WO2021174841A1 - 测温方法、测温装置、电子设备及计算机可读存储介质 - Google Patents

测温方法、测温装置、电子设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2021174841A1
WO2021174841A1 PCT/CN2020/119459 CN2020119459W WO2021174841A1 WO 2021174841 A1 WO2021174841 A1 WO 2021174841A1 CN 2020119459 W CN2020119459 W CN 2020119459W WO 2021174841 A1 WO2021174841 A1 WO 2021174841A1
Authority
WO
WIPO (PCT)
Prior art keywords
black body
temperature
infrared image
position information
image
Prior art date
Application number
PCT/CN2020/119459
Other languages
English (en)
French (fr)
Inventor
张耀威
胡晨
周舒畅
Original Assignee
北京迈格威科技有限公司
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 北京迈格威科技有限公司 filed Critical 北京迈格威科技有限公司
Priority to US17/759,835 priority Critical patent/US20230075679A1/en
Publication of WO2021174841A1 publication Critical patent/WO2021174841A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/52—Radiation pyrometry, e.g. infrared or optical thermometry using comparison with reference sources, e.g. disappearing-filament pyrometer
    • G01J5/53—Reference sources, e.g. standard lamps; Black bodies
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/02—Constructional details
    • G01J5/08—Optical arrangements
    • G01J5/0859—Sighting arrangements, e.g. cameras
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
    • G01J5/0025—Living bodies
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/02—Constructional details
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/48—Thermography; Techniques using wholly visual means
    • G01J5/485—Temperature profile
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/52—Radiation pyrometry, e.g. infrared or optical thermometry using comparison with reference sources, e.g. disappearing-filament pyrometer
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/80—Calibration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J2005/0077—Imaging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person

