阅读说明：本技术 一种基于人脸识别的距离测定系统 (Distance measuring system based on face recognition ) 是由 王晓晗 于 2020-12-08 设计创作，主要内容包括：本发明公开了一种基于人脸识别的距离测定系统,本发明涉及摄像头的照射距离测定技术领域,解决了现有技术中,对于摄像头的照射距离不能够进行测定,导致人脸识别数据和人体温度数据准确性低的技术问题,通过距离检测单元对摄像头的距离进行检测,通过勾股定理获取到X1、X2以及R检测光线的长度,并通过公式获取到摄像头的最远清晰照射距离X,获取到清晰照射系数的最高阈值和最低阈值并分别标记为L1和L2；并将最高阈值L1和最低阈值L2发送至服务器；提高了摄像头的准确性,提高了用户的使用质量。(The invention discloses a distance measuring system based on face recognition, which relates to the technical field of irradiation distance measurement of cameras and solves the technical problem that the irradiation distance of the camera cannot be measured in the prior art, so that the accuracy of face recognition data and human body temperature data is low, the distance of the camera is detected through a distance detection unit, the lengths of X1, X2 and R detection light rays are obtained through the Pythagorean theorem, the farthest clear irradiation distance X of the camera is obtained through a formula, and the highest threshold and the lowest threshold of a clear irradiation coefficient are obtained and respectively marked as L1 and L2; and sending the highest threshold value L1 and the lowest threshold value L2 to the server; the accuracy of the camera is improved, and the use quality of a user is improved.)

1. A distance measuring system based on face recognition is characterized by comprising a server, a distance detecting unit, an adjusting unit, a recommending unit, a registration unit and a database;

the distance detection unit is used for detecting the distance of the camera, and the specific distance detection process is as follows:

the method comprises the steps that firstly, cameras are sequenced, the cameras at the head end and the tail end are marked as O1 and O2, and meanwhile two rectangular coordinate systems are established by taking O1 and O2 as original points respectively;

step two, putting the face area into a rectangular coordinate system, and marking the face area as P; setting the putting position of the face area at the coincidence position of a first quadrant of an O1 coordinate system and a second quadrant of an O2 coordinate system;

emitting first detection rays at an origin O1 and an origin O2, emitting the detection rays at the origin O1 and the origin O2 to two sides of the human face area, respectively marking the first detection rays as X1 and X2, simultaneously acquiring any coordinate on an X axis of an O1 coordinate system, marking the coordinate as a central coordinate, emitting a second detection ray at the position of the central coordinate, and marking the second detection ray as R;

step four, coordinates (0, f1) and (0, f2) on the Y axis of an O1 coordinate system and an O2 coordinate system are acquired, and f1 is f2, f1 and f2 are all expressed as the shortest clear irradiation distance of the camera, the lengths of the X1, X2 and R detection light are acquired through the pythagorean theorem, and the farthest clear irradiation distance X of the camera is acquired through a formula X1 × c1+ X2 × c2+ R × c3, wherein c1, c2 and c3 are preset proportionality coefficients, and c1 > c2 > c3 > 0;

step five, comparing the farthest clear irradiation distance X with the shortest clear irradiation distance to obtain the highest threshold and the lowest threshold of the clear irradiation coefficients, and respectively marking as L1 and L2; and sends the highest threshold L1 and the lowest threshold L2 to the server.

2. The distance measuring system based on face recognition according to claim 1, wherein the registration login unit is used for a user and an operator to submit user information and operator information for registration through a mobile phone terminal, and send the user information and the operator information which are successfully registered to the database for storage; the user information comprises the name, age, occupation and the mobile phone number of the personal real name authentication of the user, and the operator information comprises the name, age, time of entry and the mobile phone number of the personal real name authentication of the operator.

