CN117877155A - Risk interception method based on automatic snapshot of mobile face - Google Patents
Risk interception method based on automatic snapshot of mobile face Download PDFInfo
- Publication number
- CN117877155A CN117877155A CN202410269291.8A CN202410269291A CN117877155A CN 117877155 A CN117877155 A CN 117877155A CN 202410269291 A CN202410269291 A CN 202410269291A CN 117877155 A CN117877155 A CN 117877155A
- Authority
- CN
- China
- Prior art keywords
- risk
- passenger
- luggage
- snapshot
- whole
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000004891 communication Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 230000002194 synthesizing effect Effects 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 230000037237 body shape Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000005021 gait Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000008093 supporting effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The application provides a risk interception method based on automatic snapshot of a mobile face, which is based on a luggage frame, wherein the luggage frame is provided with a camera and a luggage sensor, and the method comprises the following steps: correlating the luggage frame with the risk luggage placed in the luggage frame; after the risk baggage sensor senses the risk baggage, the camera starts wide-angle snapshot and starts focusing snapshot after the risk baggage is not sensed; acquiring local passenger characteristics from the focusing snapshot image, and matching whole-body passenger characteristics from the wide-angle snapshot image according to the local passenger characteristics; uploading the characteristics of the whole-body passengers and the characteristics of the local passengers to a server for analyzing and searching risk passengers; and intercepting the risk baggage and the risk passenger in the risk interception channel. According to the risk interception method based on automatic mobile face snapshot, the advantages of focusing snapshot and wide-angle snapshot are combined, the risk passengers are accurately analyzed and found, the mutual correlation of the luggage frame, the risk luggage and the risk passengers is achieved, and the success rate of interception is improved.
Description
Technical Field
The application belongs to the technical field of customs risk interception systems, and particularly relates to a risk interception method based on automatic snapshot of a mobile face.
Background
In the current customs risk interception system, when the centralized baggage is transported to a station for security check, a mode of diversion of people and objects is adopted, passengers enter a customs check area through a guard check area and a side check area in sequence, the baggage is transported to a baggage turntable by a conveyor belt after being checked and controlled from a baggage sorting area, and checking and controlling equipment such as an X-ray security check machine, explosive detection equipment, chemical detection equipment and the like are adopted.
If the baggage inspection abnormality is marked as abnormal baggage, the baggage inspection abnormality is tracked by sealing the baggage, and the baggage inspection abnormality is intercepted in a risk interception channel after the baggage is extracted by a passenger. However, in reality, after passengers find that the baggage is tracked, the passengers avoid the monitoring maliciously, the passengers can not accurately analyze and find the passengers carrying the abnormal baggage finally by adopting the methods of transferring bags, discarding bags, damaging the tracking device and the like in the middle of the tracking, so that the success rate of intercepting the risk passengers and the risk baggage is directly reduced.
Disclosure of Invention
An aim of the embodiment of the application is to provide a risk interception method based on automatic snapshot of a mobile face, so as to solve the technical problem that the success rate of the prior art on a risk passenger and a risk baggage interception process is insufficient.
In order to achieve the above purpose, the technical scheme adopted in the application is as follows: the risk interception method based on automatic snapshot of a mobile face is provided, and is based on a luggage frame, wherein the luggage frame is provided with a camera and a luggage sensor, and the method comprises the following steps:
correlating the luggage frame with the risk luggage placed in the luggage frame;
after the risk baggage sensor senses the risk baggage, the camera starts wide-angle snapshot and starts focusing snapshot after the risk baggage is not sensed;
acquiring local passenger characteristics from the focusing snapshot image, and matching whole-body passenger characteristics from the wide-angle snapshot image according to the local passenger characteristics;
uploading the characteristics of the whole-body passengers and the characteristics of the local passengers to a server for analyzing and searching risk passengers;
and intercepting the risk baggage and the risk passenger in the risk interception channel.
Preferably, the luggage frame is provided with two cameras, and the two cameras are arranged at intervals.
Preferably, the partial passenger features include facial features and palm features.
Preferably, after the luggage frame is placed in the frame returning device, the communication connection is automatically established between the luggage frame and a base station of the frame returning device, and the camera restarts the wide-angle snapshot.
Preferably, the method for uploading the whole-body passenger characteristics and the local passenger characteristics to a server for analyzing and searching the risk passengers comprises the following steps:
three-dimensional modeling is carried out on the whole-body passenger characteristics and the local passenger characteristics in a server, and a 3D whole-body driving real person model of the risk passenger is synthesized;
and analyzing and searching the ID of the risk passenger from the passenger registration record library based on the biological characteristics of the 3D whole-body driven real-person model.
Preferably, a method for analyzing and searching the ID of a risk passenger from a passenger registration record library based on the biological characteristics of a 3D whole body driven real person model comprises the following steps:
detecting face, sex and age group information of the risk passenger based on the 3D whole-body driving real-person model;
and analyzing and searching the ID of the risk passenger from the passenger registration record library according to the face, sex and age group information.
Preferably, after synthesizing the 3D whole-body driven real person model of the risk passenger, the method further comprises the steps of:
predicting the height and weight of the risk passenger based on the 3D whole-body driving real person model.
Preferably, after matching the whole-body passenger feature from the wide-angle snap shot image according to the local passenger feature, the method further comprises the steps of:
acquiring suspicious luggage features from the wide-angle snap images based on the whole-body passenger features;
three-dimensional modeling is carried out based on suspicious luggage characteristics, and a suspicious luggage 3D physical model is synthesized;
and splicing the suspicious luggage 3D physical model with the 3D whole-body driving real-person model to obtain the 3D passenger whole-body model of the hand-held luggage.
Preferably, the method for matching the whole-body passenger characteristics from the wide-angle snap shot image according to the local passenger characteristics comprises the following steps:
recording the state change time of the luggage sensor;
extracting wide-angle snap shot images shot by a plurality of cameras before the state change time of the Li Ganying device at intervals;
human body detection is carried out from a plurality of wide-angle snap images extracted from the frame interval, and all human body targets are obtained;
searching corresponding feature points which are most matched with the local passenger features in all human body targets;
and outputting the whole-body passenger characteristics according to the corresponding characteristic points.
Preferably, the luggage frame is further provided with a bottom boss, a control board and a power supply, the control board is electrically connected with the camera, the luggage sensor and the power supply respectively, and the bottom boss, the control board, the luggage sensor, the power supply and the camera are located on the same side of the luggage frame.
Compared with the prior art, the risk interception method based on automatic mobile face snapshot, based on the luggage frame provided with the camera and the luggage sensor, acquires local passenger characteristics from the focusing snapshot image firstly, changes the sensing state of the luggage sensor into a time boundary, matches the whole-body passenger characteristics of the passenger from the wide-angle snapshot image, integrates the advantages of focusing snapshot and wide-angle snapshot, mutually compensates the defects of the local passenger characteristics and the whole-body passenger characteristics, accurately analyzes and searches out the risk passenger, realizes the correlation of the luggage frame, the risk passenger and the risk passenger, and improves the success rate of intercepting the risk passenger and the risk luggage.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required for the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a risk interception method based on automatic mobile face snapshot provided in an embodiment of the present application;
fig. 2 is a schematic diagram of a customs risk interception system provided in an embodiment of the present application;
fig. 3 is a schematic diagram of a process for extracting a risky baggage from a risky passenger on a baggage carousel according to an embodiment of the present application;
fig. 4 is a schematic diagram of a risk passenger provided in an embodiment of the present application while extracting a risk baggage;
fig. 5 is a schematic diagram of an interception process implemented by a risk interception channel according to an embodiment of the present application;
FIG. 6 is an exemplary diagram of a carry-on baggage 3D passenger whole-body model provided in accordance with an embodiment of the present application;
fig. 7 is a schematic perspective view of a luggage frame according to an embodiment of the present disclosure;
fig. 8 is a schematic perspective view of another view of the luggage frame of fig. 7.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved by the present application more clear, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
It will be understood that when an element is referred to as being "mounted" or "disposed" on another element, it can be directly on the other element or be indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or be indirectly connected to the other element.
It is to be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate or are based on the orientation or positional relationship shown in the drawings, merely to facilitate description of the present application and simplify description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be configured and operated in a particular orientation, and therefore should not be construed as limiting the present application.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Referring to fig. 1 to 5, a risk interception method based on automatic capturing of a mobile face according to an embodiment of the present application will now be described. The risk interception method based on automatic snapshot of the mobile face is based on a luggage frame, and the luggage frame is provided with a camera and a luggage sensor, and the method comprises the following steps:
step S1, associating a luggage frame with risk luggage placed in the luggage frame;
step S2, after the risk baggage sensor senses the risk baggage, a camera starts wide-angle snapshot and starts focusing snapshot after the risk baggage is not sensed;
step S3, local passenger characteristics are obtained from the focusing snapshot image, and whole-body passenger characteristics are matched from the wide-angle snapshot image according to the local passenger characteristics;
step S4, uploading the whole-body passenger characteristics and the local passenger characteristics to a server for analyzing and searching risk passengers;
and S5, intercepting the risk baggage and the risk passenger in the risk interception channel.
