Infrared temperature measurement method, program product and equipment

Abstract

The invention discloses an infrared temperature measurement method, a program product and equipment. The method comprises the following steps: acquiring an infrared image acquired from a monitoring scene; calculating an actual distance between a target in the infrared image and an image acquisition device, and calculating an initial temperature of the target; obtaining a temperature correction model, wherein the temperature correction model comprises a temperature compensation model and / or a target background radiation correction model; and correcting the initial temperature based on the temperature correction model and the actual distance to obtain the actual temperature of the target.

Description

Technical Field

[0001] The present invention relates to the field of temperature measurement technology, and in particular to an infrared temperature measurement method, a computer program product and an infrared temperature measurement device. Background Art

[0002] Infrared temperature measuring equipment refers to an infrared imaging device that collects infrared images and then obtains the temperature information of the target. However, the distance between the target and the infrared temperature measuring equipment will affect the accuracy of the temperature measurement. At the same time, due to the influence of background radiation outside the target area, such as background stray light or diffuse light, the temperature accuracy of the target will also be affected. The infrared temperature measurement method in the prior art does not take these factors into consideration, so the temperature measurement accuracy is not high. Summary of the invention

[0003] In order to solve the existing technical problems, the present invention provides an infrared temperature measurement method, a computer program product and an infrared temperature measurement device, which can improve the accuracy of temperature measurement.

[0004] In a first aspect, an infrared temperature measurement method is provided, comprising: acquiring an infrared image captured of a monitoring scene; calculating the actual distance between a target in the infrared image and an image acquisition device and calculating the initial temperature of the target; acquiring a temperature correction model, wherein the temperature correction model comprises a temperature compensation model and / or a target background radiation correction model; and correcting the initial temperature based on the temperature correction model and the actual distance to obtain the actual temperature of the target.

[0005] In a second aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, an infrared temperature measurement method as described in any one of the first aspects of the present application is implemented.

[0006] In a third aspect, an infrared temperature measurement device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes an infrared temperature measurement method as described in any one of the first aspects of the present application.

[0007] The present application obtains an infrared image of the monitoring scene, calculates the actual distance between the target in the infrared image and the image acquisition device, and calculates the initial temperature of the target, and automatically identifies the target distance through the actual infrared image to obtain the real distance, not the estimated distance, so that the subsequent temperature correction is more accurate; based on the actual distance, the initial temperature of the target in the infrared image is accurately corrected using a temperature compensation model and / or a target background radiation correction model, which effectively reduces the error in temperature measurement accuracy caused by factors such as the difference between the calibration scene and the actual application scene, the change in the actual use distance of the product, and background radiation, and greatly improves the temperature measurement accuracy and stability of ultra-high temperature temperature measurement products in actual application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is an application environment diagram of an infrared temperature measurement method in an embodiment;

[0009] Figure 2 is a flow chart of an infrared temperature measurement method in one embodiment;

[0010] Figure 3 A schematic diagram of determining the actual distance of a target in one embodiment;

[0011] Figure 4 A schematic diagram of a block diagram for constructing model parameters in one embodiment;

[0012] Figure 5 is a flow chart of an infrared temperature measurement method in another embodiment;

[0013] Figure 6 is a schematic diagram of an infrared temperature measuring device in an embodiment;

[0014] Figure 7 Schematic diagram of an infrared temperature measuring device in one embodiment. DETAILED DESCRIPTION

[0015] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0016] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art of the technical field of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the scope of protection of the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0017] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it should be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0018] See also Figure 1 , see Figure 1, is an application environment diagram of an infrared temperature measurement method in an embodiment. The infrared temperature measurement method is applied to an infrared temperature measurement device 10 (hereinafter referred to as "temperature measurement device 10"), and the temperature measurement device 10 includes an image acquisition device 12, a processor 13 and a memory 14. The image acquisition device 12 is used to acquire an infrared image of the scene to be monitored by the temperature measurement device 10. The processor 13 calculates the initial temperature of the target based on the infrared image acquired by the image acquisition device 12 for the monitored scene, and corrects the initial temperature according to a pre-stored model. The memory 14 is used to store programs and various types of data corresponding to the infrared temperature measurement method.

[0019] The temperature measuring device 10 includes but is not limited to handheld detection devices, non-handheld autonomously movable detection devices, and non-handheld non-autonomously movable detection devices. Among them, the handheld detection devices include but are not limited to handheld imaging devices with infrared thermal imaging functions, and handheld imaging devices with visible light imaging functions. Among them, the non-handheld autonomously movable detection devices include but are not limited to autonomously movable detection devices with infrared thermal imaging functions, and autonomously movable detection devices with visible light imaging functions. Non-handheld non-autonomously movable detection devices include but are not limited to non-handheld and non-autonomously movable devices with infrared thermal imaging functions, and non-handheld and non-autonomously movable devices with visible light imaging functions. Among them, through the temperature measuring device 10, the user can perform infrared temperature measurement on a certain scene, such as an ultra-high temperature scene. There is currently no targeted correction and compensation solution for infrared ultra-high temperature measurement.

[0020] The image acquisition device 12 may be a combination of one or more sensors. The image acquisition device 12 may be a monocular vision sensor or a multi-vision sensor. For example, it may be a combination of one or more sensors selected from the group consisting of a thermal imaging sensor, a visible light image sensor, a millimeter wave sensor, a laser radar sensor, an infrared thermal imaging sensor, and a depth sensor.

