WO2021253187A1 - 红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质 - Google Patents

红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质 Download PDF

Info

Publication number
WO2021253187A1
WO2021253187A1 PCT/CN2020/096195 CN2020096195W WO2021253187A1 WO 2021253187 A1 WO2021253187 A1 WO 2021253187A1 CN 2020096195 W CN2020096195 W CN 2020096195W WO 2021253187 A1 WO2021253187 A1 WO 2021253187A1
Authority
WO
WIPO (PCT)
Prior art keywords
infrared image
gray
relationship
target
scale transformation
Prior art date
Application number
PCT/CN2020/096195
Other languages
English (en)
French (fr)
Inventor
张青涛
曹子晟
王黎
Original Assignee
深圳市大疆创新科技有限公司
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 深圳市大疆创新科技有限公司 filed Critical 深圳市大疆创新科技有限公司
Priority to PCT/CN2020/096195 priority Critical patent/WO2021253187A1/zh
Publication of WO2021253187A1 publication Critical patent/WO2021253187A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/42—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation

Definitions

  • This application relates to the field of image processing technology, and in particular to an infrared image processing method, image acquisition equipment, image processing equipment, and computer-readable storage media.
  • infrared thermal imaging technology has been widely used in people's lives. If the surface temperature of an object exceeds absolute zero, electromagnetic waves will be radiated. As the temperature changes, the radiation intensity and wavelength distribution characteristics of electromagnetic waves will also change. Electromagnetic waves with wavelengths between 0.75 ⁇ m and 1000 ⁇ m are called "infrared.” Infrared thermal imaging technology is the use of photoelectric technology to detect the infrared specific band signal of the thermal radiation of the object, and then convert the signal into images and graphics that can be visually distinguished by humans, and the temperature value can be further calculated. Infrared thermal imaging technology enables humans to surpass visual barriers, so that people can "see" the temperature distribution on the surface of the object.
  • the infrared device collects the infrared image, it will store or transmit two channels of image data, one is raw raw data in raw format, and the other is processed by image enhancement and pseudo-color mapping.
  • JPEG color image viewed by the human eye.
  • raw images can be used for accurate temperature measurement, and JPEG images can be viewed by human eyes.
  • the prior art method of storing or transmitting data in two or two formats takes up a large amount of storage resources and transmission resources, and is expensive.
  • one of the objectives of the present application is to provide an infrared image processing method, image acquisition device, image processing device, and computer-readable storage medium.
  • an embodiment of the present application provides an infrared image processing method, including:
  • the target infrared image is an image after gray-scale transformation processing
  • an embodiment of the present application provides an infrared image processing method, including:
  • gray-scale conversion processing on the original infrared image based on a gray-scale conversion relationship to obtain a target infrared image, where the gray-scale conversion relationship represents a gray-scale conversion relationship in the process of converting from the original infrared image to the target infrared image;
  • an image processing device including:
  • a memory for storing processor executable instructions
  • the processor calls the executable instruction, and when the executable instruction is executed, it is used to execute:
  • the target infrared image is an image after gray-scale transformation processing
  • an image acquisition device including:
  • a memory for storing processor executable instructions
  • the processor calls the executable instruction, and when the executable instruction is executed, it is used to execute:
  • the gray-scale conversion relationship represents the gray-scale conversion relationship in the process of converting from the original infrared image to the target infrared image
  • an embodiment of the present application provides a computer-readable storage medium having computer instructions stored thereon, and when the instructions are executed by a processor, the method described in any one of the first aspect or the second aspect is implemented.
  • the infrared image processing method, image acquisition device, image processing device, and computer-readable storage medium provided by the embodiments of the present application can acquire the gray scale transformation relationship of the target infrared image when acquiring the target infrared image, so as to be able to The original infrared image is restored from the target infrared image according to the gray-scale transformation relationship, where the original infrared image can be used for temperature measurement, and accurate temperature measurement results can be obtained.
  • the target infrared image has better results.
  • the display effect can be used for viewing; further, in the case of meeting the user’s viewing needs and ensuring accurate temperature measurement, this embodiment does not need to additionally store or transmit the original infrared image, but can obtain the infrared image from the target The original infrared image is restored in the process, which also effectively saves storage resources or transmission resources.
  • FIG. 1 is a schematic diagram of a scenario provided by an embodiment of the present application.
  • Fig. 2 is a schematic diagram of an infrared image processing flow provided by an embodiment of the present application
  • FIG. 3 is a schematic diagram of another infrared image processing flow provided by an embodiment of the present application.
  • Fig. 4 is a schematic structural diagram of an image acquisition device provided by an embodiment of the present application.
  • the embodiments of the present application provide an infrared image processing method.
  • an infrared image processing method When acquiring an infrared image of a target, in addition to being able to view and aim based on the target infrared image, it can also acquire the transformation from the original infrared image to the target.
  • the gray-scale transformation relationship of the infrared image so that the original infrared image can be restored from the target infrared image according to the gray-scale transformation relationship, and the temperature measurement is performed based on the original infrared image, which is beneficial to ensure the temperature measurement result.
  • this embodiment does not need to additionally store or transmit the original infrared image, but can restore the original infrared image from the target infrared image
  • the image also effectively saves storage resources or transmission resources.
  • the infrared image processing method of the embodiment of the present application can be applied to the fields of human body temperature measurement, industrial equipment detection, rescue scene, security inspection, power equipment maintenance diagnosis, and railway inspection, please refer to the figure 1.
  • the image acquisition device 10 (such as an infrared camera, or a device equipped with an infrared camera, such as a drone, etc.) acquires the original infrared image by shooting a target object (such as a human body, an object, an electric tower or a certain area), Then perform gray scale conversion processing on the infrared image to obtain the target infrared image, and then only store or transmit the target infrared image to the image processing device 20.
  • the image processing method can restore the original infrared image from the target infrared image, thereby obtaining the original infrared image used for temperature measurement and the target infrared image used for sighting, wherein the image processing device 20 can restore the original infrared image according to
  • the original infrared image is used to obtain the temperature information of the target object, so as to understand the condition of the target object based on the temperature information.
  • the image processing device 20 may be a terminal device (such as a mobile phone, a computer, a pad, a remote controller with a screen, etc.) capable of data processing.
  • the image acquisition device 10 and the image processing device 20 may be two separate devices, or the same device that integrates the image acquisition function and the image processing function, which is not done in this embodiment. Any restrictions.
  • FIG. 2 is a schematic diagram of an infrared image processing method provided by an embodiment of this application.
  • the method can be applied to an image acquisition device.
  • the image acquisition device includes, but is not limited to, an infrared camera.
  • Equipment such as man-machine, unmanned vehicle, unmanned ship, computer, tablet, mobile phone, personal digital assistant (PDA), server or cloud.
  • the method includes:
  • step S101 an original infrared image is acquired.
  • step S102 the original infrared image is subjected to gray-scale conversion processing based on the gray-scale conversion relationship to obtain a target infrared image, and the gray-scale conversion relationship represents the transformation from the original infrared image to the target infrared image. Gray scale transformation relationship.
  • step S103 the target infrared image is stored or transmitted.
  • the image acquisition device uses the gray-scale conversion relationship to perform gray-scale conversion processing on the original infrared image to obtain a target infrared image, and the target infrared image has a good display effect, and further Therefore, it is only necessary to store or transmit the infrared image of the target.
  • the image acquisition device does not need to store or transmit two infrared images.
  • the receiver can restore or obtain two types or formats of infrared images based on the target infrared image.
  • the target infrared image stored by the image acquisition device can also be used by other devices.
  • a display device can acquire and display the target infrared image stored by the image acquisition device.
  • FIG. 3 is a schematic diagram of another infrared image processing method provided by an embodiment of this application.
  • the method can be applied to image processing equipment including but not limited to drones, Equipment with image processing capabilities such as humans, vehicles, unmanned ships, computers, tablets, mobile phones, personal digital assistants (PDAs), servers or clouds.
  • the method includes:
  • step S201 an infrared image of the target is acquired; the infrared image of the target is an image that has undergone gray-scale transformation processing.
  • step S202 a grayscale transformation relationship of the target infrared image is acquired, and the grayscale transformation relationship represents a grayscale transformation relationship in the process of transforming from the original infrared image to the target infrared image.
  • step S203 the target infrared image is processed according to the gray scale transformation relationship to restore the original infrared image.
  • step S204 temperature measurement is performed according to the original infrared image.
  • the image processing device can restore the original infrared image from the target infrared image based on the gray-scale transformation relationship.
  • Infrared image where the original infrared image can be used for temperature measurement, and accurate temperature measurement results can be obtained, and the target infrared image has a better display effect and can be used for observation;
  • another channel of image data (original infrared image) can be recovered to obtain two channels of image data, which can meet the user's viewing needs and ensure accurate temperature measurement. Effectively save storage resources or transmission resources.
  • the embodiment shown in FIG. 2 (the process of acquiring the infrared image of the target) and the embodiment shown in FIG. 3 (the process of measuring the temperature) can be executed by the same device, that is, the image acquisition device
  • the image processing device and the image processing device may be the same device that integrates the image acquisition function and the image processing function.
  • the device after the device acquires the target infrared image according to the original infrared image, it only needs to store the target infrared image and all the The gray-scale transformation relationship, the stored infrared image of the target and the gray-scale transformation relationship can be acquired during the subsequent temperature measurement, and the original infrared image can be restored from the target infrared image according to the gray-scale transformation relationship.
  • the target infrared image stored by the image acquisition device can also be used by other devices, for example, a display device can acquire and display the stored target infrared image.
  • the embodiment described in Fig. 2 (the process of obtaining the infrared image of the target) and the embodiment shown in Fig. 3 (the process of measuring the temperature) can also be executed by different devices, that is, the image acquisition device and the image
  • the processing device may be two separate devices.
  • the image acquisition device that executes the embodiment shown in FIG. 2 may send the target infrared image to the image processing device that executes the embodiment shown in FIG. 3, and then the image processing device can The original infrared image is restored from the target infrared image according to the gray-scale transformation relationship, so as to obtain the original infrared image for temperature measurement and the target infrared image for sighting.
  • the gray-scale transformation relationship may be pre-stored on the image processing device, and the gray-scale transformation relationship does not need to be transmitted; or, the image acquisition device also
  • the gray scale conversion relationship may be transmitted to the image processing device when transmitting the target infrared image, and this embodiment does not impose any limitation on this.
  • the original infrared image may be an unprocessed image (raw image) taken by the image acquisition device; or, in order to further improve the accuracy of temperature measurement, the original infrared image may be a preprocessed image
  • the preprocessing includes, but is not limited to, correction processing (such as sensor responsivity correction, offset correction), noise removal processing, or dead pixel removal processing and other operations.