3. The distance measuring system based on face recognition according to claim 1, wherein the adjusting unit is configured to analyze and adjust the cameras, the camera information includes the number of cameras, the illumination angles of the cameras, and the illumination distances of the cameras, and the specific analysis and adjustment process is as follows:

s1: acquiring the number of cameras, and marking the number of the cameras as SL;

s2: acquiring an irradiation angle of the camera, and marking the irradiation angle of the camera as JD;

s3: acquiring the irradiation distance of the camera, and marking the irradiation distance of the camera as JL;

s4: by the formulaAcquiring an analysis coefficient FX of the camera, wherein s1, s2 and s3 are preset proportionality coefficients, and s1 is larger than s2 is larger than s3 is larger than 0;

s5: the camera analysis coefficient FX is compared with the highest threshold L1 and the lowest threshold L2 within the server:

if the analysis coefficient FX of the camera is larger than L1, judging that the distance of the camera exceeds the threshold range, namely the face recognition and temperature detection data are inaccurate, generating a distance overlength signal and sending the distance overlength signal to a mobile phone terminal of an operator;

if the analysis coefficient L2 of the camera is not less than FX and not more than L1, judging that the distance of the camera is within the threshold range, namely the face recognition and temperature detection data are accurate, generating an accurate signal and sending the accurate signal to the mobile phone terminal of the user;

and if the analysis coefficient FX of the camera is less than L2, judging that the distance of the camera does not reach the threshold range, namely the face recognition and temperature detection data are inaccurate, generating a too short distance signal and sending the too short distance signal to the mobile phone terminal of the user.

4. The distance measuring system based on face recognition of claim 1, wherein the recommending unit is configured to recommend to a user who does not use the system, the user usage information includes the number of cameras that the user needs to install, the illumination area of the cameras that the user needs, and the percentage of accuracy of data acquisition of the cameras that the user needs, and mark the user as i, i ═ 1, 2, ·.. and n, n is a positive integer, and the specific analysis and recommendation process is as follows:

SS 1: acquiring the number of cameras required to be installed by a user, and marking the number of the cameras required to be installed by the user as Si;

SS 2: acquiring the irradiation area of a camera required by a user, and marking the irradiation area of the camera required by the user as Ji;

SS 3: acquiring the percentage of data acquisition accuracy of a camera required by a user, and marking the percentage of the data acquisition accuracy of the camera required by the user as Bi;

SS 4: by the formula Mi ═ beta (Si × v1+ Ji × v2+ Bi × v3)³Acquiring a recommendation coefficient Xi of a user, wherein v1, v2 and v3 are all preset proportionality coefficients, v1 is greater than v2 is greater than v3 is greater than 0, and beta is an error correction factor and is 1.023654;

SS 5: comparing the recommendation coefficient Xi of the user with a recommendation coefficient threshold:

if the recommendation coefficient Xi of the user is larger than or equal to the recommendation coefficient threshold, judging that the recommendation coefficient of the user is high, generating a recommendation signal, simultaneously marking the user as a recommended user, and sending the recommendation signal and the recommended user to a server;

if the recommendation coefficient Xi of the user is smaller than the recommendation coefficient threshold, judging that the recommendation coefficient of the user is low, generating an un-recommendation signal, marking the user as an un-recommendation user, and sending the un-recommendation signal and the un-recommendation user to a server.

Technical Field

The invention relates to the technical field of irradiation distance measurement of cameras, in particular to a distance measurement system based on face recognition.

Background

With the maturity of the face technology, the application of face recognition relates to all walks of life, but face recognition also begins to reveal some technical problems, such as face steal brushing, face mistake brushing and the like, especially some potential safety hazards, and more attention is paid to, such as face brushing payment, face brushing door opening and the like, in order to reduce the problem of false brushing and steal brushing as far as possible. The face recognition distance needs to be calculated, a face target is locked through the distance, and then whether the face is in an effective recognition area or not is judged. In addition, when human body temperature is detected, the human body temperature is basically calculated only by simple distance calculation at present, the human body temperature is not locked by a human face, and the distance from a human face characteristic point to a camera is calculated, so that the human body temperature is easily interfered by other objects or other human faces, and the temperature detection accuracy is influenced.

