WO2021196360A1 - 一种温度测量方法及系统 - Google Patents

一种温度测量方法及系统 Download PDF

Info

Publication number
WO2021196360A1
WO2021196360A1 PCT/CN2020/090924 CN2020090924W WO2021196360A1 WO 2021196360 A1 WO2021196360 A1 WO 2021196360A1 CN 2020090924 W CN2020090924 W CN 2020090924W WO 2021196360 A1 WO2021196360 A1 WO 2021196360A1
Authority
WO
WIPO (PCT)
Prior art keywords
temperature
measured
value
target
distance
Prior art date
Application number
PCT/CN2020/090924
Other languages
English (en)
French (fr)
Inventor
黄源浩
许星
徐剑
江隆业
Original Assignee
深圳奥比中光科技有限公司
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 深圳奥比中光科技有限公司 filed Critical 深圳奥比中光科技有限公司
Publication of WO2021196360A1 publication Critical patent/WO2021196360A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/0022Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
    • G01J5/0025Living bodies
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/10Radiation pyrometry, e.g. infrared or optical thermometry using electric radiation detectors
    • G01J5/20Radiation pyrometry, e.g. infrared or optical thermometry using electric radiation detectors using resistors, thermistors or semiconductors sensitive to radiation, e.g. photoconductive devices
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/80Calibration
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01KMEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
    • G01K13/00Thermometers specially adapted for specific purposes
    • G01K13/20Clinical contact thermometers for use with humans or animals
    • G01K13/223Infrared clinical thermometers, e.g. tympanic
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/50Depth or shape recovery
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • G06V40/166Detection; Localisation; Normalisation using acquisition arrangements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168Feature extraction; Face representation
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01JMEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J2005/0077Imaging
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10024Color image
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10028Range image; Depth image; 3D point clouds
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30196Human being; Person
    • G06T2207/30201Face