  • the grayscale transformation here includes but is not limited to operations such as contrast stretching or color inversion processing; in one example, the grayscale transformation processing on the original infrared image includes: performing grayscale transformation processing on the original infrared image Contrast stretch processing; that is, the target infrared image is an image after contrast stretch processing.
  • the image acquisition device may store all the infrared images of the target after acquiring the target infrared image.
  • the gray-scale transformation relationship and the target infrared image so that when temperature measurement is subsequently required, the image processing device can restore the original infrared image from the target infrared image based on the gray-scale transformation relationship to Perform temperature measurement based on the original infrared image.
  • there is no need to store the original infrared image and the original infrared image is restored from the target infrared image based on the gray-scale transformation relationship, which is beneficial to save storage resources.
  • the gray scale transformation relationship may be stored in an image file indicating the target infrared image, and subsequently, when performing temperature measurement, the image processing device may quickly read from the image file indicating the target infrared image.
  • the target infrared image and the gray scale transformation relationship are obtained, and storage resources are also effectively saved.
  • the gray scale transformation relationship used by different original infrared images may be the same or different.
  • the gray-scale transformation relationship only needs to be stored once, and the gray-scale transformation relationship is changed.
  • the gray scale transformation relationship may be stored in an image file indicating the target infrared image, so as to facilitate and quickly obtain the target infrared image and the corresponding gray scale transformation relationship.
  • the image acquisition device may transmit the target infrared image to the image processing device, and then the image processing device may The original infrared image is restored from the target infrared image according to the gray-scale transformation relationship to perform temperature measurement based on the original infrared image, thereby ensuring the accuracy of temperature measurement; in addition, compared to transmitting the original infrared image and the target infrared For images, only transmitting the gray scale transformation relationship and the target infrared image is also beneficial to saving transmission resources.
  • the gray scale transformation relationship used by different original infrared images may be the same or different.
  • the image acquisition device may notify the image processing device of the gray-scale transformation used in the original infrared image in advance. Relationship, or only need to send the gray-scale transformation relationship to the image processing device once, or the gray-scale transformation relationship is pre-stored on the image processing device, and then each subsequent time the target infrared image is acquired, It is only necessary to send the target infrared image without repeating the gray-scale transformation relationship, thereby further saving transmission resources. Then, after the image processing device receives the target infrared image, it can be based on the pre-received or pre-stored The gray scale transformation relationship restores the original infrared image from the target infrared image.
  • the image processing device sends the target infrared image and the gray scale transformation relationship.
  • the gray scale transformation relationship may be stored in an image file indicating the target infrared image, and the image processing device may, after receiving the image file indicating the target infrared image, start from the instruction
  • the gray-scale transformation relationship is quickly acquired from the image file of the target infrared image, and then the original infrared image is restored from the target infrared image according to the gray-scale transformation relationship.
  • the gray-scale transformation relationship includes at least one gray-scale transformation parameter, and the gray-scale transformation parameter may be determined according to the gray level of the original infrared image, so that different target infrared images obtained correspond to different The gray scale transformation parameters.
  • the gray scale transformation parameter suitable for itself can be obtained, so that the obtained target infrared image has a better look and feel.
  • the gray level distribution in the original infrared image can be counted through a gray level histogram, so as to determine the gray level transformation parameter according to the calculated gray level in the original infrared image;
  • Gray-level histogram is a function of gray-level, it represents the number of pixels with a certain gray-level in the image, and reflects the frequency of a certain gray-level in the image.
  • the image processing device of the embodiment shown in FIG. 3 can restore the original infrared image from the target infrared image based on the gray-scale transformation relationship, it is necessary to make all The gray-scale transformation relationship is reversible, so that the image processing device can perform reverse processing on the target infrared image according to the gray-scale transformation relationship to restore the original infrared image.
  • the gray-scale transformation relationship may be monotonic, for example, the gray-scale transformation relationship may have monotonic increase or monotonic decrease. , That is, in a specified interval, when the argument x of the function f(x) increases (or decreases) within its defined interval, the function value f(x) also increases (or decreases), here
  • the independent variable x of can refer to the pixel value of the pixel in the original infrared image
  • the function value f(x) can refer to the pixel value of the pixel in the target infrared image; in this way, when performing temperature measurement, the image processing The device can perform reverse processing on the target infrared image according to the gray-scale transformation relationship to restore the original infrared image.
  • the gray-scale transformation relationship may also be represented by a relationship table.
  • the relationship table indicates the correspondence between the pixel values of different pixels in the original infrared image and the pixel values of different pixels in the target infrared image. relation.
  • the relationship table includes the different pixel values a, b, and c of the 3 pixels in the original infrared image and the different pixel values A, B, and C of the 3 pixels in the target infrared image, and the pixel values a, b, and c.
  • pixel values A, B, and C are different from each other, where a corresponds to A, b corresponds to B, and c corresponds to C.
  • a probability accumulation curve can be obtained by a histogram equalization method, or a Gaussian curve obtained by using a Gaussian function. Do not make any restrictions.
  • the image acquisition device when the image acquisition device performs gray-scale conversion processing on the original infrared image based on the gray-scale conversion relationship, it may perform global gray-scale conversion on the original infrared image based on the global conversion relationship. Processing, and/or (and/or representing two or one of both), performing local gray scale transformation processing on the original infrared image based on a local transformation relationship.
  • the global grayscale transformation relationship indicates that the target infrared image has undergone global grayscale transformation processing
  • the local grayscale transformation relationship indicates that the target infrared image has undergone local grayscale transformation processing.
  • the global transformation relationship and the local transformation relationship are both reversible.
  • the original infrared image may be selected to perform global grayscale transformation processing and local grayscale transformation processing, or one of the two, according to actual needs, so as to meet the individual needs of users.
  • the image acquisition device when performing local grayscale transformation processing on the original infrared image, the image acquisition device needs to acquire the area that undergoes local grayscale transformation processing in the original infrared image, and then according to the area and the corresponding local grayscale A transformation relationship is used to obtain a position correspondence relationship; the position correspondence relationship indicates different local grayscale transformation relationships corresponding to different regions in the target infrared image.
  • the image processing device of the embodiment shown in FIG. 3 can determine the area of the target infrared image for local gray-scale transformation processing according to the position correspondence, so that the target infrared image can be obtained from Correctly restore the original infrared image.
  • the position correspondences corresponding to different target infrared images may be the same or different.
  • the image acquisition device only needs to store the position correspondence once, and compare the position correspondence with the corresponding one or more target infrared images
  • the association can effectively save storage space; and/or, the image acquisition device of the embodiment shown in FIG. 2 only needs to send the position correspondence once to the image processing device of the embodiment shown in FIG.
  • the target infrared image is acquired for the second time, only the target infrared image needs to be sent to the image processing device without repeating sending the position correspondence, which is beneficial to saving transmission resources.
  • the image acquisition device needs to store the position correspondences corresponding to the target infrared images each time after acquiring the position correspondences And/or, the image acquisition device of the embodiment shown in FIG. 2 sends the position correspondence corresponding to the target infrared image to the image processing device of the embodiment shown in FIG. 3.
  • the position correspondence can be stored in an image file indicating the target infrared image, so that in the subsequent temperature measurement process, the image processing device of the embodiment shown in FIG.
  • the position correspondence is quickly acquired in the image file of the target infrared image, and the storage space is also effectively saved.
  • the target infrared image is an image that has undergone global grayscale transformation processing and/or local grayscale transformation processing
  • the target infrared image corresponds to a global grayscale transformation relationship and grayscale Degree transformation relationship
  • the global grayscale transformation relationship indicates that the target infrared image has undergone global grayscale transformation processing
  • the local grayscale transformation relationship indicates that the target infrared image has undergone local grayscale transformation processing.
  • the image processing device needs to determine a target area corresponding to the local grayscale transformation relationship in the target infrared image, and then according to the local grayscale transformation relationship.
  • the degree transformation relationship processes the target area in the target infrared image to ensure the accuracy of the restored original infrared image.
  • the image acquisition device of the embodiment shown in FIG. 2 acquires a position correspondence relationship that represents different local grayscale transformation relationships corresponding to different regions in the target infrared image.
  • the image processing device may obtain the position correspondence relationship.
  • the position correspondence relationship may be obtained from an image file indicating the target infrared image, and then based on the partial gray Degree transformation relationship and the position correspondence relationship of the target infrared image to determine the target area, so that the image processing device can process the target area in the target infrared image according to the local gray-scale transformation relationship to ensure The accuracy of the restored original infrared image.
  • the image acquisition device may also perform pseudo-color mapping processing on the infrared image after gray-scale transformation processing according to the pseudo-color mapping relationship, so as to obtain the The target infrared image, and the pseudo-color mapping relationship represents the color correspondence relationship between the original infrared image and the target infrared image.
  • the pseudo-color mapping relationship is also reversible, so that the original infrared image can be restored from the target infrared image based on the pseudo-color mapping relationship later.
  • the embodiment of the present application does not impose any restriction on the representation form of the pseudo-color mapping relationship, and specific settings can be made according to actual application scenarios.
  • the pseudo-color mapping relationship may be expressed in a function equation relationship.
  • this embodiment does not impose any restriction on the specific function expression form, and specific settings can be made according to actual application scenarios.
  • the pseudo-color mapping relationship may also be represented by a relationship table, and the relationship table indicates the difference between the pixel values of different pixels in the original infrared image and the pixel values of different pixels in the target infrared image. Correspondence of colors.
  • the relationship table includes the different gray values of 3 pixels in the original infrared image, which are 100, 120, and 150, and the different RGB values of 3 pixels in the target infrared image, which are (90, 180, 60). , (108,216,36) and (135,270,45), where 100 corresponds to (90,180,60), 120 corresponds to (108,216,36), and 130 corresponds to (135,270,45).
  • it can also be represented by a change curve that reflects the pseudo-color mapping relationship, which is not limited in this embodiment.