Definitions

  • the present disclosure relates to the field of artificial intelligence, and in particular to a temperature measurement method, a temperature measurement device, electronic equipment, and a computer-readable storage medium.
  • infrared thermal imaging equipment improves the efficiency of temperature detection and the safety of temperature measurement, it still causes temperature deviations due to the equipment itself and the surrounding environment, resulting in low accuracy of temperature measurement results.
  • the purpose of the present disclosure is to provide a temperature measurement method, temperature measurement device, electronic equipment, and computer-readable storage medium to alleviate the problem of inaccurate temperature measurement caused by external environment or equipment factors, and effectively improve the temperature measurement accuracy.
  • the embodiments of the present disclosure provide a temperature measurement method, including: obtaining a pair of image frames containing a target object through a visible light camera and a thermal imaging camera, wherein the pair of image frames includes visible light images collected at the same time And infrared images, and a black body is also arranged in the image acquisition area of the thermal imaging camera; the measured temperature of the target object is determined based on the image frame; the black body detection is performed on the infrared image to obtain the black body detection Result, wherein the detection result of the black body includes the position information of the black body in the infrared image; based on the detection result of the black body and the infrared image, the measured temperature of the black body is determined; The measured temperature and the preset temperature of the black body are corrected, and the measured temperature of the target object is corrected, and the corrected temperature is used as the temperature measurement result of the target object.
  • the step of determining the measured temperature of the target object based on the image frame pair includes: performing target object detection on the visible light image in the image frame pair to obtain the target object in the visible light image Position information in the infrared image; based on the spatial position relationship between the visible light camera and the thermal imaging camera, and the position information of the target object in the visible light image, determine the position information of the target object in the infrared image; Determine the measured temperature of the target object according to the position information of the target object in the infrared image.
  • the detection result of the black body further includes a state in which the black body is located, and the state includes a occluded state and a non-occluded state.
  • the step of performing black body detection on the infrared image through a preset neural network model to obtain a detection result of the black body includes: performing black body detection on the infrared image through a preset neural network model to obtain the black body The position information in the infrared image and the confidence of the position information; the state of the black body is determined according to the position information of the black body in the infrared image and the confidence of the position information.
  • the step of determining the state of the black body according to the position information of the black body in the infrared image and the confidence of the position information includes: if the black body is in the infrared image If the position information of the black body is empty, it is determined that the probability of being occluded by the black body is 100%, so it can be determined that the state of the black body is the occlusion state; if the position information of the black body in the infrared image is non-empty, based on The confidence level of the position information determines the occlusion probability of the black body, and then determines the state of the black body according to the occlusion probability of the black body.
  • the step of determining the occlusion probability of the black body based on the confidence level of the position information includes: determining according to the correspondence between the confidence level of the position information and the occlusion probability of the black body set in advance The occlusion probability of the black body corresponding to the confidence level of the position information, in the correspondence relationship, the confidence level of the position information is negatively related to the occlusion probability of the black body.
  • the step of determining the state of the black body according to the occlusion probability of the black body includes: if the occlusion probability of the black body is greater than a preset threshold, determining that the state of the black body is occlusion State; if the probability of being blocked by the black body is less than the preset threshold, it is determined that the state of the black body is a non-blocking state.
  • the step of determining the measured temperature of the black body based on the detection result of the black body and the infrared image includes: if the state of the black body is in a blocking state, acquiring the infrared image collection time The historical measurement temperature of the black body in the previous adjacent designated time period, and based on the historical measurement temperature of the black body, the measured temperature corresponding to the black body at the time of the infrared image acquisition is determined; if the state of the black body is not In the occlusion state, the area where the black body is located in the infrared image is determined based on the position information of the black body in the infrared image, and the temperature of the area represented by the infrared image is determined as the location of the black body. The measured temperature corresponding to the moment of infrared image acquisition.
  • the step of correcting the measured temperature of the target object according to the measured temperature of the black body and the preset temperature of the black body includes: comparing the measured temperature of the black body with the preset temperature of the black body. The difference between the temperatures is set as a temperature correction value; the measured temperature of the target object is corrected based on the temperature correction value.
  • An embodiment of the present disclosure also provides a temperature measurement device, including: an image acquisition module configured to acquire a pair of image frames containing a target object through a visible light camera and a thermal imaging camera, wherein the pair of image frames includes visible light collected at the same time Image and infrared image, and a black body is also arranged in the image acquisition area of the thermal imaging camera; an object temperature determination module configured to determine the measured temperature of the target object based on the pair of image frames; a black body detection module configured as a pair Perform black body detection on the infrared image to obtain a detection result of the black body, wherein the detection result of the black body includes the position information of the black body in the infrared image and the confidence level of the position information; a black body temperature determination module , Configured to determine the measured temperature of the black body based on the detection result of the black body and the infrared image; a temperature correction module, configured to determine the target temperature according to the measured temperature of the black body and the preset temperature of the black body The measured temperature of the
  • the embodiment of the present disclosure also provides an electronic device, including a processor, a storage device, an input device, an output device, an image acquisition device, and a bus system.
  • a computer program is stored on the storage device, and the computer program, when run by the processor, executes the method according to any one of the foregoing embodiments, and the input device is configured as a device for a user to input instructions
  • the output device is configured to output information to the outside
  • the image capture device is configured to capture an image desired by the user and store the captured image in the storage device for use by other components
  • the bus system is configured to Interconnect the other components mentioned above.
  • the embodiment of the present disclosure also provides a computer-readable storage medium, the computer-readable storage medium stores computer program instructions, an application program, and data used and/or generated by the application program.
  • the computer program instructions are executed by the processor, the steps of the method described in any one of the foregoing embodiments are executed, and the data used and/or generated in this process is stored.
  • the embodiments of the present disclosure provide a temperature measurement method, a temperature measurement device, an electronic device, and a computer-readable storage medium.
  • a pair of image frames containing a target object is acquired through a visible light camera and a thermal imaging camera.
  • a black body is also set in the image acquisition area of the thermal imaging camera, and then based on the image frame, the measured temperature of the target object is determined, and the black body detection is performed on the infrared image to obtain the black body detection result (including the black body in the infrared image
  • the measured temperature of the black body is determined, so as to correct the measured temperature of the target object according to the measured temperature of the black body and the preset temperature of the black body.
  • the corrected temperature is used as the temperature measurement result of the target object.
  • the above method uses the characteristics of the black body itself to correct the measured temperature of the target object, calibrate the temperature measurement error caused by the external environment and the temperature measurement device itself, thereby improving the accuracy of the temperature measurement.
  • FIG. 1 shows a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure
  • FIG. 2 shows a schematic flowchart of a temperature measurement method provided by an embodiment of the present disclosure
  • FIG. 3 shows a schematic flowchart of another temperature measurement method provided by an embodiment of the present disclosure
  • Fig. 4 shows a schematic structural diagram of a temperature measuring device provided by an embodiment of the present disclosure.
  • embodiments of the present disclosure provide a temperature measurement method, temperature measurement device, electronic equipment, and computer readable Storage medium, this technology can be applied to equipment that needs to perform temperature measurement, such as temperature measurement equipment.
  • this technology can be applied to equipment that needs to perform temperature measurement, such as temperature measurement equipment.
  • FIG. 1 a schematic structural diagram of an electronic device.
  • the electronic device 100 includes one or more processors 102, one or more storage devices 104, an input device 106, an output device 108, an image acquisition device 110, and
  • the bus system 112 and/or other forms of connection mechanisms are used to interconnect the above-mentioned other components through the bus system 112 and/or other forms of connection mechanisms (not shown).
  • the components and structure of the electronic device 100 shown in FIG. 1 are only exemplary and not restrictive, and the electronic device may also have other components and structures as required.
  • the processor 102 may be configured to be implemented in at least one hardware form of a digital signal processor (DSP), a field programmable gate array (FPGA), and a programmable logic array (PLA).
  • DSP digital signal processor
  • FPGA field programmable gate array
  • PDA programmable logic array
  • the processor 102 also It can be configured as a central processing unit (CPU), graphics processing unit (GPU), or other forms of processing units with data processing capabilities and/or instruction execution capabilities, or a combination of several, and can be configured to control
  • CPU central processing unit
  • GPU graphics processing unit
  • the other components in the electronic device 100 can perform desired functions.
  • the storage device 104 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and/or nonvolatile memory.
  • the volatile memory may include random access memory (RAM) and/or cache memory (cache), for example.
  • the non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, and the like.
  • One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 102 may run the program instructions to implement the client in the embodiments of the present disclosure (implemented by the processor) described below. Function and/or other desired functions.
  • Various application programs and various data such as various data used and/or generated by the application program, can also be stored in the computer-readable storage medium.
  • the input device 106 may be configured as a device used by the user to input instructions, and may include one or more of a keyboard, a mouse, a microphone, and a touch screen.
  • the output device 108 may be configured to output various information (for example, images or sounds) to the outside (for example, a user), and may include one or more of a display, a speaker, and the like.
  • the image capture device 110 may be configured to capture images (such as photos, videos, etc.) desired by the user, and store the captured images in the storage device 104 for use by other components.
  • Exemplarily, example electronic devices for implementing the temperature measurement method, temperature measurement device, electronic device, and computer-readable storage medium according to the embodiments of the present disclosure may include smart terminals such as temperature measurement cameras, smart phones, and wearable electronic devices. Wait. Referring to the schematic flow chart of a temperature measurement method shown in FIG. 2, the method mainly includes the following steps S202 to S210.
  • a pair of image frames containing the target object may be acquired through a visible light camera and a thermal imaging camera, where the image frame pair may include a visible light image and an infrared image acquired at the same time, and the image acquisition area of the thermal imaging camera is also Can be set with bold.
  • Visible light is the part of the electromagnetic spectrum that the human eye can perceive. Generally, the wavelength of visible light is between 400 and 760 nm.
  • the visible light image obtained by the visible light camera is also the image that the human eye can see.
  • the visible light image obtained by the visible light camera can directly reflect The current state presented by the image acquisition area of the visible light camera, such as showing the position of the target object located in the image acquisition area.
  • the target object may include, but is not limited to, the human body and other natural organisms that can be used as infrared radiation sources. Take the human body as an example. Since the human body is a natural biological infrared radiation source, it can continuously emit and absorb infrared radiation to the surroundings. The temperature distribution of the normal human body has certain stability and characteristics.
  • Called an infrared camera can obtain infrared images that reflect the temperature of the human body.
  • a visible light image can be collected by a visible light camera
  • an infrared image can be collected by a thermal imaging camera
  • the visible light image and the infrared image collected by the visible light camera and the thermal imaging camera at the same time can be used as a set of image frame pairs.
  • the visible light camera and the thermal imaging camera can be time-synchronized in advance.
  • a black body is an idealized object in thermal radiation. It has the ability to completely absorb any wavelength of external radiation without any reflection, with an absorption ratio of 1, and at any temperature, to absorb all incident radiation of any wavelength. This feature, so you can regard the black body as a kind of thermostat.
  • the embodiment of the present disclosure can set a black body in the image acquisition area of the thermal imaging camera, and then collect the black body temperature measured by the temperature measuring device in real time, and the difference between the measured temperature of the black body and the temperature set by the black body itself is Temperature deviation caused by the environment or the equipment itself.
  • the measured temperature obtained by the sensor when extracting infrared data may be lower than the real temperature, or when the device is running for a long time, the temperature of the device may rise, making the measured temperature higher than the real temperature , This will cause the measurement temperature of the device to be inaccurate, and the black body is set in the image acquisition area of the thermal imaging camera, and the constant temperature characteristics of the black body can be used to determine whether the measured temperature of the device has a temperature deviation.
  • step S204 the measured temperature of the target object is determined based on the image frame pair.
  • the image collection range has a certain deviation, so the images collected for the same area are also different, that is, the position of the same target object in the visible light image and the infrared image is also different. But there will be a certain correspondence.
  • the corresponding relationship between the visible light image and the infrared image can be determined according to the spatial position relationship between the visible light camera and the infrared camera, for example, to identify the target person A is located in the first location area in the visible light image, and then based on the corresponding relationship between the visible light image and the infrared image, the first location area is converted into the second location area in the infrared image, and the second location area is the target person The position of A in the infrared image, so that the temperature of the second location area displayed in the infrared image is taken as the measured temperature of the target person A.
  • step S206 black body detection is performed on the infrared image to obtain a black body detection result.
  • the detection result of the black body includes position information of the black body in the infrared image.
  • the position of the black body can be manually checked and calibrated, so as to realize the black body detection of the infrared image.
  • the embodiments of the present disclosure can optionally perform black body detection on infrared images through a preset neural network model.
  • the neural network model can be implemented based on a target detection algorithm. Specifically, such as SSD (SingleShotMultiBoxDetector), YOLO (YouOnlyLookOnce: Unified, Real-TimeObjectDetection) and Convolutional Neural Networks (CNN) and other neural network models are implemented.
  • the position information of the black body in the infrared image can be obtained through the obtained results, and the position information may include the position coordinates of the black body in the infrared image.
  • the position information of the black body is empty (such as no position coordinate output), it is considered that the black body is not detected in the infrared image.
  • the embodiment of the present disclosure automatically detects the black body through the neural network model, which effectively improves the efficiency and reliability of black body calibration, and reduces the limitation of the black body position, without requiring the black body position to remain unchanged, and the black body position can be flexibly adjusted according to requirements , Only the black body is located in the image collection area of the thermal imaging camera. Even if the positional relationship between the black body and the thermal imaging camera changes, a more accurate black body detection result can be obtained through the neural network model to avoid the change in the position of the black body. The temperature detection is not accurate.
  • step S208 based on the detection result of the black body and the infrared image, the measured temperature of the black body is determined.
  • the area where the black body is located in the infrared image is determined, and the temperature of this area presented in the infrared image is taken as the measured temperature of the black body.
  • step S210 the measured temperature of the target object is corrected according to the measured temperature of the black body and the preset temperature of the black body, and the corrected temperature is used as the temperature measurement result of the target object.
  • the preset temperature of the black body can be set between 30 degrees and 40 degrees. Specifically, it can be empirically set according to the environment where the black body is located. For example, when outdoors, the preset temperature of the black body can be set as 34 degrees. Since the black body has a constant temperature characteristic, when the measured temperature of the black body is different from the preset temperature of the black body, it indicates that there is a deviation in the measured temperature of the temperature measuring device.
  • the target person is set
  • the corrected value of the measured temperature of A is 0.4 degrees. Assuming that the measured temperature of the target person A through the thermal imaging camera is 37.6 degrees, the corrected temperature is 37.2 degrees.
  • the corrected temperature of 37.2 degrees is used as the temperature measurement result of the target person A, so as to avoid falsely reporting the target person A as a high-risk person.
  • the above-mentioned use of the constant temperature characteristic of the black body to correct the measured temperature of the target object can reduce the temperature measurement error caused by the equipment or environmental factors, and improve the accuracy of the temperature measurement.
  • the above-mentioned temperature measurement method uses the characteristics of the black body itself to correct the measurement temperature of the target object, calibrate the temperature measurement error caused by the external environment and the temperature measurement device itself, thereby improving the accuracy of temperature measurement.
  • the above method can realize black body automatic detection based on the neural network model, without manually calibrating the black body position, avoiding the tedious and human error of manual calibration, making the measured temperature of the black body more real and reliable, thereby further improving the reliability of temperature correction and making the correction
  • the subsequent temperature measurement results are more accurate.
  • the embodiments of the present disclosure provide a specific implementation for determining the measured temperature of the target object based on the image frame, that is, the foregoing step S204 can be performed with reference to the following steps (1) to (3).
  • step (1) target object detection is performed on the visible light image in the image frame pair, and the position information of the target object in the visible light image can be obtained.
  • the target detection algorithm can be used to detect the target object on the visible light image.
  • the target detection algorithm can select single target detection or multi-target detection according to the actual situation, which is not limited here. Taking multi-target detection as an example, multiple target objects can be detected and identified in the visible light image, and the position information of each target object can be determined on the visible light image.
  • step (2) based on the spatial position relationship between the visible light camera and the thermal imaging camera, and the position information of the target object in the visible light image, the position information of the target object in the infrared image can be determined. For example, given the first position coordinates of the target person A in the visible light image, according to the spatial position relationship between the visible light camera and the thermal imaging camera, the first position coordinates are projected and converted to the second position coordinates in the infrared image, thereby obtaining the target person A's position information in the infrared image.
  • the measured temperature of the target object can be determined according to the position information of the target object in the infrared image. That is, the temperature corresponding to the area where the target object is located in the infrared image is determined as the measured temperature of the target object.
  • the detection result of the black body obtained through the preset neural network model detection also includes the state of the black body, and the state includes the occluded state and the non-occluded state. Based on this, the above step S206 may optionally include the following step 1. And step 2.
  • step 1 black body detection is performed on the infrared image through a preset neural network model, and the position information of the black body in the infrared image and the confidence of the position information are obtained.
  • the input of the preset neural network model is an entire infrared image
  • the output is the position information of the detected black body (such as the position coordinates of the black body) and the confidence of the black body position information.
  • the position information of the detected black body is in the lower left corner of the infrared image, and the confidence level is 90%, it means that the probability that the black body may be in the lower left corner of the infrared image is 90%.
  • black body detection is performed on infrared images through a preset neural network model, and the shape or size of the black body can also be obtained.
  • the shape of the black body can include a circle or a square, etc. In practical applications, it can be based on the detected black body
  • the proportion of the size in the infrared image determines whether the distance between the black body and the thermal imaging camera is reasonable. If the black body is too close to the thermal imaging camera and the proportion of the black body in the entire infrared image is too large, the target object cannot be detected normally; if the black body is too far away from the thermal imaging camera and the proportion of the black body in the infrared image is too small, It will be more difficult to accurately determine the measured temperature of the black body.
  • step 2 the state of the black body is determined according to the position information of the black body in the infrared image and the confidence of the position information.
  • the state of the black body includes the occluded state and the non-occluded state.
  • the embodiment of the present disclosure optionally provides a specific implementation of step 2, which can be implemented with reference to the following steps 2.1 to 2.3.
  • step 2.1 if the position information of the black body in the infrared image is empty, it is determined that the probability of the black body being occluded is 100%.
  • the black body in the infrared image is empty, that is, the black body is not detected in the infrared image, but the black body is located in the image collection range of the thermal imaging camera. If the black body is not detected, it is determined that the black body is The occlusion probability is 100%, that is, the state of the black body is the occlusion state.
  • step 2.2 if the position information of the black body in the infrared image is not empty, the occlusion probability of the black body is determined based on the confidence of the position information.
  • the corresponding relationship between the confidence of the preset position information and the probability of being occluded by the black body can be determined to determine the position corresponding to the confidence of the position information.
  • the occlusion probability of a black body In the correspondence relationship between the confidence of the position information and the occlusion probability of the black body, the confidence of the position information is negatively related to the occlusion probability of the black body, that is, the lower the confidence of the position information, the occlusion probability Higher. For example, when the confidence level of the position information is 15%, the probability that the black body is occluded is set to 85% in the correspondence relationship. It should be noted that the above examples are only illustrative and should not be regarded as limiting.
  • step 2.3 the state of the black body is determined according to the probability of the black body being occluded.
  • the state of the black body is determined to be the occlusion state; if the occlusion probability of the black body is less than the preset threshold, the state of the black body is determined to be the non-occlusion state.
  • the preset threshold can be set according to empirical values.
  • the measured temperature of the black body can be determined by combining the infrared image, which can be implemented with reference to the following steps (1) and (2).
  • step (1) if the state of the black body is in the occluded state, the historical measurement temperature of the black body in the vicinity of the specified time before the infrared image collection time can be obtained, and based on the historical measurement temperature of the black body, it is determined that the black body is in the infrared image collection time The corresponding measurement temperature.
  • the adjacent designated time can be flexibly set.
  • the measured temperature can be the average detection temperature of the unobstructed black body of multiple frames contained within the specified time period before the acquisition time of the current infrared image, or it can be the black body of all frames contained within the specified time period before the current infrared image collection time. Because the measured temperature of the black body in the blocked state before the collection time has been corrected by the historical frame temperature, the average of the measured temperatures of all frames in a period of time before the collection time can also be used as the measured temperature at the collection time.
  • step (2) if the black body is in a non-occluded state, the area of the black body in the infrared image is determined based on the position information of the black body in the infrared image, and the temperature of the area represented by the infrared image is determined as the black body The corresponding measured temperature at the moment of infrared image acquisition.
  • the difference between the measured temperature of the black body and the preset temperature of the black body can be used as the temperature correction value, and the measured temperature of the target object can be corrected based on the temperature correction value, thereby avoiding The problem of inaccurate temperature measurement of the target object caused by environmental or equipment factors improves the accuracy of temperature measurement.
  • the embodiments of the present disclosure provide a specific example of applying the foregoing temperature measurement method.
  • the method mainly includes the following Step S302 to Step S314.
  • a visible light image can be collected by a visible light camera, and an infrared image can be collected by an infrared camera (ie, the aforementioned thermal imaging camera). Based on the visible light image and the infrared image, the location information and the measured temperature of the person to be detected can be determined.
  • step S304 the infrared image is input to a black body detection model, and the black body detection model can determine the position information of the black body and determine whether the black body is blocked. If yes, go to step S306; if not, go to step S308.
  • the black body is set in the collection area of the infrared camera, and the black body detection model can detect the position of the black body in the infrared image and the confidence that the black body is located at that position, so as to obtain the probability of the black body being occluded based on the confidence of the position, and then According to the probability that the black body is occluded, it is judged whether the black body is occluded.
  • the measured temperature of the black body can be determined based on historical infrared image frames.
  • the historical infrared image frame may be one or more frames of unobstructed infrared images before the current infrared image collection time, or it may be all the infrared images collected in a period of time before the current collection time.
  • the average value of the black body detection temperature of the historical infrared image frame may be used as the measured temperature of the black body that is currently blocked.
  • the measured temperature of the black body can be determined based on the current infrared image.
  • the black body detection model detects the temperature of the area where the black body is located in the current infrared image, which is the current measured temperature of the black body.
  • the temperature correction value may be determined based on the preset temperature of the black body and the measured temperature of the black body. Specifically, the temperature correction value is a value obtained by the difference between the preset temperature of the black body and the detected temperature of the black body.
  • step S312 the measured temperature of the person to be inspected can be corrected according to the temperature correction value to obtain the corrected temperature result.
  • the temperature measurement method provided by the embodiments of the present disclosure uses the constant temperature characteristics of the black body itself to correct the measured temperature of the target object, and calibrate the temperature measurement error caused by the external environment and the temperature measurement device itself, on the other hand, it is based on a neural network
  • the model realizes the automatic detection of black body without manual calibration of the black body position, avoids the tedious and human error of manual calibration, and makes the measured temperature of the black body more real and reliable.
  • the above method judges whether the black body is occluded.
  • the black body has a different state, and the black body temperature measurement method is determined differently, which further improves the accuracy of the black body temperature measurement result and comprehensively improves the temperature correction. Reliability makes the final corrected temperature more true and accurate.
  • the embodiment of the present disclosure provides a temperature measurement device.
  • the device includes the following modules:
  • the image acquisition module 402 may be configured to acquire a pair of image frames containing the target object through a visible light camera and a thermal imaging camera, where the image frame pair may include a visible light image and an infrared image collected at the same time, and the image acquisition area of the thermal imaging camera There is also a black body inside;
  • the object temperature determination module 404 may be configured to determine the measured temperature of the target object based on the image frame pair;
  • the black body detection module 406 may be configured to perform black body detection on the infrared image to obtain a detection result of the black body, where the detection result includes position information of the black body in the infrared image;
  • the black body temperature determination module 408 may be configured to determine the measured temperature of the black body based on the detection result of the black body and the infrared image;
  • the temperature correction module 410 may be configured to correct the measured temperature of the target object according to the measured temperature of the black body and the preset temperature of the black body, and use the corrected temperature as the temperature measurement result of the target object.
  • the above-mentioned temperature measuring device uses the characteristics of the black body itself to correct the measured temperature of the target object, and calibrate the temperature measurement error caused by the external environment and the temperature measuring device itself, thereby improving the accuracy of temperature measurement.
  • the above-mentioned object temperature determination module 404 may be configured as follows: perform target object detection on the visible light image in the image frame pair to obtain position information of the target object in the visible light image; based on the spatial position relationship between the visible light camera and the thermal imaging camera , And the position information of the target object in the visible light image, determine the position information of the target object in the infrared image; determine the measured temperature of the target object according to the position information of the target object in the infrared image.
  • the detection result also includes the state of the black body, and the state includes a occluded state and a non-occluded state.
  • the black body detection module 406 may include: a position detection unit configured to perform black body detection on the infrared image through a preset neural network model to obtain the position information of the black body in the infrared image and the confidence of the position information; a state determination unit, configured According to the position information of the black body in the infrared image and the confidence of the position information, the state of the black body is determined.
  • the above-mentioned state determination unit may be configured as follows: if the position information of the black body in the infrared image is empty, determine that the probability of being blocked by the black body is 100%; if the position information of the black body in the infrared image is not empty, based on The confidence of the position information determines the probability of black body being occluded; the state of the black body is determined according to the probability of black body being occluded.
  • the aforementioned state determining unit may be configured to determine the occlusion probability of a black body corresponding to the confidence level of the position information according to a preset correspondence between the confidence level of the position information and the occlusion probability of the black body, wherein: In the corresponding relationship, the confidence of the position information is negatively related to the probability of being occluded by the black body.
  • the above-mentioned state determination unit may be configured as follows: if the occlusion probability of the black body is greater than a preset threshold, it is determined that the state of the black body is in the occlusion state; if the occlusion probability of the black body is less than the preset threshold, it is determined that the black body is located The state is non-occluded.
  • the black body temperature determination module 408 may be configured as follows: if the black body is in a blocked state, obtain the historical measured temperature of the black body in the vicinity of the specified time before the infrared image collection time, and determine the black body based on the historical measured temperature of the black body The corresponding measured temperature at the moment of infrared image acquisition; if the state of the black body is in an unobstructed state, determine the area of the black body in the infrared image based on the position information of the black body in the infrared image, and the temperature of the area represented by the infrared image Determine the measured temperature corresponding to the black body at the moment of infrared image acquisition.
  • the temperature correction module 410 may be configured to use the difference between the measured temperature of the black body and the preset temperature of the black body as the temperature correction value, and correct the measured temperature of the target object based on the temperature correction value.
  • the embodiment of the present disclosure also provides a computer-readable storage medium for use in the above-mentioned temperature measurement method, temperature measurement device, and electronic equipment provided by the embodiment of the present disclosure.
  • the computer-readable storage medium may be configured to store computer program instructions, application programs, and data used and/or generated by the application programs.
  • the steps of the method described in any one of the foregoing embodiments are executed, and the data used and/or generated in this process is stored.
  • the computer program instructions can be configured to execute the methods described in the foregoing method embodiments, and for specific implementation, please refer to the method embodiments, which will not be repeated here.
  • the functions of the embodiments of the present disclosure are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer readable storage medium.
  • the technical solution of the present disclosure can be embodied in the form of a software product in essence or a part that contributes to the existing technology or a part of the technical solution, and the computer software product can be stored in a storage medium, It includes several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present disclosure.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes.
  • the temperature measurement method, temperature measurement device, electronic equipment, and computer-readable storage medium use the characteristics of the black body to correct the measurement temperature of the target object, and calibrate the temperature measurement equipment due to the external environment and the temperature measurement device.
  • the temperature measurement error caused by itself improves the accuracy of temperature measurement.
  • the embodiments of the present disclosure can realize black body automatic detection based on the neural network model, without manually calibrating the black body position, avoiding the tedious and human error of manual calibration, making the measured temperature of the black body more realistic and reliable, thereby further improving the reliability of temperature correction , Which makes the corrected temperature measurement result more accurate.
  • the terms “installed”, “connected”, and “connected” should be interpreted broadly, for example, they may be fixed connections or detachable connections. , Or integrally connected; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication between two components.
  • installed should be interpreted broadly, for example, they may be fixed connections or detachable connections. , Or integrally connected; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication between two components.
  • the present disclosure provides a temperature measurement method, a temperature measurement device, an electronic device, and a computer-readable storage medium, which alleviate the problem of inaccurate temperature measurement caused by external environment or equipment factors.
  • the black body automatic detection based on the neural network model does not require manual calibration of the black body position, avoids the tedious and human error of manual calibration, makes the measured temperature of the black body more realistic and reliable, and calibrates the temperature measurement error caused by the external environment and the temperature measurement equipment itself. , Further improve the reliability of temperature correction, thereby effectively improving the accuracy of temperature measurement.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Radiation Pyrometers (AREA)

