CN113687370A - Detection method, detection device, electronic equipment and storage medium - Google Patents

Detection method, detection device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113687370A
CN113687370A CN202110896289.XA CN202110896289A CN113687370A CN 113687370 A CN113687370 A CN 113687370A CN 202110896289 A CN202110896289 A CN 202110896289A CN 113687370 A CN113687370 A CN 113687370A
Authority
CN
China
Prior art keywords
temperature
coverage area
height
angle
measured object
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110896289.XA
Other languages
Chinese (zh)
Inventor
郑金松
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Opnous Smart Sensing & Ai Technology
Original Assignee
Opnous Smart Sensing & Ai Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Opnous Smart Sensing & Ai Technology filed Critical Opnous Smart Sensing & Ai Technology
Priority to CN202110896289.XA priority Critical patent/CN113687370A/en
Publication of CN113687370A publication Critical patent/CN113687370A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
    • G01S17/06—Systems determining position data of a target
    • G01S17/08—Systems determining position data of a target for measuring distance only
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
    • G01S17/894—3D imaging with simultaneous measurement of time-of-flight at a 2D array of receiver pixels, e.g. time-of-flight cameras or flash lidar
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • General Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Radiation Pyrometers (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

A detection method, a detection device, an electronic device and a storage medium are provided, and the method comprises the following steps: s1, acquiring a depth value image of the measured object in the first field angle coverage area by using the ToF sensing module; s2, outputting a first judgment result according to the depth value image; s3, when the first judgment result is in a preset state, acquiring temperature data of the measured object in a second field angle coverage area acquired by a temperature detection module, wherein the first field angle coverage area and the second field angle coverage area form at least one overlapping area, and the measured object is located in the overlapping area; and S4, outputting a second judgment result according to the temperature data. The invention determines whether the detected object exists in the coverage area of the field angle through the ToF sensing module, further determines whether the detected object is a living body through the temperature detection module, further determines whether the detected object is a target object, eliminates the influence of an obstacle object and improves the accuracy of the detection result.

Description

Detection method, detection device, electronic equipment and storage medium
Technical Field
The present application relates to the field of detection technologies, and in particular, to a detection method, an apparatus, an electronic device, and a storage medium.
Background
ToF is an abbreviation of Time of Flight (ToF) technology, a ToF sensing module utilizes a ToF sensor to emit modulated infrared light, the infrared light is reflected after encountering an object, and the distance of the object can be calculated by calculating the Time difference or phase difference between light emission and reflection, so that three-dimensional space information of the object can be obtained, and the application scene is wide.
However, the ToF sensor cannot recognize whether the object to be detected is a living body or not, resulting in a deficiency in living body detection.
Disclosure of Invention
In view of this, the present application provides a detection method, an apparatus, an electronic device and a storage medium to solve the problem that the existing ToF sensor cannot identify whether the detected object is a living body, which results in a deficiency in living body detection.
A method of detection, comprising: s1, acquiring a depth value image of the measured object in the first field angle coverage area by using the ToF sensing module; s2, outputting a first judgment result according to the depth value image; s3, when the first judgment result is in a preset state, acquiring temperature data of the measured object in a second field angle coverage area acquired by a temperature detection module, wherein the first field angle coverage area and the second field angle coverage area form at least one overlapping area, and the measured object is located in the overlapping area; and S4, outputting a second judgment result according to the temperature data.
Optionally, the first determination result includes a first state, a second state and a third state, where the first state indicates that the measured object does not exist in the first field angle coverage area, the second state indicates that the first target object exists in the first field angle coverage area, and the third state indicates that the second target object exists in the first field angle coverage area; step S2 specifically includes: performing algorithm processing on the depth value image to calculate the height of the detected object, and outputting the first state when the height is less than or equal to a first height threshold value or the detected object is not detected; and outputting the second state when the height is greater than a first height threshold and less than a second height threshold, and outputting the third state when the height is greater than or equal to the second height threshold.
Optionally, the preset state includes the second state and the third state; step S3 specifically includes: and when the first judgment result is in the second state or the third state, acquiring temperature data of the measured object in a second field angle coverage area acquired by the temperature detection module.
Optionally, the second determination result includes that the measured object is a living body and the measured object is a non-living body, and step S4 specifically includes: acquiring space coordinate information of a first area of the measured object according to the depth value image, wherein the first area is a top area of the measured object relative to the ground; acquiring temperature values of pixel points in corresponding areas in the temperature data according to the space coordinate information of the first area; and when the temperature value is smaller than the preset temperature threshold value, the measured object is judged to be a non-living body.
Optionally, the spatial coordinate information of the measured object and the corresponding temperature coordinate need to satisfy the following formula:
Figure BDA0003198059080000021
wherein the u2 and the v2 are the v2 th row and the u2 th column in the temperature data, and the fx1And f isy1Focal lengths in the x-axis and y-axis directions of the TOF coordinate system, respectively, said sum cy1The central positions of the X-axis and the Y-axis of the TOF coordinate system respectively11R said12R said13R said21R said22R said23R said31R said32R said33As a rotary system of the temperature detection module, txThe t isyThe t iszAnd the x, the y and the z are space coordinate information of the measured object.
Optionally, S4 further includes: taking the pixel points in the corresponding area in the temperature data as a central point, and reading a temperature value set of all the pixel points in a preset radius around the central point; acquiring a maximum temperature value in the temperature value set; and when the maximum temperature value is smaller than the preset temperature threshold value, the measured object is judged to be a non-living body.