However, in the prior art, the irradiation distance of the camera cannot be measured, so that the accuracy of face recognition data and human body temperature data is low, and the working efficiency of the camera is reduced.

Disclosure of Invention

The invention aims to provide a distance measuring system based on face recognition, which detects the distance of a camera through a distance detecting unit, improves the accuracy of the camera and improves the use quality of a user.

The purpose of the invention can be realized by the following technical scheme:

a distance measuring system based on face recognition comprises a server, a distance detecting unit, an adjusting unit, a recommending unit, a registration unit and a database;

the distance detection unit is used for detecting the distance of the camera, and the specific distance detection process is as follows:

the method comprises the steps that firstly, cameras are sequenced, the cameras at the head end and the tail end are marked as O1 and O2, and meanwhile two rectangular coordinate systems are established by taking O1 and O2 as original points respectively;

step two, putting the face area into a rectangular coordinate system, and marking the face area as P; setting the putting position of the face area at the coincidence position of a first quadrant of an O1 coordinate system and a second quadrant of an O2 coordinate system;

emitting first detection rays at an origin O1 and an origin O2, emitting the detection rays at the origin O1 and the origin O2 to two sides of the human face area, respectively marking the first detection rays as X1 and X2, simultaneously acquiring any coordinate on an X axis of an O1 coordinate system, marking the coordinate as a central coordinate, emitting a second detection ray at the position of the central coordinate, and marking the second detection ray as R;

step four, coordinates (0, f1) and (0, f2) on the Y axis of an O1 coordinate system and an O2 coordinate system are acquired, and f1 is f2, f1 and f2 are all expressed as the shortest clear irradiation distance of the camera, the lengths of the X1, X2 and R detection light are acquired through the pythagorean theorem, and the farthest clear irradiation distance X of the camera is acquired through a formula X1 × c1+ X2 × c2+ R × c3, wherein c1, c2 and c3 are preset proportionality coefficients, and c1 > c2 > c3 > 0;

step five, comparing the farthest clear irradiation distance X with the shortest clear irradiation distance to obtain the highest threshold and the lowest threshold of the clear irradiation coefficients, and respectively marking as L1 and L2; and sends the highest threshold L1 and the lowest threshold L2 to the server.

Furthermore, the registration login unit is used for submitting user information and operator information for registration through a mobile phone terminal by a user and an operator, and sending the user information and the operator information which are successfully registered to the database for storage; the user information comprises the name, age, occupation and the mobile phone number of the personal real name authentication of the user, and the operator information comprises the name, age, time of entry and the mobile phone number of the personal real name authentication of the operator.

Further, the adjusting unit is configured to analyze camera information and adjust the cameras, where the camera information includes the number of the cameras, an irradiation angle of the cameras, and an irradiation distance of the cameras, and a specific analyzing and adjusting process is as follows:

s1: acquiring the number of cameras, and marking the number of the cameras as SL;

s2: acquiring an irradiation angle of the camera, and marking the irradiation angle of the camera as JD;

s3: acquiring the irradiation distance of the camera, and marking the irradiation distance of the camera as JL;

s4: by the formulaAcquiring an analysis coefficient FX of the camera, wherein s1, s2 and s3 are preset proportionality coefficients, and s1 is larger than s2 is larger than s3 is larger than 0;

s5: the camera analysis coefficient FX is compared with the highest threshold L1 and the lowest threshold L2 within the server:

if the analysis coefficient FX of the camera is larger than L1, judging that the distance of the camera exceeds the threshold range, namely the face recognition and temperature detection data are inaccurate, generating a distance overlength signal and sending the distance overlength signal to a mobile phone terminal of an operator;

if the analysis coefficient L2 of the camera is not less than FX and not more than L1, judging that the distance of the camera is within the threshold range, namely the face recognition and temperature detection data are accurate, generating an accurate signal and sending the accurate signal to the mobile phone terminal of the user;

and if the analysis coefficient FX of the camera is less than L2, judging that the distance of the camera does not reach the threshold range, namely the face recognition and temperature detection data are inaccurate, generating a too short distance signal and sending the too short distance signal to the mobile phone terminal of the user.

