CN113759433A - Method and device for screening contraband and security inspection equipment - Google Patents
Method and device for screening contraband and security inspection equipment Download PDFInfo
- Publication number
- CN113759433A CN113759433A CN202110924809.3A CN202110924809A CN113759433A CN 113759433 A CN113759433 A CN 113759433A CN 202110924809 A CN202110924809 A CN 202110924809A CN 113759433 A CN113759433 A CN 113759433A
- Authority
- CN
- China
- Prior art keywords
- mark
- measured
- contraband
- detected
- 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.)
- Granted
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012216 screening Methods 0.000 title claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 19
- 239000003550 marker Substances 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 238000013135 deep learning Methods 0.000 claims description 11
- 238000003384 imaging method Methods 0.000 description 13
- 238000012549 training Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000009434 installation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000012491 analyte Substances 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 230000002458 infectious effect Effects 0.000 description 2
- 230000001678 irradiating effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000002285 radioactive effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- G01V5/22—
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
- G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
Abstract
The invention discloses a contraband screening method, a device and security inspection equipment, and relates to the technical field of intelligent detection, wherein the method comprises the steps of determining a first mark of a detected object before security inspection; performing security inspection operation on the object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not; determining a second marker of the test object after the security check; and resetting the second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the number of the safety checks and the second mark. The second marks are reset for the plurality of measured objects in the object image by determining the first marks, the security inspection quantity and the second marks of the measured objects, and then whether each measured object contains contraband or not is judged, so that if the contraband exists in the measured objects, the detected objects can be positioned, and the security inspection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of intelligent detection, in particular to a contraband screening method, a contraband screening device and security inspection equipment.
Background
At present, security inspection machines are used in various industries to inspect contraband articles, such as stations, public exhibitions and postal express industries. The imaging principle of the security inspection machine is as follows: and the detected object enters the security check cavity, the X-ray source is opened, and when the package completely passes through the X-ray detection plate, the ray scanning is completed, and a corresponding X-ray image is generated. The X-ray detection plate is generally arranged in the middle position inside the security inspection cavity.
In the conventional security inspection mode, generally, an inspector checks a security inspection image to manually judge whether a detected object contains prohibited articles, if so, the corresponding detected object is taken out and then subjected to subsequent processing (such as unpacking, centralized processing and the like), and the manual security inspection processing method is not applicable to large-flow security inspection occasions or high-speed security inspection occasions.
Among the current solution, through giving the measured object automatic marking, when checking out contraband to confirm target measured object fast, but under a lot of large-traffic article security installations, the condition that a plurality of parcels were stacked can appear, gets into the security installations passageway and generates on a security installations image when a plurality of parcels, leads to can't give the accurate mark correlation image of measured object, and then leads to parcel and mark mismatch, image security installations efficiency.
Disclosure of Invention
The embodiment of the invention provides a contraband screening method, a contraband screening device and security inspection equipment, which can realize more accurate screening of target detected objects containing contraband.
The invention provides a contraband screening method on one hand, which comprises the following steps: determining a first mark of the detected object before security inspection; performing security inspection operation on the object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not; determining a second signature of the test object after security; resetting a second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the number of the safety checks and the second mark; and determining target objects containing contraband in the object images of the multiple objects to be detected.
In an embodiment, the determining a target object containing contraband in the object images of the plurality of objects to be measured includes: slicing the object image to determine the number of the measured objects contained in the object image and the spacing distance between every two adjacent measured objects; and performing security inspection operation on each measured object in the object image based on the number and the spacing distance so as to determine a target measured object containing contraband in the object image.
In an embodiment, after determining the target object containing the contraband in the object image, the method further includes: and moving the target object to a target area based on the second mark of the target object.
In an embodiment, the resetting the second mark for each measured object in the image of the object includes: and resetting the second mark of each measured object in the object image based on the number, the spacing distance and the generation time of the second mark of the measured object after the security check.
In an embodiment, the determining the target object containing the contraband in the object image includes: and carrying out contraband identification on the object image through a deep learning network model, and determining whether the detected object contains contraband.