Optionally, the first angle of view includes a first horizontal angle of view and a first vertical angle of view, and the farthest distance l of the first horizontal angle of view coverage area needs to satisfy the following relationship: l<(h-h1)tan(FOV1yAnd/2 + α), wherein h is the height of the measured object, h1 is the second height threshold, FOV1y is the first vertical field angle of the ToF sensor in the vertical direction, and α is the included angle between the ToF sensor and the z direction.
Optionally, the second angle of view includes a second vertical angle of view, and the second vertical angle of view FOV2y of the temperature detection module in the vertical direction satisfies the following formula:
Figure BDA0003198059080000031
h is the vertical distance between the temperature detection module and the installation ground, H is the height of the measured object, alpha is the included angle between the temperature detection module and the z direction, and l is the farthest distance of the first horizontal field angle coverage area.
A detection device, comprising: the ToF sensing module comprises a ToF sensor and a processor, wherein the ToF sensor is connected with the processor and is used for acquiring a depth value image of a measured object in a first field angle coverage area; the temperature detection module is connected with the processor and is used for acquiring temperature data of the measured object in a second field angle coverage area, the first field angle coverage area and the second field angle coverage area form at least one overlapping area, and the measured object is located in the overlapping area; and the processor is used for outputting a judgment result according to the depth value image and the temperature data.
Optionally, the processor is specifically configured to: performing algorithm processing on the depth value image to calculate the height of the measured object; judging whether the object to be measured exists in the first field angle coverage area or not according to the comparison result of the height of the object to be measured and the first height threshold and the second height threshold; and when the measured object exists in the first view angle coverage area, judging whether the measured object is a living body according to the temperature data.
Optionally, the first angle of view includes a first horizontal angle of view and a first vertical angle of view, and the farthest distance l of the first horizontal angle of view coverage area needs to satisfy the following relationship: l<(h-h1)tan(FOV1yAnd/2 + α), wherein h is the height of the measured object, h1 is the second height threshold, FOV1y is the first vertical field angle of the ToF sensor in the vertical direction, and α is the included angle between the ToF sensor and the z direction.
Optionally, the second angle of view comprises a second vertical angle of view, and the second vertical angle of view FOV2y satisfies the following formula:
Figure BDA0003198059080000041
h is the vertical distance between the temperature detection module and the installation ground, H is the height of the measured object, alpha is the included angle between the temperature detection module and the z direction, and l is the farthest distance of the first horizontal field angle coverage area.
Optionally, a parallel distance between the ToF sensor and the temperature detection module is a preset parallel distance; the preset parallel distance is in the range of 1-10 cm.
An electronic device comprises the detection device.
A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the detection method.
According to the detection method, the ToF sensing module is used for collecting the depth value image of the detected object in the field angle coverage area to determine whether the detected object exists in the field angle coverage area, the temperature detection module is used for detecting the temperature data of the detected object in the field angle coverage area to further determine whether the detected object is a living body, so that whether the detected object is a target object is further determined, the influence of an obstacle object is eliminated, and the accuracy of the detection result is improved.
Further, when h is>h1When the object to be measured stands within a distance less than l, in order to ensure h-h1Is still within the detectable range of FOV1y, l should satisfy the following formula: l<(h-h1)tan(FOV1yAnd/2 + alpha), wherein h is the height of the measured object, h1 is the second height threshold, FOV1y is the first vertical field angle of the ToF sensor in the vertical direction, and alpha is the included angle between the ToF sensor and the z direction, so as to improve the accuracy of the detection result.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a detection apparatus according to an embodiment of the present invention;
FIG. 2 is a schematic view of an installation manner of a detection device according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart illustrating a detection method according to an embodiment of the present invention;
FIG. 4 is a graph of the relationship between the pixel location and the coordinates of spatial points in a depth value image collected by a ToF sensor module;
FIG. 5 is a schematic flow chart illustrating a detection method according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of an in vivo identification protocol according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of a scheme for identifying adults or children according to an embodiment of the invention;
fig. 8 is a schematic structural diagram of an air conditioning apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application. The following embodiments and their technical features may be combined with each other without conflict.
Referring to fig. 1, a schematic structural diagram of a detection apparatus according to an embodiment of the invention is shown.
In this embodiment, the detection device includes a ToF sensing module 1 and a temperature detection module 2.
The ToF sensing module 1 includes a ToF sensor 11 and a processor 12, where the ToF sensor 11 is connected to the processor 12 and is configured to acquire a depth value image of a measured object in a first horizontal field angle coverage area.
ToF sensor 11 is a sensor for detecting distance, and other sensors, such as laser radar, millimeter wave radar, and ultrasonic radar, may be used in alternative embodiments. ToF sensor 11 also includes any depth map sensor based on different detection principles, including sensors based on different detection principles of structured light, pulsed, continuous wave, etc. For example, the ToF sensor 11 actively and continuously emits infrared laser pulses, and simultaneously controls the gates of the photosensors, so as to realize the energy collected by the reflected light at 2 different times, i.e., Q1 and Q2; the sum of Q1 and Q2 corresponds to the total amount of reflected light, and the proportion of Q2 relative to the sum is exactly equal to the delay Δ t of the reflected light relative to the emitted light, so that the distance L between ToF sensor 11 and the object to be measured is obtained by multiplying the delay by the speed of light c, and dividing by 2, according to this delay.
Figure BDA0003198059080000061
Where c is the speed of light, c is 299792.458km/s (kilometers per second), Δ t is the delay time of reflected light relative to emitted light, Q1And Q2Is the energy collected by the reflected light at 2 different times.