Definitions

  • This application relates to the technical field of temperature measurement, in particular to a temperature measurement method and system.
  • Non-contact body temperature detection is more and more widely used in homes and public places.
  • the hand-held clinical thermometer needs to measure the corresponding part of the person to be measured while still, which has high accuracy but poor user experience, and the measurement speed is slow.
  • Infrared thermal imaging cameras based on infrared temperature measurement technology can quickly detect the temperature of objects. It has the advantages of wide measurement range, easy rapid and dynamic measurement, and can determine the temperature of small targets. It can be used in airports, subway stations, hospitals, etc. Public places with heavy traffic. Theoretically, an object with a temperature higher than absolute zero will continuously emit infrared radiation energy to the surrounding space. Therefore, by measuring the infrared energy radiated by the object itself, the surface temperature of the object can be accurately determined.
  • the infrared thermal imager is based on This principle completes temperature measurement.
  • the infrared thermal imager uses the difference in thermal contrast between the target object and the surrounding environment due to the difference in temperature and emissivity, and displays the infrared radiation energy density distribution map, which becomes a "thermal image.”
  • the infrared thermal imager is susceptible to the distance of the object to be measured during the temperature measurement process. The distance between the object to be measured and the thermal imager has a different effect on the temperature of the object to be measured. As the measurement distance increases, the atmosphere penetrates The rate is reduced, and measurement errors are prone to occur during measurement.
  • the purpose of this application is to provide a temperature measurement method and system to solve at least one of the above-mentioned background technical problems.
  • a temperature measurement method includes the following steps:
  • S101 Acquire a first temperature value of at least one target to be measured in the field of view area
  • the temperature error is calculated by the functional relationship between the pre-calibrated distance and the temperature error, and the first temperature value is corrected by using the temperature error to obtain a second temperature value.
  • the second temperature value is the temperature of the target to be measured.
  • it further includes the steps:
  • an infrared detector is used to collect the infrared radiation signal in the field of view area and convert the response to the corresponding electrical signal, and the electrical signal is processed to obtain the far-infrared image of the field of view area; at the same time, using A depth camera collects a depth image of the field of view area; positioning and recognizing the far-infrared image and the depth image to obtain the first temperature value and the distance value of at least one of the targets to be measured.
  • the infrared detector and the depth camera are calibrated in advance, so that the far-infrared image obtained by the infrared detector and the depth image obtained by the depth camera have one pixel unit.
  • the corresponding position relationship is based on the first pixel of at least one of the target under test in the depth image in the field of view, and according to the one-to-one corresponding position relationship, it is determined that the target under test is in the far-infrared The corresponding second pixel on the image.
  • step S103 before step S103, it further includes a step of pre-calibrating the relationship between the distance and the temperature error; the relationship between the calibration distance and the temperature error includes the following steps:
  • S202 Calculate the temperature error between the measured temperature value and the set temperature value of the calibration object
  • a temperature measurement system includes an infrared detector, a depth camera, a storage unit, and a processing unit; wherein the infrared detector is used to receive infrared radiation signals of the target to be measured and obtain a far-infrared image of the field of view area; the depth camera Used to collect the depth image of the field of view area where the target to be measured is located; the storage unit is used to store the pre-calibrated distance and the temperature error function relationship; the processing unit and the infrared detector and the depth The camera is connected to obtain the first temperature value of at least one of the target under test in the far-infrared image, and obtain the corresponding distance value of the target under test in the depth image, and use the distance value to combine The temperature error is calculated according to the functional relationship between the pre-calibrated distance and the temperature error, the first temperature value is corrected by the temperature error, and the second temperature value is calculated, and the second temperature is the temperature of the target to be measured.
  • the processing unit performs positioning and recognition on the depth image to obtain the first temperature value and the distance value of at least one of the objects to be measured; specifically, it is determined in the field of view area
  • the first pixel of at least one of the target under test in the depth image based on the pre-calibrated far-infrared image and the pixel unit in the depth image have a one-to-one corresponding positional relationship; it is determined that the target under test is located The corresponding second pixel on the far-infrared image.
  • it also includes an RGB camera for collecting color images of the field of view area; by pre-calibrating the corresponding relationship between the RGB camera and the depth camera and the infrared detector, using the color image According to the calibrated corresponding relationship, the pixels of the target to be tested are acquired in the depth image and the far-infrared image of the target to be tested, so as to perform location recognition through the color image.
  • an RGB camera for collecting color images of the field of view area
  • the embodiment of the present application provides a temperature measurement method.
  • a depth camera and an infrared detector to collect the same field of view area, the position of the target to be measured in the far-infrared image is determined according to the pixel points of the target to be measured in the depth image;
  • the distance value obtained in the image corrects the temperature value obtained in the far-infrared image to obtain the precise temperature value of the target to be measured, and the accuracy of temperature measurement is improved through the synergy of the depth camera and the infrared detector.
  • Fig. 1 is a flowchart of a temperature measurement method according to some embodiments of the present application.
  • Fig. 2 is a flowchart of a method for calibrating the relationship between distance and temperature error according to other embodiments of the present application.
  • Fig. 3 is a structural diagram of a temperature measurement system according to other embodiments of the present application.
  • connection can be used for fixing or circuit connection.
  • first and second are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Therefore, the features defined with “first” and “second” may explicitly or implicitly include one or more of these features.
  • “plurality” means two or more, unless otherwise specifically defined.
  • Fig. 1 shows a schematic flow chart of a temperature measurement method according to an embodiment of the present application. The method includes the following steps:
  • S101 Acquire a first temperature value of at least one target to be measured in the field of view area
  • S102 Acquire a distance value corresponding to the target to be measured in the field of view area
  • step S103 According to the distance value obtained in step S102, the temperature error is calculated by the functional relationship between the pre-calibrated distance and the temperature error, and the first temperature value is corrected by the temperature error to obtain the second temperature value, which is the target to be measured temperature.
  • it further includes the following steps:
  • S104 Display the corrected second temperature value of the target to be measured.
  • an infrared detector is used to collect the infrared radiation signal in the field of view area and respond, convert it into a corresponding electrical signal, and process the electrical signal to obtain a far-infrared image of the field of view area; where, The value of each pixel in the far-infrared image is the first temperature value (that is, the rough temperature value) of the object in the field of view area.
  • the depth camera is used to collect the near-infrared image and/or the depth image of the field of view. The value of each pixel in the near-infrared image and/or the depth image represents the distance value of the object on the pixel from the depth camera.
  • the depth cameras involved in the embodiments of the present application include structured light, TOF (time of flight), or binocular ranging technology depth cameras. Perform positioning recognition on the far-infrared image and the depth image to obtain the first temperature value and the distance value of at least one of the targets.
  • the positions of the infrared detector and the depth camera are relatively fixed, that is, the separation distance between the infrared detector and the depth camera remains constant.
  • the infrared detector and the depth camera are fixedly installed together, and the distance between the infrared detector and the depth camera can be ignored, so that the distance between the depth camera and the infrared detector can be considered as the distance between the target and the infrared detector. The distance is equal.
  • the infrared detector and the depth camera are calibrated in advance, so that the pixel units in the far infrared image obtained by the infrared detector and the depth image obtained by the depth camera have a one-to-one correspondence.
  • the target to be measured is a human face as an example
  • the depth value of each pixel is obtained by using the depth image
  • the feature is extracted and analyzed by the convolutional neural network, which can quickly locate the corresponding pixel area of the human face in the depth image (First pixel), where the method for locating the face based on the depth image can adopt the existing technology, which will not be repeated here.
  • the pixel area (second pixel) corresponding to the face in the far-infrared image can be determined.
  • the pixel area of the human face can also be located according to the far-infrared image, and the pixel area of the human face in the depth image can be further determined according to the pre-calibrated correspondence relationship. It is understandable that locating the face area based on the depth image is simple, fast, and accurate, and the algorithm is simple, which can speed up the measurement speed of the system.
  • the first temperature value of the second pixel according to the distance value of the first pixel and the function relationship between the pre-calibrated distance and the temperature error to obtain the second temperature value of the second pixel, that is, the precise temperature of the target to be measured value.
  • the first temperature value of the target to be measured obtained by the far-infrared detector usually has a large error, and the error gradually increases as the distance of the measurement target increases.