It will be appreciated that referring to fig. 2 and 3, in the present embodiment, a baggage inspection anomaly may be marked as an abnormal baggage, while being transported within a baggage compartment.
In this way, in step S1, the luggage frame and the risk baggage placed in the luggage frame are correlated, and preferably, the identifiable code is provided on the luggage frame, and the correlation is performed by scanning the identifiable code on the luggage frame and the check-in code on the baggage.
In step S2, please refer to fig. 3 and 4, after the risk baggage is placed in the baggage frame, the baggage sensor is shielded, the baggage sensor starts the wide-angle snapshot after sensing the risk baggage, the wide-angle snapshot image of the surrounding environment is obtained in advance through the wide-angle snapshot, the view field in the wide-angle snapshot image is wide, and the whole-body image of the passenger on the front side of the baggage frame passing through the baggage turntable can be obtained, but the disadvantage of the wide-angle snapshot image is that the distance is far, the definition is low, and because the passengers around the baggage turntable are numerous, the risk passenger cannot be distinguished temporarily.
Once the passenger carries out the dangerous luggage, the luggage sensor is not shielded, namely, the focusing snapshot is started immediately after the Li Ganying device does not sense the dangerous luggage, at the moment, the passenger is positioned right in front of the luggage frame in a short distance, local passenger characteristics of key parts of the passenger, such as local face characteristics, can be acquired more clearly through the focusing snapshot, but the disadvantage of the focusing snapshot image is that the quantity of the acquired local passenger characteristics is small.
In step S3, referring to fig. 3 and 4, local passenger features are acquired from the focused snap images, the sensing state of the baggage sensor is changed to be a time boundary, and then the whole-body passenger features of the passenger are matched from the wide-angle snap images, so that the same passenger can be accurately found out from the wide-angle snap images snapped in advance through the same camera on the baggage frame, and the whole-body passenger features and the local passenger features of the same risk passenger before and after the risk baggage is extracted are acquired.
In step S4, the whole-body passenger characteristics and the local passenger characteristics are uploaded to a server to analyze and search for the risk passengers, the advantages of focusing snapshot and wide-angle snapshot can be integrated in the server, the defects of the local passenger characteristics and the whole-body passenger characteristics are mutually compensated, the risk passengers are accurately analyzed and searched for, and comprehensive characteristic information and identity information of the risk passengers are acquired, so that the correlation among a luggage frame, the risk baggage and the risk passengers is realized.
In step S5, referring to fig. 5, the risk interception channel is located in the customs inspection area, and the passengers arrive at the exit through the channel, and based on the comprehensive feature information and the identity information of the risk passengers acquired in step S4, the risk passengers and the risk baggage can be intercepted simultaneously through the risk interception channel. The risk interception channel may be described by referring to patent publication number CN 209962301U.
Compared with the prior art, the risk interception method based on automatic mobile face snapshot, based on the luggage frame provided with the camera and the luggage sensor, acquires local passenger characteristics from the focusing snapshot image firstly, changes the sensing state of the luggage sensor into a time boundary, matches the whole-body passenger characteristics of the passenger from the wide-angle snapshot image, integrates the advantages of focusing snapshot and wide-angle snapshot, mutually compensates the defects of the local passenger characteristics and the whole-body passenger characteristics, accurately analyzes and searches out the risk passenger, realizes the correlation of the luggage frame, the risk passenger and the risk passenger, and improves the success rate of intercepting the risk passenger and the risk luggage.
In another embodiment of the present application, please refer to fig. 7 to 8 together, the luggage frame is provided with two cameras, and the two cameras are disposed at intervals.
It will be appreciated that by providing two cameras, a greater viewing angle may be obtained. In addition, when the risk passengers extract the baggage, the short-distance focusing snapshot process can obtain focusing snapshot images from different directions, so that richer local passenger characteristics can be obtained.
Further, in step S3, the local passenger features include a face feature and a palm feature.
