includes: determining a target device set, the target device set including device detectors within the target area, target devices detected during the second time period; removing illegal target equipment in the target equipment set, and/or removing target equipment which remains static in the second time period in the target equipment set; and searching for the equipment detector bound by the snapshot equipment corresponding to at least one target image in the target equipment set, and detecting the target equipment in the corresponding first time period.
Specifically, if the target device is an illegal device, the device information of two different target devices may be the same, and it is subsequently impossible to determine which target device actually corresponds to the same object as the target profile.
In an application scene, when the equipment detector collects MAC information of target equipment, illegal target equipment can be removed according to the OUI library of the global organization unique identifier.
If the target device remains still for the second period of time, which indicates that the target device has been left out, the device detector detects this because: the user's residence is within the detection range of the device detector, but the user is out of the way, and the snapshot device cannot possibly take a snapshot of it, and thus removes it as well.
Wherein, the standard for judging whether the target device is static is as follows: during the second time period, if the target device is always detected by one or the same set of device detectors, i.e. if the number of device detectors detecting the target device does not exceed the number threshold, it is determined that the target device is in a stationary state.
If the overlap ratio evaluation value corresponding to the target device is determined in a segmented manner, before determining the sub-overlap ratio evaluation value corresponding to the target device and the first sub-time period, the multiple second sub-archives need to be subjected to deduplication processing, and multiple sub-target device sets need to be subjected to deduplication processing, wherein the multiple sub-target device sets respectively include the target devices detected by the device detector in the target area in the multiple first sub-time periods.
Specifically, a plurality of second sub-archives and a sub-target device set corresponding to each second sub-archive are determined, wherein the sub-target device set corresponding to the second sub-archives includes: and the equipment detector in the target area detects target equipment in a first sub-time period corresponding to the second sub-file.
And then, performing the following repeated processing on each second sub-file and the corresponding sub-target equipment set respectively:
and carrying out duplicate removal processing on the second sub-files, so that the number of target images corresponding to the same snapshot device in the second sub-files after duplicate removal is at most one in the same second sub-time period.
And removing illegal target equipment in the sub-target equipment set, and/or removing target equipment which remains static in the sub-target equipment set in the corresponding first sub-time period.
For a better understanding of the above solution, it is described in detail herein with reference to the examples:
firstly, all the snapshot devices and the device detectors in the target area are obtained, and the binding relationship is established between the snapshot devices and the device detectors which meet the binding relationship.
Acquiring a file B of the target object A, finding a target image of the last N days from the file B, and then respectively executing the following operations on sub-files formed by the target image of each day:
for sub-archive A1, a corresponding sub-target device set C is first determined, which includes target devices detected by device detectors in the target area within the day corresponding to sub-archive A1.
Performing deduplication processing on the sub-archive a1 and the sub-target equipment set C, wherein the process comprises the following steps:
the time of each day is divided into time blocks, for example, by cutting each day's time in units of one second, to yield 86400 time blocks.
If there is a target image corresponding to the same capture device in sub-file a1 within a certain time block, the deduplication is performed until only one is retained.
If an illegal target device exists in the sub-target device set C, the illegal target device is removed, and/or if a stationary target device exists in the sub-target device set C, the stationary target device is removed.
After deduplication, the sub-archive a1 and the sub-target equipment set C are processed as follows:
for each target image in sub-archive A1, its corresponding first time period is determined, which is a time block Ti-1、TiAnd Ti+1Time period of composition, TiIs the time block, T, at which the snapshot time point of the target image is locatedi-1、Ti+1The two adjacent time blocks are respectively the front time block and the back time block.
And then searching for the equipment detector bound to the snapshot equipment corresponding to each target image, and detecting the target equipment in the first time period corresponding to the target image.
Then, the following steps are respectively executed for each found target device, and the target device L is taken as an example for explanation:
and responding to the device detector bound to the snapshot device corresponding to the target image, detecting the target device L in a first time period corresponding to the target image, and defining the target image as a first target image.
Responding to a certain equipment detector bound to the snapshot equipment corresponding to the target image, detecting the target equipment L in a first time period corresponding to the target image, and defining the equipment detector as a target equipment detector; after querying the target device detectors, a first distance between any two target device detectors is determined, and a maximum first distance is found.
When the sub-file A1 is queried, the device detectors of the target device are detected in the target area, then a second distance between any two device detectors is determined, and the largest second distance is found.
Then, the sub-coincidence evaluation value S corresponding to the target device L is determined according to the following formula:
Figure BDA0003507296090000161
wherein, T1Is the number of first target images, T2D is the maximum first distance, d' is the maximum second distance, d is the number of target images in sub-file A1maxThe distance threshold described above. Through the steps, the corresponding sub-contact ratio evaluation value of the target device L in N days per day can be determined, then the corresponding sub-contact ratio evaluation values are added to obtain a sum value, and the sum value is divided by the number of days that the target object A leaves the door in the last N days to obtain the corresponding contact ratio evaluation value of the target device L in N days. It will be appreciated that the number of days that the target object a has left the door in the last N days is equal to the number of sub-files comprising at least one target image, i.e. if the number of target images in the corresponding sub-file of a certain day is zero, it means that the target object a has not left the door in that day.
By analogy, a coincidence evaluation value corresponding to each target device can be determined.
And finally, if the coincidence degree evaluation value corresponding to the target device is greater than the threshold value, determining that the target device is the device carried by the target object A.
The above process of determining the target device associated with the target profile in the searched target device is specifically described, and the following specific application after determining the associated target device is described:
in an application scenario, determining target devices associated with a plurality of target files according to the method, where the association method further includes:
s140: and in response to the plurality of target files being simultaneously associated with the same target device, merging the plurality of target files.
Specifically, if multiple target files are associated with the same target device at the same time, it is indicated that the multiple target files correspond to the same target object, and the target files corresponding to the same target object are merged.
The above scheme can avoid the following defects in the prior art:
