CN114994100A - Self-service railway passenger security inspection system and detection method thereof - Google Patents
Self-service railway passenger security inspection system and detection method thereof Download PDFInfo
- Publication number
- CN114994100A CN114994100A CN202210628840.7A CN202210628840A CN114994100A CN 114994100 A CN114994100 A CN 114994100A CN 202210628840 A CN202210628840 A CN 202210628840A CN 114994100 A CN114994100 A CN 114994100A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- probability
- target
- view
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 title claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 46
- 230000000007 visual effect Effects 0.000 claims abstract description 29
- 238000005516 engineering process Methods 0.000 claims abstract description 25
- 238000010521 absorption reaction Methods 0.000 claims abstract description 12
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims description 17
- 238000010276 construction Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract 1
- 238000000034 method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- G01N23/046—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 using tomography, e.g. computed tomography [CT]
-
- 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
- G06V10/761—Proximity, similarity or dissimilarity measures
Abstract
The invention relates to the technical field of passenger security check, in particular to a self-service railway passenger security check system and a detection method thereof. Establishing a multi-view image synchronization mechanism according to the speed of a conveying belt in a security inspection conveying box and the moving position of a package; establishing image matching based on a space coordinate system, and recovering the shape of the object under multiple viewing angles; analyzing abnormal areas of the absorption characteristics of the x-rays in the main view angle image and the side view angle image respectively; respectively carrying out database matching on the characteristic abnormal region in the main visual angle image and the side visual angle image by using a template matching technology; integrating the main visual angle, the side visual angle, the target types and the similar probability matched with the multi-visual angle template, and calculating the comprehensive evaluation probability of each target by using a probability estimation formula; and outputs an abnormality target with a similarity probability exceeding 60%. The invention improves the detection probability and reduces the false alarm through a multi-view technology, gives an alarm through constraint conditions and intelligent judgment or passes judgment, and realizes self-help and high-efficiency railway safety inspection.
Description
Technical Field
The invention relates to the technical field of passenger security check, in particular to a self-service railway passenger security check system and a detection method thereof.
Background
China is the country with the longest railway transportation mileage all over the world, and billions of passengers are transported by railway every year. The contradiction between large passenger traffic and throughput of railway security inspection is increasingly obvious, passengers need to queue for long time for security inspection when entering the station at most over the metro level, and even if security inspection ports are all opened during holidays, the average queuing time of the security inspection still exceeds fifteen minutes, so that a large amount of time cost is paid.
For most long-distance passengers and short-distance passengers, because of frequent train taking, they have a finger for checking contraband at the station, and they do not carry luggage with them or carry a small amount of conventional luggage, but still need to queue up with passengers carrying restricted goods, consuming a lot of time. There is a need in the railway department to develop a self-service security check system to help these passengers pass through security check quickly, realize quick shunting, reduce average waiting time, and improve the traveling experience of passengers.
Disclosure of Invention
In order to solve the technical problems, the invention provides a self-service railway passenger security inspection system. The invention uses conventional x-ray perspective, intelligently identifies the existence of forbidden targets through images, improves the detection probability through a multi-view technology, reduces false alarms, gives an alarm through constraint conditions and intelligent judgment or passes judgment, and realizes self-service and high-efficiency railway security inspection.
