CN115527293B

CN115527293B - Method for opening door by security chip based on human body characteristics and security chip device

Info

Publication number: CN115527293B
Application number: CN202211487248.6A
Authority: CN
Inventors: 赵仲明; 刘曼; 李�杰
Original assignee: Guangzhou Wise Security Technology Co Ltd
Current assignee: Guangzhou Wise Security Technology Co Ltd
Priority date: 2022-11-25
Filing date: 2022-11-25
Publication date: 2023-04-07
Anticipated expiration: 2042-11-25
Also published as: CN115527293A

Abstract

The application discloses a method for opening a door by a security chip based on human body characteristics, a security chip device, equipment and a medium, and belongs to the technical field of communication. The method comprises the following steps: acquiring a human body image through an image acquisition unit of a vehicle terminal; the processing unit identifies the brightness information of the color image and determines the fusion weight of the color image and the infrared image; the processing unit fuses the color image and the infrared image to obtain a fused image; the checking unit compares the fused image with user human body characteristic data which are prestored in the storage unit under different brightness information by adopting a safety checking rule; the processing unit generates an unlocking instruction after the vehicle terminal recognizes that the user reaches a certain area, and controls the vehicle door to be unlocked through the vehicle bus. According to the scheme, the safety chip is used for recognizing the human body image and calculating the characteristic data of the user, the effect of controlling the automatic unlocking of the vehicle door can be achieved, and the convenience and the safety of vehicle use are improved.

Description

Method for opening door by security chip based on human body characteristics and security chip device

Technical Field

The application belongs to the technical field of communication, and particularly relates to a method for opening a door by a security chip based on human body characteristics, a security chip device, equipment and a medium.

Background

With the development of economy, people have more and more large demands on vehicles, and higher standards are provided for the use convenience of automobiles. Meanwhile, the automobile industry is continuously improving and promoting in the aspect of driving, and is also continuously innovated in the aspect of user experience, especially in the aspect of vehicle unlocking modes.

In the prior art, unlocking is usually performed manually by using a mechanical key or by using a remote control key to send out electric waves, and an automobile antenna receives the electric waves. However, the above unlocking methods all require the automobile key to be carried, and once the automobile key is forgotten to be carried or the key is lost, the automobile cannot be used continuously, and meanwhile, anyone can unlock the automobile by using the key of the same automobile, and the automobile cannot identify whether the user is the user himself or herself. Therefore, the existing vehicle unlocking mode is complicated and has the problem of poor safety.

Disclosure of Invention

The embodiment of the application aims to provide a method for opening a door by a security chip based on human body characteristics, a security chip device, equipment and a medium, and solves the problems that in the prior art, a user can unlock a vehicle conveniently and the vehicle cannot identify whether the user is the user or not, and the security chip is used for carrying out image identification and comparison calculation on human body images and human body data of the user, so that the effect of judging whether the user is the vehicle user or not according to the characteristics of the user and further automatically unlocking a vehicle door or not can be realized, and the convenience and the security of the user for using the vehicle are improved.

In a first aspect, an embodiment of the present application provides a method for a security chip to open a door based on human body characteristics, where the method is executed by the security chip, and the security chip is disposed at a vehicle terminal; the method comprises the following steps:

when the vehicle terminal identifies that the human body approaches the vehicle, the human body image is acquired through an image acquisition unit of the vehicle terminal; wherein the human body image comprises a color image and an infrared image;

the processing unit identifies brightness information of the color image and determines the fusion weight of the color image and the infrared image according to the brightness information;

the processing unit fuses the color image and the infrared image based on the fusion weight to obtain a fused image;

the checking unit compares the fused image with user human body characteristic data which are prestored in a storage unit and are under different brightness information by adopting a safety checking rule; if the comparison is successful, determining that the unlocking condition of the vehicle is met;

the processing unit generates an unlocking instruction after the vehicle terminal recognizes that the user reaches a certain area, and controls the vehicle door to be unlocked through the vehicle bus.

Further, the check unit compares the fused image with the user human body characteristic data which is prestored in the storage unit and is under different brightness information by adopting a safety check rule, and the check unit comprises:

acquiring user human body characteristic data under target brightness information matched with the current brightness information from a storage unit;

acquiring a face image and a posture image in the fusion image;

for the face image, obtaining face feature data by adopting a first feature conversion rule; for the posture image, obtaining posture characteristic data by adopting a second characteristic conversion rule;

and comparing the human face characteristic data and the posture characteristic data with the user human body characteristic data under the target brightness information.

Further, comparing the human face feature data and the posture feature data with the user human body feature data under the target brightness information, and calculating the human face feature data and the posture feature data, including:

determining a first comparison weight of the face feature data and a second comparison weight of the posture feature data;

comparing and calculating the face feature data and the user human body feature data based on the first comparison weight to obtain a first comparison result; comparing and calculating the posture characteristic data and the user human body characteristic data based on the second comparison weight to obtain a second comparison result;

and determining a comparison calculation result according to the first comparison result and the second comparison result.

Further, the sum of the first contrast weight and the second contrast weight is 1;

the determination process of the first contrast weight and the second contrast weight comprises the following steps:

acquiring a target area where a face image in the human body image is located;

determining the first contrast weight according to the distribution position of the target region in the human body image, the average brightness of the target region and the image quality of the target region;

determining the second contrast weight according to the first contrast weight.

Further, the human body feature data of the user are obtained by encrypting the human face feature data and encrypting the posture feature data based on different encryption rules determined by different fusion weights;

correspondingly, after determining the fusion weight of the color image and the infrared image according to the brightness information, the method further comprises the following steps:

determining a face encryption rule and a posture encryption rule according to the fusion weight;

and encrypting the face feature data by adopting the face encryption rule, and encrypting the posture feature data by adopting the posture encryption rule.