[0021] The processor 13 may be one or more processors. When there are multiple processors 13, the multiple processors may be integrated on one chip or independently arranged on each chip. The temperature measuring device 10 may also be fixedly installed on a fixed device or at a fixed position in a fixed scene.

[0022] The temperature measuring device 10 may also include other sensor modules, including but not limited to environmental perception sensors and motion posture sensors. Environmental perception sensors include but are not limited to one or more combinations of the following sensors: brightness sensors, temperature sensors, haze sensors and other environmental sensors. Motion posture sensors include but are not limited to one or more combinations of the following: inertial sensors (Inertial Measurement Unit, IMU), speed sensors, acceleration sensors, gyroscope sensors, geomagnetic sensors, rotation vector sensors, steering wheel angle sensors, level sensors, tilt sensors, vibration sensors, displacement sensors and gravity sensors, etc.

[0023] The temperature measuring device 10 may also include a display terminal for displaying temperature data of an area of ​​interest in the current infrared image.

[0024] See also Figure 2 , is a flow chart of an infrared temperature measurement method provided in an embodiment of the present application. An infrared temperature measurement method is applied to an infrared temperature measurement device, and the infrared temperature measurement method includes the following steps:

[0025] S10: Acquire an infrared image of the monitoring scene.

[0026] In this embodiment, the monitoring scene indicates the scene that needs temperature measurement, including but not limited to general temperature measurement scenes and ultra-high temperature temperature measurement scenes. For example, the ultra-high temperature temperature measurement scene is a production scene in a steel plant, which is used to monitor the temperature of one or more devices. The infrared image is an infrared frame image captured in real time by the image acquisition device 12. The infrared image is the infrared radiation emitted by the target captured by the temperature measuring device 10 using an infrared detector and converted into an electrical signal. These electrical signals are processed and analyzed by amplification, analog-to-digital conversion (AD conversion), calibration and other signal processing, and finally converted into temperature data.

[0027] S11, calculating the actual distance between the target in the infrared image and the image acquisition device and calculating the initial temperature of the target.

[0028] In this embodiment, the actual distance is calculated based on the image coordinates of the target and the world coordinates of the target, which can represent the real distance between the target and the image acquisition device, not the artificially estimated distance. After the laboratory calibration of the infrared temperature measurement equipment in the prior art is completed, in the actual application scenario, the user needs to input the distance between the image acquisition device and the target. The prior art generally adopts the artificial estimation method, but this distance usually directly affects the output of the actual temperature result. Therefore, in the embodiment of the present application, a model is established by an infrared monocular ranging algorithm, and automatic target distance recognition is performed through actual infrared images to obtain the real distance, not the estimated distance, so that the subsequent temperature correction is more accurate.

[0029] In this embodiment, the target can be identified from the infrared image to obtain the target area, and the initial temperature of the target can be obtained based on the pixel values ​​of the pixels in the target area. For example, the center point of the target area is used as the initial temperature of the target, or the average value of the pixel values ​​of all the pixels in the target area is calculated and the average value is used as the initial temperature of the target. Of course, other calculation methods can also be selected.

[0030] S12. Acquire a temperature correction model, wherein the temperature correction model includes a temperature compensation model and / or a target background radiation correction model.

[0031] In this embodiment, the temperature correction model is a model used to correct the temperature later, which can be a temperature compensation model, a target background radiation correction model, a temperature compensation model and a target background radiation correction model. The temperature compensation model indicates the mapping relationship between distance and temperature, wherein different distances correspond to different temperature fitting parameters. The temperature compensation model can reduce the influence of distance attenuation on temperature accuracy. The target background radiation correction model is used to indicate the mapping relationship between distance-size-temperature. At the same distance, different sizes correspond to different temperature fitting parameters. The target background radiation correction model can reduce the influence of background radiation on accuracy, such as reducing the influence of stray light and diffuse light in the background.

[0032] The temperature correction model and parameters are pre-stored in the memory, which facilitates the subsequent correction using the stored data, thereby improving the correction speed.

[0033] S13. Based on the temperature correction model and the actual distance, the initial temperature is corrected to obtain the actual temperature of the target.

[0034] In the above embodiment, by acquiring an infrared image of the monitoring scene, calculating the actual distance between the target in the infrared image and the image acquisition device and the initial temperature of the target, automatic target distance recognition is performed through the actual infrared image to obtain the real distance, not the estimated distance, so that the subsequent temperature correction is more accurate; based on the actual distance, the initial temperature of the target in the infrared image is accurately corrected using a temperature compensation model and / or a target background radiation correction model, and the infrared monocular recognition distance is combined with temperature measurement compensation to perform temperature correction in a more targeted manner and better ensure the temperature measurement accuracy; effectively reducing the errors in temperature measurement accuracy caused by factors such as differences between calibration scenarios and actual application scenarios, changes in the actual use distance of the product, and background radiation, and greatly improving the temperature measurement accuracy and stability of ultra-high temperature temperature measurement products in actual application scenarios.

[0035] In some embodiments, obtaining the temperature correction model includes:

[0036] The target temperature accuracy configured is acquired based on the user interface, and the temperature correction model is acquired according to the target temperature accuracy.