Further, the recommendation unit is configured to recommend a user who does not use the system to analyze user usage information, where the user usage information includes the number of cameras that the user needs to install, an irradiation area that the user needs to have the cameras, and a percentage of accuracy of data acquisition of the cameras that the user needs, and the user is marked as i, i ═ 1, 2,... times, n, n are positive integers, and a specific analysis recommendation process is as follows:

SS 1: acquiring the number of cameras required to be installed by a user, and marking the number of the cameras required to be installed by the user as Si;

SS 2: acquiring the irradiation area of a camera required by a user, and marking the irradiation area of the camera required by the user as Ji;

SS 3: acquiring the percentage of data acquisition accuracy of a camera required by a user, and marking the percentage of the data acquisition accuracy of the camera required by the user as Bi;

SS 4: by the formula Mi ═ beta (Si × v1+ Ji × v2+ Bi × v3)³Acquiring a recommendation coefficient Xi of a user, wherein v1, v2 and v3 are all preset proportionality coefficients, v1 is greater than v2 is greater than v3 is greater than 0, and beta is an error correction factor and is 1.023654;

SS 5: comparing the recommendation coefficient Xi of the user with a recommendation coefficient threshold:

if the recommendation coefficient Xi of the user is larger than or equal to the recommendation coefficient threshold, judging that the recommendation coefficient of the user is high, generating a recommendation signal, simultaneously marking the user as a recommended user, and sending the recommendation signal and the recommended user to a server;

if the recommendation coefficient Xi of the user is smaller than the recommendation coefficient threshold, judging that the recommendation coefficient of the user is low, generating an un-recommendation signal, marking the user as an un-recommendation user, and sending the un-recommendation signal and the un-recommendation user to a server.

Compared with the prior art, the invention has the beneficial effects that:

1. in the invention, the distance detection unit detects the distance of the cameras, the cameras are sequenced, the cameras at the head end and the tail end are marked as O1 and O2, and meanwhile, two rectangular coordinate systems are established by respectively taking O1 and O2 as origins; putting the face area into a rectangular coordinate system, and marking the face area as P; setting the putting position of the face area at the coincidence position of a first quadrant of an O1 coordinate system and a second quadrant of an O2 coordinate system; emitting first detection light rays at an origin O1 and an origin O2, emitting the detection light rays at the origin O1 and the origin O2 to two sides of a human face area, respectively marking the first detection light rays as X1 and X2, simultaneously acquiring any coordinate on an X axis of an O1 coordinate system, marking the coordinate as a central coordinate, emitting second detection light rays at the position of the central coordinate, and marking the second detection light rays as R; acquiring coordinates (0, f1) and (0, f2) on Y axes of an O1 coordinate system and an O2 coordinate system, wherein f1 is f2, and f1 and f2 are all expressed as the shortest clear irradiation distance of the camera, acquiring the lengths of X1, X2 and R detection light rays through the Pythagorean theorem, acquiring the farthest clear irradiation distance X of the camera through a formula, acquiring the highest threshold and the lowest threshold of a clear irradiation coefficient, and respectively marking the highest threshold and the lowest threshold as L1 and L2; and sending the highest threshold value L1 and the lowest threshold value L2 to the server; the irradiation distance of the camera is measured, so that the accuracy of the camera is improved, and the use quality of a user is improved;

2. in the invention, the use information of a user is analyzed through a recommending unit, the user who does not use the system is recommended, the number of cameras required to be installed by the user, the irradiation area of the cameras required by the user and the percentage of data acquisition accuracy of the cameras required by the user are obtained, the recommending coefficient Xi of the user is obtained through a formula, if the recommending coefficient Xi of the user is more than or equal to a recommending coefficient threshold value, the recommending coefficient of the user is judged to be high, a recommending signal is generated, the user is marked as a recommending user, and the recommending signal and the recommending user are sent to a server; if the recommendation coefficient Xi of the user is smaller than the recommendation coefficient threshold, judging that the recommendation coefficient of the user is low, generating an un-recommendation signal, marking the user as an un-recommendation user, and sending the un-recommendation signal and the un-recommendation user to a server; the method and the system have the advantages that the requirements of the users are reasonably analyzed, the users are reasonably recommended, the adjusting time of the users is saved, and meanwhile, the safety of the users is improved.

Drawings

In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.

FIG. 1 is a functional block diagram of the present invention;

fig. 2 is a schematic diagram of a distance detecting unit according to the present invention.

Detailed Description

The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1-2, a distance measuring system based on face recognition includes a server, a distance detecting unit, an adjusting unit, a recommending unit, a registration unit, and a database;

the registration login unit is used for submitting user information and operator information for registration through a mobile phone terminal by a user and an operator, and sending the user information and the operator information which are successfully registered to the database for storage; the user information comprises the name, age and occupation of the user and the mobile phone number of the personal real name authentication, and the operator information comprises the name, age, time of entry and the mobile phone number of the personal real name authentication;

the distance detection unit is used for detecting the distance of the camera, and the specific distance detection process is as follows:

the method comprises the steps that firstly, cameras are sequenced, the cameras at the head end and the tail end are marked as O1 and O2, and meanwhile two rectangular coordinate systems are established by taking O1 and O2 as original points respectively;

step two, putting the face area into a rectangular coordinate system, and marking the face area as P; setting the putting position of the face area at the coincidence position of a first quadrant of an O1 coordinate system and a second quadrant of an O2 coordinate system;

emitting first detection rays at an origin O1 and an origin O2, emitting the detection rays at the origin O1 and the origin O2 to two sides of the human face area, respectively marking the first detection rays as X1 and X2, simultaneously acquiring any coordinate on an X axis of an O1 coordinate system, marking the coordinate as a central coordinate, emitting a second detection ray at the position of the central coordinate, and marking the second detection ray as R;

step four, coordinates (0, f1) and (0, f2) on the Y axis of an O1 coordinate system and an O2 coordinate system are acquired, and f1 is f2, f1 and f2 are all expressed as the shortest clear irradiation distance of the camera, the lengths of the X1, X2 and R detection light are acquired through the pythagorean theorem, and the farthest clear irradiation distance X of the camera is acquired through a formula X1 × c1+ X2 × c2+ R × c3, wherein c1, c2 and c3 are preset proportionality coefficients, and c1 > c2 > c3 > 0;

step five, comparing the farthest clear irradiation distance X with the shortest clear irradiation distance to obtain the highest threshold and the lowest threshold of the clear irradiation coefficients, and respectively marking as L1 and L2; and sending the highest threshold value L1 and the lowest threshold value L2 to the server;

the adjusting unit is used for analyzing the camera information and adjusting the camera, the camera information comprises the number of the cameras, the irradiation angle of the cameras and the irradiation distance of the cameras, and the specific analysis and adjustment process comprises the following steps:

s1: acquiring the number of cameras, and marking the number of the cameras as SL;

s2: acquiring an irradiation angle of the camera, and marking the irradiation angle of the camera as JD;

s3: acquiring the irradiation distance of the camera, and marking the irradiation distance of the camera as JL;

s4: by the formulaAcquiring an analysis coefficient FX of the camera, wherein s1, s2 and s3 are preset proportionality coefficients, and s1 is larger than s2 is larger than s3 is larger than 0;

s5: the camera analysis coefficient FX is compared with the highest threshold L1 and the lowest threshold L2 within the server:

if the analysis coefficient FX of the camera is larger than L1, judging that the distance of the camera exceeds the threshold range, namely the face recognition and temperature detection data are inaccurate, generating a distance overlength signal and sending the distance overlength signal to a mobile phone terminal of an operator;