By utilizing the characteristic that the ToF sensor 11 is an area array, the distance value between each point of the user and the ToF sensor 11 can be acquired, and a depth value image is generated according to the distance value, wherein the depth value image has N pixel points, N is an integer greater than or equal to zero, each pixel point corresponds to a position point in the actual space, and the depth value of each pixel point corresponds to the distance value of the position point. Therefore, the depth value image may be a data matrix including N array-arranged depth values, or a point cloud image constructed according to the depth values of the respective pixel points and representing a three-dimensional stereo image.
The temperature detection module 2 is connected to the processor 12 and configured to acquire temperature data of the object to be detected in a second horizontal field angle coverage area, where the first horizontal field angle coverage area and the second horizontal field angle coverage area form at least one overlapping area, and the object to be detected is located in the overlapping area.
The temperature detection module 2 uses thermal imaging technology, including any thermal sensor technology based on detecting human body infrared information, and the temperature detection module 2 is a thermopile or a thermal imager.
The processor 12 is configured to output a determination result according to the depth value image and the temperature data.
For example, whether an object exists in the object to be measured is determined according to the depth value image, and after the object is determined to exist, whether the object to be measured is a living body, such as a human body, is determined according to the temperature data.
Whether a person exists in the specific area can be judged through the combination of the depth value image and the temperature data, so that person detection is achieved.
Referring to fig. 2, a schematic view of an installation manner of a detection apparatus according to an embodiment of the invention is shown.
The schematic view of the installation of the detection device in fig. 2 includes a top view and a side view. In the top view of fig. 2, FOV1x represents the first horizontal field angle of the ToF sensing module 1 in the x direction, FOV2x represents the second horizontal field angle of the temperature detection module 2 in the x direction, i is the farthest distance between the first horizontal field angle FOV1x and the second horizontal field angle FOV2x in the y direction, w is the maximum width covered by the first horizontal field angle in the x direction, and the preset parallel distance d is the average distance between the temperature detection module 2 and the ToF sensing module 1, and is controlled to be 1-10 cm, preferably 3 cm, in order to avoid being affected at the edge. The first horizontal field FOV1x coverage area and the second horizontal field FOV2x coverage area form at least one overlap area, in which the object to be measured is located.
In the side view of fig. 2, the detection device is installed at a position with a height H from the ground, FOV1y represents a first vertical field angle of the ToF sensing module in the y direction, FOV2y represents a second vertical field angle of the temperature detection module in the y direction, the coverage area of the second vertical field angle FOV2y includes a coverage area of the first vertical field angle FOV1y, the ToF sensing module forms an angle α with the z direction, and α is in a range of 0 ≦ α ≦ 90 °. h represents the height of the object to be measured, h0And h1Are a preset first height threshold and a second height threshold. When h is generated>h1When the object to be measured stands within a distance less than l, in order to ensure h-h1Is still within the detectable range of FOV1y, l should satisfy the following formula:
l<(h-h1)tan(FOV1y/2+α)
wherein, h is the height of the measured object, h1 is the second height threshold, FOV1y is the first vertical field angle of the ToF sensor in the vertical direction, and α is the included angle between the ToF sensor and the z direction, so as to improve the accuracy of the detection result.
The width of the forehead of a person is 10-15 cm, and the length of the forehead of the person is 15-20 cm. Therefore, the temperature detection module can satisfy the view angle covered by the TOF sensing module under the condition that the second horizontal view angle is greater than or equal to the first horizontal view angle, that is, FOV2x is greater than or equal to FOV1 x. The value of the second vertical field angle FOV2y of the temperature detection module needs to be set at the distance l, and the field angle thereof can detect the height of the human body. Taking the example of a person standing at a height of 1.8 meters at distance l, the second vertical field of view satisfies the following equation:
Figure BDA0003198059080000071
for example, FOV2y is 162 °.
The processor 12 is further configured to: performing algorithm processing on the depth value image to calculate the height h of the measured object; judging whether the object to be measured exists in the first field angle coverage area or not according to the comparison result of the height h of the object to be measured, a first height threshold h0 and a second height threshold h 1; and when the measured object exists in the first view angle coverage area, judging whether the measured object is a living body according to the temperature data.
Optionally, when the height h of the object to be measured is smaller than the first height threshold h0 or the object to be measured is not detected, it is determined that the object to be measured does not exist in the first field-of-view coverage area, when the height h of the object to be measured is greater than the first height threshold h0 and smaller than the second height threshold h1, it is determined that the object to be measured is the first target object, and when the height h of the object to be measured is greater than the second height threshold h1, it is determined that the object to be measured is the second target object, so as to implement the identification of the object to be measured.
The detection device of the embodiment utilizes the ToF sensing module to realize distance detection of the detected object in the first view angle region so as to judge whether the detected object exists in the first view angle region and the distance between the detected object, and then detects the temperature of the detected object by combining the temperature detection module so as to further judge whether the detected object is a living body, such as a person, thereby improving the accuracy of person identification.
Referring to fig. 3, a flow chart of a detection method according to an embodiment of the invention is shown.
In this embodiment, the ToF sensing module and the temperature detecting module are installed in the manner shown in fig. 2, and the detecting method of this embodiment includes the following steps:
and S1, acquiring a depth value image of the measured object in the first field angle coverage area by using the ToF sensing module. The principle of the depth value image collected by the ToF sensing module is similar to that described above, and is not described herein again.
And S2, outputting a first judgment result according to the depth value image.