[0037] In this embodiment, the temperature correction model can be a temperature compensation model, a target background radiation correction model, a temperature compensation model and a target background radiation correction model. Different temperature correction models correspond to different temperature accuracy. For example, the accuracy of the temperature compensation model and the target background radiation correction model is higher than the accuracy of using a model alone. In order to meet user needs, a temperature accuracy selection control can be provided on the user interface, and the target temperature accuracy is selected through the temperature accuracy selection control to obtain the temperature correction model corresponding to the target temperature accuracy. The temperature accuracy selection control includes but is not limited to one or more of the following: a check box, an input box, a drop-down box, a click box, etc. In an optional implementation, different temperature correction models can also be set according to different scenes, and a scene selection control is configured on the user interface. The target scene is selected through the scene selection control to obtain the model corresponding to the target scene. In an optional implementation, the temperature correction model defaults to one of the temperature compensation model, the target background radiation correction model, the temperature compensation model and the target background radiation correction model, and the default model is directly obtained from the memory. In an optional implementation, when the temperature correction model is a temperature compensation model and a target background radiation correction model, the user interface also provides configuration items for the execution order of these two models, obtains the execution order of the configuration based on the user interface, and performs subsequent temperature correction according to the execution order of the configuration.

[0038] In the above embodiment, different temperature accuracies can be provided on the user interface, and a temperature correction model suitable for the demand can be selected according to the temperature accuracy, so that the correction of the temperature accuracy is more in line with the actual demand.

[0039] In some embodiments, the temperature compensation model indicates a mapping relationship between distance and temperature, and the mapping relationship between distance and temperature includes a first mapping relationship between the distance and a first temperature fitting parameter and a second mapping relationship between the actual temperature and the measured temperature at the same distance, wherein the first temperature fitting parameter indicates a fitting parameter in the second mapping relationship.

[0040] In this embodiment, the temperature compensation model is calibrated in advance, and the temperature of the calibration object with different temperatures is collected at different distances for fitting. Different distances correspond to different first temperature fitting parameters, wherein the first mapping relationship can be a linear fitting model or a nonlinear fitting model, and the two variables in the first mapping relationship are the distance and the first temperature fitting parameter, so after one of the variables is known, the other variable can be obtained. After the actual distance is known, the first temperature fitting parameter corresponding to the actual distance can be obtained, so that the second mapping relationship corresponding to the actual distance can be obtained, and the two variables in the second mapping relationship are the real temperature and the measured temperature. The initial temperature is used as the measured temperature, and the real temperature, that is, the compensated temperature, can be output. Different distances correspond to different second mapping relationships. The temperature compensation model can reduce the influence of temperature accuracy caused by distance attenuation.

[0041] In the above embodiment, the temperature compensation model is obtained by prior calibration, different distances correspond to different first temperature fitting parameters, and different distances correspond to different second mapping relationships. The temperature compensation model can reduce the impact of temperature accuracy caused by distance attenuation.

[0042] In some embodiments, the target background radiation correction model is used to indicate a mapping relationship between distance, size and temperature, and the mapping relationship between distance, size and temperature includes a third mapping relationship between the indicated size and a second temperature fitting parameter at the same distance and a fourth mapping relationship between the actual temperature and the measured temperature at the same size, wherein the second temperature fitting parameter indicates a fitting parameter in the fourth mapping relationship.

[0043] In this embodiment, the target background radiation correction model is calibrated in advance. At different distances, the calibration is performed to obtain the mapping relationship between the size and temperature corresponding to each distance. That is to say, the target background radiation correction model corresponding to different distances is different. At the same distance, different sizes correspond to different second temperature fitting parameters. The two variables in the third mapping relationship are the size and the second temperature fitting parameter. After the size is known, the second temperature fitting parameter corresponding to the size can be obtained. Different sizes also correspond to different fourth mapping relationships. The two variables in the fourth mapping relationship are the real temperature and the measured temperature. After obtaining the second temperature fitting parameter, the fourth mapping relationship corresponding to the second temperature fitting parameter can be obtained, and the temperature output by the fourth mapping relationship can be used as the corrected temperature. The third mapping relationship and the fourth mapping relationship can be linear models or nonlinear models. The target background radiation correction model can reduce the impact of background radiation on temperature accuracy.

[0044] In the above embodiment, the target background radiation correction model is obtained by prior calibration, different distances correspond to different size-temperature mapping relationships, different sizes correspond to different second temperature fitting parameters, and different sizes correspond to different fourth mapping relationships. The temperature compensation model can reduce the impact of temperature accuracy caused by distance attenuation.

[0045] In some embodiments, the correcting the initial temperature based on the temperature correction model and the actual distance to obtain the actual temperature of the target includes at least one of the following:

[0046] Based on the actual distance, the initial temperature is compensated by using the temperature compensation model to obtain a compensated temperature value of the target; the target size of the target is obtained; based on the actual distance, the compensated temperature value and the target size, the compensated temperature value is corrected by using the target background radiation correction model to determine the actual temperature of the target;

[0047] Acquire the target size of the target, and based on the actual distance and the target size, use the target background radiation correction model to correct the initial temperature to obtain the corrected temperature of the target; based on the actual distance, use the temperature compensation model to compensate the corrected temperature to obtain the corrected temperature value of the target, and use the corrected temperature value of the target as the actual temperature of the target;

[0048] Based on the actual distance, the initial temperature is compensated by using the temperature compensation model to obtain a compensated temperature value of the target, and the compensated temperature value is used as the actual temperature of the target;

[0049] The target size of the target is obtained, and based on the actual distance and the target size, the initial temperature is corrected using the target background radiation correction model to obtain a corrected temperature of the target, and the corrected temperature of the target is used as the actual temperature of the target.

[0050] In this embodiment, the temperature correction model includes a temperature compensation model and a target background radiation correction model. The temperature compensation model may be executed first and then the target background radiation correction model.

[0051] Optionally, based on the actual distance, compensating the initial temperature using the temperature compensation model to obtain a compensated temperature value of the target includes:

[0052] According to the first mapping relationship between the distance and the first temperature fitting parameter in the temperature compensation model, the first target temperature fitting parameter corresponding to the actual distance is calculated; according to the second mapping relationship corresponding to the first target temperature fitting parameter and the initial temperature, the compensated temperature value is calculated.

[0053] Optionally, the correcting the compensated temperature value based on the actual distance, the compensated temperature value and the target size by using the target background radiation correction model to determine the actual temperature of the target includes:

[0054] Obtain a third mapping relationship corresponding to the actual distance, and obtain a second target temperature fitting parameter corresponding to the target size according to the target size and the third mapping relationship corresponding to the actual distance; calculate the actual temperature according to a fourth mapping relationship corresponding to the second target temperature fitting parameter and the compensated temperature value.

[0055] In this embodiment, the actual distance is used as the input variable of the first mapping relationship, and the value of another variable, i.e., the first target temperature fitting parameter, is output through the first mapping relationship. The first target temperature fitting parameter is then used as the parameter value of the second mapping relationship, and the initial temperature is used as the measured temperature in the second mapping relationship. The temperature value output by the second mapping relationship is used as the compensated temperature value. According to the actual distance, the mapping relationship between the distance-size-temperature corresponding to the actual distance is obtained, and the third mapping relationship corresponding to the actual distance is obtained from the mapping relationship between the distance-size-temperature corresponding to the actual distance. The target size is used as the input variable of the third mapping relationship, and the second target temperature fitting parameter corresponding to the target size is output through the third mapping relationship. According to the mapping relationship between the distance-size-temperature corresponding to the actual distance, the fourth mapping relationship corresponding to the second target temperature fitting parameter is obtained from the mapping relationship between the distance-size-temperature corresponding to the actual distance, and the compensated temperature value is used as the input value of the fourth mapping relationship, and the actual temperature is output through the fourth mapping relationship.

[0056] In this embodiment, the temperature correction model includes a temperature compensation model and a target background radiation correction model, and the target background radiation correction model can be executed first and then the temperature compensation model. According to the actual distance, a mapping relationship between distance-size-temperature corresponding to the actual distance is obtained, and a third mapping relationship corresponding to the actual distance is obtained from the mapping relationship between distance-size-temperature corresponding to the actual distance, and the target size is used as an input variable of the third mapping relationship. The second target temperature fitting parameter corresponding to the target size is output through the third mapping relationship. According to the mapping relationship between distance-size-temperature corresponding to the actual distance, a fourth mapping relationship corresponding to the second target temperature fitting parameter is obtained, and the initial temperature is used as the input value of the fourth mapping relationship. The temperature value output through the fourth mapping relationship is used as the correction temperature. The actual distance is used as the input variable of the first mapping relationship, and the value of another variable, that is, the first target temperature fitting parameter, is output through the first mapping relationship. The first target temperature fitting parameter is then used as the parameter value of the second mapping relationship and the correction temperature is used as the input quantity in the second mapping relationship, and the temperature value output from the second mapping relationship is used as the actual temperature.

[0057] In some optional embodiments, only the temperature compensation model or the target background radiation correction model may be executed.

[0058] In an optional implementation, obtaining the target size of the target includes at least one of the following:

[0059] The target contour is identified by using an image recognition algorithm, the target area is calculated based on the target contour, and the target area is used as the target size;

[0060] The target area is obtained from the infrared image, the center point of the target is obtained according to the target area, the target pixel points in the preset direction of the center point that are greater than the preset pixel threshold are selected, the target distance between the target pixel point farthest from the center point in each preset direction and the center point is calculated, and the target size is determined based on the minimum target distance.

[0061] In this embodiment, the configuration of the preset direction is related to the shape of the target. A circle can be determined with the center point as the center and the minimum target distance as the radius, and the area of ​​the circle can be used as the target size. A square can also be determined with the center point as the center and the minimum target distance as the side length, and the area of ​​the square can be used as the target size. Of course, there are other methods for determining the target size based on the minimum target distance, which are not listed here.

[0062] In the above embodiment, the target background radiation correction model is obtained by pre-calibration, different distances correspond to different size-temperature mapping relationships, different sizes correspond to different second temperature fitting parameters, and different sizes correspond to different fourth mapping relationships. The temperature compensation model can reduce the influence of temperature accuracy caused by distance attenuation; the model is established through the infrared monocular ranging algorithm, and the automatic target distance recognition is performed through the actual infrared image, and temperature compensation is performed on this basis, which can unify the calibration of the distance standard in practical applications and better compensate for the monitoring temperature. At the same time, combined with the distance information identified by the above target, the background radiation correction algorithm can better perform temperature correction for the actual scene temperature difference of different test targets, further improving the temperature measurement accuracy of the target.

[0063] In some embodiments, the method further comprises:

[0064] Obtaining a pre-stored temperature compensation model;

[0065] The obtaining of a pre-stored temperature compensation model comprises:

[0066] Get the real temperature of multiple calibration objects with different temperatures;

[0067] Collect the measured temperature of each calibration object at different distances;

[0068] Fitting the measured temperature and the actual temperature of each calibration object corresponding to each distance to obtain a second mapping relationship corresponding to each distance and a first temperature fitting parameter corresponding to each distance;

[0069] The first temperature fitting parameters corresponding to each distance are fitted to obtain the first mapping relationship.