The invention provides a security inspection device on the other hand, which comprises a security inspection device, a conveyor belt, a first counter, a second counter and a control module; the conveyor belt is arranged in the channel of the security inspection device and is used for enabling a detected object to penetrate through the channel of the security inspection device; the first counter is arranged at the entrance of the channel and used for determining a first mark of the measured object before security check; the security inspection device comprises a security inspection cavity, an X-ray source and an X-ray detection plate, and is used for performing security inspection operation on the object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not; the second counter is arranged at the rear side of the X-ray detection plate, is close to the X-ray detection plate and is used for determining a second mark of the detected object after security inspection; the control module is connected to the first counter, the second counter and the security inspection device, and is used for resetting the second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the number of the detected objects and the second mark.
In an implementation manner, the control module is further configured to determine a target object including contraband in the multiple objects to be measured in the object image, and record a second mark corresponding to the target object.
In an embodiment, the apparatus further comprises a third counter and a rejecting device; the third counter is arranged at the outlet of the security inspection device, and a preset distance is reserved between the third counter and the second technical device and used for determining a third mark of the detected object after the security inspection is finished; the removing device is arranged at the moving tail end of the conveyor belt, is connected to the control module and is used for moving the target measured object to the target area based on the second mark and the third mark corresponding to the target measured object.
In an embodiment, the moving the target object to the target area based on the second mark and the third mark corresponding to the target object includes: and under the condition that the second mark corresponding to the target object to be detected is the same as the third mark recorded by the third counter, moving the target object to be detected to the target area.
In another aspect, the present invention provides a contraband screening apparatus, including: the first marking module is used for determining a first mark of the detected object before security check; the security inspection module is used for performing security inspection operation on the object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not; the second marking module is used for determining a second mark of the detected object after security check; the resetting module is used for resetting the second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the security check quantity and the second mark; and the inspection module is used for determining a target object containing contraband in the object images of the multiple objects to be detected.
In the embodiment of the invention, the first mark, the security inspection quantity and the second mark of the detected object are determined, the second mark is reset for the plurality of detected objects in the object image, and then whether each detected object contains contraband or not is judged, so that if the detected object contains the contraband, the detected object can be positioned, and the security inspection efficiency is improved.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
FIG. 1 is a schematic diagram illustrating a flow chart of a method for screening contraband according to an embodiment of the present invention;
FIG. 2 is a block diagram of a security inspection apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural component diagram of a contraband screening apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, in one aspect, the present invention provides a method for screening contraband, including:
102, performing security inspection operation on an object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not;
104, resetting a second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the checked quantity and the second mark;
and 105, determining target objects containing contraband in the object images of the multiple objects to be detected.
In this embodiment, the method is mainly applied to security inspection equipment for inspecting contraband articles in a detected object, including infectious articles, radioactive articles, corrosive articles, control tools, and the like.
In step 101, before the object to be detected enters the security check, a first mark of the object to be detected is first acquired, where the first mark may be a security check serial number of the object to be detected entering the security check machine in sequence, and the security check serial number may be acquired by triggering counting by a sensing element pre-installed on the security check device when the object to be detected enters the security check device entrance, where the sensing element may be a pressure sensor or an infrared sensor, but is not limited thereto. The security check serial number may be obtained by scanning a specific marker (e.g., a two-dimensional code) previously attached to each object to be tested.
In step 102, after the first mark of each object to be detected is obtained, the object to be detected is moved into a security inspection machine, and contraband scanning is performed on the object to be detected, wherein the scanning mode is that the object to be detected is irradiated by using X-rays to generate a corresponding object image, and meanwhile, the number of the detected objects is recorded, and then whether the object to be detected contains the contraband can be judged through a manual inspection or image identification mode.
In step 103, after the security check of the measured object is completed, a second mark in the measured object is obtained, where the second mark may represent a security check serial number of the measured object after the security check, and the security check serial number may be obtained by triggering, during the security check of the measured object, a sensing element pre-installed on a security check device to count, where the sensing element may be a pressure sensor or an infrared sensor, but is not limited thereto. The security check serial number may be acquired by scanning a specific marker (for example, a two-dimensional code) attached to each object to be measured in advance, or by recording the security check serial number while irradiating X-rays.
In step 104, after the first mark, the number of checked objects, and the second mark are obtained, it is further determined whether the object image includes a plurality of measured objects based on the first mark, the number of checked objects, and the second mark.
The judgment process of whether a plurality of measured objects are contained is as follows:
firstly, defining that the first mark and the second mark are serial numbers, and defining the distance between the object to be detected and an X-ray trigger point in the security inspection device from the entrance as an imaging segment.