  • the pseudo-color mapping relationship corresponding to different target infrared images may be the same or different.
  • the image acquisition device of the embodiment shown in FIG. 2 only needs to store the pseudo-color mapping relationship once, and map the pseudo-color The relationship is associated with the corresponding one or more target infrared images, which can effectively save storage space; and/or, the image acquisition device of the embodiment shown in FIG. 2 only needs to send the pseudo-color mapping relationship once to FIG. 3
  • the image processing device of the illustrated embodiment then only needs to send the target infrared image to the image processing device every time the target infrared image is subsequently acquired without repeating the transmission of the pseudo-color mapping relationship, which is conducive to saving Transmission resources.
  • the image acquisition device of the embodiment shown in FIG. 2 needs to store the pseudo-color mapping relationship each time after acquiring the pseudo-color mapping relationship.
  • the pseudo-color mapping relationship corresponding to the target infrared image; and/or, the image acquisition device of the embodiment shown in FIG. 2 sends the pseudo-color mapping relationship corresponding to the target infrared image to the embodiment shown in FIG. 3 Image processing equipment.
  • the pseudo-color mapping relationship can be stored in an image file indicating the target infrared image, so that the pseudo-color mapping relationship can be quickly obtained in the subsequent temperature measurement process, and it is also effective in saving Up storage space.
  • the image acquisition device can store the designated identifier for indicating the pseudo-color mapping relationship in the image file indicating the target infrared image.
  • the image acquisition device can store the designated identifier for indicating the pseudo-color mapping relationship in the image file indicating the target infrared image.
  • the designated identifier is stored in the image file of the infrared image. In the image file indicating the target infrared image, storing the designated identifier can further save storage resources or transmission resources.
  • the image processing device acquires the pseudo-color mapping relationship of the target infrared image, and the pseudo-color mapping relationship represents the relationship between the original infrared image and the target infrared image And then restore the target infrared image according to the pseudo-color mapping relationship.
  • the image processing device first uses a pseudo-color mapping relationship to perform preliminary restoration processing on the target infrared image, and then uses a gray scale transformation relationship to perform further restoration processing on the target infrared image after the preliminary restoration processing, so as to obtain Original infrared image of temperature measurement.
  • the image processing device may obtain the pseudo-color mapping relationship from an image file indicating the target infrared image.
  • different types of pseudo-color mapping relationships are pre-stored on the image processing device, and different pseudo-color mapping relationships correspond to different designated identifiers, wherein the designated identifiers are used to indicate the pseudo-color mapping relationships If stored in an image file indicating the target infrared image, the image processing device can obtain the pseudo-color mapping relationship of the target infrared image according to the designated identifier.
  • the image processing device may obtain a temperature measurement value according to the original infrared image and a pre-stored temperature correspondence; the temperature correspondence characterizes the Different temperature values corresponding to different pixel values in the original infrared image.
  • the pixel value of the pixel in the original infrared image maintains a correct correspondence with the temperature value, and therefore, a correct temperature measurement value can be obtained based on the original infrared image.
  • this embodiment also provides an image acquisition device 30.
  • the image acquisition device 30 includes: a processor 31; and a memory 32 for storing instructions executable by the processor 31.
  • the processor 31 calls the executable instruction, and when the executable instruction is executed, it is used to execute: obtain a target infrared image; the target infrared image is an image after gray-scale transformation processing; and obtain the target
  • the gray-scale transformation relationship of the infrared image represents the gray-scale transformation relationship in the process of transforming from the original infrared image to the target infrared image; the target infrared image is reversed according to the gray-scale transformation relationship Processing to restore the original infrared image; temperature measurement is performed according to the original infrared image.
  • the processor 31 may be a central processing unit (Central Processing Unit, CPU), other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), Ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the memory 32 stores an executable instruction computer program of the infrared image processing method.
  • the memory 32 may include at least one type of storage medium.
  • the storage medium includes a flash memory, a hard disk, a multimedia card, and a card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), Magnetic storage, magnetic disks, optical disks, etc.
  • the image capture device 30 may cooperate with a network storage device that performs the storage function of the memory 32 through a network connection.
  • the memory 32 may be an internal storage unit of the image acquisition device 30, such as a hard disk or a memory of the image acquisition device 30.
  • the memory 32 may also be an external storage device of the image capture device 30, such as a plug-in hard disk equipped on the image capture device 30, a Smart Media Card (SMC), a Secure Digital (SD) card, and a flash memory card. (Flash Card) and so on.
  • the memory 32 may also include both an internal storage unit of the image acquisition device 30 and an external storage device.
  • the memory 32 is used to store computer programs and other programs and data required by the device.
  • the memory 32 can also be used to temporarily store data that has been output or will be output.
  • the various embodiments described herein may be implemented using a computer-readable medium such as computer software, hardware, or any combination thereof.
  • the implementation described here can be implemented by using application-specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays ( FPGA), a processor, a controller, a microcontroller, a microprocessor, and an electronic unit designed to perform the functions described herein are implemented.
  • ASIC application-specific integrated circuits
  • DSP digital signal processors
  • DSPD digital signal processing devices
  • PLD programmable logic devices
  • FPGA field programmable gate arrays
  • a processor a controller
  • microcontroller programmable gate array
  • FPGA field programmable gate arrays
  • the software code can be implemented by a software application (or program) written in any suitable programming language, and the software code can be stored in a memory and executed by the controller.
  • the gray scale transformation relationship is stored in an image file indicating the target infrared image.
  • the gray scale transformation relationship is reversible.
  • the gray scale transformation relationship is monotonic.
  • the grayscale transformation relationship includes at least one of the following: a global grayscale transformation relationship or a local grayscale transformation relationship.
  • the global grayscale transformation relationship indicates that the target infrared image has undergone global grayscale transformation processing; the local grayscale transformation relationship indicates that the target infrared image has undergone local grayscale transformation processing.
  • the processor 31 is further configured to: in the target infrared image, determine a target corresponding to the local gray scale transformation relationship Region; processing the target region in the target infrared image according to the local gray scale transformation relationship.
  • the target area is determined based on the local gray scale transformation relationship and the position correspondence relationship of the target infrared image, and the position correspondence relationship represents different parts corresponding to different areas in the target infrared image. Gray scale transformation relationship.
  • the position correspondence is stored in an image file indicating the target infrared image.
  • the gray-scale transformation relationship includes at least one gray-scale transformation parameter; different target infrared images correspond to different gray-scale transformation parameters.
  • the gray scale transformation parameter is determined according to the gray scale of the original infrared image.
  • the processor is further configured to: obtain a pseudo-color mapping relationship of the target infrared image; the pseudo-color mapping relationship represents the color correspondence relationship between the original infrared image and the target infrared image ; Perform restoration processing on the target infrared image according to the pseudo-color mapping relationship.
  • the pseudo-color mapping relationship is stored in an image file indicating the target infrared image.
  • the designated identifier for indicating the pseudo-color mapping relationship is stored in an image file indicating the target infrared image; the processor is further configured to: obtain the target infrared image according to the designated identifier The pseudo-color mapping relationship.
  • the original infrared image is an image that has been preprocessed; the preprocessing includes at least one of the following operations: correction processing, noise removal processing, or dead pixel removal processing.
  • the processor 31 when performing temperature measurement based on the original infrared image, is specifically configured to: obtain a temperature measurement value according to the original infrared image and a pre-stored temperature correspondence; the temperature correspondence Characterizing different temperature values corresponding to different pixel values in the original infrared image.
  • the target infrared image is an image after contrast stretching processing.
  • the image acquisition device further includes a communication module configured to receive the target infrared image and/or the gray scale transformation relationship.
  • this embodiment also provides an image processing device, including: a processor; and a memory for storing executable instructions of the processor.
  • the processor calls the executable instruction, and when the executable instruction is executed, it is used to execute: obtain the original infrared image; perform gray-scale conversion processing on the original infrared image based on the gray-scale conversion relationship to obtain the target infrared Image, the gray-scale transformation relationship represents the gray-scale transformation relationship in the process of transforming from the original infrared image to the target infrared image; storing or transmitting the target infrared image.
  • the gray scale transformation relationship is stored in an image file indicating the target infrared image.
  • the gray scale transformation relationship is reversible.
  • the gray scale transformation relationship is monotonic.
  • the processor is further configured to: store the gray scale transformation relationship in the memory.
  • it further includes a communication module; the communication module is configured to: transmit the gray scale transformation relationship.
  • the processor is specifically configured to: perform global grayscale transformation processing on the original infrared image based on a global transformation relationship, and/or perform local grayscale transformation on the original infrared image based on a local transformation relationship deal with.
  • the processor is further configured to: obtain a region in the original infrared image subjected to local gray scale transformation processing; obtain a position correspondence relationship according to the region and the corresponding local gray scale transformation relationship; The position correspondence relationship indicates different local gray scale transformation relationships corresponding to different regions in the target infrared image.
  • the position correspondence is stored in an image file indicating the target infrared image.
  • the gray-scale transformation relationship includes at least one gray-scale transformation parameter; different target infrared images correspond to different gray-scale transformation parameters.
  • the gray scale transformation parameter is determined according to the gray scale of the original infrared image.
  • the processor is further configured to: perform pseudo-color mapping processing on the infrared image processed by gray-scale transformation according to the pseudo-color mapping relationship; the pseudo-color mapping relationship represents the original infrared image and the The color correspondence between target infrared images.
  • the pseudo-color mapping relationship is stored in an image file indicating the target infrared image.
  • different pseudo-color mapping relationships correspond to different designated identifiers; the designated identifiers used to indicate the pseudo-color mapping relationships are stored in an image file indicating the target infrared image.
  • the original infrared image is an image that has been preprocessed; the preprocessing includes at least one of the following operations: correction processing, noise removal processing, or dead pixel removal processing.
  • the processor is specifically configured to: perform contrast stretching processing on the original infrared image.
  • non-transitory computer-readable storage medium including instructions, such as a memory including instructions, which may be executed by a processor of an electronic device to complete the foregoing method.
  • the non-transitory computer-readable storage medium may be ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
  • the electronic device when the instructions in the storage medium are executed by the processor, the electronic device can execute the aforementioned infrared image processing method.