Abstract

一种测温方法、测温装置、电子设备及计算机可读存储介质，方法包括：通过可见光相机和热成像相机获取包含有目标对象的图像帧对，包括同一时刻采集的可见光图像和红外图像，热成像相机的图像采集区域内还设置有黑体（S202）；基于图像帧对确定目标对象的测量温度（S204）；对红外图像进行黑体检测，得到黑体的检测结果，包括黑体在红外图像中的位置信息（S206）；基于黑体的检测结果和红外图像，确定黑体的测量温度（S208）；根据黑体的测量温度以及黑体的预设温度，对目标对象的测量温度进行修正，将修正后的温度作为目标对象的测温结果（S210）。可以有效提升温度测量的准确性。

Description

测温方法、测温装置、电子设备及计算机可读存储介质
相关申请的交叉引用
本公开要求于2020年03月02日提交中国专利局的申请号为2020101375467、名称为“测温方法、装置、电子设备及计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本公开中。
技术领域
本公开涉及人工智能领域，尤其是涉及一种测温方法、测温装置、电子设备及计算机可读存储介质。
背景技术
在爆发诸如新冠肺炎、流感等疫情发生后，“发烧”、“高温”成了筛选疑似携带者的信号之一。现有的测温设备大致分为三种，例如传统的水银体温计、手持接触式测温设备以及红外成像测温设备。在公共场所，为了提高测温的便捷性，通常采用目前市面上常见的手持接触式测温设备，例如温度枪，但通过温度枪进行温度检测需要大量人工来筛查，在大人流大密度的公共场所下，不仅严重影响效率，而且在一定程度上也会增加群体传染的风险，此外，采用温度枪进行温度检测，可能会由于设备自身以及外界环境的变化造成较大的误差，测温结果不准确。基于此，诸如机场、火车站等部分公共场所开始采用红外热成像设备。而现有的红外热成像设备虽然提升了温度检测效率以及测温安全性，但是仍旧会由于设备本身以及周围环境等原因造成温度偏差，导致测温结果准确性不高。
发明内容
有鉴于此，本公开的目的在于提供一种测温方法、测温装置、电子设备及计算机可读存储介质，缓解由于外界环境或设备因素导致的温度测量不准确的问题，有效提升温度测量的准确性。
为了实现上述目的，本公开实施例提供了一种测温方法，包括：通过可见光相机和热成像相机获取包含有目标对象的图像帧对，其中，所述图像帧对包括同一时刻采集的可见光图像和红外图像，且所述热成像相机的图像采集区域内还设置有黑体；基于所述图像帧对确定所述目标对象的测量温度；对所述红外图像进行黑体检测，得到所述黑体的检测结果，其中，所述黑体的检测结果包括所述黑体在所述红外图像中的位置信息；基于所述黑 体的检测结果和所述红外图像，确定所述黑体的测量温度；根据所述黑体的测量温度以及所述黑体的预设温度，对所述目标对象的测量温度进行修正，将修正后的温度作为所述目标对象的测温结果。
可选地，所述基于所述图像帧对确定所述目标对象的测量温度的步骤，包括：对所述图像帧对中的可见光图像进行目标对象检测，得到所述目标对象在所述可见光图像中的位置信息；基于所述可见光相机和所述热成像相机的空间位置关系，以及所述目标对象在所述可见光图像中的位置信息，确定所述目标对象在所述红外图像的位置信息；根据所述目标对象在所述红外图像的位置信息，确定所述目标对象的测量温度。
可选地，所述黑体的检测结果还包括所述黑体所处的状态，所述状态包括遮挡状态和非遮挡状态。所述通过预设的神经网络模型对所述红外图像进行黑体检测，得到所述黑体的检测结果的步骤，包括：通过预设的神经网络模型对所述红外图像进行黑体检测，得到所述黑体在所述红外图像中的位置信息以及所述位置信息的置信度；根据所述黑体在所述红外图像中的位置信息以及所述位置信息的置信度确定所述黑体所处的状态。
可选地，所述根据所述黑体在所述红外图像中的位置信息以及所述位置信息的置信度确定所述黑体所处的状态的步骤，包括：如果所述黑体在所述红外图像中的位置信息为空，确定所述黑体的被遮挡概率为100％，因此可以确定所述黑体所处的状态为遮挡状态；如果所述黑体在所述红外图像中的位置信息为非空，基于所述位置信息的置信度确定所述黑体的被遮挡概率，然后根据所述黑体的被遮挡概率确定所述黑体所处的状态。
可选地，所述基于所述位置信息的置信度确定所述黑体的被遮挡概率的步骤，包括：根据预先设定的位置信息的置信度与黑体的被遮挡概率之间的对应关系，确定与所述位置信息的置信度对应的所述黑体的被遮挡概率，在所述对应关系中，所述位置信息的置信度与所述黑体的被遮挡概率负相关。
可选地，所述根据所述黑体的被遮挡概率确定所述黑体所处的状态的步骤，包括：如果所述黑体的被遮挡概率大于预设阈值，确定所述黑体所处的状态为遮挡状态；如果所述黑体的被遮挡概率小于所述预设阈值，确定所述黑体所处的状态为非遮挡状态。
可选地，所述基于所述黑体的检测结果和所述红外图像，确定所述黑体的测量温度的步骤，包括：如果所述黑体所处的状态为遮挡状态，获取所述红外图像采集时刻之前的邻近指定时长内所述黑体的历史测量温度，并基于所述黑体的历史测量温度确定所述黑体在所述红外图像采集时刻所对应的测量温度；如果所述黑体所处的状态为非遮挡状态，基于所述黑体在所述红外图像中的位置信息确定所述黑体在所述红外图像中所处的区域，将所述红外图像表征的所述区域的温度确定为所述黑体在所述红外图像采集时刻所对应的测量温度。
可选地，所述根据所述黑体的测量温度以及所述黑体的预设温度，对所述目标对象的测量温度进行修正的步骤，包括：将所述黑体的测量温度与所述黑体的预设温度之间的差值作为温度修正值；基于所述温度修正值对所述目标对象的测量温度进行修正。
本公开实施例还提供一种测温装置，包括：图像获取模块，配置成通过可见光相机和热成像相机获取包含有目标对象的图像帧对，其中，所述图像帧对包括同一时刻采集的可见光图像和红外图像，并且所述热成像相机的图像采集区域内还设置有黑体；对象温度确定模块，配置成基于所述图像帧对确定所述目标对象的测量温度；黑体检测模块，配置成对所述红外图像进行黑体检测，得到所述黑体的检测结果，其中，所述黑体的检测结果包括所述黑体在所述红外图像中的位置信息以及所述位置信息的置信度；黑体温度确定模块，配置成基于所述黑体的检测结果和所述红外图像，确定所述黑体的测量温度；温度修正模块，配置成根据所述黑体的测量温度以及所述黑体的预设温度，对所述目标对象的测量温度进行修正，然后将修正后的温度作为所述目标对象的测温结果。
本公开的实施例还提供了一种电子设备，包括：处理器、存储装置、输入装置、输出装置、图像采集装置以及总线系统。所述存储装置上存储有计算机程序，所述计算机程序在被所述处理器运行时执行如前述实施例中任一项所述的方法，所述输入装置被配置成用户用于输入指令的装置，所述输出装置被配置成向外部输出信息，图像采集装置被配置成拍摄用户期望的图像并将所拍摄的图像存储在所述存储装置中以供其他组件使用，所述总线系统被配置成使上述其他组件互连。
本公开的实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序指令、应用程序和所述应用程序使用和/或产生的数据，通过所述应用程序使所述计算机程序指令被处理器运行时执行前述实施例中任一项所述的方法的步骤，并且存储在这一过程中使用和/或产生的数据。
本公开的实施例提供了一种测温方法、测温装置、电子设备及计算机可读存储介质，通过可见光相机和热成像相机获取包含有目标对象的图像帧对(包括同一时刻采集的可见光图像和红外图像)，且热成像相机的图像采集区域内还设置有黑体，然后基于图像帧对确定目标对象的测量温度，通过对红外图像进行黑体检测，得到黑体的检测结果(包括黑体在红外图像中的位置信息以及黑体的状态)，之后基于黑体的检测结果和红外图像，确定黑体的测量温度，从而根据黑体的测量温度以及黑体的预设温度，对目标对象的测量温度进行修正，最后将修正后的温度作为目标对象的测温结果。上述方式利用黑体自身特性对目标对象的测量温度进行修正，校准了因外界环境以及测温设备自身所导致的温度测量误差，从而提升了测温准确性。
本公开实施例的其他特征和优点将在随后的说明书中阐述，或者，部分特征和优点可 以从说明书推知或毫无疑义地确定，或者通过实施本公开实施例的上述技术即可得知。
为使本公开的上述目的、特征和优点能更明显易懂，下文特举较佳实施例，并配合所附附图，作详细说明如下。
附图说明
为了更清楚地说明本公开具体实施方式或现有技术中的技术方案，下面将对具体实施方式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，下面描述中的附图是本公开的一些实施方式，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1示出了本公开实施例所提供的一种电子设备的结构示意图；
图2示出了本公开实施例所提供的一种测温方法的流程示意图；
图3示出了本公开实施例所提供的另一种测温方法的流程示意图；
图4示出了本公开实施例所提供的一种测温装置的结构示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚，下面将结合附图对本公开的技术方案进行描述，显然，所描述的实施例是本公开一部分实施例，而不是全部的实施例。
考虑到现有技术中的测温设备由于外界环境或设备因素导致的温度测量不准确，为改善此问题，本公开实施例提供了一种测温方法、测温装置、电子设备及计算机可读存储介质，该技术可应用于需要进行温度测量的设备，诸如应用于测温设备。为便于理解，以下对本公开实施例进行详细介绍。
参照图1，描述了用于实现本公开实施例的一种测温方法、测温装置、电子设备及计算机可读存储介质的示例电子设备100。
如图1所示的一种电子设备的结构示意图，电子设备100包括一个或更多个处理器102、一个或更多个存储装置104、输入装置106、输出装置108、图像采集装置110、以及总线系统112和/或其它形式的连接机构，通过总线系统112和/或其它形式的连接机构(未示出)使上述其他组件互连。应当注意，图1所示的电子设备100的组件和结构只是示例性的，而非限制性的，根据需要，所述电子设备也可以具有其他组件和结构。
所述处理器102可以被配置成采用数字信号处理器(DSP)、现场可编程门阵列(FPGA)、可编程逻辑阵列(PLA)中的至少一种硬件形式来实现，所述处理器102还可以被配置成中央处理单元(CPU)、图形处理单元(GPU)或者具有数据处理能力和/或指令执行能力的其它形式的处理单元中的一种或几种的组合，并且可以被配置成控制所述电子设备100中的其 它组件以执行期望的功能。