For example, a first determination result is output according to the value of a pixel point in the depth value image, or the depth value image is inversely mapped to a spatial coordinate system to obtain spatial coordinate information of the object to be measured, and the first determination result is output according to the spatial coordinate information. The first determination result includes whether or not an object exists in the first view angle region, the size of the object, the distance of the object, and the like.
In an optional embodiment, the first determination result includes a first state, a second state, and a third state, where the first state indicates that the measured object does not exist in the first viewing angle coverage area, the second state indicates that the first target object exists in the first viewing angle coverage area, and the third state indicates that the second target object exists in the first viewing angle coverage area; step S2 specifically includes: performing algorithm processing on the depth value image to calculate the height of the measured object, and outputting the first state when the height is smaller than or equal to a first height threshold; and outputting the second state when the height is greater than a first height threshold and less than a second height threshold, and outputting the third state when the height is greater than or equal to the second height threshold.
For example, the distance of the object to be measured is calculated according to the position of the distance between the highest point and the lowest point in the vertical direction in the depth value image. However, the distance calculation method is not accurate, and in order to improve the calculation accuracy, the depth value image may be inversely mapped to a world coordinate system to obtain a spatial coordinate position of the measured object, and the height of the measured object is calculated according to the coordinate information of the measured object, which is specifically implemented as follows:
referring to fig. 4, a relationship between the pixel position and the coordinates of the spatial point in the depth value image collected by the ToF sensing module is shown.
In fig. 4, (x, y, z) is a point in the world coordinate system, that is, a certain point coordinate of the object, and the coordinate of the point coordinate in the pixel coordinate system is (u, v), for simplicity, the world coordinate system and the TOF coordinate system can be combined into one, and any point in the world coordinate system is mapped into the image coordinate system by means of pinhole imaging, and the final transformation is realized by means of translation between the image coordinate system and the pixel coordinate system. The depth value image data output by the TOF sensing module is typically represented in a matrix form. The coordinate value (x, y) of the measured object can be calculated by the following formula:
Figure BDA0003198059080000091
Figure BDA0003198059080000092
the matrix expression is:
Figure BDA0003198059080000093
wherein u, v and z are information in the depth value image, u and v are pixel coordinate values, u represents a row, v represents a column, z represents a corresponding depth value, fx1、fy1、cx1、cy1(fx1And fy1Focal lengths in the x-axis and y-axis directions of the TOF coordinate system respectively; c. Cx1And cy1The central position in the x-axis and y-axis directions of the TOF coordinate system, respectively) is an internal parameter of the TOF sensing module, which can be determined by a calibration algorithm. Therefore, through the formula, the transformation from any point in the world coordinate system to the ToF depth value image can be realized, the relation between the pixel position (u, v) and the coordinate of the space point (x, y, z) in the depth value image is found, the depth value image of the ToF sensing module can be inversely mapped to the world coordinate system, the coordinate information of the measured object in the world coordinate system is obtained, the height of the measured object can be calculated according to the coordinate information of the measured object, and the accuracy of the calculation result is high.
Setting a first height threshold value h0 and the height of the measured object as h, and when h is more than or equal to h0When the first determination result status1 is 1, it indicates that the object exists in the first viewing angle coverage area, i.e., the first state, and when h is<h0When the first determination result status1 is 0, it indicates that the object to be detected does not exist in the first viewing angle coverage area, i.e., the second state, so as to achieve the detection of the object to be detected.
In an optional embodiment, the first determination result further includes a third state, and the third state indicates that the object to be measured existing in the first field angle coverage area is a target object. The target object includes a target person such as a child, an infant, or the like, or a target pet such as a kitten, a puppy, or the like. When the height of the object to be measured is greater than the first height threshold, that is, when the object to be measured exists in the first field angle coverage area, step S2 further includes: and comparing the height with a second height threshold, and when the height is smaller than or equal to the second height threshold, determining that the object to be measured existing in the first field angle coverage area is a target object.
For example, in a certain application scenario, such as an air conditioner, if an adult or a child is identified as an important detection item, the height h of the detected object may be further analyzed, a second height threshold h1 is set, and when the height h of the detected object satisfies h0≤h≤h1Then outputting the second state to judge the object to be measured as the first target object, i.e. child, when h1When the time is less than or equal to h, outputting a third state, and judging the detected object as a second target object to form a person; otherwise, h is less than or equal to h0The object is not recognized and a first state is output. The first determination result status1 indicates an adult as 3, a child as 2, and no object as 0, respectively.
And S3, when the first judgment result is in a preset state, acquiring temperature data of the measured object in a second field angle coverage area acquired by the temperature detection module, wherein the first field angle coverage area and the second field angle coverage area form at least one overlapping area, and the measured object is located in the overlapping area.
For example, the first determination result includes whether an object exists in the first view angle region, the size of the object, the distance between the objects, and the like, different preset states are set according to corresponding situations, and when the first determination result is in the corresponding preset state, the temperature data of the sensor module is acquired, and further determination is performed in combination with the temperature data.
In an optional embodiment, the preset state includes the second state and the third state; step S3 specifically includes: and when the first judgment result is in the second state or the third state, acquiring temperature data of the measured object in a second field angle coverage area acquired by the temperature detection module.
As can be seen from the above discussion, when the first determination result is the second state or the third state, that is, status1 is 1, 2, or 3, which indicates that the object to be measured is present, the child is present, and the adult is present in the first angle-of-view region, at this time, the temperature data of the object to be measured in the second angle-of-view coverage region acquired by the temperature detection module is further acquired.