The invention relates to a self-service railway passenger security check system and a detection method thereof, which adopt the following technical scheme:
a self-service railway passenger security inspection system comprises an information acquisition terminal, a central processing module and a display control terminal;
the information acquisition terminal comprises a security check transmission box, an image acquisition end and an information preprocessing module; the security inspection transmission box is arranged on the ground and is internally provided with a transmission channel; the image acquisition ends are distributed in a cross way and are all arranged on the side wall of the transmission channel; the image acquisition end is used for acquiring the classification information of all luggage packaged articles in the security check transmission box and the position information of article movement; the information preprocessing module receives information from the image acquisition end, and establishes a multi-view image synchronization mechanism according to the speed of the conveyor belt and the moving position of the package, so that objects in the package correspond to each other at different views;
the central processing module comprises an information receiving module, a space construction module, a template matching module and a core algorithm module; the information receiving module is used for receiving the signal data of the information preprocessing module; the space construction module is used for establishing image matching based on a three-dimensional space coordinate system based on the signal data of the information receiving module and recovering the shape of an object under multiple visual angles; the template matching module is used for estimating abnormal areas in the multi-view target images by using a multi-view template matching technology, giving the similarity probability of different types of targets and taking the similarity probability as a special mark area; the core algorithm module is used for calculating the comprehensive evaluation probability of each target by utilizing a probability estimation formula through integrating the target types and the similar probabilities matched with the main visual angle, the side visual angle and the multi-visual-angle template based on the object image display and the marking region;
wherein the similarity probability calculation formula of the core algorithm module is as follows:
P = MAX（P1，P2，P3） ...... ；
p1- -Primary View image match probability for a target;
p2 — side view angle image match probability for a target;
p3 — multi-view image pair some target match probability;
p- - -the integrated probability, taking its maximum value;
when P is more than or equal to 60%, detecting similar prohibited articles in the security inspection system, and automatically alarming;
the display control terminal comprises a display, an image display module, a data statistics module, an alarm lamp and a console module; the display is used for the staff to visually check all luggage packages in the conveying channel; the image display module is used for displaying the suspicious target through the display and simultaneously displaying the luggage package x-ray image and the position of the suspicious object; the data statistics module is used for visually displaying the corresponding similarity probability of the luggage package;
the alarm lamp is arranged at the output end of the conveying channel and used for prompting the passing state of self-service security check of passengers, a red lamp indicates that suspicious objects exist, and a green lamp indicates that the suspicious objects pass; the console module includes an auxiliary display screen for displaying luggage package information and an abnormal marking area on the auxiliary display screen using a console mode, reducing the possibility of others seeing except the customer himself.
Preferably, the display control terminal further comprises an anomaly analysis processing module, wherein the anomaly analysis processing module is used for recording an image with abnormal characteristics and a matching probability lower than 30% after the image is processed by the core algorithm, and reporting the image to an administrator in time; after judging, the administrator manually inputs the category of the target; and the image is used as a marked image and enters a machine database of an artificial intelligence algorithm.
Preferably, the image acquisition end adopts an X-ray camera.
Preferably, the space construction module comprises a main view module and a side view module; the main view angle module is used for analyzing the abnormal area of the absorption characteristic of the x-ray in the main view angle image and marking the abnormal area of the characteristic by utilizing a gray segmentation technology; and the side view angle module is used for analyzing the abnormal region of the absorption characteristic of the x-ray in the side view angle image and marking the abnormal region of the characteristic by utilizing a gray segmentation technology.
Preferably, the main view module and the side view module respectively match the characteristic abnormal region in the main view image and the side view image by using a template matching technology, and give the similarity probability of different types of objects.
A detection method of a self-service railway passenger security inspection system comprises the following steps:
a. establishing multi-view images synchronously; establishing a multi-view image synchronization mechanism according to the speed of a conveying belt in a security inspection conveying box and the moving position of the package, so that objects in the package correspond to each other at different views;
b. constructing a space coordinate system: according to the information provided by the synchronization mechanism, image matching based on a space coordinate system is established, and the shape of the object under multiple viewing angles is recovered;
c. analyzing abnormal areas of the absorption characteristics of the x-rays in the main view angle image and the side view angle image respectively, and marking the abnormal areas of the characteristics by utilizing a gray segmentation technology;
d. and (3) estimating an abnormal area: in a multi-view target image, estimating an abnormal area by using a multi-view template matching technology, and giving the similarity probability of different types of targets;
e. calculating the comprehensive evaluation probability: integrating the main visual angle, the side visual angle, the target types and the similar probability matched with the multi-visual angle template, and calculating the comprehensive evaluation probability of each target by using a probability estimation formula; and outputting an abnormal target with the similarity probability exceeding 60%;
f. and (4) visual display: displaying a suspicious target, a package x-ray diagram and position information of the suspicious object in an image form by using a screen through a display, and displaying the type and the similarity probability of the suspicious target in a text form;
g. and f, prompting the passing state of self-service security check of the passengers by using a warning lamp based on the similarity probability in the step f, wherein if the similarity probability is more than 60%, prompting a red lamp to alarm, wherein the red lamp is suspicious and the green lamp is normal and passes.