  • the depth image is used to obtain the distance value of the target to be measured. , Combine the calibrated functional relationship to find the real-time temperature error, and correct the first temperature value in the far-infrared image in real time to obtain a more accurate temperature value.
  • the near-infrared image and/or depth image collected by the depth camera can be used to locate the key points of the human face in the infrared image, and obtain multiple key points including at least the forehead, eyes, face contour, and neck.
  • the first pixel of a point, the corresponding second pixel is determined according to the first pixel, and the first pixel on the second pixel is corrected based on the distance value on the first pixel of each key point based on the function relationship between the pre-calibrated distance and the temperature error.
  • Temperature value Preferably, the first pixel of the face and forehead can be identified in the depth image, the corresponding second pixel is determined and corrected, and the accurate temperature of the forehead can be quickly obtained.
  • FIG. 2 shows a flowchart of a method for calibrating the relationship between distance and temperature error according to another embodiment of the present application, including the following steps:
  • the black body is used as the calibration object, the black body is heated to a set temperature, and the black body is used to simulate the radiation of the human body.
  • the set temperature is within the normal human body temperature range, such as 36 degrees, and the black body surface emissivity is set to 0.97 (The same as the emissivity of human skin).
  • S202 Calculate the temperature error between the measured temperature value of the calibration object and the set temperature value.
  • S203 Construct a polynomial fitting function, fit the temperature error and the distance according to the polynomial fitting function, and calculate the value of the undetermined coefficient in the polynomial fitting function.
  • the calculated polynomial function relationship is stored in the storage unit, which is convenient for the subsequent correction unit to call the polynomial function to calculate the temperature error.
  • the temperature of the black body is changed, and the temperature errors of the black body at different distances in multiple sets of different temperatures are measured to obtain multiple sets of fitting parameters.
  • the distance value of at least one target to be measured in the depth image is acquired by the processing unit, and the first temperature value corresponding to the target to be measured in the far-infrared image is correspondingly acquired.
  • the value is the precise temperature value of the target to be measured.
  • T 1 is the second temperature value
  • T 0 is the first temperature value
  • y is the temperature error.
  • the corrected second temperature value is displayed in real time in the display imaging unit.
  • FIG. 3 shows a structural block diagram of a temperature measurement system according to another embodiment of the present application.
  • the temperature measurement system includes: an infrared detector 301, a depth camera 302, a processing unit 303, a storage unit 304, and an imaging display unit 305.
  • the infrared detector 301 is used to receive the infrared radiation signal of the target to be measured and obtain the far-infrared image of the field of view area.
  • the infrared detector includes a thermopile type, a pyroelectric type, a diode type or a microbolometer, etc.
  • the infrared detector is a microbolometer, which includes a MEMS sensor and a CMOS readout circuit; wherein the upper MEMS sensor absorbs infrared radiation energy, and the temperature change caused by the absorbed energy causes the material resistance to change, and the CMOS readout circuit
  • the small resistance changes are output as electrical signals, and the electrical signals are amplified and exchanged to form a far-infrared image of the field of view.
  • the value of each pixel in the far-infrared image is the first object in the field of view. Temperature value.
  • the depth camera 302 is used to collect a near-infrared image and/or a depth image of the area where the target to be measured is located, and the value of each pixel in the near-infrared image and/or the depth image represents the distance value of the object on the pixel from the depth camera.
  • the processing unit 303 is connected to the infrared detector 301 and the depth camera 302 (it is understandable that the connection here can be a wired connection or a wireless connection), and is used to obtain the first temperature of at least one target to be measured in the far-infrared image Value (rough temperature value), and obtain the corresponding distance value of the target to be measured in the depth image, use the distance value and calculate the temperature error according to the relationship between the pre-calibrated distance and the temperature error, use the temperature error to correct the first temperature value, and calculate the first temperature value.
  • the second temperature value is to obtain the precise temperature value of the target to be measured.
  • the processing unit 303 may be a host computer, and the data acquired by the infrared detector 301 and the depth camera 302 are transmitted to the host computer in a wireless manner, and processed in the host computer. In this way, the computing power and speed of the system can be improved.
  • the processing unit 303 performs positioning recognition on the far-infrared image and the depth image, and obtains the first temperature value and the distance value of at least one of the targets to be measured.
  • the infrared detector and the depth camera are calibrated in advance so that the acquired far-infrared image and the pixel unit in the depth image have a one-to-one corresponding position relationship, that is, a pre-calibrated corresponding relationship.
  • the first pixel in the depth image of at least one target in the field of view is determined, and the second pixel corresponding to the target in the far-infrared image is determined according to the pre-calibrated correspondence relationship.
  • the infrared detector and the depth camera are fixedly installed together, and the distance between the infrared detector and the depth camera can be ignored, so that the distance between the target to be measured and the depth camera can be considered equal to the distance from the infrared detector to the target to be measured .
  • the depth value of each pixel is obtained from the depth image, and the feature is extracted and analyzed by the convolutional neural network, which can quickly locate the corresponding pixel area of the human face in the depth image ( The first pixel), where the method for locating a human face based on the depth image can adopt the existing technology, which will not be repeated here.
  • the pixel area (second pixel) corresponding to the face in the far-infrared image can be determined.
  • the pixel area of the human face can also be located according to the far-infrared image, and the pixel area of the human face in the depth image can be further determined through a pre-calibrated correspondence relationship. It is understandable that locating the face area based on the depth image is simple, fast, and accurate, and the simple algorithm can speed up the measurement speed of the system.
  • the first temperature value of the target to be measured obtained by the far-infrared detector usually has a large error, and the error gradually increases as the distance of the measurement target increases.
  • the depth image is used to obtain the distance value of the target to be measured.
  • the distance value on the first pixel obtained from the depth image is the distance between the target to be measured and the far-infrared detector, and the distance value is taken into the polynomial fitting function to obtain the corresponding value of the current distance.
  • T 1 T 0 +y
  • the imaging display unit 305 is used to display the corrected second temperature value of the target to be measured.
  • the processing unit 303 may also perform face recognition based on the acquired depth image, and perform key feature point matching on the face information acquired in the depth image with pre-stored face information, and if the matching is successful, the recognition is confirmed .
  • the polynomial fitting function y Ax 3 +Bx 2 +Cx+D enters the temperature errors at multiple different distances, and the corresponding fitting parameters [A,B,C,D] are obtained by solving the equations, and the The function relationship between the temperature error and the distance obtained is stored in the storage unit 304.
  • the storage unit 304 is also used to store a face database for face recognition, and methods and procedures for face recognition.
  • the temperature measurement system further includes an RGB camera for collecting color images of the field of view area.
  • an RGB camera for collecting color images of the field of view area.
  • the second pixel in the corresponding far-infrared image and the first pixel in the depth image are determined according to the third pixel of the target to be measured in the color image.
  • the position of the object to be measured can be determined through the depth image, and the position of the object to be measured can also be determined by using an RGB camera.
  • the temperature measurement system further includes a monitoring unit for providing early warning information.
  • a temperature threshold is set in the monitoring unit, and the corrected second temperature value is compared with the temperature threshold. When the second temperature value is higher than the threshold, an alarm sound or prompt characters are displayed on the imaging display unit.
  • the embodiment of the present application further provides a storage medium for storing a computer program, and the computer program at least executes the above-mentioned method when the computer program is executed.
  • the storage medium may be implemented by any type of volatile or non-volatile storage device, or a combination thereof.
  • the non-volatile memory can be read-only memory (ROM, Read Only Memory), programmable read-only memory (PROM, Programmable Read-Only Memory), and erasable programmable read-only memory (EPROM, Erasable Programmable Read-Only).
  • Memory Electrically Erasable Programmable Read-Only Memory (EEPROM, Electrically Erasable Programmable Read-Only Memory), Magnetic Random Access Memory (FRAM, Ferromagnetic Random Access Memory), Flash Memory (Flash Memory), Magnetic Surface Memory, Optical Disks, Or CD-ROM (Compact Disc Read-Only Memory); magnetic surface memory can be disk storage or tape storage.
  • the volatile memory may be a random access memory (RAM, Random Access Memory), which is used as an external cache.
  • RAM random access memory
  • SRAM static random access memory
  • SSRAM synchronous static random access memory
  • Synchronous Static Random Access Memory Synchronous Static Random Access Memory
  • DRAM Dynamic Random Access Memory
  • SDRAM Synchronous Dynamic Random Access Memory
  • DDRSDRAM Double Data Rate Synchronous Dynamic Random Access Memory
  • ESDRAM Enhanced Synchronous Dynamic Random Access Memory
  • SLDRAM synchronous connection dynamic random access memory
  • SLDRAM SyncLink Dynamic Random Access Memory
  • DRAM Direct Rambus Random Access Memory
  • the storage media described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memory.
  • the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the present application implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing relevant hardware through a computer program.
  • the computer program can be stored in a computer-readable storage medium. When the program is executed by the server, it can implement the steps of the foregoing method embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Radiation Pyrometers (AREA)