所述存储装置104可以包括一个或更多个计算机程序产品，所述计算机程序产品可以包括各种形式的计算机可读存储介质，例如易失性存储器和/或非易失性存储器。所述易失性存储器例如可以包括随机存取存储器(RAM)和/或高速缓冲存储器(cache)等。所述非易失性存储器例如可以包括只读存储器(ROM)、硬盘、闪存等。在所述计算机可读存储介质上可以存储一个或更多个计算机程序指令，处理器102可以运行所述程序指令，以实现下文所述的本公开实施例中(由处理器实现)的客户端功能以及/或者其它期望的功能。在所述计算机可读存储介质中还可以存储各种应用程序和各种数据，例如所述应用程序使用和/或产生的各种数据等。
所述输入装置106可以被配置成用户用于输入指令的装置，并且可以包括键盘、鼠标、麦克风和触摸屏等中的一个或更多个。
所述输出装置108可以被配置成向外部(例如，用户)输出各种信息(例如，图像或声音)，并且可以包括显示器、扬声器等中的一个或更多个。
所述图像采集装置110可以被配置成拍摄用户期望的图像(例如照片、视频等)，并且将所拍摄的图像存储在所述存储装置104中以供其它组件使用。
示例性地，用于实现根据本公开的实施例的测温方法、测温装置、电子设备及计算机可读存储介质的示例电子设备可以包括智能终端诸如测温相机、智能手机、穿戴式电子设备等。参见图2所示的一种测温方法的流程示意图，该方法主要包括如下步骤S202至步骤S210。
在步骤S202中，可以通过可见光相机和热成像相机获取包含有目标对象的图像帧对，其中，图像帧对可以包括同一时刻采集的可见光图像和红外图像，并且热成像相机的图像采集区域内还可以设置有黑体。
可见光是电磁波谱中人眼可以感知的部分，一般可见光的波长在400～760nm之间，可见光相机获取的可见光图像也即人眼可以看到的图像，通过可见光相机获取的可见光图像可以直观反映出可见光相机的图像采集区域所呈现的当前状态，诸如呈现出位于图像采集区域内的目标对象的位置等。其中，目标对象可以包括但不限于人体等可作为红外辐射源的自然生物。以目标对象是人体为例，由于人体是一个自然的生物红外辐射源，能够不断向周围发射和吸收红外辐射，正常人体的温度分布具有一定的稳定性和特征性，通过热成像相机(也可称为红外相机)可以获取反映人体温度的红外图像。在本公开的实施例中，可以通过可见光相机采集可见光图像，并且通过热成像相机采集红外图像，然后将可见光相机和热成像相机在同一时刻采集的可见光图像和红外图像作为一组图像帧对。在实际应用中，可见光相机和热成像相机可以预先进行时间同步。
黑体是在热辐射中一种理想化的物体，具备在任何条件下，完全吸收任何波长的外来辐射而无任何反射、吸收比为1且在任何温度下对入射的任何波长的辐射全部吸收三种特性，因此可以将黑体视为一种恒温体。本公开的实施例可以在热成像相机的图像采集区域内设置黑体，然后通过实时采集测温设备测量得到的黑体温度，而黑体的测量温度和黑体自身设定的温度之间的差值即为环境或设备自身导致的温度偏差。例如，当环境温度较低时，传感器在提取红外数据时得到的测量温度可能比真实温度偏低，或者当设备长时间运行时可能导致设备的温度升高，从而使得测量温度比真实温度偏高，这均会导致设备的测量温度不准确，而将黑体设置在热成像相机的图像采集区域内，可以利用黑体的恒温特性判断设备的测量温度是否具有温度偏差。
在步骤S204中，基于图像帧对确定目标对象的测量温度。
可以理解的是，由于可见光相机和红外相机的位置不同，所以图像采集范围具有一定偏差，因此针对同一区域采集到的图像也不同，即同一目标对象在可见光图像和红外图像中的位置也不同，但是会具有一定的对应关系。在图像帧对中的可见光图像和红外图像均为同一时刻采集的基础上，可以根据可见光相机和红外相机之间的空间位置关系来确定可见光图像和红外图像的对应关系，例如，识别出目标人物A在可见光图像中所处的第一位置区域，然后基于可见光图像和红外图像之间的对应关系，将第一位置区域转换为红外图像中的第二位置区域，第二位置区域即为目标人物A在红外图像中所处的位置，从而将红外图像中所显示的第二位置区域的温度作为目标人物A的测量温度。
在步骤S206中，对红外图像进行黑体检测，得到黑体的检测结果。该黑体的检测结果包括黑体在红外图像中的位置信息。
可选地，可以利用人工检查并标定黑体位置，从而实现对红外图像的黑体检测。
考虑到在实际应用中，可能会因各种原因使得需要黑体校准的设备的位置发生移动或者黑体自身的位置移动，黑体检测结果将发生变化，为了能够更好的节约标定黑体的成本，以及避免人工标定误差，同时也尽量提高黑体检测效率，本公开的实施例可选地可以通过预设的神经网络模型对红外图像进行黑体检测，神经网络模型可以基于目标检测算法实现，具体可采用诸如SSD(SingleShotMultiBoxDetector)、YOLO(YouOnlyLookOnce:Unified,Real-TimeObjectDetection)和卷积神经网络(ConvolutionalNeuralNetworks,CNN)等神经网络模型实现。对红外图像进行黑体检测，即在红外图像中对黑体进行目标检测，可以通过得到的结果获取到黑体在红外图像中的位置信息，该位置信息可以包括黑体在红外图像中的位置坐标。当然，在实际应用中，如果黑体的位置信息为空(诸如无位置坐标输出)，则认为未在红外图像中检测到黑体。
本公开的实施例通过神经网络模型对黑体进行自动检测，有效提升了黑体标定效率和 可靠性，而且降低了黑体位置的局限性，无需要求黑体位置保持不变，可以根据需求而灵活调整黑体位置，只需黑体位于热成像相机的图像采集区域即可，即便黑体与热成像相机之间的位置关系发生变化，也可以通过神经网络模型得到较为准确的黑体检测结果，避免由于黑体的位置变化造成的温度检测不准确的情况。
在步骤S208中，基于黑体的检测结果和红外图像，确定黑体的测量温度。
根据黑体的检测结果中所携带的黑体在红外图像中的位置信息，确定黑体在红外图像中所处的区域，将红外图像中所呈现的该区域的温度作为黑体的测量温度。
在步骤S210中，根据黑体的测量温度以及黑体的预设温度，对目标对象的测量温度进行修正，将修正后的温度作为目标对象的测温结果。
可选地，例如，黑体的预设温度可以设置在30度到40度之间，具体地可以根据黑体所处的环境进行经验设置，诸如当在室外时，可以设定黑体的预设温度为34度。由于黑体具有恒温特性，当黑体的测量温度与黑体的预设温度存在区别时，说明测温设备的测量温度存在偏差。例如，当黑体的预设温度为34度，而测温设备得到的黑体的测量温度为34.4度时，可以确定测温设备的测温结果比实际温度偏高0.4度，因此设定对目标人物A的测量温度进行修正的修正值为0.4度，假设目标人物A通过热成像相机得到的测量温度为37.6度，则修正后的温度为37.2度。将修正后的温度37.2度作为目标人物A的测温结果，从而避免了将目标人物A误报为高危人员。上述利用黑体的恒温特性对目标对象的测量温度进行修正，可以降低由于设备或环境因素导致的测温误差，提升了温度测量的准确性。
本公开实施例提供的上述测温方法，利用黑体自身特性对目标对象的测量温度进行修正，校准了因外界环境以及测温设备自身所导致的温度测量误差，从而提升了测温准确性，此外，上述方式可基于神经网络模型实现黑体自动检测，无需人工标定黑体位置，避免了人工标定的繁琐与人为误差，使得黑体的测量温度更真实可靠，从而进一步提升了温度修正的可靠性，使得修正后的测温结果更准确。
为便于理解，本公开的实施例提供了一种基于图像帧对确定目标对象的测量温度的具体实施方式，即上述步骤S204可以参照如下步骤(1)至步骤(3)执行。
在步骤(1)中，对图像帧对中的可见光图像进行目标对象检测，可以得到目标对象在可见光图像中的位置信息，其中，可以采用目标检测算法对可见光图像进行目标对象检测。目标检测算法可以根据实际情况选择单目标检测或多目标检测等，在此不进行限定。以多目标检测为例，在可见光图像中可以对多个目标对象进行检测识别，并在可见光图像上确定每个目标对象的位置信息。
在步骤(2)中，基于可见光相机和热成像相机的空间位置关系，以及目标对象在可见光图像中的位置信息，可以确定目标对象在红外图像的位置信息。诸如，已知目标人物A 在可见光图像中的第一位置坐标，根据可见光相机和热成像相机的空间位置关系，将第一位置坐标投影转换至红外图像中的第二位置坐标，从而得到目标人物A在红外图像中的位置信息。
在步骤(3)中，根据目标对象在红外图像的位置信息，可以确定目标对象的测量温度。即，将目标对象在红外图像所处区域对应的温度确定为目标对象的测量温度。
考虑到黑体可能会被遮挡，例如在火车站等公共场合中，行人可能会全部或部分遮挡黑体，为了尽可能避免将遮挡了黑体的物体温度作为黑体的测量温度，从而影响测温准确性，本公开的实施例通过预设的神经网络模型检测得到黑体的检测结果还包括黑体所处的状态，该状态包括遮挡状态和非遮挡状态，基于此，上述步骤S206可以可选地包括如下步骤1和步骤2。
在步骤1中，通过预设的神经网络模型对红外图像进行黑体检测，得到黑体在红外图像中的位置信息以及位置信息的置信度。
例如，预设的神经网络模型的输入是一整幅红外图像，输出是检测到的黑体的位置信息(诸如黑体的位置坐标)以及黑体位置信息的置信度。例如当检测到黑体的位置信息为在红外图像的左下角，且置信度为90％，则说明黑体可能在红外图像左下角的几率为90％。
可选地，通过预设的神经网络模型对红外图像进行黑体检测，还可以得到黑体的形状或大小，黑体的形状可以包括圆形或方形等，在实际应用中，可以基于检测出的黑体的大小在红外图像中的占比判别黑体与热成像相机之间的距离是否合理。若黑体距离热成像相机过近，整个红外图像中黑体占比太大，则无法对目标对象进行正常的检测；若黑体距离热成像相机过远，红外图像中黑体的大小占比过小时，则会较难准确地确定黑体的测量温度。
在步骤2中，根据黑体在红外图像中的位置信息以及位置信息的置信度确定黑体所处的状态。黑体所处的状态包括遮挡状态和非遮挡状态，本公开实施例可选地给出了步骤2的具体实施方式，可以参照如下步骤2.1至步骤2.3实现。
在步骤2.1中，如果黑体在红外图像中的位置信息为空，确定黑体的被遮挡概率为100％。
可选地，如果黑体在红外图像中的位置信息为空，即红外图像中没有检测到黑体，但是黑体是位于热成像相机的图像采集范围内，如果未检测到黑体，此时确定黑体的被遮挡概率为100％，即黑体所处的状态为遮挡状态。
在步骤2.2中，如果黑体在红外图像中的位置信息为非空，基于位置信息的置信度确定黑体的被遮挡概率。
可选地，如果黑体在红外图像中的位置信息为非空时，可以根据预先设定的位置信息 的置信度与黑体的被遮挡概率之间的对应关系，确定与位置信息的置信度对应的黑体的被遮挡概率，在位置信息的置信度与黑体的被遮挡概率的对应关系中，位置信息的置信度与黑体的被遮挡概率负相关，即位置信息的置信度越低，则被遮挡概率越高。例如，当位置信息的置信度为15％时，在对应关系中设定黑体被遮挡的概率为85％。应当注意的是，以上举例仅为示意性说明，不应当被视为限制。
在步骤2.3中，根据黑体的被遮挡概率确定黑体所处的状态。
如果黑体的被遮挡概率大于预设阈值，确定黑体所处的状态为遮挡状态；如果黑体的被遮挡概率小于预设阈值，确定黑体所处的状态为非遮挡状态。其中，预设阈值可以根据经验值进行设置。
在已知携带有黑体的位置信息以及黑体是否被遮挡的状态的黑体检测结果的基础上，可以结合红外图像确定黑体的测量温度，具体可参照如下步骤(1)和步骤(2)实现。
在步骤(1)中，如果黑体所处的状态为遮挡状态，则可以获取红外图像采集时刻之前的邻近指定时长内黑体的历史测量温度，并基于黑体的历史测量温度确定黑体在红外图像采集时刻所对应的测量温度。邻近指定时长可以灵活设置。该测量温度可以是当前红外图像的采集时刻之前邻近指定时长内包含的多帧未被遮挡的黑体的平均检测温度，也可以是当前红外图像的采集时刻之前邻近指定时长内包含的所有帧的黑体的平均检测温度，由于采集时刻之前处于遮挡状态的黑体的测量温度已经经过历史帧温度校正，因此也可以采用采集时刻前一段时间内所有帧的测量温度平均值作为采集时刻的测量温度。
在步骤(2)中，如果黑体所处的状态为非遮挡状态，则基于黑体在红外图像中的位置信息确定黑体在红外图像中所处的区域，将红外图像表征的区域的温度确定为黑体在红外图像采集时刻所对应的测量温度。
通过上述步骤确定了黑体的测量温度后，可以将黑体的测量温度与黑体的预设温度之间的差值作为温度修正值，并基于温度修正值对目标对象的测量温度进行修正，从而可以避免由于环境或设备因素导致的目标对象的测量温度不准确的问题，提升了温度测量的准确性。
在本公开的前述实施例的基础上，本公开的实施例提供了一种应用前述测温方法的具体示例，参见图3所示的另一种测温方法的流程示意图，该方法主要包括如下步骤S302至步骤S314。
在步骤S302中，可以通过可见光相机采集可见光图像，并通过红外相机(即前述热成像相机)采集红外图像，基于可见光图像和红外图像可以确定待检测人员的位置信息和测量温度。
在步骤S304中，将红外图像输入至黑体检测模型，通过黑体检测模型可以确定黑体的 位置信息并判断黑体是否被遮挡。如果是，则执行步骤S306；如果否，则执行步骤S308。具体而言，在红外相机的采集区域内设置黑体，黑体检测模型可以检测出黑体在红外图像中的位置以及黑体位于该位置的置信度，从而基于位置的置信度得到黑体被遮挡的概率，进而根据黑体被遮挡的概率判别出黑体是否被遮挡。
在步骤S306中，基于历史红外图像帧可以确定黑体的测量温度。历史红外图像帧可以是当前红外图像采集时刻的前一帧或多帧未被遮挡的红外图像，也可以是当前采集时刻的前一段时间内采集的所有红外图像。可选地，可以将历史红外图像帧的黑体检测温度的均值作为当前被遮挡的黑体的测量温度。
在步骤S308中，基于当前的红外图像可以确定黑体的测量温度。当确定黑体未被遮挡时，黑体检测模型检测出黑体在当前红外图像中的位置所在区域的温度，即为黑体当前的测量温度。
在步骤S310中，基于黑体预设温度和黑体的测量温度可以确定温度修正值。具体而言，温度修正值为黑体预设温度和黑体检测温度作差得到的值。
在步骤S312中，根据温度修正值可以对待检测人员的测量温度进行修正，得到修正后的温度结果。通过对人员温度进行修正，可以缓解由于周围环境或者设备因素导致的温度测量不准确的问题，提升温度检测的准确性。
本公开的实施例提供的测温方法，一方面利用黑体自身的恒温特性对目标对象的测量温度进行修正，校准因外界环境以及测温设备自身所导致的温度测量误差，另一方面基于神经网络模型实现黑体自动检测，无需人工标定黑体位置，避免了人工标定的繁琐与人为误差，使得黑体的测量温度更真实可靠。可选地，上述方法通过对黑体是否被遮挡的状态进行判别，黑体的状态不同，黑体的测量温度的确定方式也不同，更进一步提升了黑体测温结果的准确性，综合提升了温度修正的可靠性，使得最终得到的修正后的温度更为真实准确。
对于本公开的实施例所提供的测温方法，本公开的实施例提供了一种测温装置，参见图4所示的一种测温装置的结构示意图，该装置包括以下模块：
图像获取模块402，可以配置成通过可见光相机和热成像相机获取包含有目标对象的图像帧对，其中，图像帧对可以包括同一时刻采集的可见光图像和红外图像，并且热成像相机的图像采集区域内还设置有黑体；
对象温度确定模块404，可以配置成基于图像帧对确定目标对象的测量温度；
黑体检测模块406，可以配置成对红外图像进行黑体检测，得到黑体的检测结果，其中，检测结果包括黑体在红外图像中的位置信息；
黑体温度确定模块408，可以配置成基于黑体的检测结果和红外图像，确定黑体的测量温度；
温度修正模块410，可以配置成根据黑体的测量温度以及黑体的预设温度，对目标对象的测量温度进行修正，将修正后的温度作为目标对象的测温结果。
本公开的实施例提供的上述测温装置，利用黑体自身特性对目标对象的测量温度进行修正，校准了因外界环境以及测温设备自身所导致的温度测量误差，从而提升了测温准确性。
可选地，上述对象温度确定模块404可以配置成以下：对图像帧对中的可见光图像进行目标对象检测，得到目标对象在可见光图像中的位置信息；基于可见光相机和热成像相机的空间位置关系，以及目标对象在可见光图像中的位置信息，确定目标对象在红外图像的位置信息；根据目标对象在红外图像的位置信息，确定目标对象的测量温度。
可选地，检测结果还包括黑体所处的状态，状态包括遮挡状态和非遮挡状态。上述黑体检测模块406，可以包括：位置检测单元，配置成通过预设的神经网络模型对红外图像进行黑体检测，得到黑体在红外图像中的位置信息以及位置信息的置信度；状态确定单元，配置成根据黑体在红外图像中的位置信息以及位置信息的置信度确定黑体所处的状态。
可选地，上述状态确定单元，可以配置成以下：如果黑体在红外图像中的位置信息为空，确定黑体的被遮挡概率为100％；如果黑体在红外图像中的位置信息为非空，基于位置信息的置信度确定黑体的被遮挡概率；根据黑体的被遮挡概率确定黑体所处的状态。
可选地，上述状态确定单元可以配置成根据预先设定的位置信息的置信度与黑体的被遮挡概率之间的对应关系，确定与位置信息的置信度对应的黑体的被遮挡概率，其中，在对应关系中，位置信息的置信度与黑体的被遮挡概率负相关。
可选地，上述状态确定单元可以配置成以下：如果黑体的被遮挡概率大于预设阈值，确定黑体所处的状态为遮挡状态；如果黑体的被遮挡概率小于预设阈值，确定黑体所处的状态为非遮挡状态。
可选地，上述黑体温度确定模块408可以配置成以下：如果黑体所处的状态为遮挡状态，获取红外图像采集时刻之前的邻近指定时长内黑体的历史测量温度，基于黑体的历史测量温度确定黑体在红外图像采集时刻所对应的测量温度；如果黑体所处的状态为非遮挡状态，基于黑体在红外图像中的位置信息确定黑体在红外图像中所处的区域，将红外图像表征的区域的温度确定为黑体在红外图像采集时刻所对应的测量温度。
可选地，上述温度修正模块410可以配置成将黑体的测量温度与黑体的预设温度之间的差值作为温度修正值，并且基于温度修正值对目标对象的测量温度进行修正。
本公开的实施例所提供的装置，其实现原理及产生的技术效果和前述实施例相同，为 简要描述，装置实施例部分未提及之处，可参考前述方法实施例中相应内容。
本公开的实施例还提供了一种计算机可读存储介质，用于本公开实施例所提供的上述测温方法、测温装置、电子设备。该计算机可读存储介质可以配置成存储计算机程序指令、应用程序和该应用程序使用和/或产生的数据。通过应用程序使计算机程序指令被处理器运行时执行前述实施例中任一项所述的方法的步骤，并且存储在这一过程中使用和/或产生的数据。计算机程序指令可以配置成执行前面方法实施例中所述的方法，具体实现可参见方法实施例，在此不再赘述。
可选地，本公开的实施例的功能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，本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-OnlyMemory)、随机存取存储器(RAM，RandomAccessMemory)、磁碟或者光盘等各种可以存储程序代码的介质。
综上所述，本公开实施例提供的测温方法、测温装置、电子设备及计算机可读存储介质，利用黑体自身特性对目标对象的测量温度进行修正，校准了因外界环境以及测温设备自身所导致的温度测量误差，从而提升了测温准确性。此外，本公开的实施例可基于神经网络模型实现黑体自动检测，无需人工标定黑体位置，避免了人工标定的繁琐与人为误差，使得黑体的测量温度更真实可靠，从而进一步提升了温度修正的可靠性，使得修正后的测温结果更准确。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统具体工作过程，可以参考前述实施例中的对应过程，在此不再赘述。
另外，在本公开实施例的描述中，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。对于本领域的普通技术人员而言，可以具体情况理解上述术语在本公开中的具体含义。
最后应说明的是，以上所述实施例，仅为本公开的具体实施方式，用以说明本公开的技术方案，而非对其限制，本公开的保护范围并不局限于此。尽管参照前述实施例对本公开进行了详细的说明，本领域的普通技术人员应当理解，任何熟悉本技术领域的技术人员在本公开揭露的技术范围内，其依然可以对前述实施例所记载的技术方案进行修改或可轻 易想到变化，或者对其中部分技术特征进行等同替换，而这些修改、变化或者替换，并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围，都应涵盖在本公开的保护范围之内。因此，本公开的保护范围应以所述权利要求的保护范围为准。
工业实用性
本公开提供一种测温方法、测温装置、电子设备及计算机可读存储介质，缓解了由于外界环境或设备因素导致的温度测量不准确的问题。基于神经网络模型实现的黑体自动检测无需人工标定黑体位置，避免了人工标定的繁琐与人为误差，使得黑体的测量温度更真实可靠，校准了因外界环境以及测温设备自身所导致的温度测量误差，进一步提升了温度修正的可靠性，从而有效提升了温度测量的准确性。

Claims (17)

  1. 一种测温方法，其特征在于，包括：
    通过可见光相机和热成像相机获取包含有目标对象的图像帧对，其中，所述图像帧对包括同一时刻采集的可见光图像和红外图像，并且所述热成像相机的图像采集区域内还设置有黑体；
    基于所述图像帧对确定所述目标对象的测量温度；
    对所述红外图像进行黑体检测，得到所述黑体的检测结果，其中，所述检测结果包括所述黑体在所述红外图像中的位置信息；
    基于所述黑体的检测结果和所述红外图像，确定所述黑体的测量温度；
    根据所述黑体的测量温度以及所述黑体的预设温度，对所述目标对象的测量温度进行修正，将修正后的温度作为所述目标对象的测温结果。
  2. 根据权利要求1所述的方法，其特征在于，所述基于所述图像帧对确定所述目标对象的测量温度的步骤，包括：
    对所述图像帧对中的可见光图像进行目标对象检测，得到所述目标对象在所述可见光图像中的位置信息；
    基于所述可见光相机和所述热成像相机的空间位置关系，以及所述目标对象在所述可见光图像中的位置信息，确定所述目标对象在所述红外图像的位置信息；
    根据所述目标对象在所述红外图像的位置信息，确定所述目标对象的测量温度。
  3. 根据权利要求1和2中任一项所述的方法，其特征在于，所述黑体的检测结果还包括所述黑体所处的状态，包括遮挡状态和非遮挡状态。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述黑体的检测结果还包括所述黑体的大小或形状，其中，基于检测出的黑体的大小在红外图像中的占比判别黑体与热成像相机之间的距离是否合理。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述对所述红外图像进行黑体检测，得到所述黑体的检测结果的步骤，包括：
    通过预设的神经网络模型对所述红外图像进行黑体检测，得到所述黑体在所述红外图像中的位置信息以及所述位置信息的置信度；
    根据所述黑体在所述红外图像中的位置信息以及所述位置信息的置信度确定所述黑体所处的状态。
  6. 根据权利要求1至5中任一项所述的方法，其特征在于，所述根据所述黑体在所述红外图像中的位置信息以及所述位置信息的置信度确定所述黑体所处的状态的步骤， 包括：
    如果所述黑体在所述红外图像中的位置信息为空，确定所述黑体的被遮挡概率为100％；
    如果所述黑体在所述红外图像中的位置信息为非空，基于所述位置信息的置信度确定所述黑体的被遮挡概率；
    根据所述黑体的被遮挡概率确定所述黑体所处的状态。
  7. 根据权利要求1至6中任一项所述的方法，其特征在于，所述基于所述位置信息的置信度确定所述黑体的被遮挡概率的步骤，包括：
    根据预先设定的位置信息的置信度与黑体的被遮挡概率之间的对应关系，确定与所述位置信息的置信度对应的所述黑体的被遮挡概率；
    其中，在所述对应关系中，所述位置信息的置信度与所述黑体的被遮挡概率负相关。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述根据所述黑体的被遮挡概率确定所述黑体所处的状态的步骤，包括：
    如果所述黑体的被遮挡概率大于预设阈值，确定所述黑体所处的状态为遮挡状态；
    如果所述黑体的被遮挡概率小于所述预设阈值，确定所述黑体所处的状态为非遮挡状态。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，所述基于所述黑体的检测结果和所述红外图像，确定所述黑体的测量温度的步骤，包括：
    如果所述黑体所处的状态为遮挡状态，获取所述红外图像采集时刻之前的邻近指定时长内所述黑体的历史测量温度，基于所述黑体的历史测量温度确定所述黑体在所述红外图像采集时刻所对应的测量温度；
    如果所述黑体所处的状态为非遮挡状态，基于所述黑体在所述红外图像中的位置信息确定所述黑体在所述红外图像中所处的区域，将所述红外图像表征的所述区域的温度确定为所述黑体在所述红外图像采集时刻所对应的测量温度。
  10. 根据权利要求1至9中任一项所述的方法，其特征在于，所述黑体的历史测量温度包括：
    当前红外图像的采集时刻之前邻近指定时长内所包含的多帧未被遮挡的黑体的平均检测温度；
    或者当前红外图像的采集时刻之前邻近指定时长内包含的所有帧的黑体的平均检测温度。
  11. 根据权利要求1至10中任一项所述的方法，其特征在于，所述根据所述黑体的测量温度以及所述黑体的预设温度，对所述目标对象的测量温度进行修正的步骤，包括：
    将所述黑体的测量温度与所述黑体的预设温度之间的差值作为温度修正值；
    基于所述温度修正值对所述目标对象的测量温度进行修正。
  12. 一种测温装置，其特征在于，包括：
    图像获取模块，配置成通过可见光相机和热成像相机获取包含有目标对象的图像帧对，其中，所述图像帧对包括同一时刻采集的可见光图像和红外图像，并且所述热成像相机的图像采集区域内还设置有黑体；
    对象温度确定模块，配置成基于所述图像帧对确定所述目标对象的测量温度；
    黑体检测模块，配置成对所述红外图像进行黑体检测，得到所述黑体的检测结果，其中，所述检测结果包括所述黑体在所述红外图像中的位置信息；
    黑体温度确定模块，配置成基于所述黑体的检测结果和所述红外图像，确定所述黑体的测量温度；
    温度修正模块，配置成根据所述黑体的测量温度以及所述黑体的预设温度，对所述目标对象的测量温度进行修正，将修正后的温度作为所述目标对象的测温结果。
  13. 根据权利要求12所述的装置，其特征在于，所述对象温度确定模块还被配置成：
    对图像帧对中的可见光图像进行目标对象检测，得到目标对象在可见光图像中的位置信息；
    基于可见光相机和热成像相机的空间位置关系，以及目标对象在可见光图像中的位置信息，确定目标对象在红外图像的位置信息；
    根据目标对象在红外图像的位置信息，确定目标对象的测量温度。
  14. 根据权利要求12和13中任一项所述的装置，其特征在于，所述黑体检测模块包括：
    位置检测单元，配置成通过预设的神经网络模型对红外图像进行黑体检测，得到黑体在红外图像中的位置信息以及位置信息的置信度；
    状态确定单元，配置成根据黑体在红外图像中的位置信息以及位置信息的置信度确定黑体所处的状态。
  15. 根据权利要求12至14中任一项所述的装置，其特征在于，所述黑体温度确定模块还被配置成：
    如果黑体所处的状态为遮挡状态，获取红外图像采集时刻之前的邻近指定时长内黑体的历史测量温度，基于黑体的历史测量温度确定黑体在红外图像采集时刻所对应的测量温度；
    如果黑体所处的状态为非遮挡状态，基于黑体在红外图像中的位置信息确定黑体在红外图像中所处的区域，将红外图像表征的区域的温度确定为黑体在红外图像采集时刻所对应的测量温度。
  16. 一种电子设备，其特征在于，包括处理器和存储装置，其中，所述存储装置上存储有计算机程序，所述计算机程序在被所述处理器运行时执行如权利要求1至11中任一项所述的方法。
  17. 一种计算机可读存储介质，所述计算机可读存储介质上存储有计算机程序，其特征在于，所述计算机程序被处理器运行时执行上述权利要求1至11中任一项所述的方法的步骤。
PCT/CN2020/119459 2020-03-02 2020-09-30 测温方法、测温装置、电子设备及计算机可读存储介质 WO2021174841A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/759,835 US20230075679A1 (en) 2020-03-02 2020-09-30 Temperature measurement method, temperature measurement apparatus, electronic device and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010137546.7 2020-03-02
CN202010137546.7A CN111366244B (zh) 2020-03-02 2020-03-02 测温方法、装置、电子设备及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2021174841A1 true WO2021174841A1 (zh) 2021-09-10

Family

ID=71206475

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/119459 WO2021174841A1 (zh) 2020-03-02 2020-09-30 测温方法、测温装置、电子设备及计算机可读存储介质

Country Status (3)