The invention has the beneficial effects that: the invention mainly solves the problems of finding and identifying prohibited articles in luggage packages in the railway passenger autonomous security inspection system; on the basis of X-ray imaging, after an X-ray digital perspective view of a luggage package is obtained, image matching based on double visual angles (a main visual angle and a side visual angle) is established, multi-observation image superposition is established in a double visual angle dimension space, and contraband is found and identified in a multi-angle image superposition image by using an artificial intelligence technology; the luggage package is subjected to rapid and efficient safety inspection finally by calculating the similarity probability of the object matching; the security inspection system replaces manual inspection, improves the discovery probability of contraband, reduces the labor intensity of workers, shortens the security inspection passing time of passengers, and greatly improves the efficiency of security inspection. The detection speed is improved, the judgment speed is far higher than that of manual detection by adopting an artificial intelligent detection technology, and the luggage package passing speed can be greatly improved; the detection probability is improved, in the area with small image contrast, the target is easily missed by manpower, but the contrast is detected and conveniently adjusted locally by a computer, and the target is found; in the aspect of object identification, the object identification based on template matching is far higher than manual identification; the labor intensity of manual security inspection is reduced, and a large amount of manpower is saved by using self-service security inspection; the privacy of the passengers is protected, self-service security inspection is adopted, the images do not need to be interpreted manually, and the privacy of the passengers is protected.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a block diagram of the overall architecture of the present invention;
FIG. 2 is a diagram showing the results of detecting contraband in passenger security inspection according to the present invention.
In the figure: the system comprises an information acquisition terminal, a 11-security inspection transmission box, a 12-image acquisition terminal, a 13-information preprocessing module, a 2-central processing module, a 21-information receiving module, a 22-space construction module, a 23-template matching module, a 24-core algorithm module, a 25-main visual angle module, a 26-side visual angle module, a 3-display control terminal, a 31-display, a 32-image display module, a 33-data statistics module, a 34-alarm lamp, a 35-console module and a 36-anomaly analysis processing module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that unless otherwise explicitly stated or limited, the terms "mounted," "connected" and "disposed" are to be construed broadly and can be, for example, fixedly connected, disposed, detachably connected, disposed or integrally connected and disposed. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example (b): as shown in fig. 1-2:
a self-service railway passenger security inspection system comprises an information acquisition terminal 1, a central processing module 2 and a display control terminal 3;
the information acquisition terminal 1 comprises a security check transmission box 11, an image acquisition end 12 and an information preprocessing module 13; the security inspection transmission box 11 is arranged on the ground and is internally provided with a transmission channel, and in the embodiment, the security inspection transmission box 11 comprises a box body and a transmission belt arranged in the box body; a conveying channel is formed between the box body and the conveying belt; the image acquisition ends are distributed in a cross mode and are arranged on the side wall of the conveying channel. The image acquisition end 12 is used for acquiring classification information of all luggage packaged articles in the security check transmission box and position information of article movement; the image acquisition end 12 adopts an X-ray camera.
The information preprocessing module 13 receives information from the image acquisition end, and establishes a multi-view image synchronization mechanism according to the speed of the conveyor belt and the moving position of the package, so that objects in the package correspond to each other at different views. And then, by an absorption anomaly analysis technology in the image, a segmented threshold detection mode is adopted, namely, the image with a threshold in a certain range is segmented and extracted, and the pixels in the threshold segment are relatively gathered, namely, the pixels are considered to be abnormal.