It will be appreciated that the local passenger features acquired from the focused snap image by the at-risk passenger at the time of baggage retrieval are facial features. After the risk passenger draws the luggage, because still need carry the luggage frame to returning frame equipment, at this moment, the passenger need stretch out the hand and get the luggage frame, still can acquire the palm portion characteristic in the focus snap-shot image that acquires through the focus snap-shot, palm portion characteristic includes palmprint or fingerprint. Meanwhile, the method is more favorable for accurately analyzing and searching the risk passengers based on the face features and the palm features, and the palm features can be used for verification after the risk passengers are intercepted.
Further, in step S2, after the luggage frame is placed in the frame returning device, the luggage frame automatically establishes communication connection with the base station of the frame returning device, and the camera restarts the wide-angle snapshot.
It will be appreciated that the frame returning device is a device for automatically recovering a luggage frame, as shown in the patent with publication number CN215278633U, where a close-range communication base station is provided at the recovery position of the frame returning device, for example, the close-range communication base station is a bluetooth communication base station, and a bluetooth device is provided in the luggage frame, after the luggage frame is placed in the frame returning device, the luggage frame and the base station of the frame returning device automatically establish communication connection, when the communication connection is established, the camera restarts the wide-angle snapshot, the passenger just leaves the luggage frame at this time and faces away from the camera, so that the camera restarts the whole-body passenger feature of the back view angle of the risk passenger after the wide-angle snapshot can be obtained. The state that the passengers approach the luggage frame is obtained by the wide-angle snapshot before the luggage is extracted by the risk passengers, and the whole-body passenger characteristics of the front view angles of the risk passengers are obtained by the camera through the wide-angle snapshot. Therefore, after the luggage frame is placed back to the frame equipment, the camera restarts the wide-angle snapshot, so that the whole-body passenger characteristics of the front view angle and the back view angle of the risk passenger can be obtained, and the accuracy of searching the risk passenger is further improved and analyzed.
It should be noted that, after the luggage frame and the base station of the frame returning device automatically establish communication connection, the image information, the associated information and the electric quantity information acquired by the camera can be uploaded to the server through the base station, and after the uploading is completed, the buffer is cleared so as to start the next cycle.
Further, in step S4, the method for uploading the whole-body passenger characteristics and the local passenger characteristics to the server to analyze and find the risky passenger includes the steps of:
three-dimensional modeling is carried out on the whole-body passenger characteristics and the local passenger characteristics in a server, and a 3D whole-body driving real person model of the risk passenger is synthesized;
and analyzing and searching the ID of the risk passenger from the passenger registration record library based on the biological characteristics of the 3D whole-body driven real-person model.
It will be appreciated that on the one hand, since the luggage frame is provided with two cameras, images can be acquired from two different angles, equivalent to a 3D camera. On the other hand, the face characteristics of the risk passengers can be acquired through focusing snapshot, the whole-body passenger characteristics of the front view angle and the back view angle of the risk passengers can be acquired through wide-angle snapshot, therefore, the realistic 3D whole-body driving real person model can be well synthesized, the face, the body shape and the gait of the passengers can be comprehensively displayed through the 3D whole-body driving real person model, analysis and searching of the identity of the risk passengers are facilitated, and workers can intercept the risk passengers in a risk interception channel according to the appearance of the 3D whole-body driving real person model.
It is worth noting that the three-dimensional modeling may be based on existing live-action three-dimensional modeling software, such as MetaShape.
Further, a method for analyzing and searching the ID of a risk passenger from a passenger registration record library based on the biological characteristics of a 3D whole body driven real person model comprises the following steps:
detecting face, sex and age group information of the risk passenger based on the 3D whole-body driving real-person model;
and analyzing and searching the ID of the risk passenger from the passenger registration record library according to the face, sex and age group information.
It is understood that detecting the face, gender, and age group information of the at-risk passenger may be based on a deep learning detection model and a classification model. Scattered features acquired from different angles are combined through the 3D whole-body driving real-person model, a more complete and clear face can be output based on the deep learning detection model, and gender and age groups can be output more accurately based on the deep learning classification model. The face, sex and age information are recorded in the passenger registration record library, so that the analysis and searching accuracy of the risk passengers is improved.
Further, after synthesizing the 3D whole-body driven real person model of the risk passenger, the method further comprises the steps of:
predicting the height and weight of the risk passenger based on the 3D whole-body driving real person model.
It can be understood that the height and the weight of the predicted risk passenger can be based on the deep learning prediction model, and when the risk interception channel intercepts the risk baggage and the risk passenger, the staff can also use the identification of the height and the weight to the risk passenger as a reference, thereby being beneficial to improving the interception success rate.
Further, referring to fig. 6, in step S3, after matching the whole-body passenger feature from the wide-angle snap shot image according to the local passenger feature, the method further includes the steps of:
acquiring suspicious luggage features from the wide-angle snap images based on the whole-body passenger features;
three-dimensional modeling is carried out based on suspicious luggage characteristics, and a suspicious luggage 3D physical model is synthesized;
and splicing the suspicious luggage 3D physical model with the 3D whole-body driving real-person model to obtain the 3D passenger whole-body model of the hand-held luggage.
It can be understood that the suspicious baggage characteristics can be obtained by detecting the baggage object in the wide-angle snap image and then calculating the distance between the baggage object and the suspicious passenger object; the method for synthesizing the 3D real model of the suspicious luggage can be based on the existing live-action three-dimensional modeling software, such as MetaShape, and the 3D real model of the suspicious luggage is spliced on the hand of the 3D whole-body driving real model on the basis. Therefore, when the risk interception channel intercepts the risk baggage and the risk passenger, the staff can further improve the interception success rate according to the whole body model of the 3D passenger of the hand baggage as a reference.
In another embodiment of the present application, in step S4, a method for matching whole-body passenger features from a wide-angle snap image according to local passenger features includes the steps of:
recording the state change time of the luggage sensor;
extracting wide-angle snap shot images shot by a plurality of cameras before the state change time of the Li Ganying device at intervals;
human body detection is carried out from a plurality of wide-angle snap images extracted from the frame interval, and all human body targets are obtained;
searching corresponding feature points which are most matched with the local passenger features in all human body targets;
and outputting the whole-body passenger characteristics according to the corresponding characteristic points.
It will be appreciated that finding the closest matching corresponding feature point may be accomplished by calculating the distance or similarity between feature points. One common distance metric method is euclidean distance or hamming distance, and cosine similarity or correlation coefficient can be used for similarity measurement.
To improve the accuracy and robustness of the matches, some mechanism may be used to filter false matches. For example, a geometric consistency-based approach combines feature-based matching results with geometric attributes of the image, screening out high quality matches by limits on translation, rotation, and scaling of the matches.
Therefore, the embodiment realizes that the whole-body passenger characteristics of the risk passenger before the Li Ganying device state change time are found out based on the focusing snap-shot image acquired after the Li Ganying device state change time.
In another embodiment of the present application, referring to fig. 7 and 8, the luggage frame is further provided with a bottom boss 10, a control board 20 and a power source 30, wherein the control board 20 is electrically connected with the camera 40, the luggage sensor 50 and the power source 30, respectively, and the bottom boss 10, the control board 20, the luggage sensor 50, the power source 30 and the camera 40 are located on the same side of the luggage frame.
It will be appreciated that the control board 20 is used to convert, store and transmit the acquired information, and the power supply 30 is used to provide electrical power. Because the bottom surface boss 10, the control panel 20, the luggage inductor 50, the power supply 30 and the camera 40 are located on the same side of the luggage frame, after the risk luggage is placed in the luggage frame, the luggage frame can be inclined by a certain angle under the supporting action of the bottom surface boss 10 under the action of gravity, so that the camera 40 is driven to deflect downwards, at this moment, the camera 40 is started to take a snapshot in a wide angle to obtain a wider view, and after the luggage is taken, the control panel 20, the luggage inductor 50, the power supply 30, the camera 40 and other objects are driven to deflect upwards under the action of gravity, so that the camera 40 starts to take a snapshot in a focusing mode, and just the face of a person is shot. Therefore, the effects of automatic zooming and shooting angle adjustment are achieved through the combination of the luggage extraction flow and the hardware and the structure of the luggage frame, the quality of the focusing snap-shot image and the quality of the wide-angle snap-shot image are improved, and the characteristics of more effective risk passengers are facilitated to be obtained.
The foregoing description of the preferred embodiments of the present application is not intended to be limiting, but is intended to cover any and all modifications, equivalents, and alternatives falling within the spirit and principles of the present application.
Claims (10)
1. The risk interception method based on automatic snapshot of the mobile face is characterized by comprising the following steps of:
correlating the luggage frame with the risk luggage placed in the luggage frame;
after the risk baggage sensor senses the risk baggage, the camera starts wide-angle snapshot and starts focusing snapshot after the risk baggage is not sensed;
acquiring local passenger characteristics from the focusing snapshot image, and matching whole-body passenger characteristics from the wide-angle snapshot image according to the local passenger characteristics;
uploading the characteristics of the whole-body passengers and the characteristics of the local passengers to a server for analyzing and searching risk passengers;
and intercepting the risk baggage and the risk passenger in the risk interception channel.
2. A risk interception method based on automatic mobile face snapshot as recited in claim 1, wherein the luggage frame is provided with two cameras, and the two cameras are arranged at intervals.
3. A risk interception method based on automatic mobile face capture as recited in claim 2, wherein said partial passenger features include face features and palm features.
4. A risk interception method based on automatic mobile face snapshot as claimed in claim 2 or 3, wherein after the luggage frame is placed in the frame returning device, the luggage frame automatically establishes communication connection with the base station of the frame returning device, and the camera restarts the wide-angle snapshot.
5. The automatic mobile face snapshot based risk interception method of claim 4 wherein uploading whole-body passenger features and local passenger features to a server analysis and risk-finding method comprises the steps of:
three-dimensional modeling is carried out on the whole-body passenger characteristics and the local passenger characteristics in a server, and a 3D whole-body driving real person model of the risk passenger is synthesized;
and analyzing and searching the ID of the risk passenger from the passenger registration record library based on the biological characteristics of the 3D whole-body driven real-person model.
6. The mobile face automatic snapshot based risk interception method of claim 5, wherein the method for analyzing and searching for an ID of a risk passenger from a passenger registration record base based on a biometric of a 3D whole body driven real person model comprises:
detecting face, sex and age group information of the risk passenger based on the 3D whole-body driving real-person model;
and analyzing and searching the ID of the risk passenger from the passenger registration record library according to the face, sex and age group information.
7. The risk interception method based on automatic mobile face snapshot of claim 5, further comprising the steps of, after synthesizing a 3D whole-body driven real person model of a risk passenger:
predicting the height and weight of the risk passenger based on the 3D whole-body driving real person model.
8. The automatic mobile face snapshot based risk interception method of claim 5, further comprising the steps of, after matching whole-body passenger features from the wide-angle snapshot image based on the local passenger features:
acquiring suspicious luggage features from the wide-angle snap images based on the whole-body passenger features;
three-dimensional modeling is carried out based on suspicious luggage characteristics, and a suspicious luggage 3D physical model is synthesized;
and splicing the suspicious luggage 3D physical model with the 3D whole-body driving real-person model to obtain the 3D passenger whole-body model of the hand-held luggage.
9. A risk interception method based on automatic mobile face snapshot as recited in claim 1, wherein the method for matching whole-body passenger features from wide-angle snapshot images based on local passenger features comprises the steps of:
recording the state change time of the luggage sensor;
extracting wide-angle snap shot images shot by a plurality of cameras before the state change time of the Li Ganying device at intervals;
human body detection is carried out from a plurality of wide-angle snap images extracted from the frame interval, and all human body targets are obtained;
searching corresponding feature points which are most matched with the local passenger features in all human body targets;
and outputting the whole-body passenger characteristics according to the corresponding characteristic points.
10. A risk interception method based on automatic mobile face snap-shots according to claim 1, wherein said luggage frame is further provided with a bottom surface boss, a control board and a power supply, said control board is electrically connected with said camera, said luggage sensor and said power supply, respectively, said bottom surface boss, said control board, said luggage sensor, said power supply and said camera are located on the same side of said luggage frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410269291.8A CN117877155B (en) | 2024-03-11 | Risk interception method based on automatic snapshot of mobile face |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410269291.8A CN117877155B (en) | 2024-03-11 | Risk interception method based on automatic snapshot of mobile face |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117877155A true CN117877155A (en) | 2024-04-12 |
| CN117877155B CN117877155B (en) | 2024-05-28 |
Family
ID=
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005055151A1 (en) * | 2003-12-03 | 2005-06-16 | Hitachi, Ltd. | Boarding security check system and method and computer program |
| US20170083768A1 (en) * | 2015-09-21 | 2017-03-23 | Nuctech Company Limited | Smart security inspection system and method |
| CN109711290A (en) * | 2018-12-13 | 2019-05-03 | 深圳三人行在线科技有限公司 | A kind of iris identification method and equipment based on dual camera |
| CN111530777A (en) * | 2020-04-20 | 2020-08-14 | 思百达物联网科技(北京)有限公司 | Self-service luggage article security inspection channel and method |
| CA3141235A1 (en) * | 2019-06-11 | 2020-12-17 | Franz Spitzer | System and method for controlling baggage |
| CN113408391A (en) * | 2021-06-15 | 2021-09-17 | 青岛民航凯亚系统集成有限公司 | Passenger hand-held luggage tracking and checking method and system based on face recognition and RFID |
| CN215642755U (en) * | 2021-07-13 | 2022-01-25 | 中华人民共和国济南海关 | Hidden marking system for illegal luggage in customs inspection |
| CN116957890A (en) * | 2023-07-17 | 2023-10-27 | 盛视科技股份有限公司 | Luggage pre-inspection risk interception method |
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005055151A1 (en) * | 2003-12-03 | 2005-06-16 | Hitachi, Ltd. | Boarding security check system and method and computer program |
| US20170083768A1 (en) * | 2015-09-21 | 2017-03-23 | Nuctech Company Limited | Smart security inspection system and method |
| CN109711290A (en) * | 2018-12-13 | 2019-05-03 | 深圳三人行在线科技有限公司 | A kind of iris identification method and equipment based on dual camera |
| CA3141235A1 (en) * | 2019-06-11 | 2020-12-17 | Franz Spitzer | System and method for controlling baggage |
| CN111530777A (en) * | 2020-04-20 | 2020-08-14 | 思百达物联网科技(北京)有限公司 | Self-service luggage article security inspection channel and method |
| CN113408391A (en) * | 2021-06-15 | 2021-09-17 | 青岛民航凯亚系统集成有限公司 | Passenger hand-held luggage tracking and checking method and system based on face recognition and RFID |
| CN215642755U (en) * | 2021-07-13 | 2022-01-25 | 中华人民共和国济南海关 | Hidden marking system for illegal luggage in customs inspection |
| CN116957890A (en) * | 2023-07-17 | 2023-10-27 | 盛视科技股份有限公司 | Luggage pre-inspection risk interception method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108256459B (en) | Security check door face recognition and face automatic library building algorithm based on multi-camera fusion | |
| CN109934176B (en) | Pedestrian recognition system, recognition method, and computer-readable storage medium | |
| US8116534B2 (en) | Face recognition apparatus and face recognition method | |
| CN107305627B (en) | Vehicle video monitoring method, server and system | |
| US9432632B2 (en) | Adaptive multi-modal integrated biometric identification and surveillance systems | |
| WO2019154384A1 (en) | System combining biological recognition and intelligent verification | |
| EP2620896B1 (en) | System And Method For Face Capture And Matching | |
| US8254633B1 (en) | Method and system for finding correspondence between face camera views and behavior camera views | |
| CN113759431B (en) | Security data association method and device and X-ray security system | |
| US20070291998A1 (en) | Face authentication apparatus, face authentication method, and entrance and exit management apparatus | |
| CN1898678A (en) | Method for acquiring human-face image, human-face discrimination and discriminating system | |
| JP2006133946A (en) | Moving object recognition device | |
| CN112307868B (en) | Image recognition method, electronic device, and computer-readable medium | |
| CN108960124A (en) | The image processing method and device identified again for pedestrian | |
| RU2315352C2 (en) | Method and system for automatically finding three-dimensional images | |
| CN111627139A (en) | Library face recognition and temperature measurement integrated safety door and detection method | |
| CN117877155B (en) | Risk interception method based on automatic snapshot of mobile face | |
| CN117877155A (en) | Risk interception method based on automatic snapshot of mobile face | |
| Islam et al. | Correlating belongings with passengers in a simulated airport security checkpoint | |
| CN110874568A (en) | Security check method and device based on gait recognition, computer equipment and storage medium | |
| CN113065491A (en) | Multi-shooting-based passenger flow statistical method and system | |
| CN114677608A (en) | Identity feature generation method, device and storage medium | |
| CN111723610A (en) | Image recognition method, device and equipment | |
| CN117152826B (en) | Real-time cross-mirror tracking method based on target tracking and anomaly detection | |
| CN113920325B (en) | Method for reducing object recognition image quantity based on infrared image feature points |
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 |