in the prior art, due to factors such as a snapshot angle and image definition, the similarity between target images of the same target object is lower than a clustering threshold, so that a phenomenon that one target object corresponds to a plurality of archives exists in a clustering process.
The target device associated with the target archive can determine whether a problem that one target object corresponds to a plurality of archives occurs, and can perform archive aggregation processing on a plurality of target archives corresponding to the same target object after determining that the problem exists.
In this application scenario, in order to further improve the accuracy, before merging the multiple target profiles simultaneously associated with the same target device, it is further required to verify whether the multiple target profiles really correspond to the same target object, where step S140 includes: determining the similarity of any two target files; and in response to the similarity being larger than the first similarity threshold, merging the two corresponding target files.
Specifically, only two target files with similarity exceeding the first similarity threshold are further determined to correspond to the same target object, and then merging processing is performed.
The reason that the plurality of target archives are associated with the same target object at the same time is considered to be that the capturing angles and the image definitions are different, and the similarity between two target images of the same target object is low under different capturing angles and different definitions, so that compared with a normal clustering process, the clustering threshold needs to be reduced, and therefore the first similarity threshold is set to be smaller than the clustering threshold (the third similarity threshold), wherein the normal clustering process is a process of clustering a plurality of images to be clustered to obtain the target archives.
In another application scenario, after a target device associated with a target profile is obtained, a track completion process may be performed on the target profile, where the process includes:
(a4) and determining a target image with the corresponding snapshot time within a third time period in the target file to form a third sub-file.
The third time period may be any time period, such as the last day, the last 5 hours, and 13:00-15:00 of a previous day.
(b4) And determining the equipment detectors bound by the snapshot equipment corresponding to each target image in the third sub-file to form a first equipment detector set.
(c4) And determining the device detectors of the associated target devices acquired in the target area in the third time period to form a second device detector set.
(d4) Target device detectors in the second set of device detectors but not in the first set of device detectors are searched.
In particular, a device detector in the second set of device detectors, but not in the first set of device detectors, is defined as a target device detector.
If the target equipment detector exists, the target equipment detector detects target equipment associated with the target file, but the capturing equipment bound by the target equipment detector does not capture a target object corresponding to the target file, which shows that the target equipment detector is not in accordance with the conventional situation, and the reason for the phenomenon is only probably that in the process of clustering, images captured by the capturing equipment bound by the target equipment detector are omitted.
(e4) And finding the snapshot device bound by each target device detector, and snapshotting the image in the corresponding fourth time period, wherein the starting time point and the ending time point of the fourth time period corresponding to the target device detector and the time for the target device detector to acquire information of the associated target device are greater than a preset time threshold.
(f4) And classifying the searched image into a target file.
Through the analysis, the target object should be captured by the capturing device bound to the target device detector before and after the target device detector detects the associated target device, so that the image captured by the capturing device bound to the target device detector in the corresponding fourth time period is considered as a missing image, and the missing image is added into the target file.
In order to further improve the accuracy, before the searched image is classified into the target file, the similarity between the searched image and the target file needs to be determined, and if the similarity of the searched image is greater than a second similarity threshold, the searched image is classified into the target file.
Similar to the above application scenario, considering that the reason for missing an image may be that the capturing angle and the image definition are different, and the similarity between two target images of the same target object is low under different capturing angles and different definitions, compared with a normal clustering process, the clustering threshold needs to be reduced, so that the second similarity threshold is set to be smaller than the clustering threshold (the third similarity threshold).
Referring to fig. 5, fig. 5 is a schematic structural diagram of an embodiment of an electronic device according to the present application. The electronic device 200 includes a processor 210, a memory 220, and a communication circuit 230, wherein the processor 210 is coupled to the memory 220 and the communication circuit 230, respectively, the memory 220 stores program data, and the processor 210 implements the steps in the method according to any of the above embodiments by executing the program data in the memory 220, and the detailed steps can refer to the above embodiments and are not described herein again.
The electronic device 200 may be any device with algorithm processing capability, such as a computer and a mobile phone, and is not limited herein.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an embodiment of an electronic device according to the present application. The electronic device 300 includes an acquisition module 310, a lookup module 320, and a determination module 330.
The obtaining module 310 is configured to obtain a target archive, where the target archive includes a target image corresponding to a same target object captured by a capturing device in a target area.
The searching module 320 is connected to the obtaining module 310, and is configured to search for a device detector bound to a capturing device corresponding to each of at least one target image, and a target device detected in a first time period corresponding to the target image, where intervals between a start time point and an end time point of the first time period corresponding to the target image and capturing time corresponding to the target image are all greater than a preset time interval.
The determining module 330 is connected to the searching module 320, and configured to determine, according to the searched target device, a target device associated with the target profile, where the target device associated with the target profile and the target profile correspond to the same target object.
The method comprises the steps that a snapshot device conducts snapshot on a target object in advance, and a time interval of information collection of the target device carried by the target object through a device detector does not exceed a preset time interval, so that the snapshot device and the device detector are bound.
The electronic device 300 performs the method steps in any of the above embodiments when operating, and the detailed steps can be referred to the above embodiments and are not described herein again.
The electronic device 300 may be any device with algorithm processing capability, such as a mobile phone and a computer.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an embodiment of a computer-readable storage medium according to the present application. The computer-readable storage medium 400 stores a computer program 410, the computer program 410 being executable by a processor to implement the steps of any of the methods described above.
The computer-readable storage medium 400 may be a device that can store the computer program 410, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, or may be a server that stores the computer program 410, and the server may send the stored computer program 410 to another device for operation, or may self-operate the stored computer program 410.
The above description is only for the purpose of illustrating embodiments of the present application and is not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application or are directly or indirectly applied to other related technical fields, are also included in the scope of the present application.