Abstract

一种红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质，所述方法包括：获取目标红外图像；所述目标红外图像为经过灰度变换处理后的图像；获取所述目标红外图像的灰度变换关系，所述灰度变换关系表征从原始红外图像变换至所述目标红外图像过程中的灰度变换关系；根据所述灰度变换关系对所述目标红外图像进行处理，还原出所述原始红外图像；根据所述原始红外图像进行温度测量。本实施例能够从所述目标红外图像中还原出所述原始红外图像，保证温度测量的准确性，只需存储或传输目标红外图像，有效节省了存储资源或者传输资源。

Description

红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质 技术领域
本申请涉及图像处理技术领域，具体而言，涉及一种红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质。
背景技术
随着技术的发展，红外热成像技术已广泛应用于人们的生活中。物体表面温度如果超过绝对零度即会辐射出电磁波，随着温度变化，电磁波的辐射强度与波长分布特性也随之改变，波长介于0.75μm到1000μm间的电磁波称为“红外线”。红外热成像技术就是运用光电技术检测物体热辐射的红外线特定波段信号，然后将该信号转换成可供人类视觉分辨的图像和图形，并可以进一步计算出温度值。红外热成像技术使人类超越了视觉障碍，由此人们可以“看到”物体表面的温度分布状况。
通常，红外设备在采集了红外图像后，会存储或传输两路图像数据，一路为raw格式的未经加工处理的原始数据，另一路是经过了图像增强、伪彩映射等处理得到的可供人眼观瞄的JPEG彩色图像。其中，raw图像可供进行精准测温，JPEG图像可供人眼观看，现有技术这种存储或传输两路或两种格式的数据的方式占用了大量的存储资源及传输资源，开销大。
发明内容
有鉴于此，本申请的目的之一是提供一种红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质。
第一方面，本申请实施例提供了一种红外图像处理方法，包括：
获取目标红外图像；所述目标红外图像为经过灰度变换处理后的图像；
获取所述目标红外图像的灰度变换关系，所述灰度变换关系表征从原始红外图像变换至所述目标红外图像过程中的灰度变换关系；
根据所述灰度变换关系对所述目标红外图像进行处理，还原出所述原始红外图像；
根据所述原始红外图像进行温度测量。
第二方面，本申请实施例提供了一种红外图像处理方法，包括：
获取原始红外图像；
基于灰度变换关系对所述原始红外图像进行灰度变换处理，获取目标红外图像， 所述灰度变换关系表征从所述原始红外图像变换至所述目标红外图像过程中的灰度变换关系；
存储或传输所述目标红外图像。
第三方面，本申请实施例提供了一种图像处理设备，包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器调用所述可执行指令，当可执行指令被执行时，用于执行：
获取目标红外图像；所述目标红外图像为经过灰度变换处理后的图像；
获取所述目标红外图像的灰度变换关系，所述灰度变换关系表征从原始红外图像变换至所述目标红外图像过程中的灰度变换关系；
根据所述灰度变换关系对所述目标红外图像进行反向处理，还原出所述原始红外图像；
根据所述原始红外图像进行温度测量。
第四方面，本申请实施例提供了一种图像采集设备，包括：
处理器；
用于存储处理器可执行指令的存储器；
其中，所述处理器调用所述可执行指令，当可执行指令被执行时，用于执行：
获取原始红外图像；
基于灰度变换关系对所述原始红外图像进行灰度变换处理，获取目标红外图像，所述灰度变换关系表征从所述原始红外图像变换至所述目标红外图像过程中的灰度变换关系；
存储或传输所述目标红外图像。
第五方面，本申请实施例提供了一种计算机可读存储介质，其上存储有计算机指令，该指令被处理器执行时实现第一方面或第二方面任意一项所述的方法。
本申请实施例所提供的一种红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质，在获取目标红外图像时，能够获取所述目标红外图像的灰度变换关系，从而能够根据所述灰度变换关系从所述目标红外图像中还原出所述原始红外图像，其中，所述原始红外图像可用于测温，能够获得精准的测温结果，所述目标红外图像具有较好的显示效果，可供进行观瞄；进一步地，在满足用户的观瞄需求以及保证精准测温的情况下，本实施例无需再另外存储或者传输原始红外图像，而能够从所述目标红外图像中还原出所述原始红外图像，也有效节省了存储资源或者传输资 源。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例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是本申请一个实施例提供的一种场景示意图；
图2是本申请一个实施例提供的一种红外图像处理的流程示意图；
图3是本申请一个实施例提供的另一种红外图像处理的流程示意图；
图4是本申请一个实施例提供的一种图像采集设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。。
针对于相关技术中的问题，本申请实施例提供了一种红外图像处理方法，在获取目标红外图像时，除了能够基于目标红外图像进行观瞄，还能够获取从原始红外图像变换至所述目标红外图像的灰度变换关系，从而能够根据所述灰度变换关系从所述目标红外图像中还原出所述原始红外图像，并基于所述原始红外图像进行测温，有利于保证温度测量结果的准确性；进一步地，在满足用户的观瞄需求以及保证精准测温的情况下，本实施例无需再另外存储或者传输原始红外图像，而能够从所述目标红外图像中还原出所述原始红外图像，也有效节省了存储资源或者传输资源。
在一示例性的应用场景中，本申请实施例的红外图像处理方法可应用于人体测温、工业设备检测、救援场景、安防巡检、电力设备检修诊断以及铁路巡检等领域，请参阅图1，图像采集设备10(比如红外相机，或者搭载有红外相机的设备，例如无人机等)通过对目标对象(比如人体、物体、电塔或者某一个区域)进行拍摄，获取原始红外图像，再对红外图像进行灰度变换处理以获取目标红外图像，然后只存储或将目标红外图像传输给图像处理设备20，图像处理设备20在获取所述目标红外图像后，基于本申请实施例的红外图像处理方法能够从所述目标红外图像中还原出所述原始红外图像，从而得到用于测温的原始红外图像以及用于观瞄的目标红外图像，其中，所述图像处理设备20可根据还原的原始红外图像来获取目标对象的温度信息，以便基于 温度信息来了解目标对象的状况。图像处理设备20可以是具备数据处理能力的终端设备(例如手机、电脑、pad、带屏遥控器等)。
可以理解的是，所述图像采集设备10和所述图像处理设备20可以是独立分开的两个设备，也可以是集成图像采集功能和图像处理功能的同一个设备，本实施例对此不做任何限制。
请参阅图2，为本申请实施例提供的一种红外图像处理方法的示意图，所述方法可应用于图像采集设备上，所述图像采集设备包括但不限于红外相机，搭载有红外相机的无人机、无人车、无人船、电脑、平板、手机、个人数字助理(PDA)、服务器或者云端等设备。所述方法包括：
在步骤S101中，获取原始红外图像。
在步骤S102中，基于灰度变换关系对所述原始红外图像进行灰度变换处理，获取目标红外图像，所述灰度变换关系表征从所述原始红外图像变换至所述目标红外图像过程中的灰度变换关系。在步骤S103中，存储或传输所述目标红外图像。
图2所示的实施例中，所述图像采集设备使用所述灰度变换关系对所述原始红外图像进行灰度变换处理从而得到目标红外图像，所述目标红外图像具有良好的显示效果，进一步地，只需存储或传输所述目标红外图像。本申请实施例中，图像采集设备无需存储或传输两路红外图像，通过传输一路数据(目标红外图像)即可实现接收端可以基于目标红外图像恢复或获得两种类型或格式的红外图像，减少了存储或传输资源；另外，所述图像采集设备存储的所述目标红外图像也可以供其他设备使用，比如显示设备可以获取所述图像采集设备存储的目标红外图像并进行显示。
相应地，请参阅图3，为本申请实施例提供的另一种红外图像处理方法的示意图，所述方法可应用于图像处理设备上，所述图像处理设备包括但不限于无人机、无人车、无人船、电脑、平板、手机、个人数字助理(PDA)、服务器或者云端等具备图像处理能力的设备。所述方法包括：
在步骤S201中，获取目标红外图像；所述目标红外图像为经过灰度变换处理后的图像。
在步骤S202中，获取所述目标红外图像的灰度变换关系，所述灰度变换关系表征从原始红外图像变换至所述目标红外图像过程中的灰度变换关系。
在步骤S203中，根据所述灰度变换关系对所述目标红外图像进行处理，还原出所述原始红外图像。
在步骤S204中，根据所述原始红外图像进行温度测量。
图3所示的实施例中，所述图像处理设备在获取所述目标红外图像以及所述灰度变换关系之后，能够基于所述灰度变换关系从所述目标红外图像中还原出所述原始红外图像，其中，所述原始红外图像可用于测温，能够获得精准的测温结果，而所述目标红外图像具有较好的显示效果，可供进行观瞄；可见，本申请实施例在获取一路图像数据(即目标红外图像)的情况下，可以恢复出另一路图像数据(原始红外图像)，从而得到两路图像数据，在满足用户的观瞄需求以及保证精准测温的情况下，也有效节省了存储资源或者传输资源。
可以理解的是，图2所述的实施例(获取所述目标红外图像的过程)以及图3所示的实施例(测温的过程)可以由同一个设备来执行，即所述图像采集设备和所述图像处理设备可以是集成图像采集功能和图像处理功能的同一个设备，比如所述设备在根据所述原始红外图像获取所述目标红外图像之后，只需存储所述目标红外图像以及所述灰度变换关系，后续在进行测温的时候可以获取存储的所述目标红外图像和所述灰度变换关系，根据所述灰度变换关系从所述目标红外图像中还原出所述原始红外图像，无需存储所述原始红外图像，有利于节省存储资源。另外，所述图像采集设备存储的所述目标红外图像也可以供其他设备使用，比如显示设备可以获取存储的目标红外图像并进行显示。
图2所述的实施例(获取所述目标红外图像的过程)以及图3所示的实施例(测温的过程)也可以由不同的设备来执行，即所述图像采集设备和所述图像处理设备可以是独立分开的两个设备，比如可以由执行图2所示实施例的图像采集设备将所述目标红外图像发送给执行图3所示实施例的图像处理设备，然后图像处理设备能够根据灰度变换关系从所述目标红外图像中还原出所述原始红外图像，从而得到用于测温的原始红外图像以及用于观瞄的目标红外图像。其中，如果不同的原始红外图像均采用相同的灰度变换关系，则所述图像处理设备上可以预存所述灰度变换关系，无需传输所述灰度变换关系；或者，所述图像采集设备也可以在传输所述目标红外图像时一并将所述灰度变换关系传输给所述图像处理设备，本实施例对此不做任何限制。