[0070] In this embodiment, the calibration object can be a standard black body source. For example, four distances that need to be calibrated are configured, and three different calibration objects are configured. The real temperatures corresponding to these three calibrations are different. At the first distance, the measured temperatures corresponding to these three different calibration objects are collected respectively, and three groups of real temperature-measured temperature are obtained. The data of these three groups of real temperature-measured temperature are fitted to obtain the second mapping relationship corresponding to the first distance and the corresponding first temperature fitting parameters. In this way, at the four calibrated distances, four groups of first temperature fitting parameters corresponding to the distances are obtained respectively. The first temperature fitting parameters corresponding to the four groups of distances-distances are fitted to obtain the first mapping relationship. The more calibration distances are configured, the more accurate the subsequent correction is. The product should be calibrated for temperature measurement accuracy at different distances in the factory using a standard black body source, and the calibration data should be fitted and applied to ensure the correction effect and save the relevant parameters.

[0071] In the above embodiment, the temperature compensation model is obtained by prior calibration, different distances correspond to different first temperature fitting parameters, and different distances correspond to different second mapping relationships. The temperature compensation model can reduce the impact of temperature accuracy caused by distance attenuation.

[0072] In some embodiments, the method further comprises:

[0073] Get the pre-stored target background radiation correction model

[0074] The obtaining of a pre-stored target background radiation correction model comprises:

[0075] At each distance, obtaining the target background radiation correction model corresponding to each distance;

[0076] The obtaining of the target background radiation correction model corresponding to each distance includes:

[0077] Get the real temperature of multiple calibration objects with different temperatures;

[0078] For any distance, at different sizes, the measured temperature of each calibration object is collected to obtain the measured temperature of each calibration object corresponding to each size;

[0079] Fitting the measured temperature and the actual temperature of each calibration object corresponding to each size to obtain a fourth mapping relationship corresponding to each size and a temperature fitting parameter corresponding to each size;

[0080] The temperature fitting parameters corresponding to each size are fitted to obtain the third mapping relationship.

[0081] In this embodiment, the calibration object can be a standard black body source. For example, ten distances that need to be calibrated are configured, and the following calibration is performed at each distance: four calibrated sizes, three different calibration objects, and the real temperatures corresponding to these three calibrations are different. At the first size, the sizes of these three calibration objects are all the first size. The measured temperatures corresponding to these three different calibration objects are collected respectively to obtain three sets of real temperature-measured temperature. The data of these three sets of real temperature-measured temperature are fitted to obtain the fourth mapping relationship corresponding to the first size and the corresponding second temperature fitting parameters. In this way, at the four calibrated distances, the second temperature fitting parameters corresponding to the four sets of size-size are obtained respectively. The second temperature fitting parameters corresponding to the four sets of size-size are fitted to obtain the third mapping relationship. The more calibrated sizes are configured, the more accurate the subsequent calibration is. The product should be calibrated for temperature measurement accuracy of different target sizes at the same distance in the factory using a standard black body source, and the target background radiation correction algorithm model should be constructed with this data, and the relevant model and corresponding key parameters should be saved.

[0082] In the above embodiment, the target background radiation correction model is obtained by prior calibration, different distances correspond to different size-temperature mapping relationships, different sizes correspond to different second temperature fitting parameters, and different sizes correspond to different fourth mapping relationships. The temperature compensation model can reduce the impact of temperature accuracy caused by distance attenuation.

[0083] In some embodiments, calculating the actual distance between the target in the infrared image and the image acquisition device includes:

[0084] Get the calibrated homography matrix;

[0085] Acquire the image coordinates of the target from the infrared image;

[0086] Calculating the world coordinates of the target according to the image coordinates and the homography matrix;

[0087] The actual distance between the target and the image acquisition device is calculated according to the image coordinates and the world coordinates.

[0088] In this embodiment, if Figure 3 As shown, Figure 3Schematic diagram of determining the actual distance of a target in an embodiment. The homography matrix H is obtained. Next, the actual distance of the target can be estimated using the homography matrix. When measuring the distance d between a target of unknown height and the camera, if the position of the bottom of the target on the ground plane, the world coordinates and the image coordinates of the target in the image are known, and the target and the camera are in the same plane, the calculation formula of the actual distance is as follows:

[0089]

[0090] Where d represents the actual distance, X c , Y c , Z c Respectively represent the optical center position coordinates of the camera, X, Y, and Z respectively represent the world coordinates of the target. According to the following formula (1), the world coordinates of the target can be calculated. Formula (1) is as follows:

[0091]

[0092] Among them, H represents the calibrated homography matrix, (u, v, z) represent the image coordinates, (X w , Y w , Z w ) represents the world coordinates. According to formula (1), when the image coordinates and homography matrix of the target are known, the world coordinates of the target can be calculated.

[0093] Optionally, obtaining a calibrated homography matrix includes:

[0094] Obtain the reference plane and the calibration points on the reference plane, and obtain the world coordinates of each calibration point;

[0095] Acquire a reference plane image, and obtain image coordinates of each calibration point based on the reference plane image;

[0096] The homography matrix is ​​obtained based on the world coordinates and image coordinates of each calibration point.

[0097] In this embodiment, a reference plane needs to be selected first, which is usually a ground plane or other easily identifiable and relatively stable plane. Mark several points with known coordinates on the selected reference plane, and ensure that these points can be clearly detected in the image. For example, the device prompts to select point 1, point 2, point 3, and point 4 in the field of view. These points can be pre-arranged artificial markers or feature points extracted from the target environment, such as corner points and protruding parts of the edge of the device. Ideally, there should be at least four non-collinear points to ensure sufficient constraints. With the calibration point pairs obtained in the above steps, the existing model can be used to solve the best fitting homography matrix H. The constructed model is stored in the device program. Here are the key parameters required for the calibration model. H contains the internal parameters of the camera, such as focal length and principal point position, external parameters, such as rotation parameters and translation parameters, and possible distortion correction information. It is unique for the target scene used for calibration, and once determined, it can be used to invert the world coordinates from the image coordinates. For example, in the application scenarios of ultra-high temperature products, such as the application in steel mills, the scene is relatively fixed, with few changes and the complexity of the high-temperature target itself is relatively low. To collect infrared thermal imaging data, it is necessary to use the equipment to collect infrared images of calibrated points in the steel mill scene as required before application to obtain the homography matrix of the steel mill.

[0098] Column vector P = (X w ,Y W ,Z w ) T , pixel coordinate vector p = (u, v, z) T According to formula (1), the following is derived:

[0099] World coordinate vector P′=H ―1 *p,

[0100] According to the above formula and the world coordinates and image coordinates of the calibration points, the unit matrix can be obtained.

[0101] In the above embodiment, by collecting infrared images of calibration points in the application scenario, the homography matrix in the application scenario is calibrated, and the calibration of the homography matrix is ​​combined with the actual application field data collection, so as to obtain a more accurate actual distance of the target and improve the accuracy of the target temperature measurement.

[0102] In some embodiments, the method further comprises:

[0103] The actual temperature of the target is displayed in the infrared image.

[0104] In the above embodiment, the actual temperature of the target is displayed in the real-time infrared image, which can facilitate the user to intuitively observe the temperature of the target and improve the user experience.

[0105] In some embodiments, Figure 4 This is a block diagram of constructing model parameters in an embodiment. In some application scenarios, it is necessary to construct the model of the calculated homography matrix, the temperature compensation model, and the target background radiation correction model in advance, and then calibrate them respectively through the collected data. Then, the parameters of the three models and the mapping relationship of the models are saved, and the saved parameters are called up in the subsequent measurement process to measure the real-time temperature.

[0106] In some embodiments, Figure 5 As shown, Figure 5 This is a flow chart of an infrared temperature measurement method in another embodiment, and the flow chart includes:

[0107] S51: Acquire an infrared image of a monitoring scene.

[0108] S52, calculating the actual distance between the target in the infrared image and the image acquisition device and calculating the initial temperature of the target.

[0109] S53: Based on the actual distance, use the temperature compensation model to compensate the initial temperature to obtain a compensated temperature value of the target.

[0110] S54: Obtain the target size of the target.

[0111] S55. Based on the actual distance, the compensated temperature value and the target size, the compensated temperature value is corrected using the target background radiation correction model to determine the actual temperature of the target.

[0112] The above steps S51-S55 have been described in detail in one or more of the above embodiments and will not be repeated here.

[0113] On the other hand, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the infrared temperature measurement method described in any embodiment of the present application.

[0114] Among them, in the computer program product, an optional implementation form of the program module architecture of the computer program that implements each step of the infrared temperature measurement method can be an infrared temperature measurement device.

[0115] See also Figure 6An embodiment of the present application provides an infrared temperature measuring device, including: an acquisition module 61, used to acquire an infrared image captured from a monitoring scene; a calculation module 62, used to calculate the actual distance between a target and an image acquisition device in the infrared image and to calculate the initial temperature of the target; the acquisition module 61 is also used to acquire a temperature correction model, wherein the temperature correction model includes a temperature compensation model and / or a target background radiation correction model; the calculation module 62 is also used to correct the initial temperature based on the temperature correction model and the actual distance to obtain the actual temperature of the target.

[0116] Optionally, the acquisition module 61 is further used for:

[0117] The target temperature accuracy configured is acquired based on the user interface, and the temperature correction model is acquired according to the target temperature accuracy.

[0118] Optionally, the temperature compensation model indicates a mapping relationship between distance and temperature, and the mapping relationship between distance and temperature includes a first mapping relationship indicating distance and a first temperature fitting parameter and a second mapping relationship indicating a true temperature and a measured temperature at the same distance, wherein the first temperature fitting parameter indicates a fitting parameter in the second mapping relationship.

[0119] Optionally, the target background radiation correction model is used to indicate a mapping relationship between distance, size and temperature, and the mapping relationship between distance, size and temperature includes a third mapping relationship between the indicated size and a second temperature fitting parameter at the same distance and a fourth mapping relationship between the actual temperature and the measured temperature at the same size, wherein the second temperature fitting parameter indicates a fitting parameter in the fourth mapping relationship.

[0120] Optionally, the calculation module 62 is further used for:

[0121] Based on the actual distance, the initial temperature is compensated by using the temperature compensation model to obtain a compensated temperature value of the target; the target size of the target is obtained; based on the actual distance, the compensated temperature value and the target size, the compensated temperature value is corrected by using the target background radiation correction model to determine the actual temperature of the target;

[0122] Acquire the target size of the target, and based on the actual distance and the target size, use the target background radiation correction model to correct the initial temperature to obtain the corrected temperature of the target; based on the actual distance, use the temperature compensation model to compensate the corrected temperature to obtain the corrected temperature value of the target, and use the corrected temperature value of the target as the actual temperature of the target;

[0123] Based on the actual distance, the initial temperature is compensated by using the temperature compensation model to obtain a compensated temperature value of the target, and the compensated temperature value is used as the actual temperature of the target;

[0124] The target size of the target is obtained, and based on the actual distance and the target size, the initial temperature is corrected using the target background radiation correction model to obtain a corrected temperature of the target, and the corrected temperature of the target is used as the actual temperature of the target.

[0125] Optionally, the calculation module 62 is further used for:

[0126] Calculating a first target temperature fitting parameter corresponding to the actual distance according to a first mapping relationship between the distance and the first temperature fitting parameter in the temperature compensation model;

[0127] The compensated temperature value is calculated according to a second mapping relationship corresponding to the first target temperature fitting parameter and the initial temperature.

[0128] Optionally, the calculation module 62 is further used for:

[0129] According to the actual distance, obtaining a mapping relationship between the distance-size-temperature corresponding to the actual distance;

[0130] Acquire a third mapping relationship corresponding to the actual distance, and acquire a second target temperature fitting parameter corresponding to the target size according to the target size and the third mapping relationship corresponding to the actual distance;

[0131] The actual temperature is calculated according to a fourth mapping relationship corresponding to the second target temperature fitting parameter and the compensated temperature value.

[0132] Optionally, the calculation module 62 is further used for:

[0133] Obtaining a pre-stored temperature compensation model;

[0134] The obtaining of a pre-stored temperature compensation model comprises:

[0135] Get the real temperature of multiple calibration objects with different temperatures;

[0136] Collect the measured temperature of each calibration object at different distances;

[0137] Fitting the measured temperature and the actual temperature of each calibration object corresponding to each distance to obtain a second mapping relationship corresponding to each distance and a first temperature fitting parameter corresponding to each distance;

[0138] The first temperature fitting parameters corresponding to each distance are fitted to obtain the first mapping relationship.

[0139] Optionally, the calculation module 62 is further used for:

[0140] Get the pre-stored target background radiation correction model

[0141] The obtaining of a pre-stored target background radiation correction model comprises:

[0142] At each distance, obtaining the target background radiation correction model corresponding to each distance;

[0143] The obtaining of the target background radiation correction model corresponding to each distance includes:

[0144] Get the real temperature of multiple calibration objects with different temperatures;

[0145] For any distance, at different sizes, the measured temperature of each calibration object is collected to obtain the measured temperature of each calibration object corresponding to each size;

[0146] Fitting the measured temperature and the actual temperature of each calibration object corresponding to each size to obtain a fourth mapping relationship corresponding to each size and a second temperature fitting parameter corresponding to each size;

[0147] The second temperature fitting parameters corresponding to each size are fitted to obtain the third mapping relationship.

[0148] Optionally, the calculation module 62 is further used for:

[0149] Get the calibrated homography matrix;

[0150] Acquire the image coordinates of the target from the infrared image;

[0151] Calculating the world coordinates of the target according to the image coordinates and the homography matrix;

[0152] The actual distance between the target and the image acquisition device is calculated according to the image coordinates and the world coordinates.

[0153] Optionally, the calculation module 62 is further used for:

[0154] Obtain the reference plane and the calibration points on the reference plane, and obtain the world coordinates of each calibration point;

[0155] Acquire a reference plane image, and obtain image coordinates of each calibration point based on the reference plane image;

[0156] The homography matrix is ​​obtained based on the world coordinates and image coordinates of each calibration point.

[0157] Optionally, the calculation module 62 is further used for:

[0158] The actual temperature of the target is displayed in the infrared image.

[0159] See also Figure 7 On the other hand, an infrared temperature measurement device 10 is provided, including a processor 13 and a memory 14. The memory 14 stores a computer program. When the computer program is executed by the processor, the processor 13 executes the steps of an infrared temperature measurement method provided in any of the above embodiments of the present application.

[0160] The processor 13 is a control center, which uses various interfaces and lines to connect various parts of the entire infrared temperature measuring device, and executes various functions and processes data of the infrared temperature measuring device by running or executing software programs and / or modules stored in the memory 14, and calling data stored in the memory 14. Optionally, the processor 13 may include one or more processing cores; preferably, the processor 13 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user pages and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 13.

[0161] The memory 14 can be used to store software programs and modules. The processor 13 executes various functional applications and data processing by running the software programs and modules stored in the memory 14. The memory 14 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of an infrared temperature measurement device, etc. In addition, the memory 14 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 14 may also include a memory processor to provide the processor 13 with access to the memory 14.

[0162] On the other hand, an embodiment of the present application further provides a storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of an infrared temperature measurement method provided in any of the above embodiments of the present application.

[0163] In another aspect of an embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, an infrared temperature measurement method as described in any embodiment of the present application is implemented.

[0164] Those skilled in the art can understand that all or part of the processes in the methods provided in the above embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0165] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An infrared temperature measurement method, characterized in that: include: Acquire infrared images of the monitoring scene; Calculating the actual distance between the target in the infrared image and the image acquisition device and calculating the initial temperature of the target; Acquire a temperature correction model, wherein the temperature correction model includes a temperature compensation model and / or a target background radiation correction model; Based on the temperature correction model and the actual distance, the initial temperature is corrected to obtain the actual temperature of the target.

2. The infrared temperature measurement method according to claim 1, characterized in that: The obtaining of the temperature correction model comprises: The target temperature accuracy configured is acquired based on the user interface, and the temperature correction model is acquired according to the target temperature accuracy.

3. The infrared temperature measurement method according to claim 1, characterized in that: The temperature compensation model indicates a mapping relationship between distance and temperature, and the mapping relationship between distance and temperature includes a first mapping relationship between the distance and a first temperature fitting parameter and a second mapping relationship between the actual temperature and the measured temperature at the same distance, wherein the first temperature fitting parameter indicates a fitting parameter in the second mapping relationship.

4. The infrared temperature measurement method according to claim 1, characterized in that: The target background radiation correction model is used to indicate a mapping relationship between distance, size and temperature, wherein the mapping relationship between distance, size and temperature includes a third mapping relationship between the indicated size and a second temperature fitting parameter at the same distance and a fourth mapping relationship between the actual temperature and the measured temperature at the same size, wherein the second temperature fitting parameter indicates a fitting parameter in the fourth mapping relationship.

5. The infrared temperature measurement method according to claim 3 or 4, characterized in that: The correcting the initial temperature based on the temperature correction model and the actual distance to obtain the actual temperature of the target includes at least one of the following: Based on the actual distance, compensating the initial temperature using the temperature compensation model to obtain a compensated temperature value of the target; obtaining a target size of the target; Based on the actual distance, the compensated temperature value and the target size, the compensated temperature value is corrected using the target background radiation correction model to determine the actual temperature of the target; Acquire the target size of the target, and based on the actual distance and the target size, correct the initial temperature using the target background radiation correction model to obtain a corrected temperature of the target; Based on the actual distance, the correction temperature is compensated by using the temperature compensation model to obtain a corrected temperature value of the target, and the corrected temperature value of the target is used as the actual temperature of the target; Based on the actual distance, the initial temperature is compensated by using the temperature compensation model to obtain a compensated temperature value of the target, and the compensated temperature value is used as the actual temperature of the target; The target size of the target is obtained, and based on the actual distance and the target size, the initial temperature is corrected using the target background radiation correction model to obtain a corrected temperature of the target, and the corrected temperature of the target is used as the actual temperature of the target.

6. The infrared temperature measurement method according to claim 5, characterized in that: The step of compensating the initial temperature based on the actual distance by using the temperature compensation model to obtain a compensated temperature value of the target includes: Calculating a first target temperature fitting parameter corresponding to the actual distance according to a first mapping relationship between the distance and the first temperature fitting parameter in the temperature compensation model; The compensated temperature value is calculated according to a second mapping relationship corresponding to the first target temperature fitting parameter and the initial temperature.

7. The infrared temperature measurement method according to claim 5, characterized in that: The method of correcting the compensated temperature value based on the actual distance, the compensated temperature value and the target size by using the target background radiation correction model to determine the actual temperature of the target includes: According to the actual distance, obtaining a mapping relationship between the distance-size-temperature corresponding to the actual distance; Acquire a third mapping relationship corresponding to the actual distance, and acquire a second target temperature fitting parameter corresponding to the target size according to the target size and the third mapping relationship corresponding to the actual distance; The actual temperature is calculated according to a fourth mapping relationship corresponding to the second target temperature fitting parameter and the compensated temperature value.

8. The infrared temperature measurement method according to claim 3, characterized in that: The method further comprises: Obtaining a pre-stored temperature compensation model; The obtaining of a pre-stored temperature compensation model comprises: Get the real temperature of multiple calibration objects with different temperatures; Collect the measured temperature of each calibration object at different distances; Fitting the measured temperature and the actual temperature of each calibration object corresponding to each distance to obtain a second mapping relationship corresponding to each distance and a first temperature fitting parameter corresponding to each distance; The first temperature fitting parameters corresponding to each distance are fitted to obtain the first mapping relationship.

9. The infrared temperature measurement method according to claim 4, characterized in that: The method further comprises: Get the pre-stored target background radiation correction model The obtaining of a pre-stored target background radiation correction model comprises: At each distance, obtaining the target background radiation correction model corresponding to each distance; The obtaining of the target background radiation correction model corresponding to each distance includes: Get the real temperature of multiple calibration objects with different temperatures; For any distance, at different sizes, the measured temperature of each calibration object is collected to obtain the measured temperature of each calibration object corresponding to each size; Fitting the measured temperature and the actual temperature of each calibration object corresponding to each size to obtain a fourth mapping relationship corresponding to each size and a second temperature fitting parameter corresponding to each size; The second temperature fitting parameters corresponding to each size are fitted to obtain the third mapping relationship.

10. The infrared temperature measurement method according to claim 1, characterized in that: The calculating the actual distance between the target in the infrared image and the image acquisition device comprises: Get the calibrated homography matrix; Acquire the image coordinates of the target from the infrared image; Calculating the world coordinates of the target according to the image coordinates and the homography matrix; The actual distance between the target and the image acquisition device is calculated according to the image coordinates and the world coordinates.

11. The infrared temperature measurement method according to claim 10, characterized in that: The step of obtaining the calibrated homography matrix comprises: Obtain the reference plane and the calibration points on the reference plane, and obtain the world coordinates of each calibration point; Acquire a reference plane image, and obtain image coordinates of each calibration point based on the reference plane image; The homography matrix is ​​obtained based on the world coordinates and image coordinates of each calibration point.

12. The infrared temperature measurement method according to claim 1, characterized in that: The method further comprises: The actual temperature of the target is displayed in the infrared image.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, an infrared temperature measurement method as described in any one of claims 1 to 12 is implemented.

14. An infrared temperature measuring device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes an infrared temperature measurement method as claimed in any one of claims 1 to 12.

Images