The central processing module 2 comprises an information receiving module 21, a space construction module 22, a template matching module 23 and a core algorithm module 24; the information receiving module 21 is configured to receive signal data of the information preprocessing module; the space construction module 22 establishes image matching based on a three-dimensional space coordinate system based on the signal data of the information receiving module, and restores the shape of the object under multiple viewing angles.
In the present embodiment, the space construction module 22 includes a main viewing angle module 25 and a side viewing angle module 26; the main view angle module 25 is configured to analyze an x-ray absorption characteristic abnormal region in a main view angle image, and mark the characteristic abnormal region by using a gray segmentation technology; the side view module 26 is configured to analyze the abnormal x-ray absorption characteristic region in the side view image, and mark the characteristic abnormal region by using a grayscale segmentation technique. The main view module 25 and the side view module 26 respectively match the characteristic abnormal regions in the main view image and the side view image by using a template matching technology, and provide the similarity probability of different types of objects.
The template matching module 23 is configured to estimate an abnormal region in the multi-view target image by using a multi-view template matching technology, give similarity probabilities of different types of targets, and use the similarity probabilities as special mark regions; template matching uses a sequential similar sequence detection method, and the type of a template target and the similarity probability of the accumulated target are given after template matching. The core algorithm module 24 calculates the comprehensive evaluation probability of each target by using a probability estimation formula by integrating the types and the similar probabilities of the targets matched with the main viewing angle, the side viewing angle and the multi-viewing-angle template based on the object image display and the marking region.
Wherein the similarity probability calculation formula of the core algorithm module 24 is:
P = MAX（P1，P2，P3） ...... ；
p1- -Primary View image match probability for a target;
p2 — side view angle image match probability for a target;
p3 — multi-view image pair some target match probability;
p- - -the integrated probability, taking its maximum value;
when P is more than or equal to 60%, similar prohibited articles are detected in the security inspection system, and automatic alarm is given.
The display control terminal 3 comprises a display 31, an image display module 32, a data statistics module 33, an alarm lamp 34 and a console module 35; the display 31 is used for the staff to visually check all luggage packages in the conveying channel; the image display module 32 is configured to display the suspicious target through the display, and simultaneously display the baggage package x-ray image and the position of the suspicious object; and the data statistics module 33 is used for visually displaying the corresponding similarity probability of the luggage package.
The alarm lamp 34 is arranged at the output end of the conveying channel and used for prompting the passing state of self-service security check of passengers, a red lamp indicates that suspicious objects exist, and a green lamp indicates that the suspicious objects pass; the console module 35 includes an auxiliary display screen for displaying luggage package information and abnormal marking areas on the auxiliary display screen using a console mode, reducing the possibility of others seeing except the customer himself.
In this embodiment, the display control terminal 3 further includes an anomaly analysis processing module 36, where the anomaly analysis processing module 36 is configured to record an image with abnormal features but a matching probability lower than 30% after the core algorithm is processed, and report the image to an administrator in time; after judging, the administrator manually inputs the category of the target; and the image is used as a mark image and enters a machine database of an artificial intelligence algorithm.
A detection method of a self-service railway passenger security inspection system comprises the following steps:
a. establishing multi-view images synchronously; establishing a multi-view image synchronization mechanism according to the speed of a conveying belt in a security inspection conveying box and the moving position of a package, so that objects in the package correspond to each other at different views;
b. constructing a space coordinate system: according to the information provided by the synchronization mechanism, image matching based on a space coordinate system is established, and the shape of the object under multiple viewing angles is recovered;
c. analyzing abnormal areas of the absorption characteristics of the x-rays in the main view angle image and the side view angle image respectively, and marking the abnormal areas of the characteristics by utilizing a gray segmentation technology; respectively carrying out database matching on the characteristic abnormal region in the main view angle image and the side view angle image by using a template matching technology to give the similarity probability of different types of targets;
d. estimating an abnormal area: in the multi-view target image, estimating an abnormal area by using a multi-view template matching technology, and giving the similarity probability of different types of targets;
e. calculating the comprehensive evaluation probability: integrating the main visual angle, the side visual angle, the target types and the similar probability matched with the multi-visual angle template, and calculating the comprehensive evaluation probability of each target by using a probability estimation formula; and outputting an abnormal target with the similarity probability exceeding 60%;
f. and (4) visual display: displaying a suspicious target, a package x-ray diagram and position information of the suspicious object in an image form by using a screen through a display, and displaying the type and the similarity probability of the suspicious target in a text form;
g. and f, prompting the passing state of self-service security check of the passengers by using a warning lamp based on the similarity probability in the step f, wherein if the similarity probability is more than 60%, prompting a red lamp to alarm, wherein the red lamp is suspicious and the green lamp is normal and passes. And the auxiliary display screen is installed by using a console mode, so that the possibility of others except the customer is reduced, and the privacy is ensured as much as possible. And further manually processing the images with abnormal features and a matching probability P lower than 30%. The image is recorded and reported to the administrator in time. After the administrator judges, the class of the target is manually input. The image is used as a mark image and enters a machine learning template of an artificial intelligence algorithm.
The working process is as follows:
and reading a synchronous signal of the x-ray camera, and calculating the time difference of the movement of the parcel from the center of the main viewing angle camera to the center of the side viewing angle camera according to the speed of the conveyor belt. Then, in the image sequence, the image of the luggage wrapped in the center of the main viewing angle camera is aligned with the image of the center of the side viewing angle, and the positions of all points of the images are calculated by using the viewing angle difference to form a multi-viewing-angle image. And then, by adopting an absorption anomaly analysis technology in the image, a segmented threshold detection mode is adopted, namely, the image with the threshold in a certain range is segmented and extracted, and the pixels in the threshold segment are relatively gathered, namely, the pixels are considered to be abnormal. And next, a template matching method is adopted, a sequential similar sequence detection method is used for template matching, and the category of a template target and the similar probability of the target are given after template matching. And through a similar probability calculation method, a core algorithm probability formula is used for calculation. And finally, outputting through a display screen, displaying the suspicious target and the probability thereof in a list form, and simultaneously adopting two types of red light and green light as the warning light, wherein the green light passes through, the red light is in doubt, and the warning is given out abnormally.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (6)
1. The utility model provides a self-service railway passenger security check system which characterized in that: the system comprises an information acquisition terminal, a central processing module and a display control terminal;
the information acquisition terminal comprises a security check transmission box, an image acquisition end and an information preprocessing module; the security inspection transmission box is arranged on the ground and internally provided with a transmission channel; the image acquisition ends are distributed in a cross way and are all arranged on the side wall of the transmission channel; the image acquisition end is used for acquiring the classification information of all luggage packaged articles in the security check transmission box and the position information of article movement; the information preprocessing module receives information from the image acquisition end, and establishes a multi-view image synchronization mechanism according to the speed of the conveyor belt and the moving position of the package, so that objects in the package correspond to each other at different views; a segmented threshold detection mode is adopted, namely, an image with a threshold in a certain range is segmented and extracted, and pixels in the threshold segment are relatively gathered, namely, the pixels are considered to be abnormal;
the central processing module comprises an information receiving module, a space construction module, a template matching module and a core algorithm module; the information receiving module is used for receiving the signal data of the information preprocessing module; the space construction module is used for establishing image matching based on a three-dimensional space coordinate system based on the signal data of the information receiving module and recovering the shape of an object under multiple visual angles; the template matching module is used for estimating abnormal areas in the multi-view target images by using a multi-view template matching technology, giving the similarity probability of different types of targets and taking the similarity probability as a special mark area; the core algorithm module is used for calculating the comprehensive evaluation probability of each target by integrating the target types and the similar probabilities matched with the main visual angle, the side visual angle and the multi-visual-angle template based on the object image display and the marking area and by utilizing a probability estimation formula;
wherein the similarity probability calculation formula of the core algorithm module is as follows:
P = MAX（P1，P2，P3） ...... ；
p1 — primary perspective image-to-target match probability;
p2 — side view angle image match probability for a target;
p3 — multi-view image match probability for a target;
p- - -the integrated probability, taking its maximum value;
when P is more than or equal to 60%, detecting similar prohibited articles in the security inspection system, and automatically alarming;
the display control terminal comprises a display, an image display module, a data statistics module, an alarm lamp and a console module; the display is used for the staff to visually check all luggage packages in the conveying channel; the image display module is used for displaying the suspicious target through the display and simultaneously displaying the X-ray diagram of the luggage package and the position of the suspicious object; the data statistics module is used for visually displaying the corresponding similarity probability of the luggage package;
the alarm lamp is arranged at the output end of the conveying channel and used for prompting the passing state of self-service security check of passengers, a red lamp indicates that suspicious objects exist, and a green lamp indicates that the suspicious objects pass; the console module includes an auxiliary display screen for displaying luggage package information and abnormal marking areas on the auxiliary display screen using a console mode, reducing the possibility of others seeing except the customer himself.
2. The self-service railway passenger security system of claim 1, wherein: the display control terminal also comprises an anomaly analysis processing module, wherein the anomaly analysis processing module is used for recording an image with abnormal characteristics and a matching probability lower than 30% after the core algorithm is processed, and reporting the image to an administrator in time; after judging, the administrator manually inputs the category of the target; and the image is used as a mark image and enters a machine database of an artificial intelligence algorithm.
3. The self-service railway passenger security system of claim 1, wherein: the image acquisition end adopts an X-ray camera.
4. The self-service railway passenger security system of claim 1, wherein: the space construction module comprises a main view angle module and a side view angle module; the main view angle module is used for analyzing the abnormal region of the x-ray absorption characteristic in the main view angle image and marking the abnormal region of the characteristic by utilizing a gray segmentation technology; and the side view angle module is used for analyzing the abnormal region of the absorption characteristic of the x-ray in the side view angle image and marking the abnormal region of the characteristic by utilizing a gray segmentation technology.
5. The self-service railway passenger security system of claim 4, wherein: and the main visual angle module and the side visual angle module respectively match the characteristic abnormal regions in the main visual angle image and the side visual angle image by using a template matching technology to give the similarity probability of different types of targets.
6. A detection method of a self-service railway passenger security inspection system is characterized by comprising the following steps: using a security system as claimed in any one of claims 1 to 5; and comprises the following steps:
a. establishing multi-view images synchronously; establishing a multi-view image synchronization mechanism according to the speed of a conveying belt in a security inspection conveying box and the moving position of a package, so that objects in the package correspond to each other at different views;
b. constructing a space coordinate system: according to the information provided by the synchronization mechanism, image matching based on a space coordinate system is established, and the shape of the object under multiple viewing angles is recovered;
c. analyzing abnormal areas of the absorption characteristics of the x-rays in the main view angle image and the side view angle image respectively, and marking the abnormal areas of the characteristics by utilizing a gray segmentation technology;
d. and (3) estimating an abnormal area: in the multi-view target image, estimating an abnormal area by using a multi-view template matching technology, and giving the similarity probability of different types of targets; template matching uses a sequential similar sequence detection method, and the type of a template target and the similar probability of the target are given after template matching;
e. calculating the comprehensive evaluation probability: integrating the main visual angle, the side visual angle, the target types and the similar probability matched with the multi-visual angle template, and calculating the comprehensive evaluation probability of each target by using a probability estimation formula; and outputting an abnormal target with the similarity probability exceeding 60%;
f. and (4) visual display: displaying a suspicious target, a package x-ray diagram and position information of the suspicious object in an image form by using a screen through a display, and displaying the type and the similarity probability of the suspicious target in a text form;
g. and f, prompting the passing state of self-service security check of the passengers by using a warning lamp based on the similarity probability in the step f, wherein if the similarity probability is more than 60%, prompting a red lamp to alarm, wherein the red lamp is suspicious and the green lamp is normal and passes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210628840.7A CN114994100A (en) | 2022-06-06 | 2022-06-06 | Self-service railway passenger security inspection system and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210628840.7A CN114994100A (en) | 2022-06-06 | 2022-06-06 | Self-service railway passenger security inspection system and detection method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114994100A true CN114994100A (en) | 2022-09-02 |
Family
ID=83032077
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210628840.7A Pending CN114994100A (en) | 2022-06-06 | 2022-06-06 | Self-service railway passenger security inspection system and detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114994100A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116543343A (en) * | 2023-07-06 | 2023-08-04 | 民航成都物流技术有限公司 | Method and device for detecting retained baggage, computer equipment and storage medium |
| CN116912186A (en) * | 2023-07-05 | 2023-10-20 | 山东能源集团鲁西矿业有限公司 | Method for arranging and detecting iron foreign matters in iron ore belt conveying process |
| CN117331138A (en) * | 2023-10-25 | 2024-01-02 | 广州古贤科技有限公司 | Intelligent detection system of intelligent analyzer |
| CN117331138B (en) * | 2023-10-25 | 2024-04-26 | 广州古贤科技有限公司 | Intelligent detection system of intelligent analyzer |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106886054A (en) * | 2017-04-13 | 2017-06-23 | 西安邮电大学 | Dangerous material automatic identification equipment and method based on 3 D X-ray imaging |
| GB201912428D0 (en) * | 2019-08-29 | 2019-10-16 | Sita Information Networking Computing Uk Ltd | Luggage identification via image recognition |
| CN110749934A (en) * | 2019-10-15 | 2020-02-04 | 北京中盾安民分析技术有限公司 | Automatic matching remote centralized interpretation system and method for intelligent passage of travel inspection |
| CN111126238A (en) * | 2019-12-19 | 2020-05-08 | 华南理工大学 | X-ray security inspection system and method based on convolutional neural network |
| WO2020173021A1 (en) * | 2019-02-25 | 2020-09-03 | 平安科技（深圳）有限公司 | Artificial intelligence-based forbidden object identification method, apparatus and device, and storage medium |
| CN112633286A (en) * | 2020-12-25 | 2021-04-09 | 北京航星机器制造有限公司 | Intelligent security inspection system based on similarity rate and recognition probability of dangerous goods |
| WO2021087962A1 (en) * | 2019-11-08 | 2021-05-14 | 中国科学院深圳先进技术研究院 | Automatic identification device and method for restricted articles |
| CN114187314A (en) * | 2021-12-06 | 2022-03-15 | 深圳市方吉无限科技有限公司 | Substance decision classification coloring method for X-ray of security inspection machine |
-
2022
- 2022-06-06 CN CN202210628840.7A patent/CN114994100A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106886054A (en) * | 2017-04-13 | 2017-06-23 | 西安邮电大学 | Dangerous material automatic identification equipment and method based on 3 D X-ray imaging |
| WO2020173021A1 (en) * | 2019-02-25 | 2020-09-03 | 平安科技（深圳）有限公司 | Artificial intelligence-based forbidden object identification method, apparatus and device, and storage medium |
| GB201912428D0 (en) * | 2019-08-29 | 2019-10-16 | Sita Information Networking Computing Uk Ltd | Luggage identification via image recognition |
| CN110749934A (en) * | 2019-10-15 | 2020-02-04 | 北京中盾安民分析技术有限公司 | Automatic matching remote centralized interpretation system and method for intelligent passage of travel inspection |
| WO2021087962A1 (en) * | 2019-11-08 | 2021-05-14 | 中国科学院深圳先进技术研究院 | Automatic identification device and method for restricted articles |
| CN111126238A (en) * | 2019-12-19 | 2020-05-08 | 华南理工大学 | X-ray security inspection system and method based on convolutional neural network |
| CN112633286A (en) * | 2020-12-25 | 2021-04-09 | 北京航星机器制造有限公司 | Intelligent security inspection system based on similarity rate and recognition probability of dangerous goods |
| CN114187314A (en) * | 2021-12-06 | 2022-03-15 | 深圳市方吉无限科技有限公司 | Substance decision classification coloring method for X-ray of security inspection machine |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116912186A (en) * | 2023-07-05 | 2023-10-20 | 山东能源集团鲁西矿业有限公司 | Method for arranging and detecting iron foreign matters in iron ore belt conveying process |
| CN116543343A (en) * | 2023-07-06 | 2023-08-04 | 民航成都物流技术有限公司 | Method and device for detecting retained baggage, computer equipment and storage medium |
| CN116543343B (en) * | 2023-07-06 | 2023-09-12 | 民航成都物流技术有限公司 | Method and device for detecting retained baggage, computer equipment and storage medium |
| CN117331138A (en) * | 2023-10-25 | 2024-01-02 | 广州古贤科技有限公司 | Intelligent detection system of intelligent analyzer |
| CN117331138B (en) * | 2023-10-25 | 2024-04-26 | 广州古贤科技有限公司 | Intelligent detection system of intelligent analyzer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114994100A (en) | Self-service railway passenger security inspection system and detection method thereof | |
| CN101179710B (en) | Intelligent video monitoring apparatus of railway crossing | |
| US8655078B2 (en) | Situation determining apparatus, situation determining method, situation determining program, abnormality determining apparatus, abnormality determining method, abnormality determining program, and congestion estimating apparatus | |
| CN106448180B (en) | A kind of major long tunnel traffic events real-time detection method and detection system | |
| CN104751634B (en) | The integrated application method of freeway tunnel driving image acquisition information | |
| Bas et al. | Automatic vehicle counting from video for traffic flow analysis | |
| US9940633B2 (en) | System and method for video-based detection of drive-arounds in a retail setting | |
| CN109977877B (en) | Intelligent auxiliary image judging method, system and system control method for security inspection | |
| CN108154110B (en) | Intensive people flow statistical method based on deep learning people head detection | |
| CN102982313B (en) | The method of Smoke Detection | |
| CN109948455B (en) | Detection method and device for left-behind object | |
| CN104821025B (en) | Passenger flow detection method and its detecting system | |
| CN110517501A (en) | A kind of vehicle overload early warning system and method | |
| CN111626203B (en) | Railway foreign matter identification method and system based on machine learning | |
| CN112016528B (en) | Behavior recognition method and device, electronic equipment and readable storage medium | |
| CN105005773A (en) | Pedestrian detection method with integration of time domain information and spatial domain information | |
| CN113298059A (en) | Pantograph foreign matter intrusion detection method, device, computer equipment, system and storage medium | |
| CN111259718A (en) | Escalator retention detection method and system based on Gaussian mixture model | |
| CN102110366A (en) | Block-based accumulated expressway vehicle parking event detecting method | |
| CN115600124A (en) | Subway tunnel inspection system and inspection method | |
| CN113743260A (en) | Pedestrian tracking method under dense pedestrian flow condition of subway platform | |
| CN112308032A (en) | Video detection intelligent collaborative linkage control method for underground air door | |
| CN114397712A (en) | Differentiated security check method and system for urban rail transit | |
| CN112700473B (en) | Carriage congestion degree judging system based on image recognition | |
| CN111055890B (en) | Intelligent detection method and detection system for railway vehicle anti-slip |
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 |