其中，所述原始红外图像可以是所述图像采集设备拍摄的未经过处理的图像(raw图像)；或者，为了进一步提高温度测量的准确性，所述原始红外图像可以是经过预处理后的图像，这里的预处理包括但不限于矫正处理(如传感器响应率矫正、偏置矫正)、噪声去除处理或者坏点去除处理等操作。
可选地，这里的灰度变换包括但不限于对比度拉伸或者反色处理等操作；在一个例子中，所述对所述原始红外图像进行灰度变换处理包括：对所述原始红外图像进行 对比度拉伸处理；即是说，所述目标红外图像为经过对比度拉伸处理后的图像。
在一种实现方式中，所述图像采集设备和所述图像处理设备是集成图像采集功能和图像处理功能的同一个设备时，所述图像采集设备在获取所述目标红外图像之后，可以存储所述灰度变换关系和所述目标红外图像，以便在后续需要进行测温时，所述图像处理设备能够基于所述灰度变换关系从所述目标红外图像中还原出所述原始红外图像，以基于所述原始红外图像进行测温。本实施例中，无需存储所述原始红外图像，基于所述灰度变换关系从所述目标红外图像中还原出所述原始红外图像，有利于节省存储资源。
可选地，所述灰度变换关系可被存储于指示所述目标红外图像的图像文件中，后续在进行测温时，所述图像处理设备可以从指示所述目标红外图像的图像文件快速读取到所述目标红外图像以及所述灰度变换关系，而且也有效节省了存储资源。
其中，不同的原始红外图像所使用的灰度变换关系可以相同也可以不同。可选地，如果使用相同的灰度变换关系对不同的原始红外图像进行灰度变换处理获取不同的目标红外图像，则只需存储一次所述灰度变换关系，并且将所述灰度变换关系与相应的一个或多个目标红外图像进行关联，从而能够进一步节省存储空间。可选地，如果使用不同的灰度变换关系对不同的原始红外图像进行灰度变换处理获取不同的目标红外图像，则需要存储不同的目标红外图像及对应的灰度变换关系。作为其中一种实现方式，可以将所述灰度变换关系存储于指示所述目标红外图像的图像文件中，从而方便快速获取所述目标红外图像及对应的灰度变换关系。
在另一种实现方式中，如果所述图像采集设备和所述图像处理设备是独立的不同设备，则所述图像采集设备可以将所述目标红外图像传输给图像处理设备，然后图像处理设备可以根据灰度变换关系从所述目标红外图像中还原出所述原始红外图像，以基于所述原始红外图像进行测温，从而保证温度测量的准确性；另外，相对于传输原始红外图像和目标红外图像，只传输所述灰度变换关系和所述目标红外图像也有利于节省传输资源。
其中，不同的原始红外图像所使用的灰度变换关系可以相同也可以不同。
可选地，如果使用相同的灰度变换关系对不同的原始红外图像进行灰度变换处理获取不同的目标红外图像，图像采集设备可以预先通知图像处理设备所述原始红外图像所使用的灰度变换关系，或者只需向所述图像处理设备发送一次所述灰度变换关系，或者所述图像处理设备上预存有所述灰度变换关系，然后在后续每次获取到所述目标红外图像时，只需发送所述目标红外图像而无需再重复发送所述灰度变换关系，从而 进一步节省传输资源，然后所述图像处理设备在接收到所述目标红外图像之后，可以根据预先收到或者预存的灰度变换关系从所述目标红外图像中还原出原始红外图像。
可选地，如果使用不同的灰度变换关系对不同的原始红外图像进行灰度变换处理获取不同的目标红外图像，则所述图像采集设备在每次获取到所述目标红外图像时，需要向图像处理设备发送所述目标红外图像以及所述灰度变换关系。在一种实现方式中，所述灰度变换关系可被存储于指示所述目标红外图像的图像文件中，则图像处理设备在接收指示所述目标红外图像的图像文件后，可以从指示所述目标红外图像的图像文件中快速获取所述灰度变换关系，然后根据所述灰度变换关系从所述目标红外图像中还原出原始红外图像。
在一种实现方式中，所述灰度变换关系包括至少一个灰度变换参数，所述灰度变换参数可以根据所述原始红外图像的灰度级所确定，使得获取的不同目标红外图像对应不同的灰度变换参数。本实施例中，可以基于原始红外图像的灰度级获取适合于自身的灰度变换参数，使得获取的目标红外图像具备更佳的观感效果。在一个例子中，可以通过灰度直方图来统计所述原始红外图像中灰度级分布情况，从而根据统计到的所述原始红外图像中的灰度级来确定所述灰度变换参数；其中，灰度直方图是灰度级的函数，它表示图像中具有某种灰度级的像素的个数，反映了图像中某种灰度级出现的频率。
进一步地，为了保证在后续的测温过程中，图3所示实施例的图像处理设备能够基于所述灰度变换关系从所述目标红外图像中还原出所述原始红外图像，则需要使所述灰度变换关系是具有可逆性的，这样所述图像处理设备才可以根据所述灰度变换关系对所述目标红外图像进行反向处理，还原出所述原始红外图像。
则在一种实现方式中，为了保证所述灰度变换关系的可逆性，则所述灰度变换关系可以是具备单调性的，比如所述灰度变换关系是具备单调递增性或者单调递减性，即在一个指定区间内，当函数f(x)的自变量x在其定义区间内增大(或减小)时，函数值f(x)也随着增大(或减小)，这里的自变量x可以指所述原始红外图像中的像素的像素值，函数值f(x)可以指所述目标红外图像中的像素的像素值；这样，在进行测温时，所述图像处理设备才可以根据所述灰度变换关系对所述目标红外图像进行反向处理，还原出所述原始红外图像。
可以理解的是，本申请实施例对于所述灰度变换关系的表示形式不做任何限制，可依据实际应用场景进行具体设置。
在一个例子中，所述灰度变换关系可以以函数等式关系表示，如函数y＝k*x+b， 其中，x为所述原始红外图像，k、b为灰度变换参数，可以根据所述原始红外图像的灰度级所确定，从而得到y，即所述目标红外图像，当然，本实施例对于具体的函数表示形式不作任何限制，可依据实际应用场景进行具体设置。
在一个例子中，所述灰度变换关系也可以以关系表来表示，所述关系表中指示所述原始红外图像中不同像素的像素值与所述目标红外图像中不同像素的像素值的对应关系。比如关系表中包括所述原始红外图像中3个像素不同的像素值a、b、c以及所述目标红外图像中3个像素不同的像素值A、B、C，像素值a、b、c和像素值A、B、C互不相同，其中，a与A对应、b与B对应、c与C对应。
在一个例子中，还可以通过体现灰度变换关系的变化曲线来表示，比如可以通过直方图均衡方法来得到一条概率累积曲线，或者也可以是使用高斯函数得到的高斯曲线，本实施例对此不做任何限制。
在图2所示的实施例中，所述图像采集设备在基于灰度变换关系对所述原始红外图像进行灰度变换处理时，可以基于全局变换关系对所述原始红外图像进行全局灰度变换处理，和/或(和/或表示两者或两者之一)，基于局部变换关系对所述原始红外图像进行局部灰度变换处理。可见，所述全局灰度变换关系指示所述目标红外图像经过全局灰度变换处理；所述局部灰度变换关系指示所述目标红外图像经过局部灰度变换处理。其中，所述全局变换关系以及所述局部变换关系均具备可逆性。则在本实施例中，可以根据实际需要，选择对所述原始红外图像进行全局灰度变换处理和局部灰度变换处理，或者两者之一，从而满足用户的个性化需求。
其中，当对所述原始红外图进行局部灰度变换处理时，所述图像采集设备需要获取所述原始红外图像中进行局部灰度变换处理的区域，然后根据所述区域以及相应的局部灰度变换关系，获取位置对应关系；所述位置对应关系指示所述目标红外图像中不同的区域对应的不同局部灰度变换关系。这样，在后续进行测温时，图3所示实施例的图像处理设备能够根据所述位置对应关系确定所述目标红外图像中进行局部灰度变换处理的区域，从而能够从所述目标红外图像中正确还原出所述原始红外图像。
其中，不同的目标红外图像对应的所述位置对应关系可以相同也可以不同。
可选地，如果不同的目标红外图像对应相同的位置对应关系，则所述图像采集设备只需存储一次所述位置对应关系，并且将所述位置对应关系与相应的一个或多个目标红外图像进行关联，从而能够有效节省存储空间；和/或，图2所述的实施例的图像采集设备只需发送一次所述位置对应关系给图3所示实施例的图像处理设备，然后在后续每次获取到所述目标红外图像时，只需给图像处理设备发送所述目标红外图像而 无需再重复发送所述位置对应关系，从而有利于节省传输资源。
可选地，如果不同的目标红外图像对应不同的位置对应关系，则所述图像采集设备在每次获取所述位置对应关系之后，均需要存储与所述目标红外图像对应的所述位置对应关系；和/或，图2所述的实施例的图像采集设备将与所述目标红外图像对应的所述位置对应关系发送给图3所示实施例的图像处理设备。
作为其中一种实现方式，所述位置对应关系可被存储于指示所述目标红外图像的图像文件中，这样后续在测温过程中，图3所示实施例的图像处理设备可以从指示所述目标红外图像的图像文件中快速获取所述位置对应关系，而且也有效节省了存储空间。
相应地，在图3所示的实施例中，所述目标红外图像是经过全局灰度变换处理和/或局部灰度变换处理的图像，所述目标红外图像对应有全局灰度变换关系和灰度变换关系，所述全局灰度变换关系指示所述目标红外图像经过全局灰度变换处理；所述局部灰度变换关系指示所述目标红外图像经过局部灰度变换处理。
其中，当所述灰度变换关系为局部灰度变换关系时，所述图像处理设备需要在所述目标红外图像中确定与所述局部灰度变换关系对应的目标区域，然后根据所述局部灰度变换关系对所述目标红外图像中的所述目标区域进行处理，保证还原的所述原始红外图像的准确性。
进一步地，基于上述的描述，图2所示实施例的图像采集设备获取有位置对应关系，所述位置对应关系表征所述目标红外图像中不同的区域对应的不同局部灰度变换关系，则在图3所示的实施例中，所述图像处理设备可以获取所述位置对应关系，作为例子，可以从指示所述目标红外图像的图像文件中获取所述位置对应关系，然后基于所述局部灰度变换关系以及所述目标红外图像的位置对应关系确定所述目标区域，从而所述图像处理设备可以根据所述局部灰度变换关系对所述目标红外图像中的所述目标区域进行处理，保证还原的所述原始红外图像的准确性。
为了进一步提高图像的显示效果，在图2所示的实施例中，所述图像采集设备还可以根据伪彩映射关系对经灰度变换处理后的红外图像进行伪彩映射处理，从而获取所述目标红外图像，所述伪彩映射关系表征所述原始红外图像与所述目标红外图像之间的色彩对应关系。其中，所述伪彩映射关系也具备可逆性，以便后续能够基于所述伪彩映射关系从目标红外图像中还原出所述原始红外图像。
可以理解的是，本申请实施例对于所述伪彩映射关系的表示形式不做任何限制，可依据实际应用场景进行具体设置。在一个例子中，所述伪彩映射关系可以以函数等 式关系表示，当然，本实施例对于具体的函数表示形式不作任何限制，可依据实际应用场景进行具体设置。在一个例子中，所述伪彩映射关系也可以以关系表来表示，所述关系表中指示所述原始红外图像中不同像素的像素值与所述目标红外图像中不同像素的像素值之间的色彩对应关系。比如关系表中包括所述原始红外图像中3个像素不同的灰度值，分别为100、120和150，以及所述目标红外图像中3个像素不同的RGB值，分别为(90,180,60)、(108,216,36)和(135,270,45)，其中，100与(90,180,60)、对应、120与(108,216,36)对应、130与(135,270,45)对应。在一个例子中，还可以通过体现伪彩映射关系的变化曲线来表示，本实施例对此不做任何限制。
其中，不同的目标红外图像对应的所述伪彩映射关系可以相同也可以不同。
可选地，如果不同的目标红外图像对应相同的伪彩映射关系，则图2所示的实施例的所述图像采集设备只需存储一次所述伪彩映射关系，并且将所述伪彩映射关系与相应的一个或多个目标红外图像进行关联，从而能够有效节省存储空间；和/或，图2所述的实施例的图像采集设备只需发送一次所述伪彩映射关系给图3所示实施例的图像处理设备，然后在后续每次获取到所述目标红外图像时，只需给图像处理设备发送所述目标红外图像而无需再重复发送所述伪彩映射关系，从而有利于节省传输资源。
可选地，如果不同的目标红外图像对应不同的伪彩映射关系，则图2所述的实施例的所述图像采集设备在每次获取所述伪彩映射关系之后，均需要存储与所述目标红外图像对应的所述伪彩映射关系；和/或，图2所述的实施例的图像采集设备将与所述目标红外图像对应的所述伪彩映射关系发送给图3所示实施例的图像处理设备。
作为其中一种实现方式，所述伪彩映射关系可被存储于指示所述目标红外图像的图像文件中，这样后续在测温过程中，可以快速获取所述伪彩映射关系，而且也有效节省了存储空间。
在另一种实现方式中，考虑到伪彩映射关系并不会随着所述原始红外图像的灰度级不同而变化，并且所述伪彩映射关系的类型有限，则可以设置不同的伪彩映射关系对应不同的指定标识，然后所述图像采集设备可以将用于指示所述伪彩映射关系的指定标识存储于指示所述目标红外图像的图像文件中，显然，相对于在指示所述目标红外图像的图像文件中存储伪彩映射关系，在指示所述目标红外图像的图像文件中指存储指定标识能够进一步节省存储资源或传输资源。
相应的，在图3所示的实施例中，所述图像处理设备获取所述目标红外图像的伪彩映射关系，所述伪彩映射关系表征所述原始红外图像与所述目标红外图像之间的色彩对应关系，然后根据所述伪彩映射关系对所述目标红外图像进行还原处理。其中， 所述图像处理设备先采用伪彩映射关系对所述目标红外图像进行初步还原处理，然后采用灰度变换关系对初步还原处理后的所述目标红外图像进行进一步还原处理，从而获取用于测温的原始红外图像。
在一种实现方式中，所述图像处理设备可以从指示所述目标红外图像的图像文件中获取所述伪彩映射关系。在另一种实现方式中，所述图像处理设备上预存有不同类型的伪彩映射关系，不同的伪彩映射关系对应不同的指定标识，其中，用于指示所述伪彩映射关系的指定标识存储于指示所述目标红外图像的图像文件中，则所述图像处理设备可以根据所述指定标识获取所述目标红外图像的伪彩映射关系。
在图3所示的实施例中，在获取所述原始红外图像之后，所述图像处理设备可以根据所述原始红外图像以及预存的温度对应关系，获取温度测量值；所述温度对应关系表征所述原始红外图像内不同的像素值对应的不同温度值。本实施例中，由于还原出所述原始红外图像，所述原始红外图像中的像素的像素值与温度值保持正确的对应关系，因此基于所述原始红外图像能够获取正确的温度测量值。
相应地，请参阅图4，本实施例还提供了一种图像采集设备30，所述图像采集设备30包括：处理器31；用于存储处理器31可执行指令的存储器32。
其中，所述处理器31调用所述可执行指令，当可执行指令被执行时，用于执行：获取目标红外图像；所述目标红外图像为经过灰度变换处理后的图像；获取所述目标红外图像的灰度变换关系，所述灰度变换关系表征从原始红外图像变换至所述目标红外图像过程中的灰度变换关系；根据所述灰度变换关系对所述目标红外图像进行反向处理，还原出所述原始红外图像；根据所述原始红外图像进行温度测量。
所述处理器31可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
所述存储器32存储所述红外图像处理方法的可执行指令计算机程序，所述存储器32可以包括至少一种类型的存储介质，存储介质包括闪存、硬盘、多媒体卡、卡型存储器(例如，SD或DX存储器等等)、随机访问存储器(RAM)、静态随机访问存储器(SRAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、可编程只读存储器(PROM)、磁性存储器、磁盘、光盘等等。而且，所述图像采集设备30可以与通过网络连接执行存储器32的存储功能的网络存储装置协作。存储器32可以是图像采 集设备30的内部存储单元，例如图像采集设备30的硬盘或内存。存储器32也可以是图像采集设备30的外部存储设备，例如图像采集设备30上配备的插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)等。进一步地，存储器32还可以既包括图像采集设备30的内部存储单元也包括外部存储设备。存储器32用于存储计算机程序以及设备所需的其他程序和数据。存储器32还可以用于暂时地存储已经输出或者将要输出的数据。
这里描述的各种实施方式可以使用例如计算机软件、硬件或其任何组合的计算机可读介质来实施。对于硬件实施，这里描述的实施方式可以通过使用特定用途集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理装置(DSPD)、可编程逻辑装置(PLD)、现场可编程门阵列(FPGA)、处理器、控制器、微控制器、微处理器、被设计为执行这里描述的功能的电子单元中的至少一种来实施。对于软件实施，诸如过程或功能的实施方式可以与允许执行至少一种功能或操作的单独的软件模块来实施。软件代码可以由以任何适当的编程语言编写的软件应用程序(或程序)来实施，软件代码可以存储在存储器中并且由控制器执行。
在一实施例中，所述灰度变换关系存储于指示所述目标红外图像的图像文件中。
在一实施例中，所述灰度变换关系具有可逆性。
在一实施例中，所述灰度变换关系具有单调性。
在一实施例中，所述灰度变换关系至少包括以下至少一项：全局灰度变换关系或局部灰度变换关系。
所述全局灰度变换关系指示所述目标红外图像经过全局灰度变换处理；所述局部灰度变换关系指示所述目标红外图像经过局部灰度变换处理。
在一实施例中，当所述灰度变换关系为局部灰度变换关系时，所述处理器31还用于：在所述目标红外图像中，确定与所述局部灰度变换关系对应的目标区域；根据所述局部灰度变换关系对所述目标红外图像中的所述目标区域进行处理。
在一实施例中，所述目标区域基于所述局部灰度变换关系以及所述目标红外图像的位置对应关系所确定，所述位置对应关系表征所述目标红外图像中不同的区域对应的不同局部灰度变换关系。
在一实施例中，所述位置对应关系存储于指示所述目标红外图像的图像文件中。
在一实施例中，所述灰度变换关系包括至少一个灰度变换参数；不同目标红外图像对应不同的灰度变换参数。
在一实施例中，所述灰度变换参数根据所述原始红外图像的灰度级所确定。
在一实施例中，所述处理器还用于：获取所述目标红外图像的伪彩映射关系；所述伪彩映射关系表征所述原始红外图像与所述目标红外图像之间的色彩对应关系；根据所述伪彩映射关系对所述目标红外图像进行还原处理。
在一实施例中，所述伪彩映射关系存储于指示所述目标红外图像的图像文件中。
在一实施例中，用于指示所述伪彩映射关系的指定标识存储于指示所述目标红外图像的图像文件中；所述处理器还用于：根据所述指定标识获取所述目标红外图像的伪彩映射关系。
在一实施例中，所述原始红外图像为经过预处理后的图像；所述预处理包括以下至少一项操作：矫正处理、噪声去除处理或者坏点去除处理。
在一实施例中，在根据所述原始红外图像进行温度测量时，所述处理器31具体用于：根据所述原始红外图像以及预存的温度对应关系，获取温度测量值；所述温度对应关系表征所述原始红外图像内不同的像素值对应的不同温度值。
在一实施例中，所述目标红外图像为经过对比度拉伸处理后的图像。
在一实施例中，所述图像采集设备还包括有通信模块，所述通信模块用于接收所述目标红外图像和/或所述灰度变换关系。
相应的，本实施例还提供了一种图像处理设备，包括：处理器；用于存储处理器可执行指令的存储器。
其中，所述处理器调用所述可执行指令，当可执行指令被执行时，用于执行：获取原始红外图像；基于灰度变换关系对所述原始红外图像进行灰度变换处理，获取目标红外图像，所述灰度变换关系表征从所述原始红外图像变换至所述目标红外图像过程中的灰度变换关系；存储或传输所述目标红外图像。
在一实施例中，所述灰度变换关系存储于指示所述目标红外图像的图像文件中。
在一实施例中，所述灰度变换关系具有可逆性。
在一实施例中，所述灰度变换关系具有单调性。
在一实施例中，所述处理器还用于：将所述灰度变换关系存储至所述存储器。
在一实施例中，还包括通信模块；所述通信模块用于：传输所述灰度变换关系。
在一实施例中，所述处理器具体用于：基于全局变换关系对所述原始红外图进行全局灰度变换处理，和/或，基于局部变换关系对所述原始红外图进行局部灰度变换处理。
在一实施例中，所述处理器还用于：获取所述原始红外图像中进行局部灰度变换处理的区域；根据所述区域以及相应的局部灰度变换关系，获取位置对应关系；所述 位置对应关系指示所述目标红外图像中不同的区域对应的不同局部灰度变换关系。
在一实施例中，所述位置对应关系存储于指示所述目标红外图像的图像文件中。
在一实施例中，所述灰度变换关系包括至少一个灰度变换参数；不同目标红外图像对应不同的灰度变换参数。
在一实施例中，所述灰度变换参数根据所述原始红外图像的灰度级所确定。
在一实施例中，所述处理器还用于：根据伪彩映射关系对经灰度变换处理后的红外图像进行伪彩映射处理；所述伪彩映射关系表征所述原始红外图像与所述目标红外图像之间的色彩对应关系。
在一实施例中，所述伪彩映射关系存储于指示所述目标红外图像的图像文件中。
在一实施例中，不同的伪彩映射关系对应不同的指定标识；用于指示所述伪彩映射关系的指定标识存储于指示所述目标红外图像的图像文件中。
在一实施例中，所述原始红外图像为经过预处理后的图像；所述预处理包括以下至少一项操作：矫正处理、噪声去除处理或者坏点去除处理。
在一实施例中，所述处理器具体用于：对所述原始红外图像进行对比度拉伸处理。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器，上述指令可由电子设备的处理器执行以完成上述方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
其中，当所述存储介质中的指令由所述处理器执行时，使得电子设备能够执行前述红外图像处理方法。
需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上对本申请实施例所提供的方法和装置进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在 具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。

Claims (64)

  1. 一种红外图像处理方法，其特征在于，包括：
    获取目标红外图像；所述目标红外图像为经过灰度变换处理后的图像；
    获取所述目标红外图像的灰度变换关系，所述灰度变换关系表征从原始红外图像变换至所述目标红外图像过程中的灰度变换关系；
    根据所述灰度变换关系对所述目标红外图像进行处理，还原出所述原始红外图像；
    根据所述原始红外图像进行温度测量。
  2. 根据权利要求1所述的方法，其特征在于，所述灰度变换关系存储于指示所述目标红外图像的图像文件中。
  3. 根据权利要求1所述的方法，其特征在于，所述灰度变换关系具有可逆性。
  4. 根据权利要求1所述的方法，其特征在于，所述灰度变换关系具有单调性。
  5. 根据权利要求1所述的方法，其特征在于，所述灰度变换关系至少包括以下至少一项：全局灰度变换关系或局部灰度变换关系；
    所述全局灰度变换关系指示所述目标红外图像经过全局灰度变换处理；
    所述局部灰度变换关系指示所述目标红外图像经过局部灰度变换处理。
  6. 根据权利要求1所述的方法，其特征在于，当所述灰度变换关系为局部灰度变换关系时，所述方法还包括：在所述目标红外图像中，确定与所述局部灰度变换关系对应的目标区域；
    所述根据所述灰度变换关系对所述目标红外图像进行处理，包括：
    根据所述局部灰度变换关系对所述目标红外图像中的所述目标区域进行处理。
  7. 根据权利要求6所述的方法，其特征在于，所述目标区域基于所述局部灰度变换关系以及所述目标红外图像的位置对应关系所确定，所述位置对应关系表征所述目标红外图像中不同的区域对应的不同局部灰度变换关系。
  8. 根据权利要求7所述的方法，其特征在于，所述位置对应关系存储于指示所述目标红外图像的图像文件中。
  9. 根据权利要求1所述的方法，其特征在于，所述灰度变换关系包括至少一个灰度变换参数；不同目标红外图像对应不同的灰度变换参数。
  10. 根据权利要求9所述的方法，其特征在于，所述灰度变换参数根据所述原始红外图像的灰度级所确定。
  11. 根据权利要求1所述的方法，其特征在于，还包括：
    获取所述目标红外图像的伪彩映射关系；所述伪彩映射关系表征所述原始红外图 像与所述目标红外图像之间的色彩对应关系；
    所述还原出所述原始红外图像，还包括：根据所述伪彩映射关系对所述目标红外图像进行还原处理。
  12. 根据权利要求11所述的方法，其特征在于，所述伪彩映射关系存储于指示所述目标红外图像的图像文件中。
  13. 根据权利要求11所述的方法，其特征在于，用于指示所述伪彩映射关系的指定标识存储于指示所述目标红外图像的图像文件中；
    所述获取所述目标红外图像的伪彩映射关系包括：根据所述指定标识获取所述目标红外图像的伪彩映射关系。
  14. 根据权利要求1所述的方法，其特征在于，所述原始红外图像为经过预处理后的图像；
    所述预处理包括以下至少一项操作：矫正处理、噪声去除处理或者坏点去除处理。
  15. 根据权利要求1所述的方法，其特征在于，所述根据所述原始红外图像进行温度测量包括：
    根据所述原始红外图像以及预存的温度对应关系，获取温度测量值；所述温度对应关系表征所述原始红外图像内不同的像素值对应的不同温度值。
  16. 根据权利要求1所述的方法，其特征在于，所述目标红外图像为经过对比度拉伸处理后的图像。
  17. 一种红外图像处理方法，其特征在于，包括：
    获取原始红外图像；
    基于灰度变换关系对所述原始红外图像进行灰度变换处理，获取目标红外图像，所述灰度变换关系表征从所述原始红外图像变换至所述目标红外图像过程中的灰度变换关系；
    存储或传输所述目标红外图像。
  18. 根据权利要求17所述的方法，其特征在于，所述灰度变换关系存储于指示所述目标红外图像的图像文件中。
  19. 根据权利要求17所述的方法，其特征在于，所述灰度变换关系具有可逆性。
  20. 根据权利要求17所述的方法，其特征在于，所述灰度变换关系具有单调性。
  21. 根据权利要求17所述的方法，其特征在于，还包括：存储或传输所述灰度变换关系。
  22. 根据权利要求17所述的方法，其特征在于，所述基于灰度变换关系对所述原 始红外图像进行灰度变换处理，包括：
    基于全局变换关系对所述原始红外图像进行全局灰度变换处理，和/或，基于局部变换关系对所述原始红外图像进行局部灰度变换处理。
  23. 根据权利要求22所述的方法，其特征在于，当对所述原始红外图进行局部灰度变换处理时，所述方法还包括：
    获取所述原始红外图像中进行局部灰度变换处理的区域；
    根据所述区域以及相应的局部灰度变换关系，获取位置对应关系；所述位置对应关系指示所述目标红外图像中不同的区域对应的不同局部灰度变换关系。
  24. 根据权利要求23所述的方法，其特征在于，所述位置对应关系存储于指示所述目标红外图像的图像文件中。
  25. 根据权利要求17所述的方法，其特征在于，所述灰度变换关系包括至少一个灰度变换参数；不同目标红外图像对应不同的灰度变换参数。
  26. 根据权利要求25所述的方法，其特征在于，所述灰度变换参数根据所述原始红外图像的灰度级所确定。
  27. 根据权利要求17所述的方法，其特征在于，所述获取目标红外图像，还包括：
    根据伪彩映射关系对经灰度变换处理后的红外图像进行伪彩映射处理；所述伪彩映射关系表征所述原始红外图像与所述目标红外图像之间的色彩对应关系。
  28. 根据权利要求27所述的方法，其特征在于，所述伪彩映射关系存储于指示所述目标红外图像的图像文件中。
  29. 根据权利要求27所述的方法，其特征在于，不同的伪彩映射关系对应不同的指定标识；用于指示所述伪彩映射关系的指定标识存储于指示所述目标红外图像的图像文件中。
  30. 根据权利要求17所述的方法，其特征在于，所述原始红外图像为经过预处理后的图像；
    所述预处理包括以下至少一项操作：矫正处理、噪声去除处理或者坏点去除处理。
  31. 根据权利要求17所述的方法，其特征在于，所述对所述原始红外图像进行灰度变换处理，包括：对所述原始红外图像进行对比度拉伸处理。
  32. 一种图像采集设备，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器调用所述可执行指令，当可执行指令被执行时，用于执行：
    获取目标红外图像；所述目标红外图像为经过灰度变换处理后的图像；
    获取所述目标红外图像的灰度变换关系，所述灰度变换关系表征从原始红外图像变换至所述目标红外图像过程中的灰度变换关系；
    根据所述灰度变换关系对所述目标红外图像进行反向处理，还原出所述原始红外图像；
    根据所述原始红外图像进行温度测量。
  33. 根据权利要求32所述的设备，其特征在于，所述灰度变换关系存储于指示所述目标红外图像的图像文件中。
  34. 根据权利要求32所述的设备，其特征在于，所述灰度变换关系具有可逆性。
  35. 根据权利要求32所述的设备，其特征在于，所述灰度变换关系具有单调性。
  36. 根据权利要求32所述的设备，其特征在于，所述灰度变换关系至少包括以下至少一项：全局灰度变换关系或局部灰度变换关系；
    所述全局灰度变换关系指示所述目标红外图像经过全局灰度变换处理；
    所述局部灰度变换关系指示所述目标红外图像经过局部灰度变换处理。
  37. 根据权利要求32所述的设备，其特征在于，当所述灰度变换关系为局部灰度变换关系时，所述处理器还用于：在所述目标红外图像中，确定与所述局部灰度变换关系对应的目标区域；根据所述局部灰度变换关系对所述目标红外图像中的所述目标区域进行处理。
  38. 根据权利要求37所述的设备，其特征在于，所述目标区域基于所述局部灰度变换关系以及所述目标红外图像的位置对应关系所确定，所述位置对应关系表征所述目标红外图像中不同的区域对应的不同局部灰度变换关系。
  39. 根据权利要求38所述的设备，其特征在于，所述位置对应关系存储于指示所述目标红外图像的图像文件中。
  40. 根据权利要求32所述的设备，其特征在于，所述灰度变换关系包括至少一个灰度变换参数；不同目标红外图像对应不同的灰度变换参数。
  41. 根据权利要求40所述的设备，其特征在于，所述灰度变换参数根据所述原始红外图像的灰度级所确定。
  42. 根据权利要求32所述的设备，其特征在于，所述处理器还用于：获取所述目标红外图像的伪彩映射关系；所述伪彩映射关系表征所述原始红外图像与所述目标红外图像之间的色彩对应关系；根据所述伪彩映射关系对所述目标红外图像进行还原处理。
  43. 根据权利要求42所述的设备，其特征在于，所述伪彩映射关系存储于指示所述目标红外图像的图像文件中。
  44. 根据权利要求42所述的设备，其特征在于，用于指示所述伪彩映射关系的指定标识存储于指示所述目标红外图像的图像文件中；
    所述处理器还用于：根据所述指定标识获取所述目标红外图像的伪彩映射关系。
  45. 根据权利要求32所述的设备，其特征在于，所述原始红外图像为经过预处理后的图像；
    所述预处理包括以下至少一项操作：矫正处理、噪声去除处理或者坏点去除处理。
  46. 根据权利要求32所述的设备，其特征在于，在根据所述原始红外图像进行温度测量时，所述处理器具体用于：根据所述原始红外图像以及预存的温度对应关系，获取温度测量值；所述温度对应关系表征所述原始红外图像内不同的像素值对应的不同温度值。
  47. 根据权利要求32所述的设备，其特征在于，所述目标红外图像为经过对比度拉伸处理后的图像。
  48. 一种图像处理设备，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器调用所述可执行指令，当可执行指令被执行时，用于执行：
    获取原始红外图像；
    基于灰度变换关系对所述原始红外图像进行灰度变换处理，获取目标红外图像，所述灰度变换关系表征从所述原始红外图像变换至所述目标红外图像过程中的灰度变换关系；
    存储或传输所述目标红外图像。
  49. 根据权利要求48所述的设备，其特征在于，所述灰度变换关系存储于指示所述目标红外图像的图像文件中。
  50. 根据权利要求48所述的设备，其特征在于，所述灰度变换关系具有可逆性。
  51. 根据权利要求48所述的设备，其特征在于，所述灰度变换关系具有单调性。
  52. 根据权利要求48所述的设备，其特征在于，所述处理器还用于：将所述灰度变换关系存储至所述存储器。
  53. 根据权利要求48所述的设备，其特征在于，还包括通信模块；
    所述通信模块用于：传输所述灰度变换关系。
  54. 根据权利要求48所述的设备，其特征在于，所述处理器具体用于：基于全局变换关系对所述原始红外图进行全局灰度变换处理，和/或，基于局部变换关系对所述原始红外图进行局部灰度变换处理。
  55. 根据权利要求54所述的设备，其特征在于，所述处理器还用于：获取所述原始红外图像中进行局部灰度变换处理的区域；根据所述区域以及相应的局部灰度变换关系，获取位置对应关系；所述位置对应关系指示所述目标红外图像中不同的区域对应的不同局部灰度变换关系。
  56. 根据权利要求55所述的设备，其特征在于，所述位置对应关系存储于指示所述目标红外图像的图像文件中。
  57. 根据权利要求48所述的设备，其特征在于，所述灰度变换关系包括至少一个灰度变换参数；不同目标红外图像对应不同的灰度变换参数。
  58. 根据权利要求57所述的设备，其特征在于，所述灰度变换参数根据所述原始红外图像的灰度级所确定。
  59. 根据权利要求48所述的设备，其特征在于，所述处理器还用于：根据伪彩映射关系对经灰度变换处理后的红外图像进行伪彩映射处理；所述伪彩映射关系表征所述原始红外图像与所述目标红外图像之间的色彩对应关系。
  60. 根据权利要求59所述的设备，其特征在于，所述伪彩映射关系存储于指示所述目标红外图像的图像文件中。
  61. 根据权利要求59所述的设备，其特征在于，不同的伪彩映射关系对应不同的指定标识；用于指示所述伪彩映射关系的指定标识存储于指示所述目标红外图像的图像文件中。
  62. 根据权利要求48所述的设备，其特征在于，所述原始红外图像为经过预处理后的图像；
    所述预处理包括以下至少一项操作：矫正处理、噪声去除处理或者坏点去除处理。
  63. 根据权利要求48所述的设备，其特征在于，所述处理器具体用于：对所述原始红外图像进行对比度拉伸处理。
  64. 一种计算机可读存储介质，其特征在于，其上存储有计算机指令，该指令被处理器执行时实现权利要求1至31任意一项所述的方法。
PCT/CN2020/096195 2020-06-15 2020-06-15 红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质 WO2021253187A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/096195 WO2021253187A1 (zh) 2020-06-15 2020-06-15 红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/096195 WO2021253187A1 (zh) 2020-06-15 2020-06-15 红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2021253187A1 true WO2021253187A1 (zh) 2021-12-23

Family

ID=79268960

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/096195 WO2021253187A1 (zh) 2020-06-15 2020-06-15 红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质

Country Status (1)

Country Link
WO (1) WO2021253187A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4751571A (en) * 1987-07-29 1988-06-14 General Electric Company Composite visible/thermal-infrared imaging apparatus
EP2437486A1 (en) * 2010-10-04 2012-04-04 Flir Systems AB IR Camera and Method for Processing Thermal Image Information
CN102609962A (zh) * 2012-01-18 2012-07-25 中国人民解放军61517部队 热红外图像模拟方法
CN102798475A (zh) * 2012-08-02 2012-11-28 电子科技大学 一种根据标准红外视频图像确定目标温度的方法
WO2014152681A2 (en) * 2013-03-14 2014-09-25 Drs Rsta, Inc. Method and system for providing scene and temperature data in a video stream
CN110853108A (zh) * 2019-10-11 2020-02-28 中国南方电网有限责任公司超高压输电公司天生桥局 一种红外热图数据的压缩存储方法
CN111145205A (zh) * 2019-12-24 2020-05-12 天津农学院 基于红外图像的多猪只场景下猪体温检测方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4751571A (en) * 1987-07-29 1988-06-14 General Electric Company Composite visible/thermal-infrared imaging apparatus
EP2437486A1 (en) * 2010-10-04 2012-04-04 Flir Systems AB IR Camera and Method for Processing Thermal Image Information
CN102609962A (zh) * 2012-01-18 2012-07-25 中国人民解放军61517部队 热红外图像模拟方法
CN102798475A (zh) * 2012-08-02 2012-11-28 电子科技大学 一种根据标准红外视频图像确定目标温度的方法
WO2014152681A2 (en) * 2013-03-14 2014-09-25 Drs Rsta, Inc. Method and system for providing scene and temperature data in a video stream
CN110853108A (zh) * 2019-10-11 2020-02-28 中国南方电网有限责任公司超高压输电公司天生桥局 一种红外热图数据的压缩存储方法
CN111145205A (zh) * 2019-12-24 2020-05-12 天津农学院 基于红外图像的多猪只场景下猪体温检测方法

Similar Documents

Publication Publication Date Title
KR101858646B1 (ko) 영상 융합 장치 및 방법
WO2018103244A1 (zh) 直播视频处理方法、装置及电子设备
EP3627440B1 (en) Image processing method and apparatus
US20220245823A1 (en) Image Processing Method and Apparatus, and Device
US10096170B2 (en) Image device for determining an invalid depth information of a depth image and operation method thereof
CN111355941B (zh) 图像颜色实时校正方法、装置和系统
CN110462617B (zh) 用于通过多个相机认证生物数据的电子装置和方法
WO2023016320A1 (zh) 图像处理方法、装置、设备及介质
US20230260263A1 (en) Systems and methods for object recognition
CN111080571A (zh) 摄像头遮挡状态检测方法、装置、终端和存储介质
US11238563B2 (en) Noise processing method and apparatus
CN112991218A (zh) 图像处理的方法、装置、设备以及存储介质
CN111383254A (zh) 一种深度信息获取方法、系统及终端设备
CN113158773B (zh) 一种活体检测模型的训练方法及训练装置
CN113469869B (zh) 一种图像管理方法和装置
US11605220B2 (en) Systems and methods for video surveillance
CN113177886B (zh) 图像处理方法、装置、计算机设备及可读存储介质
WO2020006907A1 (zh) 一种拍摄控制方法、终端及计算机可读存储介质
CN109886864B (zh) 隐私遮蔽处理方法及装置
WO2021253187A1 (zh) 红外图像处理方法、图像采集设备、图像处理设备以及计算机可读存储介质
WO2023040725A1 (zh) 白平衡处理方法与电子设备
US20190208064A1 (en) Electronic device and method for image processing based on context information
US20200088831A1 (en) Mobile body detection device, mobile body detection method, and mobile body detection program
CN116668862A (zh) 图像处理方法与电子设备
CN114550256A (zh) 极小目标检测方法、装置、设备及计算机可读介质

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: 20940784

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: 20940784

Country of ref document: EP

Kind code of ref document: A1