In a second aspect, an embodiment of the present application provides a security chip device for opening a door based on human body characteristics, where the device is configured with a security chip, and the security chip is disposed at a vehicle terminal; the device comprises:

the image acquisition unit is used for acquiring a human body image when the vehicle terminal identifies that the human body approaches the vehicle; wherein the human body image comprises a color image and an infrared image;

the processing unit is used for identifying the brightness information of the color image and determining the fusion weight of the color image and the infrared image according to the brightness information;

the processing unit is further used for fusing the color image and the infrared image based on the fusion weight to obtain a fused image;

the checking unit is used for comparing the fused image with user human body characteristic data which are prestored in the storage unit under different brightness information by adopting a safety checking rule; if the comparison is successful, determining that the vehicle unlocking condition is met;

and the processing unit is used for generating an unlocking instruction after the vehicle terminal identifies that the user reaches a certain area, and controlling the unlocking of the vehicle door through the vehicle bus.

Further, the verification unit includes:

the characteristic data acquisition subunit is used for acquiring user human body characteristic data under target brightness information matched with the current brightness information from the storage unit;

the face image acquisition subunit is used for acquiring a face image and a posture image in the fusion image;

the characteristic data conversion subunit is used for obtaining the human face characteristic data for the human face image by adopting a first characteristic conversion rule; obtaining body state feature data of the body state image by adopting a second feature conversion rule;

and the comparison calculation subunit is used for comparing and calculating the human face characteristic data and the posture characteristic data with the user human body characteristic data under the target brightness information.

Further, the comparison calculation subunit is specifically configured to:

In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor, and when the program or instructions are executed by the processor, the steps of the method for opening a door by a security chip based on human body characteristics according to the first aspect are implemented.

In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instructions are stored, and when the program or instructions are executed by a processor, the program or instructions implement the steps of the method for opening a door by a security chip based on human body characteristics according to the first aspect.

In the embodiment of the application, when the vehicle terminal identifies that the human body approaches the vehicle, the image acquisition unit of the vehicle terminal acquires the human body image; wherein the human body image comprises a color image and an infrared image; the processing unit identifies brightness information of the color image and determines the fusion weight of the color image and the infrared image according to the brightness information; the processing unit fuses the color image and the infrared image based on the fusion weight to obtain a fusion image; the checking unit compares the fused image with user human body characteristic data which are prestored in the storage unit under different brightness information by adopting a safety checking rule; if the comparison is successful, determining that the vehicle unlocking condition is met; the processing unit generates an unlocking instruction after the vehicle terminal recognizes that the user reaches a certain area, and controls the vehicle door to be unlocked through the vehicle bus. According to the scheme, the problem of convenience of a user for unlocking the vehicle and the problem of safety of the vehicle whether the user is a user or not in the prior art are solved, the safety chip is used for carrying out image recognition and contrast calculation on the human body image and the human body data of the user, the effect of judging whether the vehicle user is the vehicle user or not and further automatically unlocking the vehicle door or not according to the characteristics of the user can be achieved, and convenience and safety of the user for using the vehicle are improved.

Drawings

Fig. 1 is a schematic flowchart of a method for opening a door by a security chip based on human body characteristics according to an embodiment of the present application;

fig. 2 is a schematic flowchart of a method for opening a door by a security chip based on human body characteristics according to a second embodiment of the present application;

fig. 3 is a schematic flowchart of a method for opening a door by a security chip based on human body characteristics according to a third embodiment of the present application;

fig. 4 is a schematic structural diagram of a security chip device for opening a door based on human body characteristics, provided by a security chip according to a fourth embodiment of the present application;

fig. 5 is a schematic structural diagram of an electronic device provided in this application embodiment five.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, specific embodiments of the present application will be described in detail with reference to the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be further noted that, for the convenience of description, only some but not all of the matters relating to the present application are shown in the drawings. Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.

The technical solutions in the embodiments of the present application will be described below clearly with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived from the embodiments in the present application by a person skilled in the art, are within the scope of protection of the present application.

The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that embodiments of the application may be practiced in sequences other than those illustrated or described herein, and that the terms "first," "second," and the like are generally used herein in a generic sense and do not limit the number of terms, e.g., the first term can be one or more than one. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.

The method, the security chip device, the apparatus and the medium for opening the door by the security chip according to the embodiments of the present application based on human body characteristics are described in detail below with reference to the accompanying drawings.

Example one

Fig. 1 is a schematic flowchart of a method for opening a door by a security chip based on human body characteristics according to an embodiment of the present application. The method is executed by a security chip, and the security chip is arranged on a vehicle terminal. As shown in fig. 1, the method specifically comprises the following steps:

s101, when the vehicle terminal recognizes that a human body approaches a vehicle, acquiring a human body image through an image acquisition unit of the vehicle terminal; wherein the human body image comprises a color image and an infrared image;

firstly, the use scene of the embodiment of the application may be a scene in which the vehicle door is automatically unlocked, specifically, after the user enters a certain range around the vehicle, the vehicle performs image recognition and data comparison on the user, and if the recognition and comparison results meet a preset error range, it is determined that the user is the vehicle owner, and then the vehicle door is automatically unlocked.

Based on the above usage scenario, the execution subject of the embodiment of the present application is a security chip disposed at a vehicle terminal, and specifically, the security chip may be a chip having image recognition, image processing, data calculation, and data encryption and decryption functions, and is not limited specifically herein.

In the scheme, the security chip can be a trusted platform module, is a device capable of independently generating a key, encrypting and decrypting, has an independent processor and a storage unit inside, and can store the key and feature data to provide encryption and security authentication services for a computer. The encryption is carried out by using the security chip, the secret key is stored in hardware, and stolen data cannot be decrypted, so that the business privacy and the data security are protected.

The security chip is equivalent to a safe case, the most important password data is stored in the security chip, the security chip is communicated with a main processor and a Basic Input Output System (BIOS) chip of the notebook through a System Management Bus (SMB), and then various security protection works are completed by matching with Management software. According to the principle of the security chip, because the password data can only be output but not input, the encryption and decryption operations are completed in the security chip, and the result is only output to the upper layer, thereby avoiding the chance of password cracking.