And S4, outputting a second judgment result according to the temperature data. The second determination result includes that the measured object is a living body and the measured object is a non-living body, and step S4 specifically includes: acquiring space coordinate information of a first area of the measured object according to the depth value image, wherein the first area is a top area of the measured object relative to the ground; acquiring temperature values of pixel points in corresponding areas in the temperature data according to the space coordinate information of the first area; and when the temperature value is smaller than the preset temperature threshold value, the measured object is judged to be a non-living body.
Optionally, the temperature detection module is a thermopile, and the temperature data of the corresponding position (u2, v2) of the measured object is obtained by rotating and positioning the spatial coordinates (x, y, z) of the measured object and by the following formula coordinate-temperature conversion formula;
Figure BDA0003198059080000111
wherein f isx1、fy1、cx1、cy1(fx1And fy1Focal lengths in the x-axis and y-axis directions of the TOF coordinate system respectively; c. Cx1And cy1The central position in the x-axis and y-axis directions of the TOF coordinate system, respectively) is an internal parameter of the TOF sensing module, which can be determined by a calibration algorithm. r is11、r12、r13、r21、r22、r23、r31、r32、r33、tx、ty、tzIs an internal parameter of the thermopile, where r11、r12、r13、r21、r22、r23、r31、r32、r33To a rotating system, tx、ty、tzIs the displacement coefficient. The first area is the head area of the measured object, and the width of the forehead of the person is 10-15 cm, the length of the forehead of the person is 15-20 cm, the width of the corresponding first area is 10-15 cm, and the length of the corresponding first area is 15-20 cm. Acquiring space coordinate information of the first area of the measured object, obtaining a temperature value T of the thermopile line v2 and the line u2 (head) by using the coordinate-temperature conversion formula, and presetting a temperature threshold value TthreadAnd when the temperature value is less than the preset temperature threshold value, the measured object is judged to be a non-living body.
In another optional embodiment, the depth value image of the object to be measured and the temperature data image of the temperature detection module may be subjected to pixel mapping according to the coordinate-temperature conversion formula, the mapped result is stored, a head pixel in the temperature image may be obtained from a pixel of the head of the object to be measured in the depth value image through the pixel mapping, and the temperature data of the pixel point is read, so that the head temperature data of the object to be measured may be obtained. According to the embodiment, the head temperature data of the measured object can be directly obtained by combining the depth value image acquired in real time with the prestored pixel mapping result.
In another optional embodiment, the depth value image and the temperature value image are subjected to image scale matching, a point cloud image is obtained according to the depth value image, and the point cloud image and the temperature image are subjected to image matching, so that the size of the object to be measured in the point cloud image is consistent with the size of the object to be measured in the temperature image, and the two images can be overlapped. For example, the ratio of the depth value image to the temperature value image is 1: 1 or 1: 2, and after the two images are overlapped, the head temperature data in the temperature image is obtained from the head position of the object to be measured in the depth value image by searching the numerical value of the pixel point at the corresponding position.
In a possible embodiment, in order to more accurately find the highest point of the human body temperature, the step S4 further includes: reading a temperature value set of all pixel points which are spaced from the pixel points by 1 pixel point; acquiring a maximum temperature value in the temperature value set; and when the maximum temperature value is smaller than the preset temperature threshold value, the measured object is judged to be a non-living body.
Specifically, all temperature values in 1 pixel point spaced from the central point (u2, v2) are read, and the total temperature values are 9 temperature point values, and the coordinates of the temperature values are as follows (u2-1, v2-1), (u2-1, v2), (u2-1, v2+1), (u2, v2-1), (u2, v2), (u2, v2+1), (u2+1, v2-1), (u2+1, v2), (u2+1, v2+1)
Taking the maximum temperature value of all points and defining as Tmax. Temperature setting threshold Tthread＝35.5℃，Tthread>35.5 ℃ and then the substance can be judged as a living body. The second determination result status2 is equal to 1, otherwise, the second determination result status2 is equal to 0, and the object is determined to be a non-living object.
Referring to fig. 5, a flow chart of a detection method according to an embodiment of the invention is shown.
And acquiring the height h of the measured object in the coverage area of the first field angle according to the ToF sensing module, setting a first height threshold h0 and a second height threshold h1, and when the measured object is not detected, namely h belongs to { }, judging that the measured object is an inanimate object when the first judgment result status1 is in a first state, namely the value is 0 and the second judgment result status2 is 0.
When the height h is less than or equal to the first height threshold h0, i.e., h is less than or equal to h0, the first determination result status1 is in the first state, i.e., the value is 0, and the second determination result status2 is 0, it is determined that the object is a non-living body.
When the height is greater than the first height threshold and less than the second height threshold, that is, h0< h < h1, the first determination result status1 is in the second state, that is, the value is 1, the thermopile is called to calculate the temperature T of the object, the temperature threshold is set to 35.5 ℃, and when T <35.5 ℃, the second determination result status2 is 0, the measured object is determined to be an inanimate object. When T >35.5 ℃, the second determination result status2 is 1, the object to be measured is determined to be a living body, and the object to be measured is a first target object, such as a child.
When the height is greater than or equal to the second height threshold, namely h is greater than or equal to h1, the first judgment result status1 is in a third state, namely the value is 2, at this time, the thermopile is called to calculate the temperature T of the object, the temperature threshold is set to 35.5 ℃, and when the T is less than 35.5 ℃, the second judgment result status2 is 0, the detected object is judged to be an inactive object. When T >35.5 ℃, the second determination result status2 is 1, the object to be measured is determined to be a living body, and the object to be measured is a second target object, such as an adult.
