An automatic identification system for prohibited items in airport security inspection
Through multi-dimensional data collection and comprehensive analysis methods, an automatic identification system for contraband inspections at airport security inspections has been established, which has solved the problems of low efficiency and poor accuracy of traditional security inspections, and has achieved efficient and accurate identification and processing of contrabands.
Patent Information
- Application Number
- CN202411156900.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-08-22
AI Technical Summary
Traditional airport security inspection methods are inefficient and prone to misjudgment. Single data collection and analysis cannot fully and accurately identify various contraband items, making it difficult to guarantee the accuracy and consistency of the identification results.
Adopt multi-dimensional data acquisition end and security inspection platform, including X-ray data acquisition module, millimeter wave data acquisition module, odor data acquisition module and identity data acquisition module, through data sorting, luggage three-dimensional model construction, primary analysis and secondary analysis modules , combined with a variety of detection methods and data analysis methods, automatically identify contraband and generate alert information.
It greatly reduces the possibility of missed inspection of contraband products, improves the speed and accuracy of security inspection, reduces manual intervention and misjudgment, and ensures the clarity and consistency of security inspection procedures.
Smart Images

Figure CN118671858B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of airport security inspection, in particular to an automatic identification system for prohibited items in airport security inspection. Background Art
[0002] Traditional airport security inspection methods mainly rely on manual inspection and simple equipment detection, which is inefficient and prone to misjudgment. Manual inspection not only consumes a lot of time and manpower, but the subjective judgment of security inspectors may be affected by many factors, making it difficult to ensure the accuracy and consistency of security inspection results.
[0003] In addition, relying solely on a single type of data collection and analysis is often unable to fully and accurately identify various types of contraband; different types of contraband have different physical characteristics and chemical properties, and require a combination of multiple detection means and data analysis methods to improve identification accuracy.
[0004] Therefore, in view of the above problems, an automatic identification system for prohibited items in airport security is proposed. Summary of the invention
[0005] The purpose of the present invention is to provide an automatic identification system for prohibited items in airport security inspection to solve the problems raised in the above-mentioned background technology.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] An automatic identification system for prohibited items in airport security inspection, comprising:
[0008] Data collection end: The data collection end includes an X-ray data collection module, a millimeter wave data collection module, an odor data collection module, and an identity data collection module, which respectively collect user identity data, human millimeter wave image data, human odor data, luggage X-ray image data, luggage millimeter wave image data, and luggage odor data of the user and luggage;
[0009] Security inspection platform; the security inspection platform includes data sorting module, baggage 3D model building module, primary analysis module, secondary analysis module and alarm module;
[0010] The data sorting module receives the user identity data, establishes the security check process timeline belonging to the user according to the user identity data and the user flight information, arranges the identity confirmation time node, the human body security check time node, the luggage first-level security check time node and the luggage second-level security check time node on the security check process timeline in chronological order, synchronizes the human body millimeter wave image data and human body odor data to the human body security check time node, synchronizes the luggage X-ray image data to the luggage first-level security check time node, and synchronizes the luggage millimeter wave image data and luggage odor data to the luggage second-level security check time node;
[0011] After receiving the security inspection process timeline, the luggage 3D model building module retrieves the luggage X-ray image data in the first-level security inspection time node of the luggage, builds a 3D model of the luggage according to the luggage X-ray image data, determines the 3D coordinates of each item in the luggage according to the 3D model of the luggage, and marks the 3D coordinates of the items in the luggage on the 3D model of the luggage;
[0012] The primary analysis module receives the three-dimensional model of the suitcase, identifies each item in the three-dimensional model of the suitcase, determines whether the identified items are prohibited items, and generates an alarm message when the items are determined to be prohibited items; unidentified items are marked as unknown on the three-dimensional model of the suitcase;
[0013] The secondary analysis module receives the three-dimensional model of the suitcase with unknown marks, determines the location information of the unrecognizable items, receives the millimeter wave image data of the suitcase and the odor data of the suitcase, performs secondary analysis and identification on the unrecognizable items in combination with the millimeter wave image data of the suitcase and the odor data of the suitcase, determines whether the unrecognizable items are contraband items, and generates an alarm message when the items are determined to be contraband items;
[0014] After receiving the alarm information, the alarm module determines the attributes of the item corresponding to the alarm information and synchronizes the alarm information to the security personnel, who then handle the items and users according to the attributes of the prohibited items.
[0015] Preferably, the X-ray data acquisition module is a plurality of X-ray detectors arranged in an arc shape on the transmission channel of the luggage security inspection machine. The X-ray data acquisition module is used at the first-level security inspection time node of the luggage compartment to perform multi-angle X-ray image data acquisition on the luggage passing through the luggage security inspection machine to obtain the luggage compartment X-ray image data.
[0016] Preferably, when building a three-dimensional model of the suitcase, the acquired X-ray image data of the suitcase is denoised and enhanced to obtain pre-processed X-ray image data of the suitcase, and key feature information of each item is extracted from the pre-processed X-ray image, the key feature information including edge, shape, and texture; a method based on multi-view geometry is used to calculate the three-dimensional coordinates of the object in combination with X-ray images taken at different angles, and a three-dimensional model of the suitcase and the items is constructed in combination with the key feature information of each item; the three-dimensional model of the item is synchronized to the three-dimensional model of the suitcase according to the three-dimensional coordinates of each item, and the construction of the three-dimensional model of the suitcase is completed.
[0017] Preferably, the millimeter wave data acquisition module includes a millimeter wave security inspection gate arranged at a human body security inspection time node and a millimeter wave detector arranged at a luggage compartment secondary security inspection time node, the millimeter wave security inspection gate collects human body millimeter wave image data, and the millimeter wave detector collects luggage compartment millimeter wave image data; the odor data acquisition module includes a first odor detector and a second odor detector arranged at the human body security inspection time node and the luggage compartment secondary security inspection time node, the first odor detector and the second odor detector respectively collect human body odor data and luggage compartment odor data for collection.
[0018] Preferably, the millimeter wave detector and the second odor detector are both installed on a robotic arm next to the conveyor belt where the secondary security inspection time node of the luggage suitcase is located. A camera is set on the robotic arm. After the primary analysis module marks the unrecognizable items on the three-dimensional model of the luggage suitcase with unknown marks, the three-dimensional model of the luggage suitcase with the unknown marks is synchronized to the secondary analysis module. The secondary analysis module determines the suitcase based on the luggage image information collected by the camera on the robotic arm, and retrieves the three-dimensional model of the suitcase with the unknown marks completed according to the luggage information to determine the location of the position item. At this time, the luggage suitcase status is turned on, and the robotic arm controls the millimeter wave detector and the second odor detector according to the position of the unknown item in the luggage suitcase to collect the luggage suitcase millimeter wave image data and luggage suitcase odor data of the unknown item.
[0019] Preferably, the primary analysis module receives human millimeter wave image data and human body odor data, analyzes the presence of dangerous goods on the human body according to the human body millimeter wave image data, and analyzes whether there is the smell of dangerous goods on the human body according to the human body odor data, and generates an alarm message when dangerous goods or the smell of dangerous goods appear on the human body.
[0020] Preferably, after the primary analysis module completes the analysis, if there are no unrecognizable items in the luggage, and the security personnel confirm that there are no prohibited items in the luggage and on the user, the primary analysis module marks the security check as passed on the security check process timeline corresponding to the user.
[0021] Compared with the prior art, the beneficial effects of the present invention are as follows: through the X-ray data acquisition module, the millimeter wave data acquisition module, the odor data acquisition module and the identity data acquisition module, users and luggage are detected from multiple dimensions, which greatly reduces the possibility of missed detection of prohibited items; the data sorting module can establish a security inspection process timeline and synchronize various data to corresponding time nodes, so that the security inspection process is clear and orderly, unnecessary waiting and confusion are reduced, and the overall security inspection speed is improved; the luggage three-dimensional model construction module can determine the three-dimensional coordinates of items in the suitcase; the primary analysis module identifies the items and determines the prohibited items; for the unidentifiable items, the secondary analysis module performs secondary analysis, which can accurately locate and analyze the suspicious items; the airport security inspection prohibited items automatic identification system reduces the need for manual intervention and the probability of human error through the automated process of data collection, sorting, analysis and alarm. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 The present invention is a schematic diagram of the overall structure of an automatic identification system for prohibited items in airport security inspection. DETAILED DESCRIPTION
[0023] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0024] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Example
[0025] See also Figure 1 , this embodiment provides a technical solution:
[0026] An automatic identification system for prohibited items in airport security inspection includes a data collection terminal and a security inspection platform.
[0027] In this embodiment, the data collection end includes an X-ray data collection module, a millimeter wave data collection module, an odor data collection module, and an identity data collection module, which respectively collect user identity data, human millimeter wave image data, human odor data, luggage X-ray image data, luggage millimeter wave image data, and luggage odor data of the user and luggage;
[0028] Among them, the X-ray data acquisition module is a number of X-ray detectors arranged in an arc shape on the transmission channel of the luggage security inspection machine. The X-ray data acquisition module is used at the first-level security inspection time node of the luggage, and performs multi-angle X-ray image data acquisition on the luggage passing through the luggage security inspection machine to obtain the luggage X-ray image data;
[0029] The millimeter wave data acquisition module includes a millimeter wave security inspection door set at the human body security inspection time node and a millimeter wave detector set at the luggage secondary security inspection time node, the millimeter wave security inspection door collects human body millimeter wave image data, and the millimeter wave detector collects luggage millimeter wave image data; the odor data acquisition module includes a first odor detector and a second odor detector set at the human body security inspection time node and the luggage secondary security inspection time node, the first odor detector and the second odor detector respectively collect human body odor data and luggage odor data for collection;
[0030] The millimeter wave detector and the second odor detector are both installed on a robotic arm next to the conveyor belt at the secondary security inspection time node of the luggage. A camera is set on the robotic arm. After the primary analysis module marks the unrecognizable items on the three-dimensional model of the luggage, the three-dimensional model of the luggage with the unknown mark is synchronized to the secondary analysis module. The secondary analysis module determines the suitcase based on the suitcase image information collected by the camera on the robotic arm, and retrieves the three-dimensional model of the suitcase with the unknown mark based on the suitcase information to determine the location of the position of the item. At this time, the suitcase status is turned on, and the robotic arm controls the millimeter wave detector and the second odor detector according to the position of the unknown item in the suitcase to collect the luggage millimeter wave image data and luggage odor data of the unknown item.
[0031] In this embodiment, the security inspection platform includes a data sorting module, a baggage three-dimensional model building module, a primary analysis module, a secondary analysis module and an alarm module;
[0032] The data sorting module receives the user identity data, establishes the security check process timeline belonging to the user according to the user identity data and the user flight information, arranges the identity confirmation time node, the human body security check time node, the luggage first-level security check time node and the luggage second-level security check time node on the security check process timeline in chronological order, synchronizes the human body millimeter wave image data and human body odor data to the human body security check time node, synchronizes the luggage X-ray image data to the luggage first-level security check time node, and synchronizes the luggage millimeter wave image data and luggage odor data to the luggage second-level security check time node;
[0033] After receiving the security inspection process timeline, the luggage 3D model building module retrieves the luggage X-ray image data in the first-level security inspection time node of the luggage, builds a 3D model of the luggage according to the luggage X-ray image data, determines the 3D coordinates of each item in the luggage according to the 3D model of the luggage, and marks the 3D coordinates of the items in the luggage on the 3D model of the luggage;
[0034] When building a three-dimensional model of the suitcase, the acquired X-ray image data of the suitcase is subjected to denoising and enhancement processing to obtain pre-processed X-ray image data of the suitcase, and key feature information of each item is extracted from the pre-processed X-ray image, the key feature information including edge, shape, and texture; a method based on multi-view geometry is used to combine X-ray images taken at different angles to calculate the three-dimensional coordinates of the object, and a three-dimensional model of the suitcase and the items is constructed in combination with the key feature information of each item; the three-dimensional model of the item is synchronized to the three-dimensional model of the suitcase according to the three-dimensional coordinates of each item, and the construction of the three-dimensional model of the suitcase is completed;
[0035] The primary analysis module receives the three-dimensional model of the suitcase, identifies each item in the three-dimensional model of the suitcase, determines whether the identified items are prohibited items, and generates an alarm message when the items are determined to be prohibited items; unidentified items are marked as unknown on the three-dimensional model of the suitcase;
[0036] At the same time, the primary analysis module receives the millimeter wave image data of the human body and the human body odor data, analyzes the presence of dangerous goods on the human body according to the millimeter wave image data of the human body, and analyzes whether there is the smell of dangerous goods on the human body according to the human body odor data, and generates an alarm message when dangerous goods or the smell of dangerous goods appear on the human body;
[0037] After the primary analysis module completes the analysis, if there are no unrecognizable items in the luggage and the security personnel confirm that there are no prohibited items in the luggage and on the user, the primary analysis module will mark the security check as passed on the security check process timeline corresponding to the user;
[0038] The secondary analysis module receives the three-dimensional model of the suitcase with unknown marks, determines the location information of the unrecognizable items, receives the millimeter wave image data of the suitcase and the odor data of the suitcase, performs secondary analysis and identification on the unrecognizable items in combination with the millimeter wave image data of the suitcase and the odor data of the suitcase, determines whether the unrecognizable items are contraband items, and generates an alarm message when the items are determined to be contraband items;
[0039] After receiving the alarm information, the alarm module determines the attributes of the item corresponding to the alarm information and synchronizes the alarm information to the security personnel, who then handle the items and users according to the attributes of the prohibited items.
[0040] In this embodiment, both the primary analysis module and the secondary analysis module are provided with a database. The database of the primary analysis module stores the appearance feature images of the contraband, and the database of the secondary analysis module stores the millimeter wave images and odor data of the contraband.
[0041] The present invention will be further described below in conjunction with the specific operation process:
[0042] Step 1: Data Collection
[0043] Collect user identity data through face recognition equipment and ID card recognition equipment;
[0044] Through the X-ray data acquisition module, a plurality of X-ray detectors arranged in an arc shape are used on the transmission channel of the baggage security inspection machine to collect multi-angle X-ray image data of the baggage passing through the baggage security inspection machine to obtain the X-ray image data of the luggage;
[0045] Using the millimeter wave data acquisition module, the millimeter wave image data of the human body is collected through the millimeter wave security inspection gate at the human body security inspection time node, and the millimeter wave image data of the luggage is collected through the millimeter wave detector installed on the mechanical arm next to the conveyor belt at the luggage secondary security inspection time node;
[0046] With the help of the odor data collection module, at the human body security inspection time node and the luggage secondary security inspection time node, the human body odor data and the luggage case odor data are collected by the first odor detector and the second odor detector respectively;
[0047] Collecting user identity data using an identity data collection module;
[0048] Step 2: Establish security inspection process timeline and organize data
[0049] The data sorting module receives the user's identity data and creates a security check process timeline belonging to the user based on the user's identity data and the user's flight information;
[0050] The security check process timeline arranges the identity confirmation time nodes, body security check time nodes, luggage first-level security check time nodes and luggage second-level security check time nodes in chronological order;
[0051] Synchronize human body millimeter wave image data and human body odor data to human body security inspection time node, synchronize luggage X-ray image data to luggage first-level security inspection time node, synchronize luggage millimeter wave image data and luggage odor data to luggage second-level security inspection time node;
[0052] Step 3: Build the 3D model of the luggage
[0053] After receiving the security inspection process timeline, the luggage 3D model building module retrieves the luggage X-ray image data in the first-level security inspection time node of the luggage;
[0054] De-noising and enhancing the acquired luggage X-ray image data to obtain pre-processed luggage X-ray image data;
[0055] Extract key feature information of each object from the preprocessed X-ray image, including edge, shape, and texture;
[0056] Using a method based on multi-view geometry, combined with X-ray images taken at different angles, the three-dimensional coordinates of the objects are calculated, and the three-dimensional model of the suitcase and items is constructed by combining the key feature information of each item;
[0057] The three-dimensional model of the items is synchronized with the three-dimensional model of the suitcase according to the three-dimensional coordinates of each item, so as to complete the construction of the three-dimensional model of the suitcase;
[0058] Step 4: Primary Analysis
[0059] The primary analysis module receives the three-dimensional model of the suitcase and identifies each item in the three-dimensional model of the suitcase;
[0060] Determine whether the identified item is a prohibited item, and generate an alarm message when the item is determined to be a prohibited item;
[0061] Unrecognizable items are marked as unknown on the 3D model of the suitcase;
[0062] Simultaneously receiving human body millimeter wave image data and human body odor data, analyzing the presence of dangerous goods on the human body according to the human body millimeter wave image data, and analyzing whether there is the smell of dangerous goods on the human body according to the human body odor data, and generating alarm information when dangerous goods or the smell of dangerous goods appear on the human body;
[0063] When there are no unrecognizable items in the luggage and the security personnel confirm that there are no prohibited items in the luggage and on the user, the security check will be marked as passed on the security check process timeline corresponding to the user;
[0064] Step 5: Secondary Analysis
[0065] The secondary analysis module receives the three-dimensional model of the suitcase with unknown markings and determines the location information of the unrecognizable items;
[0066] Receiving the luggage millimeter wave image data and the luggage odor data, performing secondary analysis and identification on the unrecognizable items in combination with the luggage millimeter wave image data and the luggage odor data, determining whether the unrecognizable items are contraband items again, and generating an alarm message when the items are determined to be contraband items;
[0067] Step 6: Alert handling
[0068] After receiving the alarm information, the alarm module determines the property of the item corresponding to the alarm information;
[0069] The alarm information is synchronized to the security personnel, who will handle the items and users according to the properties of the prohibited items;
[0070] For example, suppose that in the primary analysis, an object with a strange shape is found to be unrecognizable. After being marked as unknown, it is determined to be a prohibited item in the secondary analysis by combining millimeter wave images and odor data. The alarm module conveys this information to the security personnel, who then take corresponding measures on the relevant items and users;
[0071] For example, in human body security checks, human millimeter wave image data can be used to detect the shape of a suspected dangerous item on a person's body. After analysis, it is determined to be a prohibited item, and an alarm is generated to notify security personnel to handle it.
[0072] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. An automatic identification system for prohibited items at airport security inspection, characterized by: include: Data collection terminal; The data collection terminal includes an X-ray data collection module, a millimeter wave data collection module, an odor data collection module, and an identity data collection module, which respectively collect user identity data, human millimeter wave image data, human odor data, luggage X-ray image data, luggage millimeter wave image data, and luggage odor data of the user and luggage; Security inspection platform; the security inspection platform includes a data sorting module, a baggage three-dimensional model building module, a primary analysis module, a secondary analysis module and an alarm module; The data sorting module receives user identity data, establishes a security check process timeline belonging to the user according to the user identity data and the user flight information, arranges the identity determination time node, the human body security check time node, the luggage first-level security check time node and the luggage second-level security check time node on the security check process timeline in chronological order, synchronizes the human body millimeter wave image data and the human body odor data to the human body security check time node, synchronizes the luggage X-ray image data to the luggage first-level security check time node, and synchronizes the luggage millimeter wave image data and the luggage odor data to the luggage second-level security check time node; After receiving the security inspection process timeline, the luggage 3D model building module retrieves the luggage X-ray image data in the first-level security inspection time node of the luggage, builds a 3D model of the luggage according to the luggage X-ray image data, determines the 3D coordinates of each item in the luggage according to the 3D model of the luggage, and marks the 3D coordinates of the items in the luggage on the 3D model of the luggage; The primary analysis module receives the three-dimensional model of the suitcase, identifies each item in the three-dimensional model of the suitcase, determines whether the identified item is a prohibited item, and generates an alarm message when the item is determined to be a prohibited item; Unrecognizable items are marked as unknown on the 3D model of the suitcase; The secondary analysis module receives the three-dimensional model of the suitcase with unknown marks, determines the location information of the unrecognizable items, receives the millimeter wave image data of the suitcase and the odor data of the suitcase, performs secondary analysis and identification on the unrecognizable items in combination with the millimeter wave image data of the suitcase and the odor data of the suitcase, determines whether the unrecognizable items are contraband again, and generates an alarm message when the items are determined to be contraband; After receiving the alarm information, the alarm module determines the property of the item corresponding to the alarm information, and synchronizes the alarm information to the security personnel, who then handle the items and users according to the properties of the prohibited items; The X-ray data acquisition module is a plurality of X-ray detectors arranged in an arc shape on the transmission channel of the luggage security inspection machine. The X-ray data acquisition module is used at the first-level security inspection time node of the luggage, and performs multi-angle X-ray image data acquisition on the luggage passing through the luggage security inspection machine to obtain the luggage X-ray image data; When building a three-dimensional model of the suitcase, the acquired X-ray image data of the suitcase is subjected to denoising and enhancement processing to obtain pre-processed X-ray image data of the suitcase, and key feature information of each item is extracted from the pre-processed X-ray image, the key feature information including edge, shape, and texture; a method based on multi-view geometry is used to combine X-ray images taken at different angles to calculate the three-dimensional coordinates of the object, and a three-dimensional model of the suitcase and the items is constructed in combination with the key feature information of each item; the three-dimensional model of the item is synchronized to the three-dimensional model of the suitcase according to the three-dimensional coordinates of each item, and the construction of the three-dimensional model of the suitcase is completed; The millimeter wave data acquisition module includes a millimeter wave security inspection gate arranged at a human body security inspection time node and a millimeter wave detector arranged at a luggage compartment secondary security inspection time node, the millimeter wave security inspection gate collects human body millimeter wave image data, and the millimeter wave detector collects luggage compartment millimeter wave image data; the odor data acquisition module includes a first odor detector and a second odor detector arranged at a human body security inspection time node and a luggage compartment secondary security inspection time node, the first odor detector and the second odor detector collect human body odor data and luggage compartment odor data respectively; The millimeter wave detector and the second odor detector are both installed on a mechanical arm beside the conveyor belt at the secondary security inspection time node of the luggage. A camera is set on the mechanical arm. After the primary analysis module performs unknown marking on the three-dimensional model of the luggage for the unrecognizable items, the three-dimensional model of the luggage with the unknown marking is synchronized to the secondary analysis module. The secondary analysis module determines the luggage according to the luggage image information collected by the camera on the mechanical arm, and retrieves the three-dimensional model of the luggage with the unknown marking of the luggage according to the luggage information to determine the location of the unknown items. At this time, the luggage state is turned on, and the mechanical arm controls the millimeter wave detector and the second odor detector according to the location of the unknown items in the luggage to collect the luggage millimeter wave image data and luggage odor data of the unknown items. The primary analysis module receives the human body millimeter wave image data and the human body odor data, analyzes the presence of dangerous goods on the human body according to the human body millimeter wave image data, and analyzes whether there is the smell of dangerous goods on the human body according to the human body odor data, and generates an alarm message when dangerous goods or the smell of dangerous goods appear on the human body; After the primary analysis module completes the analysis, if there are no unrecognizable items in the luggage, and the security personnel confirm that there are no prohibited items in the luggage and on the user, the primary analysis module marks the security check as passed on the security check process timeline corresponding to the user.