Claims (19)

1. An association method, characterized in that the method comprises:
acquiring a target file, wherein the target file comprises a target image corresponding to the same target object, which is captured by capturing equipment in a target area;
searching for a device detector bound to at least one piece of snapshot device corresponding to each target image, and detecting the target devices in a first time period corresponding to the target images, wherein the intervals between the starting time point and the ending time point of the first time period corresponding to the target images and the snapshot time corresponding to the target images are larger than a preset time interval;
determining the target equipment associated with the target archive according to the searched target equipment, wherein the target equipment associated with the target archive and the target archive correspond to the same target object;
and binding the snapshot equipment and the equipment detector in response to that the snapshot equipment takes a snapshot of the target object and the time interval of the equipment detector for acquiring information of the target equipment carried by the target object does not exceed the preset time interval in advance.
2. The method of claim 1, further comprising:
and in response to the fact that the distance between the snapshot device and the device detector does not exceed a corresponding distance threshold value in advance, determining that the time interval between the snapshot device taking a snapshot of the target object and the device detector acquiring information of the target device carried by the target object does not exceed the preset time interval.
3. The method according to claim 2, characterized in that the corresponding distance threshold is equal to the sum of the maximum snapping distance of the snapping device, the maximum detection distance of the device detector, the maximum moving distance of the target object within the detection time interval of the device detector.
4. The association method according to claim 1, wherein the step of finding the target device detected in the first time period corresponding to the target image by the device detector bound to the capturing device corresponding to each of the at least one target image comprises:
determining the target image corresponding to the snapshot time within a second time period in the target file to form a first sub-file;
and searching the equipment detector bound by the capturing equipment corresponding to at least one target image in the first sub-file, and detecting the target equipment in the corresponding first time period.
5. The association method according to claim 4, wherein the step of determining the target device associated with the target profile according to the found target device comprises:
determining a coincidence degree evaluation value corresponding to each target device according to at least one target image in the first sub-archive, wherein the coincidence degree evaluation value corresponding to the target device represents coincidence degrees of the target device and the target object corresponding to the target archive in the motion trail in the second time period;
and determining the target equipment associated with the target file according to the contact ratio evaluation value corresponding to each target equipment.
6. The method of claim 5, wherein the step of determining a goodness-of-contact estimate for each of the target devices based on at least one of the target images in the first sub-archive comprises:
determining a first evaluation value and a second evaluation value corresponding to each target device according to at least one target image in the first sub-file;
determining the contact ratio evaluation value corresponding to each target device according to at least one of the first evaluation value and the second evaluation value corresponding to each target device;
the first evaluation value corresponding to the target device represents, and the coincidence ratio between the snapshot device bound to the device detector which detects the target device in the target region within the second time period and the snapshot device of the target object corresponding to the target file captured within the second time period;
the second evaluation value corresponding to the target device represents coincidence degree of a path length traveled by the target object corresponding to the target profile in the second time period and a path length traveled by the target device in the second time period.
7. The method according to claim 6, wherein the step of obtaining the first evaluation value corresponding to the target device comprises:
determining a first number of at least one of the target images in the first sub-archive;
determining a second number of first target images in at least one target image in the first sub-file, wherein the device detector bound to the capturing device corresponding to the first target image detects the target device within the corresponding first time period;
and determining a first ratio of the second quantity to a third quantity to obtain the first evaluation value corresponding to the target device, wherein the third quantity is equal to the sum of the first quantity and a first positive number.
8. The method according to claim 6, wherein the step of obtaining the second evaluation value corresponding to the target device comprises:
searching for a first device detector in the device detectors bound to the capturing device corresponding to the at least one target image, wherein the first device detector detects the target device within the corresponding first time period;
determining first distances of any two first equipment detectors, and searching the largest first distance;
a second device detector that determines that the target device is detected within the target zone during the second time period;
determining a second distance between any two second target equipment detectors, and searching for the largest second distance;
and determining a second ratio of the maximum first distance to a third distance to obtain the second evaluation value corresponding to the target device, wherein the third distance is equal to the sum of the maximum second distance and a second positive number.
9. The method according to claim 6, wherein the step of determining the evaluation value of the degree of overlap corresponding to each target device according to at least one of the first evaluation value and the second evaluation value corresponding to each target device comprises:
and determining the product of the square value of the first evaluation value corresponding to each target device and the square root of the corresponding second evaluation value to obtain the coincidence evaluation value corresponding to each target device.
10. The association method according to claim 5, wherein the step of determining a coincidence evaluation value corresponding to each of the target devices from at least one of the target images in the first sub-archive comprises:
dividing the second time period into a plurality of first sub-time periods;
determining the target images with corresponding capturing time within each first sub-time period in at least one target image in the first sub-archives to form second sub-archives corresponding to the first sub-time periods;
determining a sub-contact ratio evaluation value corresponding to each target device and each first sub-time period according to each second sub-file, wherein the sub-contact ratio evaluation value corresponding to the target device and the first sub-time period represents the contact ratio of the target device and the target object corresponding to the target file in the motion trajectory of the target object in the first sub-time period;
and determining the ratio of the sum of the sub-contact ratio evaluation values corresponding to the target devices to the number of target first sub-time periods to obtain the contact ratio evaluation value corresponding to each target device, wherein the number of the target images with corresponding capturing time in the target first sub-time periods is at least one.
11. The method according to claim 4, wherein, before the searching for the device detector to which the capturing device corresponding to each of the at least one target image in the first sub-file is bound, the method further comprises:
dividing the second time period into a plurality of second sub-time periods;
and performing duplicate removal processing on the first sub-file, so that the number of the target images corresponding to the same snapshot device in the duplicate-removed first sub-file in the same second sub-time period is at most one.
12. The method of claim 4, wherein the step of searching for the device detector bound by the capturing device corresponding to each of the at least one target image in the first sub-file, the target device detected in the corresponding first time period comprises:
determining a set of target devices, the set of target devices including the device detector within the target area, the target devices detected during the second time period;
removing illegal target devices in the target device set, and/or removing the target devices which remain static in the target device set in the second time period;
and searching the equipment detector bound by the capturing equipment corresponding to at least one target image in the target equipment set, and detecting the target equipment in the corresponding first time period.
13. The method of claim 1, wherein the target profile is plural in number, the method further comprising:
and responding to the simultaneous association of a plurality of target files and the same target equipment, and merging the plurality of target files.
14. The method of claim 13, wherein the step of merging the plurality of target profiles comprises:
determining the similarity of any two target files;
and in response to the similarity being larger than a first similarity threshold, merging the corresponding two target files.
15. The method of claim 1, further comprising:
determining the target image corresponding to the snapshot time within a third time period in the target archive to form a third sub-archive;
determining the equipment detectors bound by the snapshot equipment corresponding to each target image in the third sub-file to form a first equipment detector set;
determining that the device detector of the associated target device is acquired in the target region within the third time period to form a second device detector set;
finding a target device detector in the second set of device detectors but not in the first set of device detectors;
searching the snapshot device bound to each target device detector, and snapshotting an image in a corresponding fourth time period, wherein the starting time point and the ending time point of the fourth time period corresponding to the target device detector, and the time for the target device detector to acquire information of the associated target device are all greater than the preset time interval;
and classifying the searched image into the target file.
16. The method of claim 15, wherein the step of including the located image in the target archive comprises:
and in response to the similarity between the searched image and the target archive being greater than a second similarity threshold, classifying the target image into the target archive.
17. The method according to claim 14 or 16, wherein the first similarity threshold and the second similarity threshold are both smaller than a third similarity threshold, and wherein the target archive is obtained by clustering a plurality of images to be clustered based on the third similarity threshold in advance.
18. An electronic device, comprising a processor, a memory and a communication circuit, wherein the processor is coupled to the memory and the communication circuit, respectively, and the memory stores program data, and the processor executes the program data in the memory to realize the steps of the method according to any one of claims 1-17.
19. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executable by a processor to implement the steps in the method according to any of claims 1-17.
CN202210141708.3A 2022-02-16 2022-02-16 Association method, electronic device and computer-readable storage medium Pending CN114648056A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210141708.3A CN114648056A (en) 2022-02-16 2022-02-16 Association method, electronic device and computer-readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210141708.3A CN114648056A (en) 2022-02-16 2022-02-16 Association method, electronic device and computer-readable storage medium

Publications (1)

Publication Number Publication Date
CN114648056A true CN114648056A (en) 2022-06-21

Family

ID=81993559

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210141708.3A Pending CN114648056A (en) 2022-02-16 2022-02-16 Association method, electronic device and computer-readable storage medium

Country Status (1)

Country Link
CN (1) CN114648056A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117453942A (en) * 2023-12-21 2024-01-26 北京瑞莱智慧科技有限公司 File aggregation method, device, computer equipment and medium for driving path

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117453942A (en) * 2023-12-21 2024-01-26 北京瑞莱智慧科技有限公司 File aggregation method, device, computer equipment and medium for driving path
CN117453942B (en) * 2023-12-21 2024-03-19 北京瑞莱智慧科技有限公司 File aggregation method, device, computer equipment and medium for driving path

Similar Documents

Publication Publication Date Title
JP5479340B2 (en) Detect and classify matches between time-based media
EP2742442B1 (en) A method for detecting a copy of a reference video, corresponding apparatus for extracting a spatio-temporal signature from video data and corresponding computer readable storage medium
CN110443833B (en) Object tracking method and device
TWI425454B (en) Method, system and computer program product for reconstructing moving path of vehicle
US8266174B2 (en) Behavior history retrieval apparatus and behavior history retrieval method
CN110348143B (en) Track merging method, track merging device and storage medium
RU2505859C2 (en) Techniques for detecting video copies
CN111368622A (en) Personnel identification method and device, and storage medium
CN105279496A (en) Human face recognition method and apparatus
CN112750317A (en) Vehicle reverse running detection method, device, equipment and computer readable storage medium
WO2014193220A2 (en) System and method for multiple license plates identification
JP2014506366A (en) Method and apparatus for comparing pictures
CN114648056A (en) Association method, electronic device and computer-readable storage medium
JP2017063266A (en) Information processing method, information processing apparatus, and program
WO2023124134A1 (en) File processing method and apparatus, electronic device, computer storage medium and program
CN114219938A (en) Region-of-interest acquisition method
CN110781797B (en) Labeling method and device and electronic equipment
CN110876029B (en) Video abstract playback method and device, electronic equipment and readable storage medium
CN113220750A (en) Method and device for identifying fellow persons and computer readable storage medium
CN105320704A (en) Cross-regional similar vehicle retrieval method and device
Srilakshmi et al. Shot boundary detection using structural similarity index
CN113505788B (en) Method, device and storage medium for acquiring road network information
CN112836565B (en) Monitoring video processing method and device, monitoring system, storage medium and terminal
CN110876092B (en) Video abstract generation method and device, electronic equipment and readable storage medium
CN113268482B (en) Data association method and device and electronic equipment

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