Defining: the first mark is X, the second mark is Y, the number of the checked objects is N, and the detected objects are packages.
The time when the y value is +1 at each time is taken as an observation point (non-initial state), and the state when the time t is recorded is Xt、Yt、Nt。
1. At time t + 1: if X is presentt+1＝Yt+1(imaging field without wrapping), Nt+1-NtWhen the image is not generated at this time, 0 (Y) th image is describedt+1Imaging individual packages and marking the packages;
2. at time t + 1: if X is presentt+1＞Yt+1(also within the imaging section) Nt+1-NtWhen the image is not generated at this time, Y is describedt+1Package number imaging anomaly (possibly missing or imaging a piece of the following package), marking the package (recording y value);
3. at time t +2, Y is now Yt+2If N is presentt+2-Nt+1When the image is generated at this time, Y is explainedt+1～Yt+nThe (integer) number package is imaged on a map, i.e. the object image contains a plurality of packages.
In a case where it is determined that the object image includes a plurality of measured objects, the second mark is reset for each measured object, and the setting method may specifically be: firstly, object recognition can be carried out on an object image through a neural network based on deep learning to obtain detected objects and position information, and a second mark is reset for each detected object according to the position information, wherein the neural network based on deep learning needs to be trained in advance, and training data are image information containing a plurality of detected objects.
In step 105, after the second mark is reset for each measured object, whether the image of each measured object contains contraband or not is detected, and specifically, the image similarity comparison between the image of the measured object and the image of the contraband can be performed through the existing algorithms (such as mean absolute difference algorithm (MAD), sum of absolute difference algorithm (SAD), sum of square error algorithm (SSD), and mean sum of square error algorithm (MSD)) to determine the target measured object containing the contraband.
Therefore, according to the scheme, the second marks are reset for the plurality of measured objects in the object image by determining the first marks, the security inspection quantity and the second marks of the measured objects, and then whether each measured object contains contraband or not is judged, so that if the contraband exists in the measured objects, the contraband can be positioned, and the security inspection efficiency is improved.
In one embodiment, determining a target object containing contraband in an object image of a plurality of objects to be measured includes:
slicing the object image to determine the number of the detected objects and the spacing distance between every two adjacent detected objects in the object image;
and performing security inspection operation on each measured object in the object image based on the quantity and the spacing distance so as to determine a target measured object containing contraband in the object image.
In this embodiment, the preferred method for determining the target object in step 105 is as follows:
firstly, slicing the object image, namely screening all the measured objects in the object image, wherein the slicing mode can obtain the corresponding outline position after the measured objects are determined through the neural network, slicing according to the outline position, and further obtaining the number of the measured objects and the spacing distance between every two adjacent measured objects in the object image.
Based on the number and the spacing distance, the security inspection sequence of each detected object can be determined, and the security inspection operation is performed on each detected object according to the security inspection sequence so as to determine the target detected object containing contraband in the object image.
In one embodiment, after determining the target object containing contraband in the image of the object, the method further comprises:
moving the target analyte to the target area based on the second indicia of the target analyte.
In this embodiment, after the target object is determined, the second mark of the target object is recorded.
The target measured object can be removed in a mode that the removing device and the counter are arranged at the outlet of the security inspection device, wherein the counter can record the serial number of the measured object moving to the removing device through the security inspection device, and therefore when the serial number recorded by the counter is consistent with the second mark of the target measured object, the removing device can move the target measured object to a target area, and a worker can conveniently obtain the target measured object.
In one embodiment, the resetting the second mark for each measured object in the image of the object includes:
and resetting the second mark of each measured object in the object image based on the number, the spacing distance and the generation time of the second mark of the measured object after the security check.
In this embodiment, the preferred manner of resetting the second mark for each measured object in the object image in step 104 is as follows:
the number of the measured objects in the image of the object and the generation time of the second mark at the interval distance after the security inspection of the measured objects are acquired, wherein the specific acquisition mode of the number and the interval distance is already explained above, and the generation time can be recorded while the second mark is determined.
And based on the generation time of the second mark, wherein the second mark is generally the mark of the first measured object in the object image, based on the generation time of the first measured object, the generation time of each remaining measured object in the object image is calculated according to the quantity and the interval distance, and then the second mark of each remaining measured object in the object image is determined based on the time sequence of the generation time.