Country Link
US (1) US20230075679A1 (zh)
CN (1) CN111366244B (zh)
WO (1) WO2021174841A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113879357A (zh) * 2021-10-14 2022-01-04 中车青岛四方机车车辆股份有限公司 列车轴温检测方法及装置
CN113959565A (zh) * 2021-09-29 2022-01-21 浙江双视红外科技股份有限公司 一种红外热像仪测温方法
CN114279575A (zh) * 2021-12-28 2022-04-05 杭州涂鸦信息技术有限公司 获取环境温度的方法、人体测温方法以及装置
CN114323306A (zh) * 2022-03-07 2022-04-12 深圳佳特安科技有限公司 一种黑体一体式体温测量装置及其检测方法
CN115836841A (zh) * 2022-11-23 2023-03-24 深兰自动驾驶研究院(山东)有限公司 乳腺监测方法、装置和计算机可读存储介质

Families Citing this family (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111366244B (zh) * 2020-03-02 2021-08-10 北京迈格威科技有限公司 测温方法、装置、电子设备及计算机可读存储介质
CN111953935A (zh) * 2020-07-07 2020-11-17 北京迈格威科技有限公司 体温监管方法、装置、智慧屏和计算机可读存储介质
CN111693150B (zh) * 2020-07-13 2021-05-04 山东科技大学 温度测量方法、云端服务器及温度测量仪
CN111811694B (zh) * 2020-07-13 2021-11-30 广东博智林机器人有限公司 一种温度校准方法、装置、设备及存储介质
CN112001886A (zh) * 2020-07-17 2020-11-27 深圳市优必选科技股份有限公司 一种温度检测方法、装置、终端及可读存储介质
CN111998959B (zh) * 2020-07-20 2022-07-22 北京百度网讯科技有限公司 基于实时测温系统的温度校准方法、装置及存储介质
CN112033543B (zh) * 2020-07-21 2021-09-17 深圳市优必选科技股份有限公司 黑体对准方法、装置、机器人及计算机可读存储介质
DE102020119264A1 (de) * 2020-07-21 2022-01-27 Mühlbauer Gmbh & Co. Kg Verfahren und Vorrichtung zur Personenzugangskontrolle in Abhängigkeit von einer Temperaturmessung
CN111879414A (zh) * 2020-08-04 2020-11-03 银河水滴科技（北京）有限公司 一种红外测温的方法、装置、计算机设备和介质
CN111964790A (zh) * 2020-08-14 2020-11-20 济南博观智能科技有限公司 一种温度校准方法及红外测温装置
CN111935469B (zh) * 2020-09-27 2021-03-26 深圳市当智科技有限公司 投影机安全工作方法和投影机
CN112161711A (zh) * 2020-09-28 2021-01-01 深圳市商汤科技有限公司 温度校正方法、装置、黑体、红外测温设备及系统
CN112229524A (zh) * 2020-10-27 2021-01-15 深圳英飞拓科技股份有限公司 一种体温筛查方法、装置、终端设备及存储介质
CN112683405A (zh) * 2020-11-11 2021-04-20 浙江大华技术股份有限公司 一种温度检测方法、系统以及存储介质
CN112435295A (zh) * 2020-11-12 2021-03-02 浙江大华技术股份有限公司 黑体位置检测方法、电子装置以及计算机可读存储介质
CN112529956A (zh) * 2020-11-12 2021-03-19 浙江大华技术股份有限公司 黑体位置检测方法、电子装置以及计算机可读存储介质
CN112556858B (zh) * 2020-12-07 2022-02-11 深圳市优必选科技股份有限公司 黑体检测方法、测温机器人、终端设备及存储介质
CN114659646A (zh) * 2020-12-07 2022-06-24 华为技术有限公司 一种测温方法、装置、设备及系统
CN112818816B (zh) * 2021-01-27 2024-03-01 杭州海康威视数字技术股份有限公司 一种温度检测方法、装置及设备
CN112880838A (zh) * 2021-02-08 2021-06-01 深圳市宇通联发科技有限公司 红外体温检测方法、存储介质以及红外体温检测设备
CN113008404A (zh) * 2021-02-22 2021-06-22 深圳市商汤科技有限公司 温度测量方法及装置、电子设备和存储介质
CN112924037A (zh) * 2021-02-26 2021-06-08 河北地质大学 基于图像配准的红外体温检测系统及检测方法
US20240138683A1 (en) * 2021-03-09 2024-05-02 C2Ro Cloud Robotics Inc. System and Method for Thermal Screening
CN113049109B (zh) * 2021-03-12 2022-11-29 红相股份有限公司 基于参考黑体的红外测温方法及计算机可读存储介质
CN113091914A (zh) * 2021-04-06 2021-07-09 佛山华数机器人有限公司 一种基于红外测温的工业机器人温度测试方法及系统
CN113084869B (zh) * 2021-04-06 2022-06-10 佛山华数机器人有限公司 一种基于红外测温的工业机器人故障诊断方法及系统
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
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
CN114910173A (zh) * 2022-06-07 2022-08-16 中国人民解放军国防科技大学 一种利用黑体标准温度源的红外测温装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080154138A1 (en) * 2003-05-27 2008-06-26 Mcquilkin Gary L Methods and apparatus for a remote, noninvasive technique to detect core body temperature in a subject via thermal imaging
CN106919806A (zh) * 2017-04-27 2017-07-04 刘斌 一种人体监测方法、装置以及系统及计算机可读存储设备
CN208420179U (zh) * 2018-05-29 2019-01-22 浙江双视红外科技股份有限公司 一种闸机单元及闸机系统
CN110060272A (zh) * 2018-01-18 2019-07-26 杭州海康威视数字技术股份有限公司 人脸区域的确定方法、装置、电子设备及存储介质
CN110108364A (zh) * 2019-05-08 2019-08-09 武汉高德智感科技有限公司 一种基于黑体定时补偿的可移动人体温度筛选方法及系统
CN111366244A (zh) * 2020-03-02 2020-07-03 北京迈格威科技有限公司 测温方法、装置、电子设备及计算机可读存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN207515910U (zh) * 2017-12-04 2018-06-19 中华人民共和国首都机场出入境检验检疫局 一种全自动红外测温仪
CN209070548U (zh) * 2018-10-26 2019-07-05 深圳市欧德克科技有限公司 一种火车站监控系统
CN109596226B (zh) * 2018-12-27 2019-12-24 武汉高德智感科技有限公司 用于红外热成像测温系统的黑体异常检测方法、装置、设备及系统
CN110135266A (zh) * 2019-04-17 2019-08-16 浙江理工大学 一种基于深度学习的双摄像头电气火灾防控方法及系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080154138A1 (en) * 2003-05-27 2008-06-26 Mcquilkin Gary L Methods and apparatus for a remote, noninvasive technique to detect core body temperature in a subject via thermal imaging
CN106919806A (zh) * 2017-04-27 2017-07-04 刘斌 一种人体监测方法、装置以及系统及计算机可读存储设备
CN110060272A (zh) * 2018-01-18 2019-07-26 杭州海康威视数字技术股份有限公司 人脸区域的确定方法、装置、电子设备及存储介质
CN208420179U (zh) * 2018-05-29 2019-01-22 浙江双视红外科技股份有限公司 一种闸机单元及闸机系统
CN110108364A (zh) * 2019-05-08 2019-08-09 武汉高德智感科技有限公司 一种基于黑体定时补偿的可移动人体温度筛选方法及系统
CN111366244A (zh) * 2020-03-02 2020-07-03 北京迈格威科技有限公司 测温方法、装置、电子设备及计算机可读存储介质

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113959565A (zh) * 2021-09-29 2022-01-21 浙江双视红外科技股份有限公司 一种红外热像仪测温方法
CN113879357A (zh) * 2021-10-14 2022-01-04 中车青岛四方机车车辆股份有限公司 列车轴温检测方法及装置
CN114279575A (zh) * 2021-12-28 2022-04-05 杭州涂鸦信息技术有限公司 获取环境温度的方法、人体测温方法以及装置
CN114279575B (zh) * 2021-12-28 2024-02-27 杭州涂鸦信息技术有限公司 获取环境温度的方法、人体测温方法以及装置
CN114323306A (zh) * 2022-03-07 2022-04-12 深圳佳特安科技有限公司 一种黑体一体式体温测量装置及其检测方法
CN115836841A (zh) * 2022-11-23 2023-03-24 深兰自动驾驶研究院(山东)有限公司 乳腺监测方法、装置和计算机可读存储介质

Also Published As

Publication number Publication date
CN111366244A (zh) 2020-07-03
CN111366244B (zh) 2021-08-10
US20230075679A1 (en) 2023-03-09

Similar Documents

Publication Publication Date Title
WO2021174841A1 (zh) 测温方法、测温装置、电子设备及计算机可读存储介质
US11002839B2 (en) Method and apparatus for measuring angular resolution of multi-beam lidar
CN111337142A (zh) 体温修正方法、装置及电子设备
CN111751003B (zh) 一种热像仪温度修正系统、方法及热像仪
CN111507200A (zh) 体温检测方法、体温检测装置、及双光相机
WO2017206444A1 (zh) 一种成像差异检测方法、装置及计算机存储介质
CN111458039A (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
CN108600736B (zh) 终端光感校准方法、装置、终端及存储介质
WO2021175281A1 (zh) 红外测温方法、装置、设备及存储介质
WO2021259365A1 (zh) 一种目标测温方法、装置及测温系统
WO2017114368A1 (zh) 摄像头模组感光质量的处理方法、装置和存储介质
US20220042851A1 (en) Face and inner canthi detection for thermographic body temperature measurement
US11818334B2 (en) Thermal image-based temperature measurement calibration method and thermal image device
WO2023273412A1 (zh) 一种光谱反射率的确定方法、装置及设备
WO2021016051A1 (en) Joint environmental reconstruction and camera calibration
JP4111660B2 (ja) 火災検出装置
TWI489861B (zh) 相機檢測方法與相機
CN111953935A (zh) 体温监管方法、装置、智慧屏和计算机可读存储介质
KR102487590B1 (ko) 얼굴 인식에 기초하여 촬영 대상의 온도를 측정하는 방법
CN114046768B (zh) 激光测距方法、装置、激光测距设备及存储介质
CN114419076B (zh) 一种数据处理方法及装置
TW201743286A (zh) 液面監測方法
WO2023273158A1 (zh) 车路协同中相机作用距离确定方法、装置和路侧设备
CN111297336B (zh) 一种基于红外和太赫兹的体温测量方法、装置及安检设备
CN104571724A (zh) 光学触控系统、触控检测方法及计算机程序产品

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: 20922752

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: 20922752

Country of ref document: EP

Kind code of ref document: A1