Referring to fig. 6, a schematic diagram of an in-vivo identification scheme according to an embodiment of the invention is shown.
Using a ToF sensing module to acquire the height h of a measured object in the coverage range of the field angle, setting a first height threshold h0, and when h is within the coverage range of the field angle>h0, outputting the first determination result status1 equal to 1, that is, the object exists in the coverage area of the field angle, at this time, calling the temperature data of the object collected by the temperature detection module, and when the maximum temperature value T in the temperature data ismax>TthreadThen, the second determination result status2 is output as 1, that is, the measured object is a living body. When h is not greater than h0, a second determination result status2 is output as 0, that is, the object to be measured is not a living body. When the maximum temperature value T in the temperature datamaxNot more than TthreadWhen the second determination result status2 is output as 0, that is, the object to be measured is not a living body.
Referring to fig. 7, a schematic diagram of a scheme for identifying adults or children according to an embodiment of the invention is shown.
In fig. 7, the protocol process for identifying adults or children is as follows: the TOF sensing module is used to acquire the height h of the measured object in the coverage area of the field angle, if the height h belongs to an empty set, no object is indicated, and the output status2 is 0, that is, no living body is detected. When the height h does not belong to the empty set, setting a first height threshold h0, and judging whether the height h is smaller than a first height threshold h0, namely h<If h0 is true, the output status2 is 0, that is, no living body is detected, and if not, the result of comparison between the height h and the second height threshold h1 is further determined, that is, h0 is determined<h<If h1 is true, the output status1 is 1, which indicates the presence of the object being measured and indicates that the object is presentCalling a temperature detection module to acquire the temperature of the measured object and judging the temperature to be a large temperature value Tmax>TthreadIf the result is true, the output status2 is 1, indicating that the object is a child, and if the result is false, the output status2 is 0, indicating that no living body is detected. When h0<h<If h1 is not satisfied, further judge h>If h1 is true, outputting status1 as 1 to indicate that the object to be detected exists, calling a temperature detection module to collect the temperature of the object to be detected, and judging as a large temperature value Tmax>TthreadIf the result is true, the output status2 is 1, indicating that the object is an adult, and if the result is false, the output status2 is 0, indicating that no living body is detected.
When h is generated>h1When the object to be measured stands within a distance less than l, in order to ensure h-h1Is still within the detectable range of FOV1y, l should satisfy the following formula:
l<(h-h1)tan(FOV1y/2+α)
wherein, h is the height of the measured object, h1 is the second height threshold, FOV1y is the first vertical field angle of the ToF sensor in the vertical direction, and α is the included angle between the ToF sensor and the z direction, so as to improve the accuracy of the detection result.
The value of the second vertical field angle FOV2y of the temperature detection module needs to be set at the distance l, and the field angle thereof can detect the height of the human body. Taking the example of a person standing at a height of 1.8 meters at distance l, the second vertical field angle FOV2y satisfies the following formula:
Figure BDA0003198059080000141
for example, FOV2y is 162 °.
In the detection method of the embodiment, the depth value image acquired by the ToF sensing module and the temperature data acquired by the temperature detection module are used as the basis for control, the method is independent of ambient light, a large amount of computing resources and a depth learning framework do not need to be constructed, and the occupation and consumption of resources are low.
The embodiment of the invention also provides electronic equipment which comprises the detection device, wherein the electronic equipment comprises air conditioning equipment, industrial automation equipment, obstacle detection equipment, automatic driving equipment, security equipment and gesture recognition equipment.
Fig. 8 is a schematic structural diagram of an air conditioning apparatus according to an embodiment of the present invention.
In fig. 8, the air conditioner includes an air conditioner main unit 501 and the detection device 100. The air conditioner host 501 is a vertical air conditioner, and the detection device 100 is disposed inside the air conditioner host 501 and monitors an external environment through a window disposed on a surface of the air conditioner host 501. The detection device 100 is connected to the air conditioner host 501, and outputs the first determination result and the second determination result to the air conditioner host 501, and the air conditioner host 501 adjusts an air outlet parameter according to the first determination result and the second determination result. The field coverage area of the ToF sensor and the temperature detection module of the detection device 100 at least partially coincides with the air outlet coverage area of the air conditioner host 501. An included angle α is formed between a sensing surface of the ToF sensor of the detection device 100 and a plane where the air outlet of the air conditioner main unit 501 is located, and is determined by the installation height H of the detection device 100, the preset heights H0 and H1 and a preset monitoring distance l. Since the mounting body 200 is rotatably mounted to the air conditioner, an included angle α between a sensing surface of the ToF sensor and a plane where the air outlet of the main air conditioner 501 is located can be changed by rotating the mounting body 200.
The detection device 100 may be used to detect persons with a height in the range h1 to h 0. In this case, the monitoring distance is determined by h1 and h0, the preset height h is the maximum height h0 that can be monitored within the monitoring distance l, and the minimum height that can be detected by the detection device 100 at the lower edge of the longitudinal viewing angle within the monitoring distance l is h 1. In some embodiments, height h1 and height h0 can be set as desired.
The control method of the air conditioner in this embodiment is to use the above-mentioned detection method to detect whether there is a person in the coverage area of the air conditioner, and whether the person is a child or an adult, and when the first determination result is output as the second state and the second determination result outputs that the object to be detected is a living body, adjust parameters of the air conditioner, such as reducing the output quantity, temperature, and the like of the air conditioner, so that the air conditioner can monitor the coverage area, and adjust the corresponding wind power condition according to the person condition.
