Novel police unmanned aerial vehicle automatic face recognition method and system and computer readable storage medium

Abstract

The invention discloses a novel police unmanned aerial vehicle automatic face recognition method and system and a computer readable storage medium, and relates to the technical field of face recognition, and the method comprises the steps: collecting a face picture through a camera installed on a police unmanned aerial vehicle; carrying out geometric feature extraction on the collected face photo, and establishing a geometric feature map; constructing a geometric model based on the geometric feature map; carrying out local feature extraction on the collected face picture, and establishing an LBP histogram; constructing a series model based on the geometric model and an LBP histogram; and comparing the series model with the face data of the face database, and performing face recognition. According to the method, the influence of environmental factors on face feature extraction can be reduced, the accuracy of face feature extraction is improved, and the accuracy and speed of face recognition are improved.

Description

Technical Field

[0001] The present invention relates to the field of face recognition technology, and in particular to a novel automatic face recognition method and system for police drones and a computer-readable storage medium. Background Art

[0002] Automatic facial recognition by police drones is a comprehensive application that integrates drone technology and facial recognition technology. This technology utilizes the advantages of drones' flexibility and maneuverability in the air and combines it with a facial recognition system to achieve real-time monitoring and identification of target persons. In police work, this technology can provide law enforcement personnel with important intelligence support and operational assistance, improving law enforcement efficiency and accuracy.

[0003] The existing automatic face recognition of police drones collects face data through the camera on the police drone, and transmits the collected face data to the police computer. The computer extracts features of the face photos transmitted by the police drone, matches the extracted features with the face data in the face library, and sends the matching results to law enforcement officers to provide support for their law enforcement. However, the existing police drones collect face data outdoors. The face data collected outdoors is easily affected by environmental factors, which in turn causes the police computer to extract incorrect face features, resulting in inaccurate face recognition, and at the same time reduces the matching speed of face recognition to a certain extent. Summary of the invention

[0004] The purpose of the present invention is to provide a novel automatic face recognition method and system for police drones and a computer-readable storage medium to improve the accuracy and speed of face recognition.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A novel automatic face recognition method for police drones, comprising:

[0007] Collecting facial photos through cameras mounted on police drones;

[0008] Extract geometric features from the collected face photos and establish a geometric feature map;

[0009] constructing a geometric model based on the geometric feature graph;

[0010] Extract local features from the collected face photos and establish an LBP histogram;

[0011] constructing a tandem model based on the geometric model and the LBP histogram;

[0012] The series model is compared with the face data in the face database to perform face recognition.

[0013] To achieve the above object, the present invention also provides the following solution:

[0014] A new type of automatic face recognition system for police drones, including:

[0015] Face collection module, used to collect face photos;

[0016] A geometric model building module is used to extract geometric features from the collected face photos, establish a geometric feature map, and build a geometric model based on the geometric feature map;

[0017] LBP histogram building module, used to extract local features from collected face photos and build LBP histogram;

[0018] A series model building module, used for building a series model based on the geometric model and the LBP histogram;

[0019] The comparison module is used to compare the series model with the face data in the face library to perform face recognition.

[0020] To achieve the above object, the present invention also provides the following solution:

[0021] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned new automatic face recognition method for police drones.

[0022] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0023] The present invention constructs a series model based on the constructed geometric model and LBP histogram, which can reduce the influence of environmental factors on facial feature extraction, improve the accuracy of facial feature extraction, and improve the accuracy and speed of face recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0025] Figure 1 A flowchart of a novel automatic face recognition method for police drones provided in Embodiment 1 of the present invention;

[0026] Figure 2 This is a structural block diagram of a new type of automatic face recognition system for police drones provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The purpose of the present invention is to provide a novel automatic face recognition method, system and computer-readable storage medium for police drones, so that the eye, nose and mouth models of the geometric feature model are integrated with the eye, nose and mouth maps of the LBP histogram, so as to reduce the influence of environmental factors on face feature extraction and improve face recognition accuracy.

[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] Embodiment 1

[0031] This embodiment provides a new automatic face recognition method for police drones. Figure 1 As shown, the method includes:

[0032] S1: Collect facial photos through the camera installed on the police drone.

[0033] By installing a camera on a drone to collect facial data, the facial data collection method has high mobility, can quickly respond and capture targets in complex environments, and to a certain extent improve the law enforcement efficiency of police officers.

[0034] S2: Extract geometric features from the collected face photos and establish a geometric feature map.

[0035] The collected face photos are subjected to geometric feature extraction, that is, the vectors consisting of the relative positions or relative distances of the organs on the face image are extracted, such as the organ positions and distances, facial shape information, organ structure relationships, etc., and a geometric feature map is established.

[0036] S3: Constructing a geometric model based on the geometric feature graph.

[0037] The key points (eyes, nose and mouth) in the geometric feature map are translated and transferred to the standard face template to obtain a geometric model.

[0038] S4: Extract local features of the collected face photos and establish an LBP histogram.

[0039] Specifically, the face image is converted into a grayscale image; according to the structure of the face and the position of the feature points, the image is divided into multiple regional blocks; the local binary pattern (LBP) algorithm, a specific feature extraction algorithm, is used to calculate the grayscale values ​​of all the pixels inside it, determine the feature vector of each regional block, combine the feature vectors of each regional block to form an overall face feature vector, and establish an LBP histogram.

[0040] S5: Construct a series model based on the geometric model and the LBP histogram.

[0041] The geometric model is filled into the LBP histogram, the nose map in the LBP histogram is used as the reference point, and the nose model in the geometric model is used as the corresponding point, so that the eye, nose and mouth models of the geometric model are merged with the eye, nose and mouth maps of the LBP histogram to obtain a series model.

[0042] By constructing a series model, the dependence of the LBP histogram on light can be reduced, and a more stable and robust feature representation can be obtained.

[0043] S6: Compare the series model with the face data in the face database to perform face recognition.

[0044] Compare the series model data with the face data in the face database to obtain the most similar picture and comparison results, complete face recognition, and display the face recognition results.

[0045] The new automatic face recognition method for police drones provided in this embodiment can reduce the impact of environmental factors on face feature extraction, improve the accuracy of face feature extraction, avoid extracting erroneous face features to a certain extent, and improve the speed of face recognition to a certain extent.

[0046] Embodiment 2

[0047] In order to execute the method corresponding to the above embodiment 1 and achieve the corresponding functions and technical effects, this embodiment provides a new automatic face recognition system for police drones. Figure 2 As shown, the system includes: a face acquisition module 1, a geometric model construction module 3, an LBP histogram establishment module 4, a series model construction module 5 and a comparison module 6.

[0048] The face collection module 1 is used to collect face photos; the face collection module 1 includes a camera, which is installed on the police drone and collects face photos through the camera.

[0049] The geometric model building module 3 is used to extract geometric features from the collected face photos, establish a geometric feature map, and build a geometric model based on the geometric feature map.

[0050] The LBP histogram building module 4 is used to extract local features from the collected face photos and build an LBP histogram.

[0051] The series model building module 5 is used to build a series model based on the geometric model and the LBP histogram.

[0052] The comparison module 6 is used to compare the series model with the face data in the face database to perform face recognition.

[0053] like Figure 2 As shown, the system also includes:

[0054] The wireless transmission module 2 installed on the police drone is connected to the face acquisition module 1, the geometric model construction module 3 and the LBP histogram establishment module 4 respectively, and is used to wirelessly transmit the face photos collected by the face acquisition module 1 to the geometric model construction module 3 and the LBP histogram establishment module 4.

[0055] The system also includes:

[0056] The display module 7 is used to display the face recognition result.

[0057] As for the system disclosed in this embodiment, since it corresponds to the method disclosed in the first embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0058] Embodiment 3

[0059] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the new automatic face recognition method for police drones in embodiment 1.

[0060] Embodiment 4

[0061] A computer program product includes a computer program, which, when executed by a processor, implements the new automatic face recognition method for police drones in embodiment one.

[0062] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided by the present invention may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, or a programmable logic device, but are not limited thereto.

[0063] All actions to obtain signals, information or data in this application are carried out in compliance with the relevant data protection laws and policies of the country where they are located, and with the authorization given by the owner of the corresponding device.

[0064] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A new automatic face recognition method for police drones, characterized in that: include: Collecting facial photos through cameras mounted on police drones; Extract geometric features from the collected face photos and establish a geometric feature map; constructing a geometric model based on the geometric feature graph; Extract local features from the collected face photos and establish an LBP histogram; constructing a tandem model based on the geometric model and the LBP histogram; The series model is compared with the face data in the face database to perform face recognition.

2. The new automatic face recognition method for police drones according to claim 1 is characterized in that: Constructing a geometric model based on the geometric feature graph specifically includes: The key points in the geometric feature map are transferred to a standard face template to construct a geometric model; the key points include eyes, nose and mouth.

3. The new automatic face recognition method for police drones according to claim 1 is characterized in that: Extract local features from the collected face photos and build an LBP histogram, including: Convert the face image to grayscale image; Dividing the grayscale image into a plurality of area blocks according to the structure and feature point positions of the face; Calculate the grayscale values ​​of all pixels in each of the area blocks using a local binary pattern to determine a feature vector of each of the area blocks; An LBP histogram is established based on the feature vectors of each of the area blocks.

4. The new automatic face recognition method for police drones according to claim 1 is characterized in that: Constructing a series model based on the geometric model and the LBP histogram specifically includes: Taking the nose map in the LBP histogram as a reference point and the nose model in the geometric model as a corresponding point, the eye model, nose model and mouth model of the geometric model are merged with the eye map, nose map and mouth map of the LBP histogram to obtain a series model.

5. The new automatic face recognition method for police drones according to claim 1 is characterized in that: Also includes: Display the face recognition results.

6. A new type of automatic face recognition system for police drones, characterized by including: Face collection module, used to collect face photos; A geometric model building module is used to extract geometric features from the collected face photos, establish a geometric feature map, and build a geometric model based on the geometric feature map; LBP histogram building module, used to extract local features from collected face photos and build LBP histogram; A series model building module, used for building a series model based on the geometric model and the LBP histogram; The comparison module is used to compare the series model with the face data in the face library to perform face recognition.

7. The new police drone automatic face recognition system according to claim 6 is characterized in that: The face collection module includes a camera, and the camera is installed on a police drone.

8. The new police drone automatic face recognition system according to claim 6 is characterized in that: Also includes: A wireless transmission module, connected to the face acquisition module, the geometric model construction module and the LBP histogram establishment module respectively, and used for wirelessly transmitting the face photos acquired by the face acquisition module to the geometric model construction module and the LBP histogram establishment module; The wireless transmission module is installed on the police drone.

9. The new police drone automatic face recognition system according to claim 6 is characterized in that: Also includes: The display module is used to display the face recognition results.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the new automatic face recognition method for police drones described in any one of claims 1 to 5 is implemented.

Images