Abstract

一种温度测量方法,包括如下步骤:S101、获取视场区域内至少一个待测目标的第一温度值(T0);S102、获取视场区域中对应待测目标的距离值;S103、根据步骤S102中获得的距离值,通过预先标定的距离与温度误差的函数关系计算温度误差,利用温度误差修正第一温度值(T0),得到第二温度值(T1),第二温度值(T1)即为待测目标的温度。通过利用深度相机(302)和红外探测器(301)采集同一视场区域,根据深度图像中待测目标的像素点确定待测目标在远红外图像中的位置;进一步根据深度图像中获取的距离值修正远红外图像中获取的温度值,获得待测目标的精确温度值,通过深度相机(302)与红外探测器(301)的协同作用提高测温的准确性。

Description

一种温度测量方法及系统
本申请要求于2020年3月31日提交中国专利局,申请号为202010246340.8,发明名称为“一种温度测量方法及系统”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及温度测量技术领域,具体涉及一种温度测量方法及系统。
背景技术
非接触式体温检测在家庭、公共场所的应用越来越广泛。其中,手持式体温计需要待测者静止时对其相应部位进行测量,精度较高但用户体验不佳,而且测量速度较慢。基于红外测温技术的红外热像仪可以快速对物体温度进行检测,其具有测量范围宽、易于快速与动态测量、可以确定微小目标的温度等优点,可以应用在机场、地铁站、医院等人流量大的公共场所。理论上,温度高于绝对零度的物体都会不停地向周围空间发出红外辐射能量,因此通过对物体自身辐射的红外能量的测量,便能准确地测定物体的表面温度,红外热像仪就是根据此原理完成测温。
具体地,红外热像仪是利用目标物体与周围环境之间由于温度与发射率的差异所产生的热对比度不同,而把红外辐射能量密度分布图显示出来,成为“热像”。但红外热像仪在测温过程中易受到待测者距离的影响,待测目标物体距离热像仪的远近对所测目标物体温度的影响不同,随着测量距离的增大,大气透过率减小,测量时容易产生测量误差。
发明内容
本申请的目的在于提供一种温度测量方法及系统,以解决上述背景技术问题中的至少一种问题。
为达到上述目的,本申请实施例的技术方案是这样实现的:
一种温度测量方法,包括如下步骤:
S101、获取视场区域内至少一个待测目标的第一温度值;
S102、获取所述视场区域中所述待测目标的距离值;
S103、根据步骤S102中获得的所述距离值,通过预先标定的距离与温度误差的函数关系计算所述温度误差,利用所述温度误差修正所述第一温度值,得到第二温度值,所述第二温度值即为所述待测目标的温度。
在一些实施例中,还包括步骤:
S104、显示所述待测目标经过修正后的所述第二温度值。
在一些实施例中,利用红外探测器采集所述视场区域内的红外辐射信号并进行响应转换为对应的电信号,对电信号进行处理获取所述视场区域的远红外图像;同时,利用深度相机采集所述视场区域的深度图像;对所述远红外图像和所述深度图像进行定位识别获取其中至少一个所述待测目标的所述第一温度值和所述距离值。
在一些实施例中,预先标定所述红外探测器和所述深度相机,使得所述红外探测器获得的所述远红外图像和所述深度相机获得的所述深度图像中的像素单元具有一一对应的位置关系,基于所述视场区域中至少一个所述待测目标在所述深度图像中的第一像素,根据所述一一对应的位置关系,确定该待测目标在所述远红外图像上对应的第二像素。
在一些实施例中,在步骤S103之前还包括有预先标定距离与温度误差关系的步骤;所述标定距离与温度误差关系包括如下步骤:
S201、获取多个预设距离处标定物体的测量温度值;
S202、计算所述标定物体的所述测量温度值与设定温度值的温度误差;
S203、构建多项式拟合函数并根据所述多项式拟合函数对所述温度误差与距离进行拟合并计算所述多项式拟合函数中待定系数的取值。
在一些实施例中,步骤S203中,构建多项式拟合函数y=Ax 3+Bx 2+Cx+D来拟合所述温度误差与距离的关系,其中,y为温度误差值,x为距离值。
本申请实施例的另一技术方案为:
一种温度测量系统,包括红外探测器、深度相机、存储单元以及处理单元;其中,所述红外探测器用于接收待测目标的红外辐射信号并获取视场区域的远红外图像;所述深度相机用于采集所述待测目标所在所述视场区域的深度图像;所述存储单元用于存储预先标定的距离与温度误差的函数关系;所述处理单元与所述红外探测器以及所述深度相机连接,以用于获取所述远红外图像中至少一个所述待测目标的第一温度值,以及获取所述深度图像中对应的所述待测目标的距离值,利用所述距离值并根据预先标定的距离与温度误差的函数关系计算温度误差,利用所述温度误差修正所述第一温度值,计算得到第二温度值,所述第二温度即为所述待测目标的温度。
在一些实施例中,所述处理单元对所述深度图像进行定位识别获取其中至少一个所述待测目标的所述第一温度值和所述距离值;具体的,确定所述视场区域中至少一个所述待测目标在所述深度图像中的第一像素;基于预先标定的所述远红外图像和所述深度图像中的像素单元具有一一对应的位置关系;确定该待测目标在所述远红外图像上对应的第二像素。
在一些实施例中,还包括有RGB相机,用于采集所述视场区域的彩色图像;通过预先标定所述RGB相机与所述深度相机以及所述红外探测器的对应关系,利用彩色图像中待测目标的像素,根据标定好的对应关系,获取待测目标在深度图像和远红外图像中的像素,从而通过彩色图像进行定位识别。
本申请实施例的又一技术方案为:
一种存储介质,用于存储计算机程序,其特征在于:所述计算机程序被执 行时至少执行上述技术方案所述的温度测量方法。
本申请实施例提供一种温度测量方法,通过利用深度相机和红外探测器采集同一视场区域,根据深度图像中待测目标的像素点确定待测目标在远红外图像中的位置;进一步根据深度图像中获取的距离值修正远红外图像中获取的温度值,获取待测目标的精确温度值,通过深度相机与红外探测器的协同作用提高测温的准确性。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是根据本申请一些实施例温度测量方法的流程图示。
图2是根据本申请另一些实施例标定距离与温度误差关系的方法流程图示。
图3是根据本申请另一些实施例温度测量系统的结构图示。
具体实施方式
为了使本申请实施例所要解决的技术问题、技术方案及有益效果更加清楚明白,以下结合附图及实施例,对本申请进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
需要说明的是,当元件被称为“固定于”或“设置于”另一个元件,它可以直接在另一个元件上或者间接在该另一个元件上。当一个元件被称为是“连接于”另一个元件,它可以是直接连接到另一个元件或间接连接至该另一个元件上。另外,连接即可以是用于固定作用也可以是用于电路连通作用。
需要理解的是,术语“长度”、“宽度”、“上”、“下”、“前”、“后”、 “左”、“右”、“竖直”、“水平”、“顶”、“底”“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系,仅是为了便于描述本申请实施例和简化描述,而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作,因此不能理解为对本申请的限制。
此外,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多该特征。在本申请实施例的描述中,“多个”的含义是两个或两个以上,除非另有明确具体的限定。
参照图1所示,图1示出了本申请实施例一种温度测量方法的流程示意图,该方法包括如下步骤:
S101、获取视场区域内至少一个待测目标的第一温度值;
S102、获取视场区域中对应待测目标的距离值;
S103、根据步骤S102中获得的距离值,通过预先标定的距离与温度误差的函数关系计算温度误差,利用温度误差修正第一温度值,得到第二温度值,第二温度值即为待测目标的温度。
在一些实施例中,还包括如下步骤:
S104、显示待测目标经过修正后的第二温度值。
具体的,在同一视场区域内,利用红外探测器采集视场区域内的红外辐射信号并进行响应,转换为对应的电信号,对电信号进行处理获取视场区域的远红外图像;其中,远红外图像中每个像素点的值即为视场区域中物体的第一温度值(即粗略温度值)。同时,利用深度相机采集视场区域的近红外图像和/或深度图像,近红外图像和/或深度图像中每个像素点的值代表了该像素点上物体距离深度相机的距离值。在本申请实施例中涉及的深度相机包括结构光、TOF(飞行时间)、或双目测距技术的深度相机。对远红外图像和深度图像进行定位识别获取其中至少一个目标的第一温度值和距离值。其中,红外探测器与深度相机的位置相对固定,即红外探测器与深度相机之间的间隔距离保持固定不变。在 一些实施例中,红外探测器与深度相机固定安装在一起,红外探测器与深度相机之间的间距可以忽略,从而可以认为待测目标距离深度相机的距离与待测目标距离红外探测器的距离相等。
预先标定红外探测器和深度相机,使得红外探测器获取的远红外图像和深度相机获得的深度图像中的像素单元具有一一对应的位置关系。确定视场区域中至少一个目标在深度图像中的像素,记为第一像素,根据预先标定的对应关系,确定该目标在红外图像上对应的像素,记为第二像素。在一些实施例中,以待测目标为人脸进行举例说明,利用深度图像获取每一个像素上的深度值,通过卷积神经网络提取特征进行分析,可以快速定位人脸在深度图像中对应像素区域(第一像素),其中,基于深度图像定位人脸的方法可以采用现有技术,在此不再赘述。根据人脸在深度图像中对应的像素区域以及预先标定的对应关系可以确定人脸在远红外图像中对应的像素区域(第二像素)。在一些实施例中,也可以根据远红外图像定位人脸的像素区域,根据预先标定的对应关系进一步确定人脸在深度图像中的像素区域。可以理解的是,基于深度图像定位人脸区域具有简单、快速、准确的特点,而且算法简单,可以加快系统的测量速度。
根据第一像素点的距离值以及预先标定的距离与温度误差的函数关系对第二像素点的第一温度值进行修正,获得第二像素点的第二温度值,即待测目标的精确温度值。在实际应用中,远红外探测器获取的待测目标的第一温度值通常存在较大的误差,而且随着测量目标的距离增大误差逐渐增大,利用深度图像获取待测目标的距离值,结合标定的函数关系求出实时的温度误差,实时修正远红外图像中的第一温度值获取更精确的温度值。
在一些实施例中,利用深度相机采集到的近红外图像和/或深度图像可以对红外图像中人脸的关键点进行定位,得到至少包括额头、眼睛、人脸轮廓、颈部等多个关键点的第一像素,根据第一像素确定对应的第二像素,通过预先标定的距离与温度误差的函数关系,基于每个关键点的第一像素上的距离值修正第二像素上的第一温度值;优选地,可以在深度图像中识别出脸部额头的第一 像素确定对应的第二像素并进行修正,快速获取额头的精确温度。
参照图2所示,图2示出了本申请另一实施例一种标定距离与温度误差关系的方法流程图,包括如下步骤:
S201:获取多个预设距离处标定物体的测量温度值;
在一些实施例中,利用黑体作为标定物体,将黑体加热到设定温度,以黑体模拟人体的辐射情况,设定温度在人体正常体温范围内,例如36度,设定黑体表面发射率为0.97(与人体皮肤发射率相同)。在红外探测器的视场内移动黑体并测量每次移动的温度数值,例如可以在距离红外探测器0.5m-6.5m的距离区间内,以0.5m为间隔,在0.5m、1m、1.5m、2m、2.5m、3m、3.5m、4m、4.5m、5m、5.5m、6m、6.5m处分别采集黑体的温度。需要说明的是,在实际应用中,为了提高测量精度,一方面需要在多个不同距离处进行多次测量,另一方面需要改变黑体的温度以获取多组温度随距离变化的数据,本申请实施例中为了更好的举例说明,只以36度温度值选定0.5m-6.5m距离区间进行标定,但不能理解为对本申请的限制。
S202:计算标定物体的测量温度值与设定温度值的温度误差。
S203:构建多项式拟合函数并根据该多项式拟合函数对温度误差与距离进行拟合并计算多项式拟合函数中待定系数的取值。
计算每一个预设距离位置处标定物体的测量温度值与设定温度值的温度误差。可以理解的是,在标定过程中,控制标定物体的设定温度值保持不变,随着距离的改变各个距离位置处标定物体的测量温度值不完全相同。获取各个距离位置处标定物体的温度误差后,构建多项式拟合函数y=Ax 3+Bx 2+Cx+D来拟合温度误差与距离的关系,其中,y为温度误差值,x为距离值,将温度误差和对应的距离值输入至所述多项式拟合函数,通过解方程组的方式即可得到参数[A,B,C,D]。
在一些实施例中,于多项式拟合函数y=Ax 3+Bx 2+Cx+D中输入多个不同距离位置处标定物体的温度误差,通过解方程组的方式求取对应的拟合参 数[A,B,C,D];其中,某一设定温度下的标定距离位置个数应大于拟合参数的个数。将计算得到的多项式函数关系存储在存储单元中,便于后续修正单元调用多项式函数计算温度误差。在一些实施例中,改变黑体的温度,测定多组不同温度下黑体在不同距离位置处的温度误差,得到多组拟合参数,对多组拟合参数中的每个参数进行求平均,最后得出拟合参数[A,B,C,D]。以N个不同温度为例进行说明,根据N个不同温度下标定物体在不同距离位置处的温度误差,可以得到N组拟合参数[A 1,B 1,C 1,D 1],[A 2,B 2,C 2,D 2]……[A n,B n,C n,D n],分别对A 1-A n、B 1-B n、C 1-C n、D 1-D n进行求平均,得到最终的拟合参数[A,B,C,D]。可以理解的是,测量数值越多,计算得到的拟合参数越精确。基于此,根据多项式拟合函数以及测量的距离值可以对第一温度值进行修正。
参照图1所示,通过处理单元获取深度图像中至少一个待测目标的距离值,对应的获取远红外图像中对应待测目标的第一温度值。将距离值带入多项式拟合函数求出对应的温度误差,根据误差修正公式T 1=T 0+y修正远红外图像中对应的第一温度值,计算得到第二温度值,该第二温度值即为待测目标的精确温度值。其中,T 1为第二温度值,T 0为第一温度值,y为温度误差。最后将修正后的第二温度值在显示成像单元中实时显示。
参照图3所示,图3示出了本申请又一实施例一种温度测量系统的结构框图。温度测量系统包括:红外探测器301、深度相机302、处理单元303、存储单元304以及成像显示单元305。
其中,红外探测器301用于接收待测目标的红外辐射信号并获取视场区域的远红外图像。在一些实施例中,红外探测器包括热电堆型、热释电型、二极管型或微测辐射热计等。优选地,红外探测器为微测辐射热计,其包括有MEMS传感器和CMOS读出电路;其中,上层的MEMS传感器吸收红外辐射能量,吸收能量产生的温度变化引起材料电阻变化,CMOS读出电路将微小的电阻变化以电信号的方式输出,将电信号经过放大和交换处理,形成视场区域的远红外图像,远红外图像中每个像素点的值即为视场区域中物体的第一温度值。
深度相机302用于采集待测目标所在区域的近红外图像和/或深度图像,近红外图像和/或深度图像中每个像素点的值代表了该像素点上物体距离深度相机的距离值。
处理单元303与红外探测器301以及深度相机302连接(可以理解的是,此处的连接可以是有线连接,也可以无线连接),用于获取远红外图像中至少一个待测目标的第一温度值(粗略温度值),以及获取深度图像中对应的待测目标的距离值,利用距离值并根据预先标定的距离与温度误差的关系计算温度误差,利用温度误差修正第一温度值,计算第二温度值,即获得待测目标的精确温度值。在一些实施例中,处理单元303可以为上位机,红外探测器301和深度相机302获取的数据通过无线方式传输至上位机,在上位机中进行处理。通过这种方式,可以提高系统的计算处理能力以及速度。
具体的,处理单元303对远红外图像和深度图像进行定位识别,获取其中至少一个待测目标的第一温度值和距离值。通常预先标定红外探测器和深度相机使得获取的远红外图像和深度图像中的像素单元具有一一对应的位置关系,即预先标定的对应关系。确定视场区域中至少一个目标在深度图像中的第一像素,根据预先标定的对应关系,确定该目标在远红外图像上对应的第二像素。在一些实施例中,红外探测器与深度相机固定安装在一起,红外探测器与深度相机的间距可以忽略,从而可以认为待测目标距离深度相机的距离与待测目标距离红外探测器的距离相等。
在一些实施例中,假设待测目标是人脸时,由深度图像获取每一个像素上的深度值,通过卷积神经网络提取特征进行分析,可以快速定位人脸在深度图像中对应像素区域(第一像素),其中,基于深度图像定位人脸的方法可以采用现有技术,在此不再赘述。根据人脸在深度图像中对应的像素区域以及预先标定的对应关系可以确定人脸在远红外图像中对应的像素区域(第二像素)。在一些实施例中,也可以根据远红外图像定位人脸的像素区域,通过预先标定的对应关系进一步确定人脸在深度图像中的像素区域。可以理解的是,基于深度图 像定位人脸区域具有简单、快速、准确的特点,而且算法简单可以加快系统的测量速度。
在实际应用中,远红外探测器获取的待测目标的第一温度值通常存在较大的误差,而且随着测量目标的距离增大误差逐渐增大,利用深度图像获取待测目标的距离值,结合标定的距离与温度误差的函数关系求出实时的温度误差,从而实时修正远红外图像中的粗略温度值以获取更精确的温度值。
具体的,根据深度图像获取的第一像素上的距离值,该距离值即为待测目标离远红外探测器的距离,将该距离值带入多项式拟合函数中求出当前距离值对应的温度误差,进一步根据误差修正公式T 1=T 0+y修正远红外图像中第二像素上的第一温度值,即可计算出此时待测目标的精确温度值,其中,T 1为第二温度值,T 0为第一温度值,y为温度误差值。
成像显示单元305用于显示待测目标经过修正后的第二温度值。
在一些实施例中,处理单元303还可以基于获取的深度图像进行人脸识别,将深度图像中获取的人脸信息与与预存储的人脸信息进行关键特征点匹配,若匹配成功则确认识别。
在一些实施例中,温度测量系统还包括存储单元304,用于存储通过构建多项式拟合函数y=Ax 3+Bx 2+Cx+D拟合出的距离与温度误差的函数关系,其中,y为温度误差值,x为距离值。具体地,采集标定物体在多个预设距离处的测量温度值,计算每一个预设距离处的测量温度值与设定温度值的温度误差,构建多项式拟合函数来拟合温度误差与距离的函数关系。多项式拟合函数y=Ax 3+Bx 2+Cx+D中输入多个不同距离处的温度误差,通过解方程组的方式求取对应的拟合参数[A,B,C,D],将求出的温度误差与距离的函数关系并将其存储在存储单元304中。
在一些实施例中,存储单元304还用于存储用于人脸识别的人脸数据库,以及进行人脸识别的方法程序。
在一些实施例中,温度测量系统还包括RGB相机,用于采集视场区域的彩 色图像。在实际应用中,可以预先标定好RGB相机与深度相机和红外探测器的对应关系,利用彩色图像中待测目标的像素,根据标定好的对应关系,获取待测目标在深度图像和远红外图像中的像素,从而通过彩色图像进行定位识别。具体地,根据彩色图像中的待测目标的第三像素确定对应的远红外图像中的第二像素以及深度图像中的第一像素。可以理解的是,在本申请实施例中,即可以通过深度图像确定待测目标的位置,也可以采用RGB相机确定待测目标的位置。
在一些实施例中,温度测量系统还包括监控单元,用于提供预警信息。在监控单元内设置温度的阈值,将修正后的第二温度值与温度阈值进行比较,当第二温度值高于阈值时,发出警报提示音或提示字符显示在成像显示单元中。
本申请实施例还提供一种存储介质,用于存储计算机程序,该计算机程序被执行时至少执行如上所述的方法。
所述存储介质可以由任何类型的易失性或非易失性存储设备、或者它们的组合来实现。其中,非易失性存储器可以是只读存储器(ROM,Read Only Memory)、可编程只读存储器(PROM,Programmable Read-Only Memory)、可擦除可编程只读存储器(EPROM,ErasableProgrammable Read-Only Memory)、电可擦除可编程只读存储器(EEPROM,ElectricallyErasable Programmable Read-Only Memory)、磁性随机存取存储器(FRAM,FerromagneticRandom Access Memory)、快闪存储器(Flash Memory)、磁表面存储器、光盘、或只读光盘(CD-ROM,Compact Disc Read-Only Memory);磁表面存储器可以是磁盘存储器或磁带存储器。易失性存储器可以是随机存取存储器(RAM,Random Access Memory),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(SRAM,Static Random Access Memory)、同步静态随机存取存储器(SSRAM,SynchronousStatic Random Access Memory)、动态随机存取存储器(DRAM,Dynamic Random AccessMemory)、同步动态随机存取存储器(SDRAM,Synchronous Dynamic Random AccessMemory)、双倍数据速率同步动 态随机存取存储器(DDRSDRAM,Double Data RateSynchronous Dynamic Random Access Memory)、增强型同步动态随机存取存储器(ESDRAM,Enhanced Synchronous Dynamic Random Access Memory)、同步连接动态随机存取存储器(SLDRAM,SyncLink Dynamic Random Access Memory)、直接内存总线随机存取存储器(DRRAM,Direct Rambus Random Access Memory)。本申请实施例描述的存储介质旨在包括但不限于这些和任意其它适合类型的存储器。
所属领域的技术人员可以清楚地了解到,为了描述的方便和简洁,仅以上述各功能单元、模块的划分进行举例说明,实际应用中,可以根据需要而将上述功能分配由不同的功能单元、模块完成,即将所述装置的内部结构划分成不同的功能单元或模块,以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中,上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。另外,各功能单元、模块的具体名称也只是为了便于相互区分,并不用于限制本申请的保护范围。上述系统中单元、模块的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述或记载的部分,可以参见其它实施例的相关描述。
所述集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请实现上述实施例方法中的全部或部分流程,也可以通过计算机程序来指令相关的硬件来完成,所述的计算机程序可存储于一计算机可读存储介质中,该计算机程序在被服务器执行时,可实现上述各个方法实施例的步骤。
以上所述实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特 征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围,均应包含在本申请的保护范围之内。

Claims (15)

  1. 一种温度测量方法,其特征在于,包括如下步骤:
    S101、获取视场区域内至少一个待测目标的第一温度值;
    S102、获取所述视场区域内所述待测目标的距离值;
    S103、根据步骤S102中获得的所述距离值,通过预先标定的距离与温度误差的函数关系计算所述温度误差,利用所述温度误差修正所述第一温度值,得到第二温度值,所述第二温度值即为所述待测目标的温度。
  2. 如权利要求1所述的温度测量方法,其特征在于,还包括步骤:
    S104、显示所述待测目标经过修正后的所述第二温度值。
  3. 如权利要求1所述的温度测量方法,其特征在于:利用红外探测器采集所述视场区域内的红外辐射信号并进行响应转换为对应的电信号,对电信号进行处理获取所述视场区域的远红外图像;同时,利用深度相机采集所述视场区域的深度图像;对所述远红外图像和所述深度图像进行定位识别获取其中至少一个所述待测目标的所述第一温度值和所述距离值。
  4. 如权利要求3所述的温度测量方法,其特征在于:预先标定所述红外探测器和所述深度相机,使得所述红外探测器获得的所述远红外图像和所述深度相机获得的所述深度图像中的像素单元具有一一对应的位置关系;
    基于所述视场区域中至少一个所述待测目标在所述深度图像中的第一像素,并根据所述一一对应的位置关系,确定该待测目标在所述远红外图像上对应的第二像素。
  5. 如权利要求1所述的温度测量方法,其特征在于,在步骤S103之前还包括有预先标定距离与温度误差关系的步骤;所述标定距离与温度误差关系包括如下步骤:
    S201、获取多个预设距离处标定物体的测量温度值;
    S202、计算所述标定物体的所述测量温度值与设定温度值的温度误差;
    S203、构建多项式拟合函数并根据所述多项式拟合函数对所述温度误差与 距离进行拟合计算所述多项式拟合函数中待定系数的取值。
  6. 如权利要求5所述的温度测量方法,其特征在于:步骤S203中,构建多项式拟合函数y=Ax 3+Bx 2+Cx+D来拟合所述温度误差与距离的关系,其中,y为温度误差值,x为距离值。
  7. 一种温度测量系统,其特征在于:包括红外探测器、深度相机、存储单元以及处理单元;其中,
    所述红外探测器用于接收待测目标的红外辐射信号并获取视场区域的远红外图像;
    所述深度相机用于采集所述待测目标所在所述视场区域的深度图像;
    所述存储单元用于存储预先标定的距离与温度误差的函数关系;
    所述处理单元与所述红外探测器以及所述深度相机连接,以用于获取所述远红外图像中至少一个所述待测目标的第一温度值,以及获取所述深度图像中对应的所述待测目标的距离值,利用所述距离值并根据预先标定的距离与温度误差的函数关系计算温度误差,利用所述温度误差修正所述第一温度值,计算得到第二温度值,所述第二温度值即为所述待测目标的温度。
  8. 如权利要求7所述的温度测量系统,其特征在于:所述处理单元对所述远红外图像和所述深度图像进行定位识别获取其中至少一个所述待测目标的所述第一温度值和所述距离值;
    具体的,确定所述视场区域中至少一个所述待测目标在所述深度图像中的第一像素,基于预先标定的所述远红外图像和所述深度图像中的像素单元具有一一对应的位置关系,确定该待测目标在所述远红外图像上对应的第二像素。
  9. 如权利要求7所述的温度测量系统,其特征在于:还包括有RGB相机,用于采集所述视场区域的彩色图像;通过预先标定所述RGB相机与所述深度相机以及所述红外探测器的对应关系,利用彩色图像中待测目标的像素,根据标定好的对应关系,获取待测目标在深度图像和远红外图像中的像素,从而通过彩色图像进行定位识别。
  10. 一种存储介质,用于存储计算机程序,其特征在于:所述计算机程序被执行时至少执行权利要求1所述的方法。
  11. 一种存储介质,用于存储计算机程序,其特征在于:所述计算机程序被执行时至少执行权利要求2所述的方法。
  12. 一种存储介质,用于存储计算机程序,其特征在于:所述计算机程序被执行时至少执行权利要求3所述的方法。
  13. 一种存储介质,用于存储计算机程序,其特征在于:所述计算机程序被执行时至少执行权利要求4所述的方法。
  14. 一种存储介质,用于存储计算机程序,其特征在于:所述计算机程序被执行时至少执行权利要求5所述的方法。
  15. 一种存储介质,用于存储计算机程序,其特征在于:所述计算机程序被执行时至少执行权利要求6所述的方法。
PCT/CN2020/090924 2020-03-31 2020-05-18 一种温度测量方法及系统 WO2021196360A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010246340.8 2020-03-31
CN202010246340.8A CN111537074A (zh) 2020-03-31 2020-03-31 一种温度测量方法及系统

Publications (1)

Publication Number Publication Date
WO2021196360A1 true WO2021196360A1 (zh) 2021-10-07

Family

ID=71973001

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/090924 WO2021196360A1 (zh) 2020-03-31 2020-05-18 一种温度测量方法及系统

Country Status (2)

Country Link
CN (1) CN111537074A (zh)
WO (1) WO2021196360A1 (zh)

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113884219A (zh) * 2021-12-06 2022-01-04 中国空气动力研究与发展中心低速空气动力研究所 一种表面温度的测量装置和测量方法
CN114034405A (zh) * 2021-11-08 2022-02-11 北京航空航天大学 一种非接触式测温方法及系统
CN114119518A (zh) * 2021-11-16 2022-03-01 国网重庆市电力公司电力科学研究院 一种电流互感器的红外图像中温度异常点检测方法及系统
CN114136461A (zh) * 2021-11-29 2022-03-04 烟台艾睿光电科技有限公司 一种红外测温方法、系统、设备及计算机可读存储介质
CN114136499A (zh) * 2021-12-02 2022-03-04 广东乐心医疗电子股份有限公司 温度标定方法及系统
CN114370944A (zh) * 2022-01-19 2022-04-19 北京理工大学 一种具有标定和修正功能的实时在线温度监测方法及系统
CN114370945A (zh) * 2022-01-13 2022-04-19 深圳市商汤科技有限公司 加热装置及红外测温装置、标定方法及测温方法
CN114427913A (zh) * 2022-01-20 2022-05-03 浙江大华技术股份有限公司 一种测温方法、装置、电子设备及存储介质
CN114689214A (zh) * 2022-04-24 2022-07-01 佛山市川东磁电股份有限公司 一种温度传感器测试设备及温度传感器补偿方法
CN114841586A (zh) * 2022-05-12 2022-08-02 广州海洋地质调查局 一种油气远景区的圈定方法及系统
CN115308167A (zh) * 2022-10-11 2022-11-08 中国航发四川燃气涡轮研究院 航空发动机红外光谱辐射计大气透过率实时测试计算方法
CN115655485A (zh) * 2022-12-21 2023-01-31 浙江华感科技有限公司 一种测温方法、装置、电子设备和存储介质
CN116845433A (zh) * 2023-07-06 2023-10-03 上海思格源智能科技有限公司 储能电池加热控制方法及系统
CN117537930A (zh) * 2023-10-31 2024-02-09 雷玺智能科技(上海)有限公司 一种基于红外热成像的阵列测温方法及管理系统
WO2024051431A1 (zh) * 2022-09-09 2024-03-14 国网山西省电力公司电力科学研究院 电力设备温度测量方法、装置、存储介质及计算机设备
CN117725344A (zh) * 2024-02-07 2024-03-19 杭州柔谷科技有限公司 基于误差的氧分压优化拟合方法、电子设备及存储介质
DE102022128511A1 (de) 2022-10-27 2024-05-02 Baumer Electric Ag Herstellungs-, Kalibrierungs- und Messwertkorrekturverfahren sowie induktiver Distanzsensor

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220061675A1 (en) * 2020-08-28 2022-03-03 Pixart Imaging Inc. Forehead temperature measurement system with high accuracy
CN112102271B (zh) * 2020-09-02 2022-04-12 浙江大学 一种基于普通数字相机的实时在线火焰温度测量方法
CN112270712A (zh) * 2020-09-08 2021-01-26 奥比中光科技集团股份有限公司 一种基于深度相机模组的温漂标定方法及系统
CN115038946A (zh) * 2020-09-15 2022-09-09 华为技术有限公司 一种测温方法和测温装置
CN112254821B (zh) * 2020-10-16 2021-12-14 盈合(深圳)机器人与自动化科技有限公司 通过视觉测距补偿体温检测精度的方法及装置
CN112525352A (zh) * 2020-11-24 2021-03-19 深圳市高巨创新科技开发有限公司 一种基于人脸识别的红外测温补偿方法及终端
CN112595419A (zh) * 2020-12-08 2021-04-02 快优智能技术有限公司 一种红外测温方法
CN112697342A (zh) * 2021-01-19 2021-04-23 潍坊歌尔微电子有限公司 温度检测方法、终端设备及存储介质
CN113110720B (zh) * 2021-03-23 2024-04-19 深圳市洲明科技股份有限公司 显示面板温度调节方法、装置、计算机设备和存储介质
CN113379617B (zh) * 2021-04-29 2022-11-08 中国船舶重工集团公司第七一九研究所 一种流道内流体温度场图像的后处理方法
CN113340433A (zh) * 2021-06-17 2021-09-03 浙江大华技术股份有限公司 温度测量方法、装置、存储介质及电子装置
CN113483896B (zh) * 2021-07-06 2022-07-12 国网浙江宁海县供电有限公司 一种电力设备测温方法、装置、计算机设备及存储介质
CN113701901B (zh) * 2021-08-23 2023-09-12 北京市计量检测科学研究院 减少环境温度对比度的红外测温方法
CN113759355B (zh) * 2021-09-09 2023-04-28 四川虹美智能科技有限公司 基于红外数据的测距方法和装置
CN114136462A (zh) * 2021-11-25 2022-03-04 深圳市商汤科技有限公司 标定方法及装置、电子设备及计算机可读存储介质
CN114414065B (zh) * 2022-01-10 2024-02-23 珠海格力电器股份有限公司 物体温度探测方法、装置、计算机设备和介质
CN115655374B (zh) * 2022-11-07 2024-06-14 中国矿业大学 一种基于温度误差修正函数的电缆故障检测系统与方法

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104155008A (zh) * 2014-07-28 2014-11-19 上海电力学院 一种红外温度监测系统测量误差修正方法
CN104568157A (zh) * 2014-12-25 2015-04-29 北京农业信息技术研究中心 一种提高热红外成像测温精度的装置及方法
CN105716721A (zh) * 2016-02-22 2016-06-29 国网江苏省电力公司电力科学研究院 一种红外温度检测精度校正方法
CN106768380A (zh) * 2016-11-16 2017-05-31 西安建筑科技大学 一种对红外测温设备的测试结果进行修正的方法
CN106767933A (zh) * 2017-02-10 2017-05-31 深圳奥比中光科技有限公司 深度相机误差的测量系统、测量方法、评价方法及补偿方法
CN106855436A (zh) * 2015-12-08 2017-06-16 深圳超多维光电子有限公司 一种终端设备及温度测量的方法
CN108917639A (zh) * 2018-05-15 2018-11-30 深圳奥比中光科技有限公司 深度成像系统及其温度误差校正方法
CN109419495A (zh) * 2017-08-25 2019-03-05 中国科学院半导体研究所 一种基于红外热像仪测量眼睛温度的校准方法
KR20190071310A (ko) * 2017-12-14 2019-06-24 주식회사 허브테크 레이더 측정 거리를 이용한 열영상 체온 보정 시스템 및 방법
CN211602174U (zh) * 2020-03-24 2020-09-29 广州尚衡信息科技有限公司 一种红外热成像系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101497659B1 (ko) * 2008-12-04 2015-03-02 삼성전자주식회사 깊이 영상을 보정하는 방법 및 장치
CN106548489B (zh) * 2016-09-20 2019-05-10 深圳奥比中光科技有限公司 一种深度图像与彩色图像的配准方法、三维图像采集装置
CN107741276A (zh) * 2017-09-05 2018-02-27 中国航空工业集团公司洛阳电光设备研究所 一种提高红外热像仪测温精度的方法
CN107730561B (zh) * 2017-10-17 2021-07-06 奥比中光科技集团股份有限公司 深度相机温度误差校正方法及系统
CN108711167A (zh) * 2018-05-15 2018-10-26 深圳奥比中光科技有限公司 深度成像系统及其温度误差校正方法

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104155008A (zh) * 2014-07-28 2014-11-19 上海电力学院 一种红外温度监测系统测量误差修正方法
CN104568157A (zh) * 2014-12-25 2015-04-29 北京农业信息技术研究中心 一种提高热红外成像测温精度的装置及方法
CN106855436A (zh) * 2015-12-08 2017-06-16 深圳超多维光电子有限公司 一种终端设备及温度测量的方法
CN105716721A (zh) * 2016-02-22 2016-06-29 国网江苏省电力公司电力科学研究院 一种红外温度检测精度校正方法
CN106768380A (zh) * 2016-11-16 2017-05-31 西安建筑科技大学 一种对红外测温设备的测试结果进行修正的方法
CN106767933A (zh) * 2017-02-10 2017-05-31 深圳奥比中光科技有限公司 深度相机误差的测量系统、测量方法、评价方法及补偿方法
CN109419495A (zh) * 2017-08-25 2019-03-05 中国科学院半导体研究所 一种基于红外热像仪测量眼睛温度的校准方法
KR20190071310A (ko) * 2017-12-14 2019-06-24 주식회사 허브테크 레이더 측정 거리를 이용한 열영상 체온 보정 시스템 및 방법
CN108917639A (zh) * 2018-05-15 2018-11-30 深圳奥比中光科技有限公司 深度成像系统及其温度误差校正方法
CN211602174U (zh) * 2020-03-24 2020-09-29 广州尚衡信息科技有限公司 一种红外热成像系统

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114034405A (zh) * 2021-11-08 2022-02-11 北京航空航天大学 一种非接触式测温方法及系统
CN114119518A (zh) * 2021-11-16 2022-03-01 国网重庆市电力公司电力科学研究院 一种电流互感器的红外图像中温度异常点检测方法及系统
CN114136461B (zh) * 2021-11-29 2023-07-14 烟台艾睿光电科技有限公司 一种红外测温方法、系统、设备及计算机可读存储介质
CN114136461A (zh) * 2021-11-29 2022-03-04 烟台艾睿光电科技有限公司 一种红外测温方法、系统、设备及计算机可读存储介质
CN114136499A (zh) * 2021-12-02 2022-03-04 广东乐心医疗电子股份有限公司 温度标定方法及系统
CN114136499B (zh) * 2021-12-02 2023-07-18 广东乐心医疗电子股份有限公司 温度标定方法及系统
CN113884219A (zh) * 2021-12-06 2022-01-04 中国空气动力研究与发展中心低速空气动力研究所 一种表面温度的测量装置和测量方法
CN114370945A (zh) * 2022-01-13 2022-04-19 深圳市商汤科技有限公司 加热装置及红外测温装置、标定方法及测温方法
CN114370945B (zh) * 2022-01-13 2023-12-15 深圳市商汤科技有限公司 加热装置及红外测温装置、标定方法及测温方法
CN114370944A (zh) * 2022-01-19 2022-04-19 北京理工大学 一种具有标定和修正功能的实时在线温度监测方法及系统
CN114370944B (zh) * 2022-01-19 2023-07-25 北京理工大学 一种具有标定和修正功能的实时在线温度监测方法及系统
CN114427913A (zh) * 2022-01-20 2022-05-03 浙江大华技术股份有限公司 一种测温方法、装置、电子设备及存储介质
CN114427913B (zh) * 2022-01-20 2024-03-22 浙江华感科技有限公司 一种测温方法、装置、电子设备及存储介质
CN114689214A (zh) * 2022-04-24 2022-07-01 佛山市川东磁电股份有限公司 一种温度传感器测试设备及温度传感器补偿方法
CN114841586A (zh) * 2022-05-12 2022-08-02 广州海洋地质调查局 一种油气远景区的圈定方法及系统
WO2024051431A1 (zh) * 2022-09-09 2024-03-14 国网山西省电力公司电力科学研究院 电力设备温度测量方法、装置、存储介质及计算机设备
CN115308167A (zh) * 2022-10-11 2022-11-08 中国航发四川燃气涡轮研究院 航空发动机红外光谱辐射计大气透过率实时测试计算方法
CN115308167B (zh) * 2022-10-11 2023-02-21 中国航发四川燃气涡轮研究院 航空发动机红外光谱辐射计大气透过率实时测试计算方法
DE102022128511A1 (de) 2022-10-27 2024-05-02 Baumer Electric Ag Herstellungs-, Kalibrierungs- und Messwertkorrekturverfahren sowie induktiver Distanzsensor
DE102022128511B4 (de) 2022-10-27 2024-08-08 Baumer Electric Ag Herstellungs-, Kalibrierungs- und Messwertkorrekturverfahren sowie induktiver Distanzsensor
CN115655485A (zh) * 2022-12-21 2023-01-31 浙江华感科技有限公司 一种测温方法、装置、电子设备和存储介质
CN115655485B (zh) * 2022-12-21 2023-04-07 浙江华感科技有限公司 一种测温方法、装置、电子设备和存储介质
CN116845433A (zh) * 2023-07-06 2023-10-03 上海思格源智能科技有限公司 储能电池加热控制方法及系统
CN116845433B (zh) * 2023-07-06 2024-05-07 上海思格源智能科技有限公司 储能电池加热控制方法及系统
CN117537930A (zh) * 2023-10-31 2024-02-09 雷玺智能科技(上海)有限公司 一种基于红外热成像的阵列测温方法及管理系统
CN117537930B (zh) * 2023-10-31 2024-05-07 雷玺智能科技(上海)有限公司 一种基于红外热成像的阵列测温方法及管理系统
CN117725344A (zh) * 2024-02-07 2024-03-19 杭州柔谷科技有限公司 基于误差的氧分压优化拟合方法、电子设备及存储介质
CN117725344B (zh) * 2024-02-07 2024-05-28 杭州柔谷科技有限公司 基于误差的氧分压优化拟合方法、电子设备及存储介质

Also Published As

Publication number Publication date
CN111537074A (zh) 2020-08-14

Similar Documents

Publication Publication Date Title
WO2021196360A1 (zh) 一种温度测量方法及系统
US9681066B2 (en) Facilitating improved calibration of captured infrared data values by an IR imaging system in a thermography arrangement
WO2021184254A1 (zh) 红外热成像测温方法、电子设备、无人机及存储介质
CN111458039B (zh) 基于红外测温摄像头的增强现实的体温测量方法和装置
Somboonkaew et al. Mobile-platform for automatic fever screening system based on infrared forehead temperature
CN109419495A (zh) 一种基于红外热像仪测量眼睛温度的校准方法
US20080071189A1 (en) Temperature Measurement Device
CN112033545B (zh) 人体温度红外测量方法、装置及计算机设备
CN107588854B (zh) 基于内置参考体的高精度测温方法
CN103528694A (zh) 一种用红外热像仪测量目标物体的温度的方法
CN105352988A (zh) 一种建筑物外墙保温性能评估系统及方法
CN113358231B (zh) 红外测温方法、装置及设备
US20220132052A1 (en) Imaging method and device
CN111920391B (zh) 一种测温方法及设备
WO2021259365A1 (zh) 一种目标测温方法、装置及测温系统
CN112964372B (zh) 一种新型红外测温装置及测温方法
CN107238440B (zh) 红外热成像检测系统的温度校正方法
CN111854964A (zh) 一种测量体温的方法、装置、测温工具及存储介质
CN111964790A (zh) 一种温度校准方法及红外测温装置
US11818334B2 (en) Thermal image-based temperature measurement calibration method and thermal image device
CN111964786A (zh) 温度检测方法及装置
CN111637974A (zh) 一种非接触式测温装置和测温方法
CN115797998A (zh) 一种基于图像融合的双波段智能测温装置和智能测温方法
CN111968163B (zh) 一种热电堆阵列测温方法及装置
KR102220654B1 (ko) 측정온도 보정시스템

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20928070

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20928070

Country of ref document: EP

Kind code of ref document: A1