In the scheme, the vehicle terminal can be a front-end device of a vehicle monitoring and management system, can also be called a vehicle scheduling and monitoring terminal, and specifically can be a terminal device which is installed in a vehicle and consists of various external devices such as a vehicle-mounted video server, an LCD touch screen, an external camera, a call handle, an automobile burglar alarm and the like. The vehicle terminal can be used for carrying out real-time monitoring, data recording, scheduling management, system management, communication management and the like on the vehicle. The safety chip is connected with the vehicle terminal through a peripheral interface of the vehicle terminal, and processes and calculates images and data of the image information acquired by the vehicle terminal.

In the scheme, the color image may be a human body image similar to a color photograph or a video image and consistent with an actual color, specifically, each pixel in the image may be divided into three primary color components of red (R), green (G), and blue (B), the color in the color image is obtained by superimposing the primary color components according to different proportions, and each primary color component directly determines the intensity of the primary color. The color image can be obtained by a camera by using the reflection principle of light. The color image has the characteristics of high definition and high reduction degree, but the color image can be limited by the brightness of the external environment, and the definition of the color image is higher when the brightness of the environment is higher. The infrared image may be an image obtained by acquiring the intensity of infrared rays radiated from the human body, and the principle of the infrared image acquisition is that all objects above the absolute temperature of the space will form a thermal infrared radiation state, while objects below the absolute temperature of the space by-273.15 degrees do not have thermal infrared radiation, and the level of radiation energy of the object is detected by a thermal infrared photographic system and is converted into an infrared image of a target object through system processing. The infrared image has the advantages that the infrared image can emit infrared light to perform night vision imaging without the help of external ambient light; the night vision range is wide, and the influence of the environment is small. Therefore, at night or in a dark environment, the human body is difficult to be subjected to photosensitive imaging due to insufficient light intensity, and the reliability of the human body image represented by the infrared image is high.

In this scheme, the vehicle terminal can set up wide angle camera in the locomotive position and discern whether there is the human body to be close to the vehicle, the mode that the image acquisition unit acquireed human image can be that utilize wide angle camera to project the human body and the optical image that scenery in the surrounding environment produced through camera LENS (LENS) on the image sensor surface, then trun into the signal of telecommunication, become digital image signal after A/D (analog-to-digital conversion) conversion, send to the processing in digital signal processing chip (DSP) again, rethread USB interface transmits to and handles in the computer, just can obtain human image. The human body image comprises a color image and an infrared image, and the color image and the infrared image are acquired simultaneously, so that the identification error caused by the external environment brightness factor can be reduced, and the reliability of human body image identification is improved.

S102, identifying brightness information of the color image by a processing unit, and determining fusion weight of the color image and the infrared image according to the brightness information;

in this embodiment, the brightness of the color image is a perceived continuum from a white surface to a black surface, and is determined by the reflection coefficient, and the brightness is emphasized by the object and is emphasized by the "reflection". In color images, the brightness and contrast are correlated, i.e. by the same increment of increase (increasing brightness) or decrease (decreasing brightness) of the RGB color componentsThe brightness adjustment is shown to be a multiplication of each component by a percentage value. The color image brightness information can be represented by a pixel value at a certain point in the image, and the processing unit in the security chip utilizes the formula for R, G and B components at a certain point in the image:

and calculating to obtain the brightness information of the color image.

In the scheme, the image fusion refers to that image data which are collected by a multi-source channel and related to the same target are subjected to image processing, computer technology and the like, favorable information in respective channels is extracted to the maximum extent, and finally high-quality images are synthesized, so that the utilization rate of image information is improved, the computer interpretation precision and reliability are improved, the spatial resolution and the spectral resolution of an original image are improved, the monitoring is facilitated, and the image fusion can be completed by a processing unit in a safety chip. Generally, image fusion is divided into three layers from low to high: data level fusion, feature level fusion and decision level fusion. The data-level fusion is also called pixel-level fusion, which refers to a process of directly processing data acquired by a sensor to obtain a fusion image, is the basis of high-level image fusion, and is also one of the key points of the current image fusion research. The advantage of this fusion is to keep as much raw data as possible on site, providing subtle information that other fusion levels cannot provide. The pixel level fusion has a space domain algorithm and a transform domain algorithm, and the space domain algorithm has various fusion rule methods, such as a logic filtering method, a gray weighted average method, a contrast modulation method and the like; the transformation domain also has a pyramid decomposition fusion method and a wavelet transformation method. The wavelet transform is currently the most important and most common method. In feature level fusion, it is ensured that the different images contain informative features, such as infrared light for the heat of the object, visible light for the brightness of the object, etc. The decision-level fusion mainly depends on subjective requirements, and also has some rules, such as Bayes method, D-S evidence method, voting method and the like. Fusion algorithms often combine the average, entropy, standard deviation, and average gradient of images; the average gradient reflects the contrast of the tiny details and the texture change characteristics in the image, and also reflects the definition of the image.

The fusion of the images at the pixel level is the lowest layer, which fuses the different physical parameters. In the obtained fusion image, each pixel is determined by the corresponding area of several source images. The feature level fusion is to fuse features extracted from each input image, such as shape, size, texture, contrast, and the like. And fusion is carried out on the extracted features, so that the useful features can be better embodied. Fusion at the symbolic decision level is a higher abstraction of the image information. At this time, the input image is already the features and the classification obtained by information extraction, and a representative symbol or a corresponding decision is obtained by fusion processing. The choice of the individual adaptation levels depends on different factors in practice, such as: an image source, etc. Meanwhile, the selection of different levels of processing is also related to the result obtained by image preprocessing.

In the scheme, a processing unit in the security chip calculates brightness information of the color image through a formula, and calculates the respective occupation ratio of the color image and the infrared image, namely the respective fusion weight of the color image and the infrared image, with the aim of highest image fusion definition under different brightness information. Since the human body image acquired by the vehicle terminal includes the color image and the infrared image, the sum of the fusion weights of the color image and the infrared image is 1.

S103, fusing the color image and the infrared image by the processing unit based on the fusion weight to obtain a fused image;

in the scheme, a processing unit in the security chip performs weighted average calculation on the pixel values and the fusion weights of the color image and the infrared image by using the fusion weights of the color image and the infrared image corresponding to different brightnesses to obtain a fusion image, specifically, weights are respectively given to gray values of the two images at the same pixel point according to gray information of the two images, and the gray value of the fusion image is a weighted sum of the gray values of the two images. If it is a color mapAnd repeating the operation on three channels to obtain the fusion gray scale on the three channels. Assuming that two images A and B to be fused are consistent in size and are M × N pixel points, the fused image F can be represented as

In which

And

is the fusion weight of images A and B and satisfies

. The image fusion method based on the pixel weighted average has the advantages of simplicity, easiness in implementation and high operation speed, and can improve the signal-to-noise ratio of the fused image.

S104, comparing the fused image with user human body characteristic data which are prestored in a storage unit under different brightness information by a verification unit by adopting a safety verification rule; if the comparison is successful, determining that the vehicle unlocking condition is met;

in the scheme, the human body characteristic data can be data which can better represent human body characteristics and distinguish a person with the vehicle automatic unlocking authority from other persons, and specifically, the human body characteristic data can be body state data such as height, three-dimensional girth, shoulder width and leg length of a user, and can also be face characteristic data such as pupil distance, nose height, forehead width and forehead height of the user. Since the computer does not recognize the image, only recognizes the number, and in order for the computer to "understand" the image and thus have a true "vision", it is necessary to obtain a representation or description of the image, which is "non-image", using values, vectors, symbols, and the like. This process is feature extraction, and the representations or descriptions of these "non-images" extracted are features. With these features in the form of numerical values or vectors, we can teach the computer how to understand the features through a training process, thereby giving the computer the ability to recognize images. Thus, the human feature data may be a number distribution matrix for representing colors, borders, and outlines of human images.

The safety check rule can be preset by the safety chip, and the human body characteristic data of the user can be allowed to change within an error range under different brightness information. Because the image definition of the color image and the infrared image acquired under different brightness information has a certain error, the fused image also has an error range. The verification unit in the safety chip can compare the identified user fusion image with user human body characteristic data which are prestored in the storage unit and under different brightness information through codes, if the comparison result accords with the error range of a safety verification rule, the user is determined to accord with the vehicle unlocking condition, wherein the storage unit can prestore the human body characteristic data of a plurality of users, specifically, the human body characteristic data of different users can be prestored in the storage unit through a camera according to the requirements of a vehicle owner, after the human body characteristic data of the fusion image is obtained, the data is compared with the characteristic data of all users in the storage unit, if matched data which accord with the range of the safety verification rule exists, the comparison is successful, and the user is determined to be the user who accords with the vehicle unlocking condition.

In the scheme, the extraction of the human body characteristic data can be that the security chip performs operations such as denoising, transformation and smoothing on the acquired image to perform information preprocessing on the image, so that the important characteristics of the image are improved, and then data extraction is performed according to the contour characteristics, the region characteristics and the like of the human body image, and the extraction mode of the human body characteristic data mainly comprises a boundary characteristic method, a Fourier characteristic operator method, a shape invariant moment method and the like. The hough transform method and the boundary direction histogram method are two most typical boundary feature methods, and the hough transform method can be that a point under an original image coordinate system corresponds to a straight line in a parameter coordinate system, whereas a straight line under the parameter coordinate system corresponds to a point under the original image coordinate system. Then, after each point in the original image coordinate system is projected to the parameter coordinate system, the gathered points are found, and the gathered points form a straight line in the original coordinate system. The boundary direction histogram method may be to first find the edge of the image by using a common image edge detection operator, and then make a histogram about the size and direction of the edge. The usual approach is to construct an image gray-scale gradient direction matrix. Commonly used edge detection operators include Laplacian operators, sobel operators, prewitt operators, canny operators, and the like. An image is composed of many discrete pixels and the operators mentioned above will approximate the value of the partial derivative by means of difference. The Canny operator is an image edge detection operator with a good effect. The method is divided into two stages, firstly, gaussian smoothing is carried out on an image, and then Roberts operator operation is carried out on the smoothed image. The Fourier feature operator is also called a Fourier shape descriptor and mainly used for carrying out discrete Fourier transform on the outline of the target boundary to obtain quantitative expression of the shape of the target boundary. The main idea of the shape invariant moment method is to use a transformation insensitive region-based geometric moment feature as a shape feature, which is called "invariant moment" because the moment feature does not change under the environment of rotation, translation and scale scaling.

And S105, the processing unit generates an unlocking instruction after the vehicle terminal recognizes that the user reaches a certain area, and controls the vehicle door to be unlocked through the vehicle bus.

In this embodiment, the vehicle bus may be a system that connects the electrical nodes inside the vehicle via a communication protocol to control the local area network inside the vehicle. The nodes complete preset control functions and actions such as on-off of lamplight, starting and stopping of a motor and the like according to the information of the nodes and the information on the bus, and communication among the nodes is achieved through the bus. Each node is generally constituted by an MCU (or DSP, etc.), interface circuits, a bus line controller, a bus driver, and the like. In addition, in order to meet the real-time requirements of each electronic system, common data (such as information of engine speed, wheel speed, throttle pedal position, etc.) of the automobile must be shared, and a Controller Area Network (CAN) is a bus commonly used in the current automobile, and is a serial communication Network capable of effectively supporting distributed control and real-time control. It connects each single control unit in some form (mostly star) to form a complete system.

In the scheme, after the user reaches a certain area, the vehicle terminal acquires the human body image of the user and extracts the characteristic data, and the area can be a range within which the vehicle terminal can accurately and clearly identify the identity of the user. And after the vehicle terminal identifies that the user is a user with the automatic unlocking authority of the vehicle door, the processing unit in the safety chip generates an unlocking instruction through coding, and controls the vehicle door to be unlocked through a vehicle bus in a wireless transmission mode.

According to the technical scheme provided by the embodiment, when the vehicle terminal identifies that the human body approaches the vehicle, the image acquisition unit of the vehicle terminal acquires the human body image; wherein the human body image comprises a color image and an infrared image; the processing unit identifies brightness information of the color image and determines the fusion weight of the color image and the infrared image according to the brightness information; the processing unit fuses the color image and the infrared image based on the fusion weight to obtain a fusion image; the checking unit compares the fused image with user human body characteristic data which are prestored in a storage unit and are under different brightness information by adopting a safety checking rule; if the comparison is successful, determining that the vehicle unlocking condition is met; the processing unit generates an unlocking instruction after the vehicle terminal recognizes that the user reaches a certain area, and controls the vehicle door to be unlocked through the vehicle bus. The problem of the user to the convenience of vehicle unblock and the security problem whether the unable discernment user of vehicle is the user of prior art is solved, carry out image recognition and contrast calculation to user's human image and human data through utilizing the security chip, can realize judging whether for the vehicle user and then whether effect of automatic unblock door according to user's characteristic, improved convenience and security that the user used the vehicle.

Example two

Fig. 2 is a schematic flowchart of a method for opening a door by a security chip based on human body characteristics according to the second embodiment of the present application. As shown in fig. 2, the specific method includes the following steps:

s201, when the vehicle terminal identifies that the human body approaches the vehicle, acquiring a human body image through an image acquisition unit of the vehicle terminal; wherein the human body image comprises a color image and an infrared image;

s202, identifying brightness information of the color image by a processing unit, and determining fusion weight of the color image and the infrared image according to the brightness information;

s203, fusing the color image and the infrared image by the processing unit based on the fusion weight to obtain a fused image;

s204, acquiring user human body characteristic data under target brightness information matched with the current brightness information from the storage unit;

in the scheme, the storage unit can pre-store the user human body characteristic data under different brightness information in a database establishing mode, wherein the user human body characteristic data can be input and identified for human body images through the camera, and specifically, the user human body data can be human body data of a plurality of users with vehicle automatic unlocking authority. The checking unit acquires the user human body characteristic data under the corresponding target brightness information by inputting the brightness information of the currently acquired image into the storage unit.

S205, acquiring a face image and a posture image in the fusion image;

in the scheme, the safety chip can perform face image recognition on the fused image, the face image recognition can be based on the facial features of people, whether the face exists in the input face image is judged firstly, and if the face exists, the position and the size of each face and the position information of each main facial organ are further given. And further extracting the identity characteristics implied in each face according to the information, and comparing the identity characteristics with the known faces so as to identify the identity of each face, specifically, the method can be used for coding the pre-stored face data characteristics, coding the characteristic data of the currently identified face image, and retrieving and comparing the current image coding with the coding. The body state image can be obtained by a security chip by combining global feature extraction and local feature extraction, the global feature describes the whole detected human body, and is generally obtained by a background subtraction method or a tracking method, information such as the edge, silhouette, optical flow and the like of the human body is generally adopted, and the features are sensitive to noise, partial shielding and change of visual angles. The human behavior recognition local feature extraction refers to extracting points or blocks of interest in a human body. Accurate body positioning and tracking is not required and local features are not very sensitive to body appearance changes, visual changes and partial occlusion problems. The fusion of global and local features combines the sufficient information content of the global features and the view angle change of the local features, and has the advantages of insensitive partial shielding problem and strong anti-interference performance.

S206, for the face image, obtaining face feature data by adopting a first feature conversion rule; for the body state image, obtaining body state feature data by adopting a second feature conversion rule;

in this scheme, the first feature conversion rule may be a conversion rule preset according to the recognition mode of the face image, and specifically, may be an algorithm rule for encoding the data features of the face, for example: convolutional neural network algorithms, and the like. And for the face image, obtaining face feature data by adopting a first feature conversion rule. The second feature transformation rule may be a transformation rule preset according to the recognition mode of the body state image, and specifically may be a rule for performing transformation according to the edge coordinates of the body state contour, for example: performing edge point tracing according to the human body image obtained by feature extraction, setting a coordinate system to obtain the coordinates of the body type edge points, obtaining the body type outline of the user according to the human body feature data, and obtaining the body type feature data according to the edge point coordinates and the outline.

S207, comparing the human face feature data and the posture feature data with user human body feature data under target brightness information;

in the scheme, the face feature data and the body state feature data are compared with the corresponding user body feature data under the current brightness information, specifically, the obtained face feature data and the body state feature data are subjected to ratio calculation with all the user body feature numbers in the storage unit to obtain the similarity between the current user and all the user feature data in the storage unit, and the comparison result is determined according to whether the similarity meets the range of the preset safety check rule or not.

Based on the above embodiment, optionally, the user human body feature data is obtained by encrypting the human face feature data and the posture feature data based on different encryption rules determined by different fusion weights;

and encrypting the face characteristic data by adopting the face encryption rule, and encrypting the posture characteristic data by adopting the posture encryption rule.

In the scheme, since data transmission is performed in the process of acquiring the human body characteristic data of the user by the security chip, in order to ensure the information security of the user, the security chip is required to encrypt the human body characteristic data of the user. The data to be stored can be encrypted from plaintext to ciphertext by an encryption algorithm and an encryption key. The plaintext may be a matrix of raw or unencrypted body characteristic data. The encryption algorithm is used for encrypting the data, input information of the encryption algorithm is a plaintext and a secret key, and the ciphertext can be in a format after the plaintext is encrypted and is output information of the encryption algorithm. The encryption algorithm is public, while the key is not. The ciphertext should not be understood by a keyless user for storage and transmission of data. The key may be a character string composed of numbers, letters or special symbols, and is used for controlling the data encryption and decryption processes. The encryption algorithm may be a transformation method adopted by encryption, wherein the encryption algorithm may be a symmetric encryption algorithm, an asymmetric encryption algorithm, or a digital digest algorithm, etc., the symmetric encryption is to use the same key for encryption and decryption, the asymmetric encryption is to use different keys for encryption and decryption, and there are usually two keys, called "public key" and "private key", which must be used in pair, otherwise, the encrypted file cannot be opened. The public key is published to the outside, and the private key cannot be known only by a person of a holder. Encryption may be performed at different levels, most commonly at the application, link and network layers. Data encryption can be divided into two approaches: one is to implement data encryption by hardware, and the other is to implement data encryption by software. Data encryption is generally referred to as encrypting data by software. There are three methods for implementing network data encryption by hardware: link layer encryption, node encryption, and end-to-end encryption. Common software encryption algorithms are classified into symmetric encryption and asymmetric encryption.

In the scheme, the encryption rule may be determined according to different image fusion weights under different luminance information, and the encryption rule may be one of a symmetric encryption algorithm, an asymmetric encryption algorithm, a digital digest algorithm, or the like. And encrypting the face characteristic data and the posture characteristic data under the corresponding brightness information according to an encryption rule to obtain the human body characteristic data of the user.

In the scheme, because the face image identification needs to identify finer data such as five sense organs and the like, and the posture image identification only needs to identify body contour data and the like, the definition requirements on the face and posture identification are inconsistent. After the fusion weight of the color image and the infrared image is determined by the obtained brightness information, the face encryption rule and the posture encryption rule can be determined according to the fusion weight, specifically, if the fusion weight of the color image is larger, the definition of the fusion image is higher, and then the face characteristic data is identified more accurately, under the condition, a more reliable encryption algorithm needs to be adopted for the face characteristic data, for example: the asymmetric encryption algorithm is used as an encryption rule, and the body state characteristic data can utilize a symmetric encryption algorithm which is simple and convenient to calculate. If the infrared image fusion weight is larger, the image definition is poorer but the stability is better, so an asymmetric encryption algorithm can be used as an encryption rule of the infrared image.

In the scheme, the face encryption rule and the posture encryption rule are determined according to the fusion weight, and the face characteristic data and the posture characteristic data are encrypted respectively based on the encryption rules, so that the leakage and the loss of the human characteristic data of a user in the transmission process can be prevented, and the safety of user information is improved.

S208, if the comparison is successful, determining that the vehicle unlocking condition is met;

s209, the processing unit generates an unlocking instruction after the vehicle terminal recognizes that the user reaches a certain area, and controls the vehicle door to be unlocked through the vehicle bus.

According to the technical scheme provided by the embodiment, the security chip acquires user human body feature data under target brightness information matched with the current brightness information from the storage unit according to the current brightness information, acquires a face image and a body state image in a current user fusion image, determines a first feature conversion rule and a second feature conversion rule according to an image acquisition mode, further determines face feature data and body state feature data in the current fusion image according to a conversion rule, and compares the face feature data and the body state feature data in the current fusion image with the user human body feature data under the current brightness information in the storage unit for calculation. According to the scheme, the safety chip is used for acquiring the feature data of the face and the posture of the current user, and whether the user is a certain user in the storage unit can be identified according to the comparison of the brightness information and the human body feature data of all users under the same brightness information in the storage unit, so that whether the user has the automatic unlocking authority of the vehicle door is judged, and the convenience of the user in using the vehicle is improved.

EXAMPLE III

Fig. 3 is a schematic flowchart of a method for opening a door by a security chip based on human body characteristics according to a third embodiment of the present application. As shown in fig. 3, the specific method includes the following steps:

s301, when the vehicle terminal recognizes that the human body approaches the vehicle, acquiring a human body image through an image acquisition unit of the vehicle terminal; wherein the human body image comprises a color image and an infrared image;

s302, identifying the brightness information of the color image by a processing unit, and determining the fusion weight of the color image and the infrared image according to the brightness information;

s303, fusing the color image and the infrared image by the processing unit based on the fusion weight to obtain a fused image;

s304, acquiring user human body characteristic data under target brightness information matched with the current brightness information from the storage unit;

s305, acquiring a face image and a posture image in the fusion image;

s306, for the face image, obtaining face feature data by adopting a first feature conversion rule; for the body state image, obtaining body state feature data by adopting a second feature conversion rule;

s307, determining a first comparison weight of the face feature data and a second comparison weight of the posture feature data;

in this scheme, the first contrast weight and the second contrast weight may be weights for performing contrast calculation on the face feature data and the posture feature data and the human body feature data stored in the storage unit, and the contrast weights may be determined according to the sharpness of the face image and the posture image in the fused human body image, for example: when the current brightness is high, the fusion weight of the color image is large, and the definition of the face image is high, the set first contrast weight is large, and the set second contrast weight is small, wherein the sum of the first contrast weight and the second contrast weight is 1.

Based on the above embodiment, optionally, the sum of the first contrast weight and the second contrast weight is 1;

acquiring a target area where a face image in the human body image is located;

determining the second contrast weight according to the first contrast weight.

In the scheme, the security chip can respectively acquire the face image and the posture image from the fused image, wherein the face feature data and the posture feature data are all factors forming the human body feature data, and therefore the sum of the first contrast weight corresponding to the face feature data and the second contrast weight corresponding to the posture feature data is 1.

In the scheme, the process of acquiring the target area where the face image in the human body image is located may be a process of judging whether a face exists in a dynamic scene and a complex background and separating the face image, and specifically, the process may be the process of acquiring the face image by using one or more methods of a reference template method, a face rule method, a sample learning method, a feature sub-face method and the like. The reference template method comprises the steps of firstly designing one or more standard face templates, then calculating the matching degree between a sample collected by testing and the standard templates, and judging whether a face exists or not through a threshold value; the face rule method can be used for extracting structural distribution characteristics of the face and generating corresponding rules according to the characteristics to judge whether the test sample contains the face; the sample learning method can be a method adopting an artificial neural network in pattern recognition, namely, a classifier is generated by learning a face image sample set and a non-face image sample set; the feature sub-face method may be to regard all face image sets as a face image subspace, and determine whether a face image exists based on a distance between a detection sample and its projection in the subspace.

In this scheme, the first contrast weight may be determined by the security chip according to the distribution position, the average brightness, and the image quality of the target area after the security chip acquires the target area where the face image is located in the human body image, and specifically may be determined according to a certain calculation formula, such as: and summing, averaging, and weighted averaging, and combining the factors to determine the first contrast weight. Because the image acquisition unit acquires human images through the wide-angle camera, the wide-angle camera has the advantages of short focal length and large visual angle, wide scenery can be shot at a short distance, the foreground is more prominent, the field depth range is remarkably larger than that of a standard lens and a telephoto lens, when the wide-angle camera is used for close shooting, the foreground is exaggerated and serious perspective distortion can be generated, if the distribution position of a target area where a human face image is located is more marginal, image distortion can be generated, and then the acquisition error of human face characteristic data is caused, therefore, the distribution positions of different target areas can be assigned according to the image distortion condition, and the first comparison weight is calculated. The average brightness may be an average calculation of brightness values of all pixel points in the face image region, and the image quality may be a sharpness of the fused image, specifically, may be represented by a fusion weight of a color image in the fused image.

In the scheme, the security chip determines the first comparison weight by combining the distribution position of the target area of the face image in the human body image, the average brightness of the target area and the image quality of the target area, and determines the second comparison weight according to the first comparison weight, so that a part with higher image definition can be set with a larger weight, the accuracy of the comparison calculation result of the current fusion image and the human body image feature data stored in the storage unit is improved, and the reliability of the comparison calculation result is improved.

S308, comparing and calculating the face feature data and the user human body feature data based on the first comparison weight to obtain a first comparison result; comparing and calculating the posture characteristic data and the user human body characteristic data based on the second comparison weight to obtain a second comparison result;

in the scheme, the comparison calculation may be a calculation in which the security chip compares the human face feature data and the posture feature data with the human body feature data of the user according to the comparison weight and the feature data. Specifically, the first comparison result may beThe similarity of the face feature data is calculated by utilizing the product of the similarity of the face feature data and the first contrast weight; the second comparison result may be calculated by using a product of the similarity of the human body characteristic data and the second comparison weight. The similarity of the face feature data may be obtained by comparing the face feature data in the current fusion image with the face feature data in the storage unit, and specifically, may be obtained by calculating a ratio of the same number of data to all the number of data, for example: the characteristic data in the face image is

The matrix is obtained by respectively comparing the human face characteristic data matrix in the current fusion image with each row of data in the human face characteristic data matrix in the storage unit through coding, and 90 pieces of consistent data are screened out, so that the similarity of the human face characteristic data is

。

S309, determining a comparison calculation result according to the first comparison result and the second comparison result;

in this scheme, the comparison calculation result may be a result obtained by performing comparison calculation on feature data of the current user fusion image and all user human body feature data stored in the storage unit by the security chip, where the comparison calculation result is used to determine whether a user consistent with the current user human body feature data exists in the storage unit, and specifically, the comparison calculation result may be determined according to a summation calculation of a first comparison result and a second comparison result, for example: the similarity between the fused image of the current user and the human body feature data of the user 1 in the storage unit is high, wherein the similarity between the human face feature data is 90% and the first comparison weight is 0.8, the similarity between the human body feature data is 80% and the second comparison weight is 0.2, and then the comparison calculation result between the current user and the user 1 in the storage unit is that

。

S310, if the comparison is successful, determining that the unlocking condition of the vehicle is met;

and S311, the processing unit generates an unlocking instruction after the vehicle terminal recognizes that the user reaches a certain area, and controls the vehicle door to be unlocked through the vehicle bus.

In the technical scheme provided by this embodiment, after determining a first comparison weight of face feature data and a second comparison weight of posture feature data, a security chip performs comparison calculation on the face feature data and the user body feature data based on the first comparison weight to obtain a first comparison result, performs comparison calculation on the posture feature data and the user body feature data based on the second comparison weight to obtain a second comparison result, and determines a comparison calculation result according to the first comparison result and the second comparison result. Different comparison weights are set for the face and the posture part through the security chip, the reliability of comparison calculation results can be improved, and the accuracy of user identity recognition is further improved.

Example four

Fig. 4 is a schematic structural diagram of a security chip device for opening a door based on human body characteristics, provided by the fourth embodiment of the present application. The device is provided with a security chip, and the security chip is arranged on a vehicle terminal. As shown in fig. 4, the secure chip apparatus includes:

an image acquisition unit 401, configured to acquire a human body image when the vehicle terminal recognizes that there is a human body approaching the vehicle; wherein the human body image comprises a color image and an infrared image;

a processing unit 402, configured to identify brightness information of the color image, and determine a fusion weight of the color image and the infrared image according to the brightness information;

the processing unit 402 is further configured to fuse the color image and the infrared image based on the fusion weight to obtain a fused image;

the checking unit 403 is configured to compare the fused image with user human body feature data, which is prestored in the storage unit and is under different luminance information, by using a safety checking rule; if the comparison is successful, determining that the unlocking condition of the vehicle is met;

and the processing unit 402 is used for generating an unlocking instruction after the vehicle terminal recognizes that the user reaches a certain area, and controlling the unlocking of the vehicle door through the vehicle bus.

Further, the verification unit includes:

the characteristic data conversion subunit is used for obtaining the human face characteristic data for the human face image by adopting a first characteristic conversion rule; for the posture image, adopting a second characteristic conversion rule to obtain posture characteristic data;

Further, the contrast calculation subunit is specifically configured to:

Further, the comparison calculation subunit is further configured to:

acquiring a target area where a face image in the human body image is located;

determining the first comparison weight according to the distribution position of the target region in the human body image, the average brightness of the target region and the image quality of the target region;

determining the second contrast weight according to the first contrast weight.

Wherein the sum of the first contrast weight and the second contrast weight is 1;

further, the feature data obtaining subunit is specifically configured to:

based on different encryption rules determined by different fusion weights, face feature data encryption and posture feature data encryption are carried out to obtain the user human body feature data;

correspondingly, the processing unit is further configured to:

According to the technical scheme provided by the embodiment, the image acquisition unit is used for acquiring the human body image when the vehicle terminal identifies that the human body approaches the vehicle; wherein the human body image comprises a color image and an infrared image; the processing unit is used for identifying the brightness information of the color image and determining the fusion weight of the color image and the infrared image according to the brightness information; the processing unit is further used for fusing the color image and the infrared image based on the fusion weight to obtain a fused image; the checking unit is used for comparing the fused image with user human body characteristic data which are prestored in the storage unit under different brightness information by adopting a safety checking rule; if the comparison is successful, determining that the unlocking condition of the vehicle is met; and the processing unit is used for generating an unlocking instruction after the vehicle terminal identifies that the user reaches a certain area, and controlling the unlocking of the vehicle door through a vehicle bus. The scheme solves the problems of convenience of unlocking the vehicle by a user and safety of whether the user cannot be identified by the vehicle as the user in the prior art, image identification and contrast calculation are carried out on human body images and human body data of the user by utilizing the safety chip, the effect of judging whether the vehicle user is the vehicle user and then automatically unlocking the vehicle door or not according to user characteristics can be realized, and convenience and safety of the user for using the vehicle are improved.

EXAMPLE five

Fig. 5 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As shown in fig. 5, an electronic device 500 is further provided in the embodiment of the present application, and includes a processor 501, a memory 502, and a program or an instruction stored in the memory 502 and capable of running on the processor 501, where the program or the instruction is executed by the processor 501 to implement each process of the method embodiment for opening a door by using a security chip based on a human body characteristic, and can achieve the same technical effect, and in order to avoid repetition, the details are not repeated here.

It should be noted that the electronic device in the embodiment of the present application includes the mobile electronic device and the non-mobile electronic device described above.

EXAMPLE six

The embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the program or the instruction implements each process of the above-mentioned method for opening a door by a security chip based on human body characteristics, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.

The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and so on.

The foregoing is considered as illustrative of the preferred embodiments of the invention and the technical principles employed. The present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A method for opening a door by a security chip based on human body characteristics is characterized in that the method is executed by the security chip which is arranged at a vehicle terminal; the method comprises the following steps:

when the vehicle terminal identifies that the human body approaches the vehicle, the human body image is acquired through an image acquisition unit of the vehicle terminal; wherein the human body image comprises a color image and an infrared image; the vehicle terminal recognizes that the vehicle with the human body approaching is detected by the vehicle terminal, and the vehicle terminal recognizes whether the human body approaching the vehicle or not by arranging a wide-angle camera at the head part;

the processing unit identifies brightness information of the color image and determines the fusion weight of the color image and the infrared image according to the brightness information; the fusion weight is determined in such a way that the processing unit calculates brightness information of the color image through a formula, and under different brightness information, the respective occupation ratios of the color image and the infrared image, that is, the respective fusion weights of the color image and the infrared image are calculated;

the processing unit fuses the color image and the infrared image based on the fusion weight to obtain a fusion image;

the check unit compares the fused image with the user human body characteristic data which is prestored in the storage unit and is under different brightness information by adopting a safety check rule, and the check unit comprises the following steps: acquiring user human body characteristic data under target brightness information matched with the current brightness information from a storage unit; acquiring a face image and a posture image in the fusion image; for the face image, obtaining face feature data by adopting a first feature conversion rule; for the posture image, obtaining posture characteristic data by adopting a second characteristic conversion rule; comparing and calculating the human face characteristic data and the posture characteristic data with the user human body characteristic data under the target brightness information; if the comparison is successful, determining that the vehicle unlocking condition is met;

2. The method according to claim 1, wherein the comparing the face feature data and the posture feature data with the user human body feature data under the target brightness information comprises:

3. The method of claim 2, wherein the sum of the first and second contrast weights is 1;

acquiring a target area where a face image in the human body image is located;

determining the second contrast weight according to the first contrast weight.

4. The method according to claim 1, wherein the user human body feature data is obtained by encrypting human face feature data and body state feature data based on different encryption rules determined by different fusion weights;

5. A safety chip device for opening a door based on human body characteristics is characterized in that the device is provided with a safety chip, and the safety chip is arranged at a vehicle terminal; the device comprises:

the image acquisition unit is used for acquiring a human body image when the vehicle terminal identifies that the human body approaches the vehicle; wherein the human body image comprises a color image and an infrared image; the vehicle terminal identifies whether a human body approaches the vehicle by arranging a wide-angle camera at the head of the vehicle to identify whether the human body approaches the vehicle;

the processing unit is used for identifying the brightness information of the color image and determining the fusion weight of the color image and the infrared image according to the brightness information; the fusion weight is determined in such a way that the processing unit calculates brightness information of the color image through a formula, and under different brightness information, the respective occupation ratios of the color image and the infrared image, that is, the respective fusion weights of the color image and the infrared image are calculated;

the checking unit is used for comparing the fused image with user human body characteristic data which are prestored in the storage unit and are under different brightness information by adopting a safety checking rule, and the checking unit comprises: the characteristic data acquisition subunit is used for acquiring user human body characteristic data under target brightness information matched with the current brightness information from the storage unit; the face image acquisition subunit is used for acquiring a face image and a posture image in the fusion image; the characteristic data conversion subunit is used for obtaining the human face characteristic data for the human face image by adopting a first characteristic conversion rule; obtaining body state feature data of the body state image by adopting a second feature conversion rule; the comparison calculation subunit is used for comparing and calculating the human face characteristic data and the posture characteristic data with the user human body characteristic data under the target brightness information; if the comparison is successful, determining that the vehicle unlocking condition is met;

and the processing unit is used for generating an unlocking instruction after the vehicle terminal identifies that the user reaches a certain area, and controlling the unlocking of the vehicle door through a vehicle bus.

6. The apparatus of claim 5, wherein the contrast calculation subunit is specifically configured to:

7. An electronic device comprising a processor, a memory, and a program or instructions stored on the memory and executable on the processor, the program or instructions when executed by the processor implementing the steps of the method of security chip opening a door based on body characteristics as claimed in any one of claims 1 to 4.

8. A readable storage medium, characterized in that the readable storage medium stores thereon a program or instructions which, when executed by a processor, implement the steps of the method for a security chip to open a door based on human body characteristics as claimed in any one of claims 1 to 4.