if the analysis coefficient L2 of the camera is not less than FX and not more than L1, judging that the distance of the camera is within the threshold range, namely the face recognition and temperature detection data are accurate, generating an accurate signal and sending the accurate signal to the mobile phone terminal of the user;

if the analysis coefficient FX of the camera is less than L2, judging that the distance of the camera does not reach the threshold range, namely the face recognition and temperature detection data are inaccurate, generating an over-short distance signal and sending the over-short distance signal to a mobile phone terminal of a user;

the recommendation unit is used for recommending users who do not use the system to analyzing user use information, the user use information comprises the number of cameras required to be installed by the users, the irradiation area of the cameras required by the users and the percentage of data acquisition accuracy of the cameras required by the users, the users are marked as i, i is 1, 2, and n is a positive integer, and the specific analysis and recommendation process is as follows:

SS 1: acquiring the number of cameras required to be installed by a user, and marking the number of the cameras required to be installed by the user as Si;

SS 2: acquiring the irradiation area of a camera required by a user, and marking the irradiation area of the camera required by the user as Ji;

SS 3: acquiring the percentage of data acquisition accuracy of a camera required by a user, and marking the percentage of the data acquisition accuracy of the camera required by the user as Bi;

SS 4: by the formula Mi ═ beta (Si × v1+ Ji × v2+ Bi × v3)³Acquiring a recommendation coefficient Xi of a user, wherein v1, v2 and v3 are all preset proportionality coefficients, v1 is greater than v2 is greater than v3 is greater than 0, and beta is an error correction factor and is 1.023654;

SS 5: comparing the recommendation coefficient Xi of the user with a recommendation coefficient threshold:

if the recommendation coefficient Xi of the user is larger than or equal to the recommendation coefficient threshold, judging that the recommendation coefficient of the user is high, generating a recommendation signal, simultaneously marking the user as a recommended user, and sending the recommendation signal and the recommended user to a server;

if the recommendation coefficient Xi of the user is smaller than the recommendation coefficient threshold, judging that the recommendation coefficient of the user is low, generating an un-recommendation signal, marking the user as an un-recommendation user, and sending the un-recommendation signal and the un-recommendation user to a server.

The working principle of the invention is as follows:

when the distance measuring system based on face recognition works, the distance detecting unit is used for detecting the distance of the cameras, sequencing the cameras, marking the cameras at the head end and the tail end as O1 and O2, and establishing two rectangular coordinate systems by taking O1 and O2 as original points respectively; putting the face area into a rectangular coordinate system, and marking the face area as P; setting the putting position of the face area at the coincidence position of a first quadrant of an O1 coordinate system and a second quadrant of an O2 coordinate system; emitting first detection light rays at an origin O1 and an origin O2, emitting the detection light rays at the origin O1 and the origin O2 to two sides of a human face area, respectively marking the first detection light rays as X1 and X2, simultaneously acquiring any coordinate on an X axis of an O1 coordinate system, marking the coordinate as a central coordinate, emitting second detection light rays at the position of the central coordinate, and marking the second detection light rays as R; acquiring coordinates (0, f1) and (0, f2) on Y axes of an O1 coordinate system and an O2 coordinate system, wherein f1 is f2, and f1 and f2 are expressed as the shortest clear irradiation distance of the camera, acquiring the lengths of X1, X2 and R detection rays through the Pythagorean theorem, acquiring the farthest clear irradiation distance X of the camera through a formula X1X c1+ X2X c2+ R X c3, acquiring the highest threshold and the lowest threshold of a clear irradiation coefficient and respectively marking as L1 and L2; and sends the highest threshold L1 and the lowest threshold L2 to the server.

The above formulas are all calculated by taking the numerical value of the dimension, the formula is a formula which obtains the latest real situation by acquiring a large amount of data and performing software simulation, and the preset parameters in the formula are set by the technical personnel in the field according to the actual situation.

The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.