In one embodiment, determining a target object containing contraband in an image of an object comprises:
and carrying out contraband identification on the object image through the deep learning network model, and determining whether the detected object contains contraband.
In this embodiment, the detection method of contraband specifically includes:
after the X-ray inspection is carried out on the measured object through the security inspection machine, an object image corresponding to each measured object is generated, wherein the object image mainly comprises the outline pattern of each object in the measured object.
And aiming at the object image, carrying out contraband identification on the object image through a deep learning network model to detect whether the detected object contains contraband, wherein the deep learning network model is a trained model, and specifically can be a convolutional neural network, a self-coding neural network and the like.
The training process of the deep learning network model comprises the following steps:
a plurality of training data including a plurality of object images including contraband and a contraband label corresponding to each object image are prepared.
Inputting a large amount of training data into the deep learning network model for pre-training so as to continuously adjust the relevant weight parameters in the model, and determining that the model training is finished when the recognition success rate reaches a preset threshold value.
In another aspect, the present invention provides a security inspection apparatus, which is shown in fig. 2 and includes a security inspection device, a conveyor belt, a first counter, a second counter, and a control module;
the conveying belt is arranged in the channel of the security inspection device and is used for enabling the detected object to penetrate through the channel of the security inspection device;
the first counter is arranged at the entrance of the channel and used for determining a first mark of the measured object before security check;
the security inspection device comprises a security inspection cavity, an X-ray source and an X-ray detection plate, and is used for performing security inspection operation on a detected object and determining an object image corresponding to the detected object and the number of the detected objects, wherein the object image is used for determining whether the detected object contains contraband or not;
the second counter is arranged at the rear side of the X-ray detection plate, is close to the X-ray detection plate and is used for determining a second mark of the detected object after security check;
the control module is connected to the first counter, the second counter and the security inspection device and used for resetting the second mark for each measured object in the object image under the condition that the plurality of measured objects are determined to be contained in the object image based on the first mark, the number of the security inspections and the second mark.
In this embodiment, the security inspection apparatus is specifically a security inspection machine, and the security inspection machine is widely applied to airports, train stations, subway stations, bus stations, government buildings, embassy, conference centers, exhibition centers, hotels, shopping malls, large-scale activities, post offices, schools, logistics industries, industrial detection, and the like.
The conveyor belt is specifically installed below the security inspection device and used for conveying the detected object from one side of the security inspection device to the other side.
The first counter is mainly an infrared sensor, a pressure sensor and the like, is particularly installed at the entrance of a channel of the security inspection device, detects the detected object or the pressure of the detected object when the detected object is conveyed to the entrance of the channel through the conveyor belt, and takes the detected times as a first mark of the detected object before the security inspection.
The security inspection device also comprises an X-ray source and an X-ray detection plate, wherein the X-ray source is positioned at the top of the security inspection device, and the X-ray detection plate is positioned at the bottom of the security inspection device. The X-ray detection plate is used for sensing that the detected object enters the security inspection device, indicating the X-ray source to shoot images of the detected object and recording the number of the detected objects.
The second counter is mainly an infrared sensor, a pressure sensor and the like, and is specifically installed at the moving rear end of the X-ray detection plate in the channel of the security inspection device, so that the second counter detects the detected object or the pressure of the detected object while the X-ray shooting is performed, and the detected times are used as a second mark of the detected object after the security inspection.
The control module is an information center for data processing and can be installed in the security inspection device. The control module is connected with the first counter, the second counter and the security inspection device at the same time, and is used for acquiring the first mark acquired by the first counter, the second mark acquired by the second counter and the recorded security inspection quantity of the security inspection device, judging whether the object image simultaneously contains a plurality of measured objects, resetting the second mark for each measured object in the object image under the condition that the object image simultaneously contains a plurality of measured objects, wherein the judging process of whether the object image contains a plurality of measured objects and the process of resetting the second mark are already set forth in the above description, and repeated description is avoided.
Therefore, according to the scheme, the second marks are reset for the plurality of measured objects in the object image by determining the first marks, the security inspection quantity and the second marks of the measured objects, and then whether each measured object contains contraband or not is judged, so that if the contraband exists in the measured objects, the contraband can be positioned, and the security inspection efficiency is improved.
In an implementation manner, the control module is further configured to determine a target object including contraband in the multiple objects to be measured in the object image, and record a second mark corresponding to the target object.
In this embodiment, the target object may be obtained by comparing and determining image similarity between an image of the object to be detected and an image of the contraband through an existing algorithm (e.g., mean absolute difference algorithm (MAD), sum of absolute differences algorithm (SAD), sum of squared errors algorithm (SSD), and sum of squared average errors algorithm (MSD)).
After the target measured object is determined, a second mark corresponding to the target measured object is recorded to be used as a parameter basis for the subsequent rejection step.
In one embodiment, the apparatus further comprises a third counter and a rejecting device;
the third counter is arranged at the outlet of the security inspection device, and a preset distance is reserved between the third counter and the second technical device and used for determining a third mark of the detected object after the security inspection is finished;
the removing device is arranged at the moving tail end of the conveyor belt, connected to the control module and used for moving the target measured object to the target area based on the second mark and the third mark corresponding to the target measured object.
In this embodiment, the third counter is also mainly specifically an infrared sensor, a pressure sensor, and the like, is installed at the outlet of the security inspection device, and is optimally installed at the moving end of the conveyor belt, and is used for recording a third mark after the security inspection of the detected object is completed, and the third mark is also like the first mark and the second mark, and is preferably used for recording a serial number of the detected object after the security inspection is completed.
The rejecting device is preferably a tilting wheel machine, particularly mounted at the end of the movement of the conveyor belt, next to the third counter, so as to synchronize as far as possible the counting time of the third counter with the rejecting movement.
The process of executing the removing action of the target measured object comprises the following steps:
when the target measured object sequentially passes through the second counter and the third counter, the second mark and the third mark are recorded respectively, and under the condition that the control module judges that the second mark and the third mark are the same, the control module sends a removing instruction to the removing device, so that the removing device moves the target measured object to a target area.
In another aspect, the present invention provides a contraband screening apparatus, as shown in fig. 3, the apparatus includes:
a first marking module 201, configured to determine a first mark of the measured object before security inspection;
the security inspection module 202 is configured to perform security inspection on the object to be inspected, and determine an object image and a security inspection quantity corresponding to the object to be inspected, where the object image is used to determine whether the object to be inspected contains contraband;
the second marking module 203 is used for determining a second mark of the detected object after the security check;
a resetting module 204, configured to reset the second mark for each measured object in the object image when it is determined that the object image includes a plurality of measured objects based on the first mark, the checked number, and the second mark;
the inspection module 205 is configured to determine a target object containing contraband in the object images of the multiple objects to be tested.
In this embodiment, the method is mainly applied to security inspection equipment for inspecting contraband articles in a detected object, including infectious articles, radioactive articles, corrosive articles, control tools, and the like.
In the first marking module 201, before the detected object enters the security check, a first mark of the detected object is first acquired, where the first mark may be a security check serial number of the detected object entering the security check machine in sequence, and the security check serial number may be acquired by triggering and counting a sensing element pre-installed on the security check device when the detected object enters the security check device inlet, where the sensing element may be a pressure sensor or an infrared sensor, but is not limited thereto. The security check serial number may be obtained by scanning a specific marker (e.g., a two-dimensional code) previously attached to each object to be tested.
In the security inspection module 202, after the first mark of each object to be detected is obtained, the object to be detected is moved into a security inspection machine to scan the object to be detected for contraband, the object to be detected is irradiated by using X-rays to generate a corresponding object image, the number of the objects to be detected is recorded, and then whether the object to be detected contains the contraband is determined by manual inspection or image recognition.
In the second marking module 203, after the security inspection of the measured object is completed, the second mark in the measured object is obtained, where the second mark may represent a security inspection serial number of the measured object after the security inspection, and the security inspection serial number is obtained by triggering, in the security inspection process of the measured object, a sensing element pre-installed on a security inspection device to count, where the sensing element may be a pressure sensor or an infrared sensor, but is not limited thereto. The security check serial number may be acquired by scanning a specific marker (for example, a two-dimensional code) attached to each object to be measured in advance, or by recording the security check serial number while irradiating X-rays.
In the resetting module 204, after the first mark, the number of checked objects, and the second mark are obtained, it is further determined whether the object image includes a plurality of objects to be measured based on the first mark, the number of checked objects, and the second mark.
The judgment process of whether a plurality of measured objects are contained is as follows:
firstly, defining that the first mark and the second mark are serial numbers, and defining the distance between the object to be detected and an X-ray trigger point in the security inspection device from the entrance as an imaging segment.
Defining: the first mark is X, the second mark is Y, the number of the checked objects is N, and the detected objects are packages.
The time when the y value is +1 at each time is taken as an observation point (non-initial state), and the state when the time t is recorded is Xt、Yt、Nt。
1. At time t + 1: if X is presentt+1＝Yt+1(imaging field without wrapping), Nt+1-NtWhen the image is not generated at this time, 0 (Y) th image is describedt+1Imaging individual packages and marking the packages;
2. at time t + 1: if X is presentt+1＞Yt+1(also within the imaging section) Nt+1-NtWhen the image is not generated at this time, Y is describedt+1Package number imaging anomaly (possibly missing or imaging a piece of the following package), marking the package (recording y value);
3. at time t +2, Y is now Yt+2If N is presentt+2-Nt+1When the image is generated at this time, Y is explainedt+1～Yt+nThe (integer) number package is imaged on a map, i.e. the object image contains a plurality of packages.
In a case where it is determined that the object image includes a plurality of measured objects, the second mark is reset for each measured object, and the setting method may specifically be: firstly, object recognition can be carried out on an object image through a neural network based on deep learning to obtain detected objects and position information, and a second mark is reset for each detected object according to the position information, wherein the neural network based on deep learning needs to be trained in advance, and training data are image information containing a plurality of detected objects.
In the inspection module 205, after the second mark is reset for each measured object, whether the image of each measured object contains contraband or not is detected, and specifically, the image similarity comparison between the image of the measured object and the image of the contraband can be performed through the existing algorithms (such as mean absolute difference algorithm (MAD), sum of absolute difference algorithm (SAD), sum of square error algorithm (SSD), and mean sum of square error algorithm (MSD)) to determine the target measured object containing the contraband.
Therefore, according to the scheme, the second marks are reset for the plurality of measured objects in the object image by determining the first marks, the security inspection quantity and the second marks of the measured objects, and then whether each measured object contains contraband or not is judged, so that if the contraband exists in the measured objects, the contraband can be positioned, and the security inspection efficiency is improved.
Another aspect of the present invention provides a computer-readable storage medium comprising a set of computer-executable instructions, which when executed, perform any one of the above methods of contraband screening.
In embodiments of the present invention, a computer-readable storage medium includes a set of computer-executable instructions that, when executed, determine a first signature of an object under test prior to a security check; performing security inspection operation on the object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not; determining a second marker of the test object after the security check; resetting the second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the number of the safety checks and the second mark; and determining target objects containing contraband in the object images of the multiple objects to be detected.
Therefore, according to the scheme, the second marks are reset for the plurality of measured objects in the object image by determining the first marks, the security inspection quantity and the second marks of the measured objects, and then whether each measured object contains contraband or not is judged, so that if the contraband exists in the measured objects, the contraband can be positioned, and the security inspection efficiency is improved.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A method for contraband screening, the method comprising:
determining a first mark of the detected object before security inspection;
performing security inspection operation on the object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not;
determining a second signature of the test object after security;
resetting a second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the number of the safety checks and the second mark;
and determining target objects containing contraband in the object images of the multiple objects to be detected.
2. The method of claim 1, wherein determining a target object containing contraband in the object images of the plurality of objects comprises:
slicing the object image to determine the number of the measured objects contained in the object image and the spacing distance between every two adjacent measured objects;
and performing security inspection operation on each measured object in the object image based on the number and the spacing distance so as to determine a target measured object containing contraband in the object image.
3. The method of claim 2, wherein after determining a target object containing contraband in the image of the object, the method further comprises:
and moving the target object to a target area based on the second mark of the target object.
4. The method of claim 2, wherein said resetting the second marker for each object under test in the image of the object comprises:
and resetting the second mark of each measured object in the object image based on the number, the spacing distance and the generation time of the second mark of the measured object after the security check.
5. The method of claim 1, wherein the determining the target object containing contraband in the image of the object comprises:
and carrying out contraband identification on the object image through a deep learning network model, and determining whether the detected object contains contraband.
6. The safety inspection equipment is characterized by comprising a safety inspection device, a conveyor belt, a first counter, a second counter and a control module;
the conveyor belt is arranged in the channel of the security inspection device and is used for enabling a detected object to penetrate through the channel of the security inspection device;
the first counter is arranged at the entrance of the channel and used for determining a first mark of the measured object before security check;
the security inspection device comprises a security inspection cavity, an X-ray source and an X-ray detection plate, and is used for performing security inspection operation on the object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not;
the second counter is arranged at the rear side of the X-ray detection plate, is close to the X-ray detection plate and is used for determining a second mark of the detected object after security inspection;
the control module is connected to the first counter, the second counter and the security inspection device, and is used for resetting the second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the number of the detected objects and the second mark.
7. The apparatus of claim 6, wherein the control module is further configured to determine a target object of the plurality of objects to be measured in the object image, the target object including contraband, and record a second mark corresponding to the target object.
8. The apparatus of claim 7, further comprising a third counter and a rejecting means;
the third counter is arranged at the outlet of the security inspection device, and a preset distance is reserved between the third counter and the second technical device and used for determining a third mark of the detected object after the security inspection is finished;
the removing device is arranged at the moving tail end of the conveyor belt, is connected to the control module and is used for moving the target measured object to the target area based on the second mark and the third mark corresponding to the target measured object.
9. The apparatus of claim 8, wherein moving the target object to the target area based on the second and third marks corresponding to the target object comprises:
and under the condition that the second mark corresponding to the target object to be detected is the same as the third mark recorded by the third counter, moving the target object to be detected to the target area.
10. An apparatus for screening contraband, the apparatus comprising:
the first marking module is used for determining a first mark of the detected object before security check;
the security inspection module is used for performing security inspection operation on the object to be inspected, and determining an object image and the number of the detected objects, wherein the object image is used for determining whether the object to be inspected contains contraband or not;
the second marking module is used for determining a second mark of the detected object after security check;
the resetting module is used for resetting the second mark for each measured object in the object image under the condition that the object image contains a plurality of measured objects based on the first mark, the security check quantity and the second mark;
and the inspection module is used for determining a target object containing contraband in the object images of the multiple objects to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110924809.3A CN113759433B (en) | 2021-08-12 | 2021-08-12 | Prohibited article screening method and device and security inspection equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110924809.3A CN113759433B (en) | 2021-08-12 | 2021-08-12 | Prohibited article screening method and device and security inspection equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113759433A true CN113759433A (en) | 2021-12-07 |
| CN113759433B CN113759433B (en) | 2024-02-27 |
Family
ID=78789157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110924809.3A Active CN113759433B (en) | 2021-08-12 | 2021-08-12 | Prohibited article screening method and device and security inspection equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113759433B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100277312A1 (en) * | 2007-02-22 | 2010-11-04 | Peter Michael Edic | In-line high-throughput contraband detection system |
| KR101305300B1 (en) * | 2012-10-11 | 2013-09-06 | 사단법인 대덕원자력포럼 | Millimeter wave search system and unified search method for freight and passenger using the system |
| US20170242148A1 (en) * | 2016-02-22 | 2017-08-24 | Rapiscan Systems, Inc. | Systems and Methods for Detecting Threats and Contraband in Cargo |
| CN207216655U (en) * | 2017-09-20 | 2018-04-10 | 重庆微标科技股份有限公司 | A kind of rays safety detection apparatus |
| CN109709619A (en) * | 2018-12-22 | 2019-05-03 | 许敬良 | Safety check luggage exports alarm system |
| CN109902643A (en) * | 2019-03-07 | 2019-06-18 | 浙江啄云智能科技有限公司 | Intelligent safety inspection method, device, system and its electronic equipment based on deep learning |
| CN110133739A (en) * | 2019-04-04 | 2019-08-16 | 南京全设智能科技有限公司 | A kind of X-ray rays safety detection apparatus and its drawing method is known automatically |
| CN110865415A (en) * | 2018-08-28 | 2020-03-06 | 浙江大华技术股份有限公司 | Security inspection method and device |
| CN111382725A (en) * | 2020-04-01 | 2020-07-07 | 上海东普信息科技有限公司 | Method, device, equipment and storage medium for processing illegal express packages |
| WO2020187077A1 (en) * | 2019-03-21 | 2020-09-24 | 长安大学 | Deep neural network-based security check system and method |
| CN112967289A (en) * | 2021-02-08 | 2021-06-15 | 上海西井信息科技有限公司 | Security check package matching method, system, equipment and storage medium |
| CN113104334A (en) * | 2021-04-16 | 2021-07-13 | 深圳蓝胖子机器智能有限公司 | Dynamic labeling method, electronic device and storage medium |
-
2021
- 2021-08-12 CN CN202110924809.3A patent/CN113759433B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100277312A1 (en) * | 2007-02-22 | 2010-11-04 | Peter Michael Edic | In-line high-throughput contraband detection system |
| KR101305300B1 (en) * | 2012-10-11 | 2013-09-06 | 사단법인 대덕원자력포럼 | Millimeter wave search system and unified search method for freight and passenger using the system |
| US20170242148A1 (en) * | 2016-02-22 | 2017-08-24 | Rapiscan Systems, Inc. | Systems and Methods for Detecting Threats and Contraband in Cargo |
| CN207216655U (en) * | 2017-09-20 | 2018-04-10 | 重庆微标科技股份有限公司 | A kind of rays safety detection apparatus |
| CN110865415A (en) * | 2018-08-28 | 2020-03-06 | 浙江大华技术股份有限公司 | Security inspection method and device |
| CN109709619A (en) * | 2018-12-22 | 2019-05-03 | 许敬良 | Safety check luggage exports alarm system |
| CN109902643A (en) * | 2019-03-07 | 2019-06-18 | 浙江啄云智能科技有限公司 | Intelligent safety inspection method, device, system and its electronic equipment based on deep learning |
| WO2020187077A1 (en) * | 2019-03-21 | 2020-09-24 | 长安大学 | Deep neural network-based security check system and method |
| CN110133739A (en) * | 2019-04-04 | 2019-08-16 | 南京全设智能科技有限公司 | A kind of X-ray rays safety detection apparatus and its drawing method is known automatically |
| CN111382725A (en) * | 2020-04-01 | 2020-07-07 | 上海东普信息科技有限公司 | Method, device, equipment and storage medium for processing illegal express packages |
| CN112967289A (en) * | 2021-02-08 | 2021-06-15 | 上海西井信息科技有限公司 | Security check package matching method, system, equipment and storage medium |
| CN113104334A (en) * | 2021-04-16 | 2021-07-13 | 深圳蓝胖子机器智能有限公司 | Dynamic labeling method, electronic device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113759433B (en) | 2024-02-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102177081B (en) | Multi-roller registered repeat defect detection of a web process line | |
| US10013615B2 (en) | Inspection methods and devices | |
| EP3346291A1 (en) | Security inspection apparatus and method | |
| US7609807B2 (en) | CT-Guided system and method for analyzing regions of interest for contraband detection | |
| CN110532852A (en) | Subway station pedestrian's accident detection method based on deep learning | |
| CN107392197A (en) | A kind of locomotive identification identification and locomotive component fault detection method and system | |
| CN114295649B (en) | Information association method, device, electronic equipment and storage medium | |
| CN110802030B (en) | Package sorting method, device and equipment and readable storage medium | |
| KR20180082956A (en) | Security Check System and Method | |
| CN105004742B (en) | A kind of ray detection quality judging method of image quality indicator and the application image quality indicator | |
| CN107855287A (en) | A kind of express delivery measurement of cargo automatic checkout system | |
| CN104267041A (en) | High-speed online detection system and method of presswork | |
| CN103425966B (en) | The method and apparatus that code is associated with part | |
| CN113759433B (en) | Prohibited article screening method and device and security inspection equipment | |
| Boos et al. | Melt pool monitoring using fuzzy based anomaly detection in laser beam melting | |
| CN109701890A (en) | Magnetic tile surface defect detection and method for sorting | |
| US20120074305A1 (en) | X-ray Backscattering Part Identification and Tagging Process and Technique | |
| KR20080028278A (en) | Optical inspection system | |
| CN116415864A (en) | Intelligent logistics quick inspection machine based on artificial intelligence | |
| CN206274312U (en) | safety inspection device | |
| US8119993B2 (en) | Method for detecting contamination on a moving object | |
| CN106353343A (en) | Small pixel transmission and multi-information fusion high-speed security check system and recognition method thereof | |
| CN206177854U (en) | System for be used for scanning imagery | |
| KR101863839B1 (en) | Method and apparatus for measuring high-speed and repetition length using image | |
| Porter et al. | Detecting, identifying, and localizing radiological material in urban environments using scan statistics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |