CN117455956A - AI technology-based man-package association tracking method and system - Google Patents
AI technology-based man-package association tracking method and system Download PDFInfo
- Publication number
- CN117455956A CN117455956A CN202311778029.8A CN202311778029A CN117455956A CN 117455956 A CN117455956 A CN 117455956A CN 202311778029 A CN202311778029 A CN 202311778029A CN 117455956 A CN117455956 A CN 117455956A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- panoramic image
- security inspection
- package
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000005516 engineering process Methods 0.000 title claims abstract description 24
- 238000007689 inspection Methods 0.000 claims abstract description 122
- 238000003384 imaging method Methods 0.000 claims abstract description 55
- 230000004913 activation Effects 0.000 claims abstract description 44
- 238000012706 support-vector machine Methods 0.000 claims abstract description 15
- 230000003213 activating effect Effects 0.000 claims abstract description 9
- 230000005540 biological transmission Effects 0.000 claims description 25
- 238000004891 communication Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
- G06T7/248—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Abstract
The invention discloses a man-package association tracking method and a man-package association tracking system based on an AI technology, which are applied to the technical field of image data processing, wherein the method comprises the following steps: and acquiring the triggering time by acquiring the first target panoramic image. And determining the activation time based on the security check machine characteristic information and the trigger time of the security check machine. And activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine. And analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package. And acquiring a second target panoramic image, and performing traversal matching on the cloud database through the binding association model to obtain a target binding association result of the target user. And carrying out personnel package association tracking of the target user and the target package according to the target binding association result. The technical problems that in the prior art, a lot of human resources are consumed in the security inspection process of personal bag association, automatic personal bag association tracking is difficult to perform, and security inspection efficiency is difficult to improve are solved.
Description
Technical Field
The invention relates to the field of image data processing, in particular to a man-package association tracking method and system based on an AI technology.
Background
Along with the increase of railway transportation passengers, the security inspection pressure is larger and larger, and when the security inspection device carries out security inspection on articles carried by the passengers, the personnel are separated from the articles carried by the passengers, and when abnormal articles are detected, the corresponding personnel are difficult to determine in time. In the prior art, security personnel are required to actively inquire or call monitoring to inquire, so that security efficiency is difficult to improve.
Therefore, in the prior art, a lot of human resources are consumed in the security inspection process, and automatic personnel package association tracking is difficult to carry out, so that the technical problem that security inspection efficiency is difficult to improve is caused.
Disclosure of Invention
The method and the system for personnel and package association tracking based on the AI technology solve the technical problems that in the prior art, a lot of human resources are consumed in personnel and package association in the security inspection process, automatic personnel and package association tracking is difficult to perform, and security inspection efficiency is difficult to improve.
The application provides a man-bag association tracking method based on an AI technology, which is applied to a man-bag association tracking system based on the AI technology, wherein the system is in communication connection with a security check machine, a front image acquisition device and a rear image acquisition device, and the method comprises the following steps: acquiring a first target panoramic image, wherein the first target panoramic image is a panoramic image with a target package of a target user, which is monitored and acquired by the front-end image acquisition equipment; acquiring trigger time, wherein the trigger time refers to time for triggering a preset line passing algorithm after the target user places the target packet in a preset belt area; determining activation time based on security check machine characteristic information of the security check machine and the trigger time; activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine, wherein the X-ray imaging refers to an X-ray imaging result of the target package; analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package; acquiring a second target panoramic image, wherein the second target panoramic image is a panoramic image with the target package, which is acquired by the rear image acquisition equipment and is monitored by the target user; performing traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user, wherein the first target panoramic image, the X-ray imaging, the target security inspection result and the second target panoramic image are stored in the cloud database; and carrying out personnel package association tracking of the target user and the target package according to the target binding association result.
The application also provides a man-package association tracking system based on AI technology, the system is in communication connection with a security check machine, a front-end image acquisition device and a rear-end image acquisition device, and the system comprises: the first image acquisition module is used for acquiring a first target panoramic image, wherein the first target panoramic image is a panoramic image with a target package of a target user, which is monitored and acquired by the front-end image acquisition equipment; the trigger time acquisition module is used for acquiring trigger time, wherein the trigger time refers to time for triggering a preset line passing algorithm after the target user places the target packet in a preset belt area; the activation time acquisition module is used for determining activation time based on the security inspection machine characteristic information of the security inspection machine and the trigger time; the imaging result acquisition module is used for activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine, wherein the X-ray imaging refers to an X-ray imaging result of the target package; the security inspection result acquisition module is used for analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package; the second image acquisition module is used for acquiring a second target panoramic image, wherein the second target panoramic image is a panoramic image with the target package, which is acquired by the rear image acquisition equipment and is monitored by the target user; the association result acquisition module is used for performing traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user, wherein the first target panoramic image, the X-ray imaging, the target security inspection result and the second target panoramic image are stored in the cloud database; and the association tracking module is used for carrying out personnel package association tracking of the target user and the target package according to the target binding association result.
The application also provides an electronic device, comprising:
a memory for storing executable instructions;
and the processor is used for realizing the man-package association tracking method based on the AI technology when executing the executable instructions stored in the memory.
The application provides a computer readable storage medium storing a computer program which, when executed by a processor, implements a person-package association tracking method based on AI technology.
According to the man-package association tracking method and system based on the AI technology, the triggering time is obtained by obtaining the first target panoramic image. And determining the activation time based on the security check machine characteristic information and the trigger time of the security check machine. And activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine. And analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package. And acquiring a second target panoramic image, and performing traversal matching on the cloud database through the binding association model to obtain a target binding association result of the target user. And carrying out personnel package association tracking of the target user and the target package according to the target binding association result. The method and the device realize automatic and accurate acquisition of the personal packet association matching result, improve the acquisition speed and the acquisition efficiency of the personal packet association, and reduce the human resources required by the acquisition of the association relationship. The technical problems that in the prior art, a lot of human resources are consumed in the security inspection process of personal bag association, automatic personal bag association tracking is difficult to perform, and security inspection efficiency is difficult to improve are solved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
Fig. 1 is a flow chart of a person-package association tracking method based on AI technology according to an embodiment of the present application;
fig. 2 is a schematic flow chart of acquiring a first target panoramic image by using a person-package association tracking method based on AI technology according to an embodiment of the present application;
fig. 3 is a schematic flow chart of acquiring activation time by using a man-package association tracking method based on AI technology according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a man-package association tracking system based on AI technology according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device of a man-package association tracking system based on AI technology according to an embodiment of the present invention.
Reference numerals illustrate: the system comprises a first image acquisition module 11, a trigger time acquisition module 12, an activation time acquisition module 13, an imaging result acquisition module 14, a security check result acquisition module 15, a second image acquisition module 16, an association result acquisition module 17, an association tracking module 18, a processor 31, a memory 32, an input device 33 and an output device 34.
Detailed Description
Example 1
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail with reference to the accompanying drawings, and the described embodiments should not be construed as limiting the present application, and all other embodiments obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.
In the following description, the terms "first", "second", "third" and the like are merely used to distinguish similar objects and do not represent a particular ordering of the objects, it being understood that the "first", "second", "third" may be interchanged with a particular order or sequence, as permitted, to enable embodiments of the application described herein to be practiced otherwise than as illustrated or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only.
While the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server, the modules are merely illustrative, and different aspects of the system and method may use different modules.
A flowchart is used in this application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
As shown in fig. 1, an embodiment of the present application provides a person-bag association tracking method based on AI technology, where the method is applied to a person-bag association tracking system based on AI technology, and the system is communicatively connected with a security check machine, a front image acquisition device and a rear image acquisition device, and the method includes:
acquiring a first target panoramic image, wherein the first target panoramic image is a panoramic image with a target package of a target user, which is monitored and acquired by the front-end image acquisition equipment;
acquiring trigger time, wherein the trigger time refers to time for triggering a preset line passing algorithm after the target user places the target packet in a preset belt area;
determining activation time based on security check machine characteristic information of the security check machine and the trigger time;
activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine, wherein the X-ray imaging refers to an X-ray imaging result of the target package;
and acquiring a first target panoramic image, wherein the first target panoramic image is a panoramic image with a target package of the target user, which is acquired by the front-end image acquisition equipment. And then, acquiring triggering time, wherein the triggering time refers to time for triggering a preset line passing algorithm after the target user places the target package in a preset belt area, the preset belt area is a belt area of a security inspection machine, the preset line passing algorithm is a position judgment algorithm in the prior art, a security inspection line is arranged on the security inspection machine in an actual scene, the security inspection line is used for indicating that a user object enters the security inspection area, the preset line passing algorithm is used for identifying the position of the security inspection object, judging whether the object passes through the security inspection line and acquiring the passing time, namely, the time for triggering the preset line passing algorithm. Further, an activation time is determined based on the security check machine characteristic information of the security check machine and the trigger time. And activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine, wherein the X-ray imaging refers to an X-ray imaging result of the target package.
As shown in fig. 2, the method provided in the embodiment of the present application further includes:
obtaining a predetermined panoramic image by the front-end image acquisition device located at the first predetermined position;
marking the preset panoramic image by using a humanoid anchor frame to obtain a preset humanoid anchor frame;
obtaining a first panoramic image time sequence through the front-end image acquisition equipment positioned at the first preset position, wherein the first panoramic image time sequence comprises a plurality of panoramic images;
acquiring a first overlapping degree of a first panoramic image and the preset humanoid anchor frame, wherein the first panoramic image is any one image in the plurality of panoramic images;
and screening according to the first overlapping degree to obtain a target image with the highest overlapping degree, and recording the target image as the first target panoramic image.
The front-end image acquisition equipment is fixed in a first preset position of the security inspection machine, a first target panoramic image is obtained, the first target panoramic image is a panoramic image with a target package of a target user, which is monitored and acquired by the front-end image acquisition equipment, and the front-end image acquisition equipment comprises: the preset panoramic image is obtained through the front-end image acquisition equipment positioned at the first preset position, and the first preset position is a fixed position of the front-end image acquisition equipment set by a professional, so that the position where the complete whole body image of the user can be acquired is ensured. And marking the human-shaped anchor frame on the preset panoramic image to obtain the preset human-shaped anchor frame, setting an optimal recognition area in the panoramic image based on professionals when marking the human-shaped anchor frame, and setting the human-shaped anchor frame in the recognition area, wherein the recognition effect is better when the overlapping rate of the recognition object passing through the human-shaped anchor frame is larger. And obtaining a first panoramic image time sequence through the front-end image acquisition equipment positioned at the first preset position, wherein the first panoramic image time sequence comprises a plurality of panoramic images with time sequence. And acquiring a first overlapping degree of the first panoramic image and the preset humanoid anchor frame, wherein the first panoramic image is any one image in the plurality of panoramic images, and the first overlapping degree is the overlapping degree of a target user and the humanoid anchor frame in the panoramic image. And screening according to the first overlapping degree to obtain a target image with the highest overlapping degree, and recording the target image as the first target panoramic image. The acquisition scheme of the second target panoramic image is consistent with that of the first target panoramic image, and only the difference of the acquisition position and the acquisition time exists.
As shown in fig. 3, the method provided in the embodiment of the present application further includes:
the security inspection machine characteristic information comprises line passing position information, belt transmission speed information and X-ray snapshot area position information of the security inspection machine;
obtaining transmission distance data based on the line passing position information and the X-ray snapshot area position information;
combining the transmission distance data and the belt transmission speed information to obtain a target transmission duration of the target packet;
and determining the activation time according to the trigger time and the target transmission time.
The characteristic information of the security inspection machine comprises line passing position information, belt transmission speed information and X-ray snapshot area position information of the security inspection machine. And obtaining transmission distance data based on the line passing position information and the X-ray snapshot area position information. And combining the transmission distance data and the belt transmission speed information to obtain the target transmission time length of the target package, wherein the target transmission time length of the target package is the delay time length of the package passing through the security inspection line to reach the position of the X-ray snapshot area. And determining the activation time according to the trigger time and the target transmission time.
Analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package;
acquiring a second target panoramic image, wherein the second target panoramic image is a panoramic image with the target package, which is acquired by the rear image acquisition equipment and is monitored by the target user;
performing traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user, wherein the first target panoramic image, the X-ray imaging, the target security inspection result and the second target panoramic image are stored in the cloud database;
and carrying out personnel package association tracking of the target user and the target package according to the target binding association result.
And analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package, and finishing dangerous goods marking of the target package. And acquiring a second target panoramic image, wherein the second target panoramic image is the panoramic image with the target package, which is acquired by the rear image acquisition equipment and is monitored by the target user. Further, traversing and matching a cloud database through a binding association model to obtain a target binding association result of the target user, wherein the first target panoramic image, the X-ray imaging, the target security inspection result and the second target panoramic image are stored in the cloud database. And realizing the association of the object user and the object user detection object result, and carrying out the personnel package association tracking of the object user and the object package according to the object binding association result. The method and the device realize automatic and accurate acquisition of the personal packet association matching result, improve the acquisition speed and the acquisition efficiency of the personal packet association, and reduce the human resources required by the acquisition of the association relationship.
The method provided by the embodiment of the application further comprises the following steps:
constructing a security inspection X-ray image database based on big data, wherein the security inspection X-ray image database comprises a plurality of historical security inspection X-ray images with historical security inspection result identifiers;
acquiring first historical image features of a first historical security inspection X-ray image, wherein the first historical security inspection X-ray image is an image with a dangerous mark in any one historical security inspection result in the plurality of historical security inspection X-ray images with the historical security inspection result marks;
and storing a dangerous feature set constructed based on the first historical image features in the security inspection support vector machine.
Before a target security inspection result of a target package is obtained, a security inspection X-ray image database is built based on big data, the security inspection X-ray image database comprises a plurality of historical security inspection X-ray images with historical security inspection result identifiers, and the historical security inspection result identifiers comprise identification results of whether security inspection passes or not and dangerous feature marks of images when the security inspection passes or not. The method comprises the steps of obtaining first historical image features of first historical security X-ray images, wherein the first historical security X-ray images are images with dangerous marks in any one of the historical security X-ray images with the historical security result identification, the first historical image features are dangerous feature marks in the first historical security X-ray images, obtaining first historical image features of the first historical security X-ray images in all the historical security X-ray images, and obtaining dangerous feature sets formed by the first historical image features. And finally, storing a dangerous feature set constructed based on the first historical image features in the security inspection support vector machine.
The method provided by the embodiment of the application further comprises the following steps:
an image feature recognition unit is embedded in the binding association model;
sequentially carrying out image feature recognition on the first target panoramic image and the second target panoramic image through the image feature recognition unit to respectively obtain a first image feature value and a second image feature value;
if the characteristic value deviation of the first image characteristic value and the second image characteristic value is in a first preset deviation threshold value, a first binding instruction is generated;
binding and associating the first target panoramic image and the second target panoramic image based on the first binding instruction to obtain a first binding and associating result;
and obtaining the target binding association result according to the first binding association result.
Performing traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user, wherein the cloud database stores the first target panoramic image, the X-ray imaging, the target security inspection result and the second target panoramic image, and the method comprises the following steps: and an image feature recognition unit is embedded in the binding association model, and the image feature recognition unit sequentially performs image feature recognition on the first target panoramic image and the second target panoramic image to respectively obtain a first image feature value and a second image feature value. If the characteristic value deviation of the first image characteristic value and the second image characteristic value is in a first preset deviation threshold, wherein the first preset deviation threshold is that the image characteristic is similar when the preset characteristic value deviation threshold is smaller than or equal to the first preset deviation threshold, and the first image characteristic value and the second image characteristic value are the same object, and a first binding instruction is generated. And carrying out binding association on the first target panoramic image and the second target panoramic image based on the first binding instruction to obtain a first binding association result. And obtaining the target binding association result according to the first binding association result.
The image feature recognition unit performs discrete cosine transform on the first target panoramic image to obtain a first discrete cosine transform coefficient;
weighting a first discrete alternating coefficient in the first discrete cosine transform coefficient to obtain a first image texture characteristic value;
and recording the first image texture characteristic value as the first image characteristic value.
And performing discrete cosine transform on the first target panoramic image based on the image characteristic recognition unit to obtain a first discrete cosine transform coefficient. And weighting a first discrete alternating coefficient in the first discrete cosine transform coefficient to obtain a first image texture characteristic value. And recording the first image texture characteristic value as the first image characteristic value. And when the second image characteristic value is obtained, performing discrete cosine transform on the second target panoramic image based on the image characteristic recognition unit, weighting a second discrete alternating coefficient in the second discrete cosine transform coefficient to obtain a second image texture characteristic value, and recording the first image texture characteristic value as the first image characteristic value.
The method provided by the embodiment of the application further comprises the following steps:
respectively acquiring a first acquisition time of the first target panoramic image and a second acquisition time of the second target panoramic image;
judging whether the activation time is between the first acquisition time and the second acquisition time;
if the time difference is in the first time difference, the activation time difference and the second time difference of the first acquisition time and the activation time are respectively acquired;
if the time deviation of the first time difference and the second time difference accords with a second preset deviation threshold value, generating a second binding instruction;
and carrying out binding association on the X-ray imaging and the first binding association result based on the second binding instruction to obtain the target binding association result, wherein the X-ray imaging is provided with the identification of the target security inspection result.
And respectively acquiring a first acquisition time of the first target panoramic image and a second acquisition time of the second target panoramic image. And judging whether the activation time is between the first acquisition time and the second acquisition time. If the time difference between the first acquisition time and the activation time is smaller than the first time difference, and the time difference between the activation time and the second acquisition time is smaller than the second time difference, the second time difference and the first time difference have smaller deviation distance, if the time difference between the first time difference and the second time difference accords with a second preset deviation threshold, the second preset deviation threshold is a preset deviation threshold, and when the time difference is smaller than or equal to the deviation threshold, the corresponding shot object of the activation time, the first target panoramic image and the second target panoramic image can be identified, and a second binding instruction is generated in a correlated mode. And carrying out binding association on the X-ray imaging and the first binding association result based on the second binding instruction to obtain the target binding association result, wherein the X-ray imaging is provided with the identification of the target security inspection result.
According to the technical scheme provided by the embodiment of the invention, the first target panoramic image is obtained, and the first target panoramic image is the panoramic image with the target package of the target user, which is monitored and collected by the front-end image collecting equipment. And acquiring triggering time, wherein the triggering time refers to the time of triggering a preset line passing algorithm after the target user places the target packet in a preset belt area. And determining the activation time based on the security check machine characteristic information of the security check machine and the trigger time. And activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine. And analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package. And acquiring a second target panoramic image, and performing traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user. And carrying out personnel package association tracking of the target user and the target package according to the target binding association result. The method and the device realize automatic and accurate acquisition of the personal packet association matching result, improve the acquisition speed and the acquisition efficiency of the personal packet association, and reduce the human resources required by the acquisition of the association relationship. The technical problems that in the prior art, a lot of human resources are consumed in the security inspection process of personal bag association, automatic personal bag association tracking is difficult to perform, and security inspection efficiency is difficult to improve are solved.
Example two
Based on the same inventive concept as the man-package association tracking method based on the AI technology in the foregoing embodiments, the present invention also provides a man-package association tracking system based on the AI technology, which can be implemented by hardware and/or software, and can be generally integrated in an electronic device, for executing the method provided by any embodiment of the present invention. As shown in fig. 4, the system is in communication connection with a security check machine, a front-end image acquisition device and a rear-end image acquisition device, and the system comprises:
a first image acquisition module 11, configured to acquire a first target panoramic image, where the first target panoramic image is a panoramic image with a target packet of a target user that is monitored and acquired by the front image acquisition device;
the trigger time obtaining module 12 is configured to obtain a trigger time, where the trigger time is a time when the target user triggers a predetermined line passing algorithm after placing the target packet in a predetermined belt area;
an activation time acquisition module 13, configured to determine an activation time based on security inspection machine feature information of the security inspection machine and the trigger time;
the imaging result obtaining module 14 is configured to activate an X-ray machine on the security inspection machine at the activation time to obtain an X-ray imaging of the X-ray machine, where the X-ray imaging is an X-ray imaging result of the target package;
the security inspection result acquisition module 15 is used for analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package;
a second image acquisition module 16, configured to acquire a second target panoramic image, where the second target panoramic image is a panoramic image with the target package of the target user that is monitored and acquired by the post-image acquisition device;
the association result obtaining module 17 is configured to perform traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user, where the cloud database stores the first target panoramic image, the X-ray imaging, the target security inspection result and the second target panoramic image;
and the association tracking module 18 is used for carrying out personal package association tracking of the target user and the target package according to the target binding association result.
Further, the first image acquisition module 11 is further configured to:
obtaining a predetermined panoramic image by the front-end image acquisition device located at the first predetermined position;
marking the preset panoramic image by using a humanoid anchor frame to obtain a preset humanoid anchor frame;
obtaining a first panoramic image time sequence through the front-end image acquisition equipment positioned at the first preset position, wherein the first panoramic image time sequence comprises a plurality of panoramic images;
acquiring a first overlapping degree of a first panoramic image and the preset humanoid anchor frame, wherein the first panoramic image is any one image in the plurality of panoramic images;
and screening according to the first overlapping degree to obtain a target image with the highest overlapping degree, and recording the target image as the first target panoramic image.
Further, the activation time acquisition module 13 is further configured to:
the security inspection machine characteristic information comprises line passing position information, belt transmission speed information and X-ray snapshot area position information of the security inspection machine;
obtaining transmission distance data based on the line passing position information and the X-ray snapshot area position information;
combining the transmission distance data and the belt transmission speed information to obtain a target transmission duration of the target packet;
and determining the activation time according to the trigger time and the target transmission time.
Further, the security check result obtaining module 15 is further configured to:
constructing a security inspection X-ray image database based on big data, wherein the security inspection X-ray image database comprises a plurality of historical security inspection X-ray images with historical security inspection result identifiers;
acquiring first historical image features of a first historical security inspection X-ray image, wherein the first historical security inspection X-ray image is an image with a dangerous mark in any one historical security inspection result in the plurality of historical security inspection X-ray images with the historical security inspection result marks;
and storing a dangerous feature set constructed based on the first historical image features in the security inspection support vector machine.
Further, the association result obtaining module 17 is further configured to:
an image feature recognition unit is embedded in the binding association model;
sequentially carrying out image feature recognition on the first target panoramic image and the second target panoramic image through the image feature recognition unit to respectively obtain a first image feature value and a second image feature value;
if the characteristic value deviation of the first image characteristic value and the second image characteristic value is in a first preset deviation threshold value, a first binding instruction is generated;
binding and associating the first target panoramic image and the second target panoramic image based on the first binding instruction to obtain a first binding and associating result;
and obtaining the target binding association result according to the first binding association result.
Further, the association result obtaining module 17 is further configured to:
the image feature recognition unit performs discrete cosine transform on the first target panoramic image to obtain a first discrete cosine transform coefficient;
weighting a first discrete alternating coefficient in the first discrete cosine transform coefficient to obtain a first image texture characteristic value;
and recording the first image texture characteristic value as the first image characteristic value.
Further, the association result obtaining module 17 is further configured to:
respectively acquiring a first acquisition time of the first target panoramic image and a second acquisition time of the second target panoramic image;
judging whether the activation time is between the first acquisition time and the second acquisition time;
if the time difference is in the first time difference, the activation time difference and the second time difference of the first acquisition time and the activation time are respectively acquired;
if the time deviation of the first time difference and the second time difference accords with a second preset deviation threshold value, generating a second binding instruction;
and carrying out binding association on the X-ray imaging and the first binding association result based on the second binding instruction to obtain the target binding association result, wherein the X-ray imaging is provided with the identification of the target security inspection result.
The included units and modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Example III
Fig. 5 is a schematic structural diagram of an electronic device provided in a third embodiment of the present invention, and shows a block diagram of an exemplary electronic device suitable for implementing an embodiment of the present invention. The electronic device shown in fig. 5 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention. As shown in fig. 5, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device may be one or more, in fig. 5, one processor 31 is taken as an example, and the processors 31, the memory 32, the input device 33 and the output device 34 in the electronic device may be connected by a bus or other means, in fig. 5, by bus connection is taken as an example.
The memory 32 is used as a computer readable storage medium for storing software programs, computer executable programs and modules, such as program instructions/modules corresponding to an AI-based person-package association tracking method in an embodiment of the present invention. The processor 31 executes various functional applications of the computer device and data processing by running software programs, instructions and modules stored in the memory 32, i.e. implements the above-described one of the man-package association tracking methods based on AI technology.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (10)
1. The utility model provides a people package association tracking method based on AI technique, its characterized in that, the method is applied to a people package association tracking system based on AI technique, the system is connected with security check machine, leading image acquisition device and post-image acquisition device communication, the method includes:
acquiring a first target panoramic image, wherein the first target panoramic image is a panoramic image with a target package of a target user, which is monitored and acquired by the front-end image acquisition equipment;
acquiring trigger time, wherein the trigger time refers to time for triggering a preset line passing algorithm after the target user places the target packet in a preset belt area;
determining activation time based on security check machine characteristic information of the security check machine and the trigger time;
activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine, wherein the X-ray imaging refers to an X-ray imaging result of the target package;
analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package;
acquiring a second target panoramic image, wherein the second target panoramic image is a panoramic image with the target package, which is acquired by the rear image acquisition equipment and is monitored by the target user;
performing traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user, wherein the first target panoramic image, the X-ray imaging, the target security inspection result and the second target panoramic image are stored in the cloud database;
and carrying out personnel package association tracking of the target user and the target package according to the target binding association result.
2. The method according to claim 1, wherein the front-end image acquisition device is fixed at a first predetermined position of the security inspection machine, and acquires a first target panoramic image, where the first target panoramic image is a panoramic image with a target package of a target user acquired by the front-end image acquisition device, and the method comprises the steps of:
obtaining a predetermined panoramic image by the front-end image acquisition device located at the first predetermined position;
marking the preset panoramic image by using a humanoid anchor frame to obtain a preset humanoid anchor frame;
obtaining a first panoramic image time sequence through the front-end image acquisition equipment positioned at the first preset position, wherein the first panoramic image time sequence comprises a plurality of panoramic images;
acquiring a first overlapping degree of a first panoramic image and the preset humanoid anchor frame, wherein the first panoramic image is any one image in the plurality of panoramic images;
and screening according to the first overlapping degree to obtain a target image with the highest overlapping degree, and recording the target image as the first target panoramic image.
3. The method of claim 1, wherein determining an activation time based on security check machine characteristic information of the security check machine and the trigger time comprises:
the security inspection machine characteristic information comprises line passing position information, belt transmission speed information and X-ray snapshot area position information of the security inspection machine;
obtaining transmission distance data based on the line passing position information and the X-ray snapshot area position information;
combining the transmission distance data and the belt transmission speed information to obtain a target transmission duration of the target packet;
and determining the activation time according to the trigger time and the target transmission time.
4. The method of claim 1, wherein analyzing the X-ray image by a security support vector machine to obtain a target security result of the target package further comprises:
constructing a security inspection X-ray image database based on big data, wherein the security inspection X-ray image database comprises a plurality of historical security inspection X-ray images with historical security inspection result identifiers;
acquiring first historical image features of a first historical security inspection X-ray image, wherein the first historical security inspection X-ray image is an image with a dangerous mark in any one historical security inspection result in the plurality of historical security inspection X-ray images with the historical security inspection result marks;
and storing a dangerous feature set constructed based on the first historical image features in the security inspection support vector machine.
5. The method of claim 1, wherein performing traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user, wherein the cloud database stores the first target panoramic image, the X-ray imaging, the target security inspection result, and the second target panoramic image, comprises:
an image feature recognition unit is embedded in the binding association model;
sequentially carrying out image feature recognition on the first target panoramic image and the second target panoramic image through the image feature recognition unit to respectively obtain a first image feature value and a second image feature value;
if the characteristic value deviation of the first image characteristic value and the second image characteristic value is in a first preset deviation threshold value, a first binding instruction is generated;
binding and associating the first target panoramic image and the second target panoramic image based on the first binding instruction to obtain a first binding and associating result;
and obtaining the target binding association result according to the first binding association result.
6. The method according to claim 5, wherein sequentially performing image feature recognition on the first target panoramic image and the second target panoramic image by the image feature recognition unit, respectively obtaining a first image feature value and a second image feature value, includes:
the image feature recognition unit performs discrete cosine transform on the first target panoramic image to obtain a first discrete cosine transform coefficient;
weighting a first discrete alternating coefficient in the first discrete cosine transform coefficient to obtain a first image texture characteristic value;
and recording the first image texture characteristic value as the first image characteristic value.
7. The method of claim 6, wherein obtaining the target binding association result from the first binding association result comprises:
respectively acquiring a first acquisition time of the first target panoramic image and a second acquisition time of the second target panoramic image;
judging whether the activation time is between the first acquisition time and the second acquisition time;
if the time difference is in the first time difference, the activation time difference and the second time difference of the first acquisition time and the activation time are respectively acquired;
if the time deviation of the first time difference and the second time difference accords with a second preset deviation threshold value, generating a second binding instruction;
and carrying out binding association on the X-ray imaging and the first binding association result based on the second binding instruction to obtain the target binding association result, wherein the X-ray imaging is provided with the identification of the target security inspection result.
8. An AI technology-based man-package association tracking system, wherein the system is in communication connection with a security check machine, a front-end image acquisition device and a rear-end image acquisition device, the system comprising:
the first image acquisition module is used for acquiring a first target panoramic image, wherein the first target panoramic image is a panoramic image with a target package of a target user, which is monitored and acquired by the front-end image acquisition equipment;
the trigger time acquisition module is used for acquiring trigger time, wherein the trigger time refers to time for triggering a preset line passing algorithm after the target user places the target packet in a preset belt area;
the activation time acquisition module is used for determining activation time based on the security inspection machine characteristic information of the security inspection machine and the trigger time;
the imaging result acquisition module is used for activating an X-ray machine on the security inspection machine under the activation time to obtain X-ray imaging of the X-ray machine, wherein the X-ray imaging refers to an X-ray imaging result of the target package;
the security inspection result acquisition module is used for analyzing the X-ray imaging through a security inspection support vector machine to obtain a target security inspection result of the target package;
the second image acquisition module is used for acquiring a second target panoramic image, wherein the second target panoramic image is a panoramic image with the target package, which is acquired by the rear image acquisition equipment and is monitored by the target user;
the association result acquisition module is used for performing traversal matching on a cloud database through a binding association model to obtain a target binding association result of the target user, wherein the first target panoramic image, the X-ray imaging, the target security inspection result and the second target panoramic image are stored in the cloud database;
and the association tracking module is used for carrying out personnel package association tracking of the target user and the target package according to the target binding association result.
9. An electronic device, the electronic device comprising:
a memory for storing executable instructions;
a processor, configured to implement the AI-technology-based people packet association tracking method of any one of claims 1 to 7 when executing the executable instructions stored in the memory.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a man-package association tracking method based on AI technology as claimed in any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311778029.8A CN117455956A (en) | 2023-12-22 | 2023-12-22 | AI technology-based man-package association tracking method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311778029.8A CN117455956A (en) | 2023-12-22 | 2023-12-22 | AI technology-based man-package association tracking method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117455956A true CN117455956A (en) | 2024-01-26 |
Family
ID=89580221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311778029.8A Pending CN117455956A (en) | 2023-12-22 | 2023-12-22 | AI technology-based man-package association tracking method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117455956A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934326A (en) * | 2015-12-29 | 2017-07-07 | 同方威视技术股份有限公司 | Method, system and equipment for safety inspection |
| CN110929066A (en) * | 2019-11-18 | 2020-03-27 | 浙江大华技术股份有限公司 | Method and device for displaying personnel and package information in association manner and security check machine |
| CN112949577A (en) * | 2021-03-29 | 2021-06-11 | 杭州海康威视数字技术股份有限公司 | Information association method, device, server and storage medium |
| CN113596590A (en) * | 2020-04-30 | 2021-11-02 | 聚好看科技股份有限公司 | Display device and play control method |
| JP2022013217A (en) * | 2020-07-03 | 2022-01-18 | 株式会社日立ソリューションズ | X-ray image processing system and x-ray image processing method |
| CN114019572A (en) * | 2021-10-11 | 2022-02-08 | 安徽太测临峰光电科技股份有限公司 | X-ray security inspection method and security inspection device based on multi-camera fusion |
| CN114677740A (en) * | 2022-04-01 | 2022-06-28 | 广州广电运通智能科技有限公司 | Person-bag association rapid person searching method, system, storage medium and terminal |
| CN115223088A (en) * | 2022-06-15 | 2022-10-21 | 北京声迅电子股份有限公司 | Security check person-bag matching system and security check person-bag matching method |
-
2023
- 2023-12-22 CN CN202311778029.8A patent/CN117455956A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934326A (en) * | 2015-12-29 | 2017-07-07 | 同方威视技术股份有限公司 | Method, system and equipment for safety inspection |
| CN110929066A (en) * | 2019-11-18 | 2020-03-27 | 浙江大华技术股份有限公司 | Method and device for displaying personnel and package information in association manner and security check machine |
| CN113596590A (en) * | 2020-04-30 | 2021-11-02 | 聚好看科技股份有限公司 | Display device and play control method |
| JP2022013217A (en) * | 2020-07-03 | 2022-01-18 | 株式会社日立ソリューションズ | X-ray image processing system and x-ray image processing method |
| CN112949577A (en) * | 2021-03-29 | 2021-06-11 | 杭州海康威视数字技术股份有限公司 | Information association method, device, server and storage medium |
| CN114019572A (en) * | 2021-10-11 | 2022-02-08 | 安徽太测临峰光电科技股份有限公司 | X-ray security inspection method and security inspection device based on multi-camera fusion |
| CN114677740A (en) * | 2022-04-01 | 2022-06-28 | 广州广电运通智能科技有限公司 | Person-bag association rapid person searching method, system, storage medium and terminal |
| CN115223088A (en) * | 2022-06-15 | 2022-10-21 | 北京声迅电子股份有限公司 | Security check person-bag matching system and security check person-bag matching method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109753928B (en) | Method and device for identifying illegal buildings | |
| CN111310645B (en) | Method, device, equipment and storage medium for warning overflow bin of goods accumulation | |
| CN110929066A (en) | Method and device for displaying personnel and package information in association manner and security check machine | |
| CN110287936B (en) | Image detection method, device, equipment and storage medium | |
| CN109754009B (en) | Article identification method, article identification device, vending system and storage medium | |
| EP3495989A1 (en) | Best image crop selection | |
| CN104573680B (en) | Image detecting method, image detection device and traffic offence detecting system | |
| US10121089B2 (en) | Object information extraction apparatus, object information extraction program, and object information extraction method | |
| CN110728754B (en) | Rigid body mark point identification method, device, equipment and storage medium | |
| CN108694399A (en) | Licence plate recognition method, apparatus and system | |
| CN108288025A (en) | A kind of car video monitoring method, device and equipment | |
| CN111666848B (en) | Method, device and equipment for detecting arrival of transport vehicle and storage medium | |
| CN108536749A (en) | The method for building personnel's Track View based on collision detection method | |
| WO2014011127A3 (en) | System for estimating gender from fingerprints | |
| CN116580357A (en) | Real-time detection method, system, equipment and storage medium for worker safety helmet | |
| CN109063567B (en) | Human body recognition method, human body recognition device and storage medium | |
| CN109558773A (en) | Information identifying method, device and electronic equipment | |
| CN113673399A (en) | Method and device for monitoring area, electronic equipment and readable storage medium | |
| CN114359792A (en) | Deep learning-based method and device for identifying insulating gloves on electric power operation site | |
| CN117455956A (en) | AI technology-based man-package association tracking method and system | |
| CN115131826A (en) | Article detection and identification method, and network model training method and device | |
| CN114140751B (en) | Examination room monitoring method and system | |
| Bourja et al. | Speed estimation using simple line | |
| CN114494355A (en) | Trajectory analysis method and device based on artificial intelligence, terminal equipment and medium | |
| CN108010020B (en) | Silicon wafer slide detection method and device |
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 |