In other alternative embodiments, the air conditioning apparatus may also be a wall-mounted air conditioner, or other types of air conditioners. The air conditioning equipment can also carry out parameter adjustment according to the number of people in the coverage area.
The present application also provides a computer-readable storage medium having a program of the detection method stored thereon, where the program of the detection method is executed by a processor to implement the steps of the detection method in any of the above embodiments.
The above-mentioned embodiments are only examples of the present application, and not intended to limit the scope of the present application, and all equivalent structures or equivalent flow transformations made by the contents of the specification and the drawings, such as the combination of technical features between the embodiments and the direct or indirect application to other related technical fields, are also included in the scope of the present application.

Claims (15)

1. A method of detection, comprising:
s1, acquiring a depth value image of the measured object in the first field angle coverage area by using the ToF sensing module;
s2, outputting a first judgment result according to the depth value image;
s3, when the first judgment result is in a preset state, acquiring temperature data of the measured object in a second field angle coverage area acquired by a temperature detection module, wherein the first field angle coverage area and the second field angle coverage area form at least one overlapping area, and the measured object is located in the overlapping area;
and S4, outputting a second judgment result according to the temperature data.
2. The detection method according to claim 1, wherein the first determination result includes a first state, a second state, and a third state, the first state indicates that the object to be detected does not exist in the first viewing angle coverage area, the second state indicates that the first target object exists in the first viewing angle coverage area, and the third state indicates that the second target object exists in the first viewing angle coverage area;
step S2 specifically includes: performing algorithm processing on the depth value image to calculate the height of the detected object, and outputting the first state when the height is less than or equal to a first height threshold value or the detected object is not detected; and outputting the second state when the height is greater than a first height threshold and less than a second height threshold, and outputting the third state when the height is greater than or equal to the second height threshold.
3. The detection method according to claim 2, wherein the preset state includes the second state and the third state;
step S3 specifically includes: and when the first judgment result is in the second state or the third state, acquiring temperature data of the measured object in a second field angle coverage area acquired by the temperature detection module.
4. The detection method according to claim 2, wherein the second determination result includes that the object to be detected is a living body and that the object to be detected is a non-living body, and the step S4 specifically includes:
acquiring space coordinate information of a first area of the measured object according to the depth value image, wherein the first area is a top area of the measured object relative to the ground;
acquiring temperature values of pixel points in corresponding areas in the temperature data according to the space coordinate information of the first area;
and when the temperature value is smaller than the preset temperature threshold value, the measured object is judged to be a non-living body.
5. The detection method according to claim 4, wherein the spatial coordinate information of the object to be detected and the corresponding temperature coordinate satisfy the following formula:
Figure FDA0003198059070000021
wherein the u2 and the v2 are the v2 th row and the u2 th column in the temperature data, and the fx1And f isy1Focal lengths in the x-axis and y-axis directions of the TOF coordinate system, respectively, said sum cy1The central positions of the X-axis and the Y-axis of the TOF coordinate system respectively11R said12R said13R said21R said22R said23R said31R said32R said33As a rotary system of the temperature detection module, txThe t isyThe t iszAnd the x, the y and the z are space coordinate information of the measured object.
6. The detection method of claim 5, wherein S4 further comprises: taking the pixel points in the corresponding area in the temperature data as a central point, and reading a temperature value set of all the pixel points in a preset radius around the central point; acquiring a maximum temperature value in the temperature value set; and when the maximum temperature value is smaller than the preset temperature threshold value, the measured object is judged to be a non-living body.
7. The detection method according to claim 2, wherein the first angle of view includes a first horizontal angle of view and a first vertical angle of view, and a farthest distance/, of the first horizontal angle of view coverage area, satisfies a relationship: l<(h-h1)tan(FOV1yV2+ α), wherein h is the height of the object under test, h1 is the second height threshold, FOV1y is the first vertical field of view of the ToF sensor in the vertical direction, and the ToF sensor is arranged in the vertical directionAnd alpha is an included angle between the ToF sensor and the z direction.
8. The inspection method according to claim 7, wherein the second angle of view includes a second vertical angle of view, and the second vertical angle of view FOV2y of the temperature inspection module in the vertical direction satisfies the following formula:
Figure FDA0003198059070000031
the temperature detection module is arranged on the installation ground, the H is the vertical distance from the temperature detection module to the installation ground, the H is the height of the measured object, the alpha is the included angle between the temperature detection module and the z direction, and the l is the farthest distance of the first horizontal field angle coverage area.
9. A detection device, comprising:
the ToF sensing module comprises a ToF sensor and a processor, wherein the ToF sensor is connected with the processor and is used for acquiring a depth value image of a measured object in a first field angle coverage area;
the temperature detection module is connected with the processor and is used for acquiring temperature data of the measured object in a second field angle coverage area, and the first field angle coverage area and the second field angle coverage area form at least one overlapping area;
and the processor is used for outputting a judgment result according to the depth value image and the temperature data.
10. The detection apparatus of claim 9, wherein the processor is specifically configured to: performing algorithm processing on the depth value image to calculate the height of the measured object;
judging whether the object to be measured exists in the first field angle coverage area or not according to the comparison result of the height of the object to be measured and the first height threshold and the second height threshold;
and when the measured object exists in the first view angle coverage area, judging whether the measured object is a living body according to the temperature data.
11. The detection apparatus as claimed in claim 10, wherein the first angle of view includes a first horizontal angle of view and a first vertical angle of view, and the farthest distance/, of the first horizontal angle of view coverage area, satisfies the following relationship: l<(h-h1)tan(FOV1yAnd/2 + α), wherein h is the height of the measured object, h1 is the second height threshold, FOV1y is a first vertical field angle of the ToF sensor in the vertical direction, and α is an included angle between the ToF sensor and the z direction.
12. The sensing apparatus of claim 11, wherein the second field of view comprises a second vertical field of view, the second vertical field of view FOV2y satisfying the following equation:
Figure FDA0003198059070000041
the temperature detection module is arranged on the installation ground, the H is the vertical distance from the temperature detection module to the installation ground, the H is the height of the measured object, the alpha is the included angle between the temperature detection module and the z direction, and the l is the farthest distance of the first horizontal field angle coverage area.
13. The apparatus according to claim 9, wherein the parallel distance between the ToF sensor and the temperature detection module is a preset parallel distance;
the preset parallel distance is in the range of 1-10 cm.
14. An electronic device, characterized in that it comprises a detection device according to any one of claims 9 to 13.
15. A readable storage medium, characterized in that the readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the detection method according to any one of claims 1 to 8.
CN202110896289.XA 2021-08-05 2021-08-05 Detection method, detection device, electronic equipment and storage medium Pending CN113687370A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110896289.XA CN113687370A (en) 2021-08-05 2021-08-05 Detection method, detection device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110896289.XA CN113687370A (en) 2021-08-05 2021-08-05 Detection method, detection device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113687370A true CN113687370A (en) 2021-11-23

Family

ID=78578968

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110896289.XA Pending CN113687370A (en) 2021-08-05 2021-08-05 Detection method, detection device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113687370A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9720086B1 (en) * 2016-11-22 2017-08-01 4Sense, Inc. Thermal- and modulated-light-based passive tracking system
CN107361748A (en) * 2017-07-20 2017-11-21 歌尔股份有限公司 A kind of temperature taking method and apparatus
CN108469304A (en) * 2018-03-30 2018-08-31 百度在线网络技术（北京）有限公司 Infrared distance measurement and detection method, device, domestic robot and storage medium
KR101961891B1 (en) * 2018-07-23 2019-03-25 (주)넥스리얼 Automatic counting method and appratus for human among the human and stuffs entering into automatic immigration check point
CN111414831A (en) * 2020-03-13 2020-07-14 深圳市商汤科技有限公司 Monitoring method and system, electronic device and storage medium
CN211904416U (en) * 2020-05-06 2020-11-10 东莞市聚亮测控科技有限公司 Temperature measuring instrument

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9720086B1 (en) * 2016-11-22 2017-08-01 4Sense, Inc. Thermal- and modulated-light-based passive tracking system
CN107361748A (en) * 2017-07-20 2017-11-21 歌尔股份有限公司 A kind of temperature taking method and apparatus
CN108469304A (en) * 2018-03-30 2018-08-31 百度在线网络技术（北京）有限公司 Infrared distance measurement and detection method, device, domestic robot and storage medium
KR101961891B1 (en) * 2018-07-23 2019-03-25 (주)넥스리얼 Automatic counting method and appratus for human among the human and stuffs entering into automatic immigration check point
CN111414831A (en) * 2020-03-13 2020-07-14 深圳市商汤科技有限公司 Monitoring method and system, electronic device and storage medium
CN211904416U (en) * 2020-05-06 2020-11-10 东莞市聚亮测控科技有限公司 Temperature measuring instrument

Similar Documents

Publication Publication Date Title
JP6667596B2 (en) Object detection system, autonomous vehicle using the same, and object detection method thereof
CN109100741B (en) Target detection method based on 3D laser radar and image data
CN109961468B (en) Volume measurement method and device based on binocular vision and storage medium
US10145951B2 (en) Object detection using radar and vision defined image detection zone
US20060115113A1 (en) Method for the recognition and tracking of objects
US8385599B2 (en) System and method of detecting objects
CN111045000A (en) Monitoring system and method
EP1705612A1 (en) Information recognition device, information recognition method, information recognition program, and alarm system
EP2315433A1 (en) Calculating energy dissipation in an IR image
CN108021899A (en) Vehicle intelligent front truck anti-collision early warning method based on binocular camera
US10205891B2 (en) Method and system for detecting occupancy in a space
CN113358231B (en) Infrared temperature measurement method, device and equipment
CN111383261A (en) Mobile robot, pose estimation method and pose estimation device thereof
KR20210135753A (en) Method and apparatus for location estimation of lidar-based vehicles
KR20220110034A (en) A method of generating an intensity information with extended expression range by reflecting a geometric characteristic of object and a LiDAR device that performs the method
US20240077586A1 (en) Method for generating intensity information having extended expression range by reflecting geometric characteristic of object, and lidar apparatus performing same method
CN113099120B (en) Depth information acquisition method and device, readable storage medium and depth camera
CA3074628C (en) Method and device for optical distance measurement
Yuan et al. DSmT-based ultrasonic detection model for estimating indoor environment contour
JP7226565B2 (en) Object recognition method and object recognition device
CN113687370A (en) Detection method, detection device, electronic equipment and storage medium
JP2015191268A (en) Person&#39;s head detection device and posture estimation device
EP4310549A1 (en) Sensing system
CN116009107B (en) Passive human body detection method, device, equipment and medium
US11494941B2 (en) Calibration system for calibrating visual coordinate system and depth coordinate system, calibration method and calibration device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination