CN112149660B - Gun identification system - Google Patents
Gun identification system Download PDFInfo
- Publication number
- CN112149660B CN112149660B CN202010767929.2A CN202010767929A CN112149660B CN 112149660 B CN112149660 B CN 112149660B CN 202010767929 A CN202010767929 A CN 202010767929A CN 112149660 B CN112149660 B CN 112149660B
- Authority
- CN
- China
- Prior art keywords
- gun
- firearm
- image
- information
- data
- 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.)
- Active
Links
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000012216 screening Methods 0.000 claims abstract description 19
- 230000003993 interaction Effects 0.000 claims abstract description 4
- 239000005337 ground glass Substances 0.000 claims description 22
- 238000003384 imaging method Methods 0.000 claims description 18
- 238000004519 manufacturing process Methods 0.000 claims description 16
- 238000005286 illumination Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 13
- 230000000007 visual effect Effects 0.000 abstract description 6
- 239000005338 frosted glass Substances 0.000 description 9
- 238000012986 modification Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012217 deletion Methods 0.000 description 3
- 230000037430 deletion Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/10—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from different wavelengths
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/09—Recognition of logos
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a gun identification system, which comprises a gun information acquisition subsystem, a gun information database and a central processing control subsystem; the gun information acquisition subsystem is used for acquiring gun data and transmitting the data to the central processing control subsystem; the gun information database is used for storing gun data and carrying out data interaction with the central processing control subsystem; and the central processing control subsystem is used for management and gun identification. According to the technical scheme, various firearms can be identified, the application range is wide, on a specific identification method, the database is screened rapidly through data such as the area, the perimeter and the maximum distance between two points of the contour image, then the database is screened further by combining with a Hu moment matching algorithm of the contour image, finally a inspector carries out manual screening and identification on a returned result, and the high efficiency and accuracy of identification are ensured through combination from visual to complex and from machine to manual.
Description
Technical Field
The invention relates to the technical field of gun identification, in particular to a gun identification system.
Background
The gun and bullet are fast and accurate to identify, examine and appraise, and are very important for the research, analysis and detection of the case.
The conventional gun identification and authentication purely by human eyes and experience cannot meet the requirements of new situations, and development of a new method for rapidly identifying and authenticating the gun is needed. Currently, there are also some technical solutions to try to solve the technical problem:
The invention patent with the application number of CN201811120409.1 discloses a gun identification management device. Including casing, controller and radio frequency identification ware, the inside bottom movable mounting of casing has charging mechanism, the inside fixed mounting of casing has the battery, and the battery is located charging mechanism's top, the inside fixed mounting of casing has the controller, and the controller is located the top of battery, the inside top fixed mounting of casing has radio frequency identification ware, the top movable mounting of casing has cleaning mechanism, the top fixed mounting of casing surface has the display screen, the fixed surface of casing installs control button, and control button and controller swing joint, the bottom movable mounting of casing surface has complementary unit. In addition, the invention patent with the application number of CN200710090704.2 provides a gun identification management system. The system is characterized in that an information card is arranged on a gun and is placed on an information read-write handle for gun information management, and the system comprises a gun registration module, a gun cancellation module, a gun information inquiry module, a personnel registration module, a personnel cancellation module, a personnel information inquiry module, a fingerprint borrowing and returning gun module, an identity card borrowing and returning gun module and a gun borrowing and returning information inquiry module.
Specifically, the invention patent with the application number of CN201811120409.1 is to scan an electronic tag attached to the surface of a gun through a device to obtain gun information, while the invention patent with the application number of CN200710090704.2 is to place an information card on the gun and read the information card through an information reading handle to obtain gun information, and the methods not only require the electronic tag (information card) and the electronic tag (information card) reading device, increase hardware cost, but also can only be used for identifying internal supervision guns, cannot be applied to identifying illegal guns, and cannot meet the requirement of quick identification of a smuggling gun.
Thus, there is a need for a better solution to this technical problem.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a gun identification system which can carry out graphical identification on various guns, and on a specific identification method, a database is firstly and rapidly screened through data such as the area, the perimeter, the maximum distance between two points and the like of a contour image, then the database is further screened by combining with a Hu moment matching algorithm of the contour image, finally, a inspector carries out manual screening and identification on a returned result, and the combination from visual to complex and from machine to manual ensures the high efficiency and accuracy of identification.
Specifically, the present invention proposes the following specific embodiments:
the embodiment of the invention provides a gun identification system, which comprises a gun information acquisition subsystem, a gun information database and a central processing control subsystem; wherein,
The gun information acquisition subsystem is used for acquiring gun data and sending the data to the central processing control subsystem;
the gun information database is used for storing gun data and carrying out data interaction with the central processing control subsystem;
the central processing control subsystem is used for carrying out binarization processing on the contour image of the gun to be identified at the specified view angle to obtain a binarized contour image;
determining a size coefficient according to the focal length of a camera shooting the contour image and the distance between the camera and the gun to be identified;
Determining the area, perimeter and maximum distance between two points of the area occupied by the gun in the binarized profile image;
matching in the gun information database according to the size coefficient, the area, the perimeter and the maximum distance between the two points;
If the candidate gun data set is obtained through matching, hu moment calculation of a binarized contour image is carried out on each gun and the gun to be identified in the candidate gun data set;
Calculating a weighted square error based on the Hu moment;
Screening firearms matched with Hu moments of the firearms to be identified in the candidate firearm data set based on the weighted square error;
And if the screening is carried out to obtain a screening gun set, sorting the guns in the screening gun set according to the weighted square error from low to high, and returning the sorted gun data to the inspector so as to be convenient for the inspector to carry out manual identification.
In a specific embodiment, the contour image is a contour gray scale image;
The area with the gray value of 0 in the binarized contour image is a gun area, and the area with the gray value of 255 is a background area; the area corresponds to the size of the area corresponding to all pixel points with gray values of 0 in the binarized contour image; the perimeter is the length integral of the edge of the area with the gray value of 0 in the binarized contour image; the maximum distance between the two points is the maximum distance between the pixel points with the gray value of 0 in the binarized contour image;
the Hu moment is obtained by calculating the contour binarization image according to the Hu moment definition.
In one specific embodiment of the present invention,
The size coefficient is calculated based on the following formula:
k=h/f; wherein k is a size coefficient; the H is the distance between the camera and the gun to be identified in the imaging direction; f is the focal length of an imaging lens of the camera;
The matching is based on the following formula:
Wherein,
The area of the binarized contour image of the gun to be identified is S, the perimeter of the binarized contour image of the gun to be identified is C, and the maximum distance between two points of the gun to be identified is L; the size coefficient of the gun to be identified is k; the area of the gun in the gun information database is S 1, the circumference of the gun is C 1, the maximum distance between two points of the gun is L 1, and the size coefficient of the gun is k 1;γs、γC、γL, which is the error control coefficient of the area, the circumference and the maximum distance between the two points respectively;
the weighted square error is calculated by the following formula:
Wherein Hu moment of the gun contour binarization image in the candidate gun data set is M; the Hu moment of the contour binarization image of the gun to be identified is N; k represents different components of Hu moment; w is the weight of different components of the Hu moment; WSE is the weighted squared error;
And screening to obtain a screened gun set which is a gun set conforming to WSE < W T in the candidate gun data set, wherein W T is a preset threshold.
In a specific embodiment, the firearm information acquisition subsystem comprises: the system comprises a basic attribute acquisition module, a contour image acquisition module, a color image acquisition module and an information acquisition computer with information acquisition software.
In a specific embodiment, the basic attribute collection module is configured to collect basic attribute information of a firearm;
The base attribute information includes any combination of one or more of the following: name, model number, surface identification, LOGO word description, size, caliber, structure, category, country of production information, manufacturer information, year of production.
In a specific embodiment, the profile image acquisition module is configured to acquire a profile image of a firearm.
In a specific embodiment, the color image acquisition module is configured to acquire a color image of the appearance of the firearm.
In a specific embodiment, the contour image acquisition module or the color image acquisition module is an image acquisition device;
The image acquisition apparatus includes: the device comprises a liftable support frame, a three-dimensional adjustable support, a ground glass plate for placing a gun, a high-definition color camera, a backlight source and a white light illumination source; wherein,
The three-dimensional adjustable bracket is arranged at the top of the supporting frame;
the ground glass flat plate is horizontally arranged in the middle of the supporting frame;
the backlight source is arranged below the ground glass plate and irradiates the ground glass plate from bottom to top;
the high-definition color camera and the white light illumination light source are arranged on the three-dimensional adjustable bracket.
In a specific embodiment, the central processing control subsystem includes: the system comprises a system management module, a gun information management module and a gun identification module; wherein,
The system management module is used for account number and authority management, system state monitoring, data query and report management;
The gun information management module is used for collecting gun information, transmitting data, filing, adding, deleting, modifying, inquiring, searching and counting;
And the gun identification module is used for identifying the gun to be identified.
In a specific embodiment, the firearm data stored in the firearm information database comprises: serial number, binarized contour image, area, perimeter, maximum distance between two points, size coefficient, color image.
In a specific embodiment, the firearm data stored in the firearm information database further comprises: gun name, model, type, structure, country of production, manufacturer, year of production, logo.
Compared with the prior art, the invention has the following effects: the method can be used for carrying out graphical identification on various firearms, is wide in application range, and on a specific identification method, the database is firstly and rapidly screened through data such as the area, the perimeter, the maximum distance between two points and the like of the contour image, then the database is further screened by combining with a Hu moment matching algorithm of the contour image, finally, a inspector carries out manual screening and identification on a returned result, and the high efficiency and accuracy of identification are ensured through combination from visual to complex and from machine to manual.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram illustrating the basic architecture of a gun recognition system according to an embodiment of the present invention;
Fig. 2 is a schematic diagram of basic architecture components of a gun information acquisition subsystem in a gun recognition system according to an embodiment of the present invention;
FIG. 3 is an illustration of an intention of a middle firearm profile image of a firearm identification system according to an embodiment of the present invention;
Fig. 4 is a schematic structural diagram of an image acquisition device in a gun recognition system according to an embodiment of the present invention;
FIG. 5 is a basic framework of a central processing control subsystem in a firearm identification system according to an embodiment of the present invention;
fig. 6 is a schematic diagram of format definition of gun information data in a gun recognition system according to an embodiment of the present invention.
Detailed Description
Hereinafter, various embodiments of the present disclosure will be more fully described. The present disclosure is capable of various embodiments and of modifications and variations therein. However, it should be understood that: there is no intention to limit the various embodiments of the disclosure to the specific embodiments disclosed herein, but rather the disclosure is to be interpreted to cover all modifications, equivalents, and/or alternatives falling within the spirit and scope of the various embodiments of the disclosure.
The terminology used in the various embodiments of the disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the various embodiments of the disclosure. As used herein, the singular is intended to include the plural as well, unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of this disclosure belong. The terms (such as those defined in commonly used dictionaries) will be interpreted as having a meaning that is the same as the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein in the various embodiments of the disclosure.
Examples
The embodiment of the invention discloses a gun identification system, which is shown in figure 1 and comprises a gun information acquisition subsystem, a gun information database and a central processing control subsystem; wherein,
The gun information acquisition subsystem is used for acquiring gun data and sending the data to the central processing control subsystem;
the gun information database is used for storing gun data and carrying out data interaction with the central processing control subsystem;
Specifically, as shown in fig. 1, the system mainly comprises a gun information acquisition subsystem, a central processing control subsystem and a gun information database. The gun information acquisition subsystem is responsible for acquiring basic information and two-dimensional images of the gun and transmitting the data to the central processing control subsystem. The gun information database is used for storing gun information and exchanging information with the central processing control subsystem.
The central processing control subsystem is responsible for information processing and management control, and is a central center for identifying and identifying firearms and controlling the work of each subsystem in a coordinated manner. Specifically, the central processing control subsystem is used for executing the following functions:
The method comprises the steps of 1, identifying and authenticating firearms, specifically, collecting contour images of the firearms to be identified by a firearms information collecting subsystem, transmitting the contour images to a central processing and controlling subsystem, processing and extracting features of the contour images by the central processing and controlling subsystem according to an intelligent analysis flow and algorithm, searching and comparing a firearms information database, returning specific information of the matched firearms if the comparison is successful, then observing and analyzing color images of the matched firearms by a checker, visually distinguishing and authenticating whether the matched firearms are consistent with the firearms to be identified, judging that the identification is successful if the matched color images are consistent with the firearms, otherwise, judging that no data of the firearms exist in the database.
Function 2, gun information management. Including gun information collection, database creation, data perfection, data modification, data deletion, data query, data statistics, and other gun-related information management.
Specifically, the gun identification method comprises the following basic flow: and acquiring a contour image of the gun to be identified at a specified visual angle, and performing binarization processing on the contour image to obtain a binarized contour image of the gun. And calculating a size coefficient k according to the height proportional relation of the camera during shooting. And calculating the area S, the perimeter C and the maximum distance L between two points of the area occupied by the gun of the binarized contour image. And searching and comparing the gun information database, and selecting gun data matched with the area S, the perimeter C and the maximum distance L between the two points to form a candidate gun data set A. If A is not null, the Hu moments of the firearm to be identified and the candidate firearm are calculated, and a weighted square error WSE is calculated. A firearm set B of WSE < threshold W T is established. If B is not empty, the firearms are arranged from low to high according to WSE and returned in sequence, a inspector visually discriminates and identifies whether the matched firearms are consistent with the firearms to be identified by observing and analyzing color images of the matched firearms, if so, the identification is successful, and if not, no data of the firearms to be identified are judged in the database.
Specifically, taking the gun identification as an example, the central processing control subsystem is used for carrying out binarization processing on the contour image of the gun to be identified at a specified visual angle to obtain a binarized contour image; specifically, the contour image is a contour gray image; the area with the gray value of 0 in the binarized contour image is a gun area, and the area with the gray value of 255 is a background area; the area corresponds to the size of the area corresponding to all pixel points with gray values of 0 in the binarized contour image; the perimeter is the length integral of the edge of the area with the gray value of 0 in the binarized contour image; the maximum distance between the two points is the maximum distance between the pixel points with the gray value of 0 in the binarized contour image;
determining a size coefficient according to the focal length of a camera shooting the contour image and the distance between the camera and the gun to be identified;
specifically, the size coefficient is calculated based on the following formula:
k=h/f; wherein k is a size coefficient; the H is the distance between the camera and the gun to be identified in the imaging direction; f is the focal length of an imaging lens of the camera;
Determining the area, perimeter and maximum distance between two points of the area occupied by the gun in the binarized profile image;
Matching in the gun information database according to the size coefficient, the perimeter, the area and the maximum distance between the two points;
If the candidate gun data set is obtained through matching, hu moment calculation of a binarized contour image is carried out on each gun and the gun to be identified in the candidate gun data set; specifically, the Hu moment is obtained by calculating the contour binarization image according to the Hu moment definition;
Calculating a weighted square error based on the Hu moment;
Wherein the matching is based on the following formula:
Wherein,
The area of the binarized contour image of the gun to be identified is S, the perimeter of the binarized contour image of the gun to be identified is C, and the maximum distance between two points of the gun to be identified is L; the size coefficient of the gun to be identified is k; the area of the gun in the gun information database is S 1, the circumference of the gun is C 1, the maximum distance between two points of the gun is L 1, and the size coefficient of the gun is k 1;γs、γC、γL, which is the error control coefficient of the area, the circumference and the maximum distance between the two points respectively;
the weighted square error is calculated by the following formula:
Wherein Hu moment of the gun contour binarization image in the candidate gun data set is M; the Hu moment of the contour binarization image of the gun to be identified is N; k represents different components of Hu moment; w is the weight of different components of the Hu moment; WSE is the weighted squared error;
And screening to obtain a screened gun set which is a gun set conforming to WSE < W T in the candidate gun data set, wherein W T is a preset threshold. And if the screening is carried out to obtain a screening gun set, sorting the guns in the screening gun set according to the weighted square error from low to high, and returning the sorted gun data to the inspector so as to be convenient for the inspector to carry out manual identification.
In the actual process, for the gun to be identified, basic attribute information, contour images and color images are acquired on a gun information acquisition subsystem. If the contour image is captured by a color camera, the color image is first converted into a gray scale image. For the contour gray level image, a proper threshold T is designed, so that the gray level value of a pixel point with the gray level value larger than or equal to T is reset to 255; as for the pixel point whose gray value is smaller than T, the gray value is reset to 0; thereby obtaining a binarized profile image p. The gray value of the gun area in the image is 0, and the rest background is 255. The threshold T is selected empirically. The focal length of an imaging lens of the contour image acquisition camera is f, the distance between the camera and the gun in the imaging direction is H, and a size coefficient k=H/f is calculated. And calculating the area S, the perimeter C and the maximum distance L between two points of the gun area for the binarized contour image. The area S is defined as the sum of the number of pixels in the image with a gray value of 0, the perimeter C is defined as the integral of the length of the edge of the region in the image with a gray value of 0, and the maximum distance L between two points is defined as the maximum distance between the pixels in the image with a gray value of 0.
And (3) searching gun data in a gun information database, wherein the area of a gun is searched to be S 1, the circumference of the gun is C 1, the maximum distance between two points is L 1, and the size coefficient is k 1. Searching gun data satisfying the following relationship:
Wherein, gamma s、γC、γL is the error control coefficient of the maximum distance between the area, the perimeter and the two points, and mainly considers the influences of the machining error of gun parts, the assembly error of the gun, the abrasion error, the image acquisition and calculation error and the like. The thresholds γ S、γC and γ L are selected empirically.
By the method, a gun data set matched with the area S, the area C and the maximum distance L between two points in the area of the gun to be identified is searched and is marked as A. If A is empty, indicating that the gun information database does not exist the gun which is matched with the area, the perimeter and the maximum distance between two points in the area of the gun to be identified, judging that the gun is not matched with the gun to be identified, and returning the result. If A is not empty, for each gun in the set, the contour binarized image m is read to find Hu moment. The Hu moment is calculated by the second-order and third-order central moments of the image, and has the invariance of image scaling, translation, rotation and mirroring. The Hu moments total 7: m= { M 1,M2,M3,M4,M5,M6,M7 }. Reading a contour binarization image n of the gun to be identified, and solving Hu moment: n= { N 1,N2,N3,N4,N5,N6,N7 }. Calculating the weighted square error of M and N
The Hu moment of the gun profile binarization image in the candidate gun data set is M; the Hu moment of the contour binarization image of the gun to be identified is N; k represents different components of Hu moment; w is the weight of different components of the Hu moment; WSE is the weighted squared error; the weighted square error WSE is calculated for all firearms in set a. Appropriate thresholds W T are designed to establish firearm set B for WSE < W T. If B is empty, indicating that the gun which is matched with the Hu moment of the binarized outline image of the gun to be identified does not exist in the gun information database, judging that the gun which is not matched with the gun to be identified does not exist, and returning a result. The threshold W T is selected empirically. If B is not empty, the guns in B are ordered from low to high according to WSE, and detailed information is returned in sequence.
And finally, manually screening and identifying the returned gun information by a checker, wherein the manual screening and identifying method is to observe the front and back high-resolution color images of the returned gun and the front and back high-resolution color images of the gun to be identified and judge whether the gun belongs to the same gun. If the firearms belong to the same gun, the identification and comparison are successful, if all returned firearms are not matched with the firearms to be identified, the information of the firearms to be identified does not exist in the database.
The following description is made with respect to various parts of the overall firearm identification system, the firearm information acquisition subsystem comprising: the system comprises a basic attribute acquisition module, a contour image acquisition module, a color image acquisition module and an information acquisition computer with information acquisition software. The basic attribute acquisition module is used for acquiring basic attribute information of the gun; the base attribute information includes any combination of one or more of the following: name, model number, surface identification, LOGO word description, size, caliber, structure, category, country of production information, manufacturer information, year of production. And the contour image acquisition module is used for acquiring contour images of the gun. The color image acquisition module is used for acquiring color images of gun appearance.
The gun information acquisition subsystem mainly comprises a basic attribute acquisition module, a contour image acquisition module, a color image acquisition module, an information acquisition computer and information acquisition software. As shown in fig. 2. The basic attribute information acquisition module is responsible for acquiring basic attribute information of the gun, such as a name, a model, a surface identifier, a LOGO text description, a size, a caliber, a structure, a type, a country of production, a manufacturer, a production year and the like of the gun. The above information is known to some of the firearms to be acquired, and is unknown to some, for example, for an illegal firearm to be acquired, the information may be largely unknown, while for a supervisory firearm to build a library, the information may be largely known. The collection of information is selective (can be determined to collect and cannot be determined to collect).
The contour image acquisition module is responsible for acquiring contour images of the gun. The contour image is to image the surface of the gun by adopting a back illumination imaging mode, wherein the area shielded by the gun in the image is almost completely black, and the area not shielded by the gun is almost completely bright. An example of a firearm profile image is shown in fig. 3. The contour image acquisition module mainly comprises a backlight source, a ground glass flat plate, a three-dimensional adjustable bracket and a high-definition camera. The gun to be collected is placed on the ground glass plate, and the backlight source is arranged below the ground glass plate and irradiates upwards from the lower side of the ground glass plate. The backlight may be a single large area light source or an array of illumination sources. The high definition camera images the firearm from above the ground glass plate downward. The camera is arranged on the three-dimensional adjustable bracket, can perform two-dimensional adjustment in the direction parallel to the frosted glass plate and perform one-dimensional adjustment in the direction perpendicular to the frosted glass plate. The firearm is positioned substantially in the center of the imaging field of view of the camera by adjusting the position of the camera in a direction parallel to the frosted glass, and the firearm fills a substantial portion of the imaging field of view of the camera by adjusting the position of the camera in a direction perpendicular to the frosted glass. The high-definition camera consists of a large-depth-of-field imaging lens and a large-area-array high-pixel-resolution industrial camera. The industrial camera may be a black-and-white camera or a color camera.
The color image acquisition module is responsible for acquiring color images of the appearance of the firearm. The color image acquisition module mainly comprises a white light illumination source, a bottom plate, a three-dimensional adjustable bracket and a high-definition color camera. And the gun to be acquired is placed on the bottom plate, the white light illumination light source irradiates downwards from the upper part of the bottom plate, and the high-definition color camera images the gun downwards from the upper part of the bottom plate. The color camera is arranged on the three-dimensional adjustable bracket, can be adjusted in two dimensions in the direction parallel to the bottom plate, and can be adjusted in one dimension in the direction perpendicular to the bottom plate. The firearm is positioned substantially in the center of the imaging field of view of the camera by adjusting the position of the camera in a direction parallel to the base plate, and the firearm fills a substantial portion of the imaging field of view of the camera by adjusting the position of the camera in a direction perpendicular to the base plate. The high-definition color camera consists of a large depth of field imaging lens and a large-area array high-pixel resolution color industrial camera.
In a specific embodiment, the contour image acquisition module and the color image acquisition module may be combined into one, and the contour image acquisition module or the color image acquisition module is an image acquisition device; the image acquisition apparatus includes: the device comprises a liftable support frame, a three-dimensional adjustable support, a ground glass plate for placing a gun, a high-definition color camera, a backlight source and a white light illumination source; wherein the three-dimensional adjustable bracket is arranged on the top of the support frame (the specific support frame can be lifted and lowered, and the three-dimensional adjustable bracket can be lifted and lowered); the ground glass flat plate is horizontally arranged in the middle of the supporting frame; the backlight source is arranged below the ground glass plate and irradiates the ground glass plate from bottom to top; the high-definition color camera and the white light illumination light source are arranged on the three-dimensional adjustable bracket.
The image acquisition device provided by the invention combines the contour image acquisition module and the color image acquisition module into a whole. The image acquisition device is structured as shown in fig. 4. The image acquisition device consists of a support frame, a ground glass flat plate, a backlight source, a white light illumination source, a three-dimensional adjustable support and a high-definition color camera. The gun to be collected is placed in the center of the ground glass plate. The backlight source is positioned below the frosted glass plate and irradiates the frosted glass plate from below to above. The high-definition color camera is arranged on the three-dimensional adjustable bracket, and the three-dimensional adjustable bracket can be used for two-dimensional adjustment in the direction parallel to the frosted glass plate, so that the central position of the view field of the camera is adjusted, one-dimensional adjustment can be carried out in the direction perpendicular to the frosted glass plate, and the size of the frosted glass plate in the imaging area of the camera is adjusted. The position of the camera is adjusted by the three-dimensional adjustable support so that the firearm is positioned substantially in the center of the camera imaging and fills a substantial portion of the field of view. The two white light illumination sources are also arranged on the three-dimensional adjustable bracket and respectively positioned at two sides of the high-definition color camera, and the ground glass flat plate is irradiated downwards from above. The adjustment position of the three-dimensional adjustable support can be obtained through scale reading.
The image acquisition device acquires images by the following steps: and placing the gun to be collected in the center of the ground glass plate, opening a backlight source and a high-definition color camera, and adjusting the position of the camera through a three-dimensional adjustable bracket to ensure that the gun is basically positioned in the center of an imaging view field of the camera and fills most of the view field. And shooting and storing the outline image of the gun. Turning off the back light source, turning on the white light illumination source, shooting and storing the color image of the gun, turning over the gun and placing the other side upwards, and shooting and storing the color image of the gun. And reading the position scale of the three-dimensional adjustable bracket in the direction vertical to the ground glass, calculating the distance H between the camera and the gun in the height direction, and storing. The gun information acquisition subsystem can also comprise an information acquisition computer and acquisition software. The acquisition software is installed on the acquisition computer.
In a specific embodiment, the central processing control subsystem includes: the system comprises a system management module, a gun information management module and a gun identification module; the system management module is used for account number and authority management, system state monitoring, data query and report management;
The gun information management module is used for collecting gun information, transmitting data, filing, adding, deleting, modifying, inquiring, searching and counting;
And the gun identification module is used for identifying the gun to be identified.
Specifically, as shown in fig. 5, the central processing control subsystem mainly comprises a central processing server and control processing software. The central processing server has strong computing power, and can be a local physical server or a cloud server according to application requirements and arrangement conditions. The control processing software is responsible for realizing the core control, management and information processing of the system. According to different implementation functions, the control processing software is mainly divided into the following modules: (1) a system management module. Including account and rights management, system status monitoring, data query, report management, and the like. (2) a firearm information management module. The management of the gun information database mainly comprises collection, data transmission, profiling, addition, deletion, modification, query retrieval, statistics and the like of gun information. (3) a firearm identification module. And the method is responsible for processing and extracting features of the two-dimensional image of the acquired gun by utilizing an image processing and intelligent recognition algorithm, and searching and comparing the two-dimensional image with the data of a gun information database, so that the gun can be recognized quickly finally.
In a specific embodiment, the firearm data stored in the firearm information database comprises: serial number, binarized contour image, area, perimeter, maximum distance between two points, size coefficient, color image. In addition, the firearm data stored in the firearm information database further includes: gun name, model, type, structure, country of production, manufacturer, year of production, logo.
Specifically, the gun information database mainly comprises a database server and database system management software. The database server has strong storage capacity and rapid data access speed, and can be a local physical server or a cloud server according to application requirements and arrangement conditions. The server is provided with database management software, such as Oracle, SQL SERVER, MYSQL, etc. The format of the firearm information data is defined as follows: for a firearm whole gun, the data at least comprises an item (necessary filling) of a serial number, a binary outline image, an area, a perimeter, a maximum distance between two points, a size coefficient, a color image and the like, and can comprise an item (optional filling) of a firearm name, a model, a type, a structure, a country of production, a manufacturer, a production year, a logo and the like. The format definition of the firearm information data can be as shown in fig. 6.
The system functions and modes of operation are described in detail below.
Aiming at the function of gun identification, for the gun to be identified, basic attribute, contour image and color image acquisition are carried out on a gun information acquisition subsystem, the acquired data are packed and sent to a central processing control subsystem through information acquisition software, and the central processing control subsystem carries out search comparison on a gun information database and is matched with the acquired data; if the matching data are found, specific information of the matching gun is returned, then a inspector visually discriminates and identifies whether the matching gun is consistent with the gun to be identified by observing and analyzing a color image of the matching gun, if so, the identification is judged to be successful, otherwise, the gun data are not judged to be in the database.
Aiming at the function of gun information management, 1, for a newly added gun, basic attribute information, contour images and color images are acquired on a gun information acquisition subsystem, the acquired data are packaged and sent to a central processing control subsystem through information acquisition software, and the central processing control subsystem performs search comparison on a gun information database and is matched with the acquired data; if no matching data is found, the database is not built for the gun model, and the gun data file is newly built in the database. 2. According to the development of system application, the gun data of the database is gradually updated, including data supplementation, modification, deletion and the like. 3. The gun information is queried, counted, supervised and analyzed, such as category statistics, structure statistics and source location statistics, and can be related to gun related cases.
Compared with the prior art, the scheme has the advantages that: (1) By adopting an image recognition mode, the gun can be recognized. (2) And the information based on basic attribute, contour image information, color image and the like plays a role together under multiple tubes, so that the accuracy and reliability of identification are improved. (3) In the identification method, the database is firstly and rapidly screened through the data such as the area, the perimeter, the maximum distance between two points and the like of the contour image, then the database is further screened by combining with the Hu moment feature matching algorithm of the contour image, finally, the return result is manually screened and identified by the inspector, and the high efficiency and accuracy of identification are ensured through combination from visual to complex and from machine to manual.
Those skilled in the art will appreciate that the drawing is merely a schematic illustration of a preferred implementation scenario and that the modules or flows in the drawing are not necessarily required to practice the invention.
Those skilled in the art will appreciate that modules in an apparatus in an implementation scenario may be distributed in an apparatus in an implementation scenario according to an implementation scenario description, or that corresponding changes may be located in one or more apparatuses different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above-mentioned inventive sequence numbers are merely for description and do not represent advantages or disadvantages of the implementation scenario.
The foregoing disclosure is merely illustrative of some embodiments of the invention, and the invention is not limited thereto, as modifications may be made by those skilled in the art without departing from the scope of the invention.
Claims (11)
1. The gun identification system is characterized by comprising a gun information acquisition subsystem, a gun information database and a central processing control subsystem; wherein,
The gun information acquisition subsystem is used for acquiring gun data and sending the data to the central processing control subsystem;
the gun information database is used for storing gun data and carrying out data interaction with the central processing control subsystem;
the central processing control subsystem is used for carrying out binarization processing on the contour image of the gun to be identified at the specified view angle to obtain a binarized contour image;
determining a size coefficient according to the focal length of a camera shooting the contour image and the distance between the camera and the gun to be identified;
Determining the area, perimeter and maximum distance between two points of the area occupied by the gun in the binarized profile image;
matching in the gun information database according to the size coefficient, the area, the perimeter and the maximum distance between the two points;
If the candidate gun data set is obtained through matching, hu moment calculation of a binarized contour image is carried out on each gun and the gun to be identified in the candidate gun data set;
Calculating a weighted square error based on the Hu moment;
Screening firearms matched with Hu moments of the firearms to be identified in the candidate firearm data set based on the weighted square error;
And if the screening is carried out to obtain a screening gun set, sorting the guns in the screening gun set according to the weighted square error from low to high, and returning the sorted gun data to the inspector so as to be convenient for the inspector to carry out manual identification.
2. A firearm identification system according to claim 1, wherein the contour image is a contour gray scale image;
The area with the gray value of 0 in the binarized contour image is a gun area, and the area with the gray value of 255 is a background area; the area corresponds to the size of the area corresponding to all pixel points with gray values of 0 in the binarized contour image; the perimeter is the length integral of the edge of the area with the gray value of 0 in the binarized contour image; the maximum distance between the two points is the maximum distance between the pixel points with the gray value of 0 in the binarized contour image;
the Hu moment is obtained by calculating the contour binarization image according to the Hu moment definition.
3. A firearm identification system according to claim 1 or 2, wherein,
The size coefficient is calculated based on the following formula:
k=h/f; wherein k is a size coefficient; the H is the distance between the camera and the gun to be identified in the imaging direction; f is the focal length of an imaging lens of the camera;
The matching is based on the following formula:
Wherein,
The area of the binarized contour image of the gun to be identified is S, the perimeter of the binarized contour image of the gun to be identified is C, and the maximum distance between two points of the gun to be identified is L; the size coefficient of the gun to be identified is k; the area of the gun in the gun information database is S 1, the circumference of the gun is C 1, the maximum distance between two points of the gun is L 1, and the size coefficient of the gun is k 1;γs、γC、γL, which is the error control coefficient of the area, the circumference and the maximum distance between the two points respectively;
the weighted square error is calculated by the following formula:
Wherein Hu moment of the gun contour binarization image in the candidate gun data set is M; the Hu moment of the contour binarization image of the gun to be identified is N; k represents different components of Hu moment; w is the weight of different components of the Hu moment; WSE is the weighted squared error;
And screening to obtain a screened gun set which is a gun set conforming to WSE < W T in the candidate gun data set, wherein W T is a preset threshold.
4. A firearm identification system according to claim 1, wherein the firearm information collection subsystem comprises: the system comprises a basic attribute acquisition module, a contour image acquisition module, a color image acquisition module and an information acquisition computer with information acquisition software.
5. The firearm identification system of claim 4, wherein the base attribute collection module is configured to collect base attribute information for a firearm;
The base attribute information includes any combination of one or more of the following: name, model number, surface identification, LOGO word description, size, caliber, structure, category, country of production information, manufacturer information, year of production.
6. The firearm identification system of claim 4, wherein the contour image acquisition module is configured to acquire a contour image of the firearm.
7. The firearm identification system of claim 4, wherein the color image acquisition module is configured to acquire a color image of the appearance of the firearm.
8. A firearm identification system according to claim 4, wherein the contour image acquisition module or the color image acquisition module is an image acquisition device;
The image acquisition apparatus includes: the device comprises a liftable support frame, a three-dimensional adjustable support, a ground glass plate for placing a gun, a high-definition color camera, a backlight source and a white light illumination source; wherein,
The three-dimensional adjustable bracket is arranged at the top of the supporting frame;
the ground glass flat plate is horizontally arranged in the middle of the supporting frame;
the backlight source is arranged below the ground glass plate and irradiates the ground glass plate from bottom to top;
the high-definition color camera and the white light illumination light source are arranged on the three-dimensional adjustable bracket.
9. A firearm identification system according to claim 1, wherein said central processing control subsystem comprises: the system comprises a system management module, a gun information management module and a gun identification module; wherein,
The system management module is used for account number and authority management, system state monitoring, data query and report management;
The gun information management module is used for collecting gun information, transmitting data, filing, adding, deleting, modifying, inquiring, searching and counting;
And the gun identification module is used for identifying the gun to be identified.
10. The firearm identification system of claim 1, wherein the firearm information database stores firearm data comprising: serial number, binarized contour image, area, perimeter, maximum distance between two points, size coefficient, color image.
11. The firearm identification system of claim 10, wherein the firearm information database stores firearm data further comprising: gun name, model, type, structure, country of production, manufacturer, year of production, logo.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010767929.2A CN112149660B (en) | 2020-08-03 | 2020-08-03 | Gun identification system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010767929.2A CN112149660B (en) | 2020-08-03 | 2020-08-03 | Gun identification system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112149660A CN112149660A (en) | 2020-12-29 |
| CN112149660B true CN112149660B (en) | 2024-07-12 |
Family
ID=73887816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010767929.2A Active CN112149660B (en) | 2020-08-03 | 2020-08-03 | Gun identification system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149660B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114299484B (en) * | 2021-12-30 | 2025-02-28 | 中国人民解放军陆军工程大学 | Embossed seal character recognition device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256404A (en) * | 2017-06-09 | 2017-10-17 | 王翔宇 | A kind of case-involving gun rifle recognition methods |
| CN110471919A (en) * | 2019-08-02 | 2019-11-19 | 合肥保安集团有限公司 | Signature safe early warning method is kept in arms based on big data and image recognition |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1643264A1 (en) * | 1996-09-18 | 2006-04-05 | MacAleese Companies, Inc. | Concealed weapons detection system |
| PL3764281T3 (en) * | 2016-02-22 | 2025-02-10 | Rapiscan Systems, Inc. | Methods of identifying firearms in radiographic images |
-
2020
- 2020-08-03 CN CN202010767929.2A patent/CN112149660B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256404A (en) * | 2017-06-09 | 2017-10-17 | 王翔宇 | A kind of case-involving gun rifle recognition methods |
| CN110471919A (en) * | 2019-08-02 | 2019-11-19 | 合肥保安集团有限公司 | Signature safe early warning method is kept in arms based on big data and image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112149660A (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145901B (en) | Article identification method, apparatus, computer readable storage medium and computer device | |
| CN102110332B (en) | Book registering and managing device based on computer vision and radio frequency identification technology | |
| CN112699876B (en) | Automatic reading method for various meters of gas collecting station | |
| CN116188475A (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
| CN102509118B (en) | Method for monitoring video retrieval | |
| CN106203415B (en) | bank card number automatic identification device based on digital image processing | |
| CN111949809A (en) | Intelligent processing method for infrared inspection data of power transmission line | |
| CN109784326A (en) | A kind of vehicle chassis detection method based on deep learning | |
| CN102024144A (en) | Container number identification method | |
| CN103530366A (en) | Vehicle searching method and system based on user-defined features | |
| CN111242899B (en) | Image-based flaw detection method and computer-readable storage medium | |
| CN110533654A (en) | The method for detecting abnormality and device of components | |
| CN114694178B (en) | Safety helmet monitoring method and system in power operation based on Faster-RCNN algorithm | |
| CN111651621B (en) | A bullet information management system and terminal | |
| CN118470005B (en) | Defect detection system based on visual recognition technology | |
| CN110288006A (en) | A kind of license plate number automatic Verification method and system | |
| CN108073940B (en) | Method for detecting 3D target example object in unstructured environment | |
| CN112149660B (en) | Gun identification system | |
| CN115131596A (en) | Defect classification device, method, and program | |
| CN109815784A (en) | A kind of intelligent method for classifying based on thermal infrared imager, system and storage medium | |
| CN110263719B (en) | Artificial intelligence oil and gas field prevention and judgment system and method based on big data monitoring | |
| Zheng et al. | An inspection method of rail head surface defect via bimodal structured light sensors | |
| CN111507177B (en) | Identification method and device for metering turnover cabinet | |
| CN118097647A (en) | License plate number shielding detection method and system | |
| CN116580026B (en) | Automatic optical detection method, equipment and storage medium for appearance defects of precision parts |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |