Photometric calibration method and device for thermal infrared camera, computer device and medium

Abstract

The present disclosure provides a photometric calibration method and device for a thermal infrared camera, computer equipment and a medium, comprising: obtaining pixel point data of a first image frame, pixel point data of a second image frame and pixel point data of a third image frame collected by the thermal infrared camera; determining a target pixel intensity value of a target feature point relative to the first image frame based on the pixel point data of the first image frame and the pixel point data of the second image frame; determining a target pixel intensity value of the target feature point relative to the second image frame based on the pixel point data of the second image frame and the pixel point data of the third image frame; and performing photometric calibration on a current pixel intensity value of the target feature point in the first image frame and a current pixel intensity value of the target feature point in the second image frame based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame. Thus, the feature point tracking efficiency is effectively improved.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of photometric calibration technology, and in particular, to a photometric calibration method, apparatus, computer equipment, and medium applicable to a thermal infrared camera. Background Art

[0002] Visible spectrum cameras are used in visual inertial odometry (VIO) technology to collect real-time images of various environments. Because the color and visibility of objects depend on energy sources such as sunlight or artificial lighting, images are dependent on lighting, with intensity changes, color balance, and orientation. The data collected by visible spectrum cameras can be significantly degraded in scenes with obstructions in the air, such as thick smoke, fog, and dust, or in scenes with poor lighting conditions, such as snow and darkness.

[0003] Related technologies use thermal infrared cameras to address the visual degradation of visible spectrum cameras in special environments. However, the process of generating thermal infrared images results in low-contrast image features and photometric inconsistencies across a series of frames. This makes it impossible to provide reliable perception data across a series of frames for computer vision algorithms that rely on the assumption of photometric consistency.

[0004] However, the luminosity of adjacent frames of images captured by the thermal infrared camera is inconsistent, which affects the efficiency of feature point tracking. Summary of the Invention

[0005] The embodiments described herein provide a method, apparatus, computer device, and medium for photometric calibration of a thermal infrared camera, which overcome the aforementioned problems.

[0006] In a first aspect, according to the present disclosure, a photometric calibration method for a thermal infrared camera is provided, comprising:

[0007] Obtaining pixel data of a first image frame, pixel data of a second image frame, and pixel data of a third image frame captured by the thermal infrared camera, where the first image frame is a previous image frame of the second image frame, and the second image frame is a previous image frame of the third image frame;

[0008] Determining a target pixel intensity value of a target feature point relative to the first image frame based on pixel data of the first image frame and pixel data of the second image frame, the target feature point being a pixel point included in both the first image frame and the second image frame;

[0009] determining a target pixel intensity value of the target feature point relative to the second image frame based on the pixel data of the second image frame and the pixel data of the third image frame;

[0010] Based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, the current pixel intensity value of the target feature point in the first image frame and the current pixel intensity value of the target feature point in the second image frame are photometrically calibrated.

[0011] In a second aspect, according to the present disclosure, a photometric calibration device for a thermal infrared camera is provided, comprising:

[0012] an acquisition module, configured to acquire pixel data of a first image frame, pixel data of a second image frame, and pixel data of a third image frame captured by the thermal infrared camera, wherein the first image frame is a previous image frame of the second image frame, and the second image frame is a previous image frame of the third image frame;

[0013] a first determining module, configured to determine a target pixel intensity value of a target feature point relative to the first image frame based on pixel data of the first image frame and pixel data of the second image frame, the target feature point being a pixel point included in both the first image frame and the second image frame;

[0014] a second determining module, configured to determine a target pixel intensity value of the target feature point relative to the second image frame based on the pixel data of the second image frame and the pixel data of the third image frame;

[0015] A calibration module is used to perform photometric calibration on a current pixel intensity value of the target feature point in the first image frame and a current pixel intensity value of the target feature point in the second image frame based on a target pixel intensity value of the target feature point relative to the first image frame and a target pixel intensity value of the target feature point relative to the second image frame.

[0016] In a third aspect, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the photometric calibration method of a thermal infrared camera in any of the above embodiments are implemented.

[0017] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the photometric calibration method for a thermal infrared camera in any of the above embodiments are implemented.

[0018] An embodiment of the present application provides a photometric calibration method for a thermal infrared camera, which obtains pixel data of a first image frame, pixel data of a second image frame, and pixel data of a third image frame captured by the thermal infrared camera, where the first image frame is the previous image frame of the second image frame, and the second image frame is the previous image frame of the third image frame; based on the pixel data of the first image frame and the pixel data of the second image frame, determines a target pixel intensity value of a target feature point relative to the first image frame, where the target feature point is a pixel point contained in both the first image frame and the second image frame; based on the pixel data of the second image frame and the pixel data of the third image frame, determines a target pixel intensity value of the target feature point relative to the second image frame; based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, photometrically calibrates the current pixel intensity value of the target feature point in the first image frame and the current pixel intensity value of the target feature point in the second image frame. In this way, the corresponding pixel intensity value is determined by the current frame image data and the next frame image data, thereby realizing the photometric calibration of two adjacent frames of images, so that the same feature points in adjacent frame images share the same pixel intensity, ensuring the contrast equivalence of adjacent frame images and effectively improving the efficiency of feature point tracking.

[0019] The above description is only an overview of the technical solutions of the embodiments of the present application. In order to more clearly understand the technical means of the embodiments of the present application, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure and are not intended to limit the present disclosure.

[0021] Figure 1 The figure is a flow chart of a photometric calibration method for a thermal infrared camera provided by the present invention.

[0022] Figure 2 It is a structural schematic diagram of a photometric calibration device for a thermal infrared camera provided by the present disclosure.

[0023] Figure 3 It is a structural diagram of a computer device provided by the present disclosure.

[0024] It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work also fall within the scope of protection of the present disclosure.

[0026] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present disclosure belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the specification and the relevant art, and will not be interpreted in an idealized or overly formal manner unless otherwise explicitly defined herein. As used herein, a statement that two or more parts are "connected" or "coupled" together shall mean that the parts are joined together either directly or through one or more intermediate components.

[0027] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase "embodiment" in various places in the specification does not necessarily refer to the same embodiment, nor does it necessarily refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0028] The term "and / or" in this document simply describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists, A and B exist simultaneously, and B exists. Additionally, the character " / " in this document generally indicates that the related objects are in an "or" relationship. Terms such as "first" and "second" are used solely to distinguish one component (or portion of a component) from another component (or portion of a component).

[0029] In the description of this application, unless otherwise specified, "plurality" means more than two (including two), and similarly, "multiple groups" means more than two (including two).

[0030] Thermal infrared cameras offer compelling complementary advantages to visible spectrum cameras and various radar technologies. The properties of the thermal infrared modality make it highly robust to low lighting conditions and the presence of adverse obstructions. As thermal infrared cameras continue to improve in resolution and portability, they are increasingly being used in applications such as robotic vision, industrial inspection, and medical imaging. However, the performance of traditional computer vision techniques developed for electro-optical imagery does not directly translate to thermal infrared cameras. This is primarily due to the photometric assumptions these algorithms require, and photometric calibration methods for RGB cameras are not applicable to thermal infrared cameras due to differences in data acquisition and sensor phenomenology.

[0031] In particular, one of the biggest challenges for visual odometry and SLAM algorithms is the photometric inconsistency caused by rapid automatic gain changes. When a hot object moves in and out of the camera's field of view, large areas of pixels are saturated, and the sensor adjusts the gain to darken the image in an attempt to avoid saturation. The resulting pixel intensity variations from one frame to the next can be noticeable, invalidating the constant brightness assumption enforced in most conventional computer vision tasks (direct or feature-based).

[0032] To this end, this embodiment processes thermal images through an online photometric calibration algorithm of a thermal infrared camera, thereby attenuating low-frequency non-uniformity and photometric inconsistency problems, so that the calibrated thermal image frame has a higher contrast than the original thermal image frame, and increases the number of tracked feature points.

[0033] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0034] Figure 1 FIG. 1 is a flow chart of a photometric calibration method for a thermal infrared camera provided by an embodiment of the present disclosure. Figure 1 As shown in the figure, the specific process of the photometric calibration method of the thermal infrared camera includes:

[0035] S110 , obtaining pixel data of a first image frame, pixel data of a second image frame, and pixel data of a third image frame captured by a thermal infrared camera.

[0036] The first image frame is the previous image frame of the second image frame, and the second image frame is the previous image frame of the third image frame. It can be understood that the first image frame and the second image frame are two adjacent image frames, and the second image frame and the third image frame are two adjacent image frames.

[0037] The pixel data of the first image frame may include, but is not limited to, the current pixel intensity value of each feature point in the first image frame, the maximum pixel intensity value and the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the first image frame. The pixel data of the second image frame may include, but is not limited to, the current pixel intensity value of each feature point in the second image frame, the maximum pixel intensity value and the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the second image frame. The pixel data of the third image frame may include, but is not limited to, the current pixel intensity value of each feature point in the third image frame, the maximum pixel intensity value and the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the third image frame.

[0038] S120 : Determine a target pixel intensity value of the target feature point relative to the first image frame based on the pixel data of the first image frame and the pixel data of the second image frame.

[0039] The target feature points are pixels contained in both the first image frame and the second image frame, that is, the target feature points are contained in both the first image frame and the second image frame.

[0040] In some embodiments, the pixel data of the first image frame includes: the current pixel intensity value of the target feature point in the first image frame, and the pixel data of the second image frame includes: the intensity difference representation data and the minimum intensity representation data corresponding to the second image frame.

[0041] The intensity difference representation data corresponding to the second image frame is the difference between the maximum pixel intensity value and the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the second image frame. The minimum intensity representation data corresponding to the second image frame is the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the second image frame.

[0042] Determining a target pixel intensity value of a target feature point relative to the first image frame based on pixel data of the first image frame and pixel data of the second image frame includes:

[0043] Obtain intensity difference characterization data and minimum intensity characterization data corresponding to the target reference frame; determine the intensity relative data between the second image frame and the target reference frame based on the intensity difference characterization data and minimum intensity characterization data corresponding to the second image frame, and the intensity difference characterization data and minimum intensity characterization data corresponding to the target reference frame; determine the intensity relative data between the first image frame and the target reference frame based on the intensity relative data between the second image frame and the target reference frame; determine the target pixel intensity value of the target feature point relative to the first image frame based on the intensity relative data between the first image frame and the target reference frame and the current pixel intensity value of the target feature point in the first image frame.

[0044] The target reference frame includes target feature points, and the target feature points have no intensity deviation in the target reference frame.

[0045] The intensity relative data between the second image frame and the target reference frame includes first difference relative data and first minimum value relative data.

[0046] The intensity relative data between the first image frame and the target reference frame includes: second difference relative data and second minimum value relative data.

[0047] The process of determining the relative intensity data between the first image frame and the target reference frame based on the relative intensity data between the second image frame and the target reference frame is shown in formula (1).

[0048]

[0049] In formula (1), C t represents the set of corresponding pixels between frame t and frame t+1. The derivation process of formula (1) is as follows.

[0050] Building a photometric model for a thermal infrared camera: A microbolometer is a temperature-dependent resistor. Infrared radiation with a wavelength between 7.5 and 14 μm impinges on the detector material, heating it and changing its resistance. This change in resistance is measured by a readout integrated circuit and processed as temperature. Many such microbolometers are arranged in a 2D grid to form a focal plane uncooled microbolometer array, where the temperature reading from each microbolometer is used to generate the intensity of the corresponding pixel in the image.

[0051] The infrared energy radiated by an object includes energy emitted, transmitted, and reflected by the object. The photometric model for thermal infrared cameras assumes that the infrared emissivity of an object is independent of the observer's viewing angle. While this only applies to blackbody objects, studies of various materials have shown that the emissivity is essentially constant for nearly all practically relevant surfaces, at least up to a viewing angle of ±45°. Furthermore, outside this range, for scenes dominated by non-conductors, the emissivity does not vary significantly with minimal changes in viewing angle, until extreme viewing angles greater than 78° are reached.

[0052] Consider a 3D point in the world coordinate system scene, which emits a constant amount of infrared energy with a radiated power of Φ0. The resistance change of the micro-bolometer is shown in formula (2).

[0053]

[0054] In formula (2), αΦ0 is the absorbed radiation power; β is the thermal coefficient; G th is the total thermal conductivity.

[0055] The change in resistance can also be expressed as the temperature change ΔT of the microbolometer, as shown in formula (3).

[0056]

[0057] In formula (3), is the average value in the temperature interval ΔT.

[0058] If the microbolometer is min , Φ max ] is sensitive to the energy range given by, then the normalized response of the sensor is given by I = (Φ-Φ min ) / (Φ max -Φ min ). The response I is used to generate the intensity value of the corresponding pixel in the synthetic image I: Ω→[0, 1], where Ω represents the image domain.

[0059] The image intensity of a scene point with constant thermal radiant energy varies when viewed at different spatial locations in the image. In visible spectrum cameras, this spatially varying image intensity contributes to radial lens vignetting and is modeled as a sixth-order polynomial, with the vignetting center coinciding with the image center, assuming the attenuation factors follow the radial model. For TIR cameras, this spatial variation does not have a predefined or symmetrical shape. This variation can be due to two main reasons: ① The response of each microbolometer may be different due to sensor design characteristics or saturation, resulting in residual errors in its readings; and ② Any infrared projection effects, including lensing, that lead to non-uniform transparency.

[0060] For photometric calibration, low-frequency inhomogeneities are of particular concern; variations distributed across a large area of ​​pixels can be significant enough to introduce photometric errors. Microbolometers can also be heated by the camera itself, most commonly due to saturation inhomogeneities and lack of cooling during operation. Consequently, cameras based on low-cost, uncooled microbolometer arrays are more susceptible to low-frequency spatial variations.

[0061] Use Ι' x =s x (Ι x +r x ) affine sensor response to model this effect. However, we note that using only the bias factor r x and ignore the scale factor s x It is sufficient to model this low-frequency effect while reducing the number of parameters by half, and the spatial offset can be expressed as shown in formula (4).

[0062] Ι' x =s x (Ι x +rx ) (4)

[0063] It is also observed that the camera tries to maintain the best possible temperature resolution at each time t (or frame) in the image, so the spatial offset can be expressed as a normalized value as shown in equation (5).

[0064]

[0065] In formula (5), in the range [I' t,min ,Ι' t,max ]Inside, Ι' t,min and Ι' t,max are the minimum and maximum responses among all microbolometers for a particular frame t, respectively. So the raw response of the sensor after spatial error is converted to I′ before being used to generate the image. t,min and scaling factor (I' t,max -Ι' t,min ) -1 This is often the main cause of gain variations or AGC effects, and also means that scene points with constant thermal radiation energy may appear with different image intensities in consecutive frames.

[0066] Combining formula (4) and formula (5), the normalized temperature response is shown in formula (6).

[0067]

[0068] Substituting parameters in formula (6) yields formula (7).

[0069]

[0070] In formula (7), similar to the visual spectrum image, the gain change is described as an affine brightness response. at =Ι' t,max -Ι' t,min , b t =Ι' t,min . Scale factor e -at The logarithmic parameterization of is to prevent it from becoming negative and make it numerically stable.

[0071] In summary, the goal of the photometric calibration proposed in this embodiment is to try to estimate a for each frame of image. t and b t And r for each pixel x , so that scene points with constant radiant energy in the world coordinate system should have the same image intensity value that is invariant to the time frame and spatial position.

[0072] Let p, m, n e Ω be the pixel positions of the same 3D world point in frames o, t and t+1 respectively, according to the photometric constancy assumption in optical flow method, we have I p = I m = I n Without loss of generality, let o be the assumed frame with b = 0, and no residual error, then we have I' o = I p,o = I p In other frames t and t+1, the parameters can also be expressed in terms of the assumed frame o.

[0073] Based on equation (7) for frame t, the target pixel intensity value at m position of the feature point in frame t is given by equation (8).

[0074]

[0075] In equation (8), p r m = r m - r p , r m is the spatial position offset of the target feature point in the current image frame; r p is the spatial position offset of the target feature point in the target reference frame; o b t and are the intensity relative data between the current image frame and the target reference frame respectively.

[0076] For frame t+1, eliminating I' p,o term, the target pixel intensity value at n position of the feature point in frame t+1 is given by equation (9).

[0077]

[0078] In equation (9), p r n = r n - r p , r n is the spatial position offset of the target feature point in the next image frame; r o b t+1 and are the intensity relative data between the next image frame and the target reference frame respectively.

[0079] The function f P (I' m,t ) can be decomposed into equation (10).

[0080]

[0081] In formula (10), P = P t ∪Ρ s is a set of unknown parameters related to time and space changes. Therefore, each frame has two unknown parameters and an additional unknown parameter P s =O(|Ω|), the goal of photometric calibration is to use the pixel correspondence between frames to perform effective estimation in a real-time online manner.

[0082] Assuming ε is zero-mean Gaussian noise, formula (9) can be transformed into formula (11).

[0083]

[0084] In formula (11), Δ n,m = p r n - p r m When ignoring HP t， P s Item, and only consider p t The parameter estimate is p t The maximum likelihood estimate of corresponds to the solution of the least squares objective function given by the above formula (1).

[0085] According to formula (10-11), the item becomes part of the error term, but unlike the ε term, it does not satisfy the zero mean. At the same time, minimizing the objective function formula (11) helps the term The minimization of It plays a reverse role, because when Δ n,m >0, will increase, and vice versa.

[0086] There are two unknown time parameters in each frame ( o a t , o b t ), in order to maintain a high frame rate throughput, it is desirable to update them with minimal computational overhead. Since the spatial changes occur in small regions of the image, it can be assumed that the pixel correspondences in most images have Δ n,m ≈0, and those with △ n,m >>0 pixel correspondences will account for a small proportion, and the RANSAC method can be used to remove outliers and estimate P t item.

[0087] Based on the relative intensity data between the first image frame and the target reference frame and the current pixel intensity value of the target feature point in the first image frame, the target pixel intensity value of the target feature point relative to the first image frame is determined, as shown in formula (12).

[0088]

[0089] In formula (12), I1 is the current pixel intensity value of the target feature point in the first image frame; o b1 and are the relative intensity data between the first image frame and the target reference frame respectively.

[0090] In some embodiments, the present invention further comprises:

[0091] Obtain a spatial position offset of the target feature point in the first image frame and a spatial position offset of the target feature point in the target reference frame; determine a spatial position offset difference of the target feature point relative to the first image frame based on the spatial position offset of the target feature point in the first image frame and the spatial position offset of the target feature point in the target reference frame; and update a target pixel intensity value of the target feature point relative to the first image frame based on the spatial position offset difference of the target feature point relative to the first image frame.

[0092] Among them, the spatial position offset difference of the target feature point relative to the first image frame is o r1=r1-r o , r1 is the spatial position offset of the target feature point in the first image frame, r o The spatial position offset of the target feature point in the target reference frame.

[0093] Based on the spatial position offset difference of the target feature point relative to the first image frame, the target pixel intensity value of the target feature point relative to the first image frame is updated. This can be done by adding the spatial position offset difference of the target feature point relative to the first image frame to the target pixel intensity value of the target feature point relative to the first image frame. For details, see formula (13).

[0094]

[0095] Therefore, by adding the spatial position offset difference of the target feature point relative to the first image frame to the target pixel intensity value of the target feature point relative to the first image frame, the accuracy of the target pixel intensity value of the target feature point relative to the first image frame can be effectively improved.

[0096] S130 : Determine a target pixel intensity value of the target feature point relative to the second image frame based on the pixel data of the second image frame and the pixel data of the third image frame.

[0097] In some embodiments, the pixel point data of the second image frame also includes: the current pixel intensity value of the target feature point in the second image frame, and the pixel point data of the third image frame includes: the intensity difference characterization data and the minimum intensity characterization data corresponding to the third image frame.

[0098] The intensity difference representation data corresponding to the third image frame is the difference between the maximum pixel intensity value and the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the third image frame. The minimum intensity representation data corresponding to the third image frame is the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the third image frame.

[0099] Determining a target pixel intensity value of a target feature point relative to the second image frame based on pixel data of the second image frame and pixel data of the third image frame includes:

[0100] Based on the intensity difference characterization data and minimum intensity characterization data corresponding to the third image frame, and the intensity difference characterization data and minimum intensity characterization data corresponding to the target reference frame, determine the intensity relative data between the third image frame and the target reference frame; based on the intensity relative data between the third image frame and the target reference frame, determine the intensity relative data between the second image frame and the target reference frame; based on the intensity relative data between the second image frame and the target reference frame and the current pixel intensity value of the target feature point in the second image frame, determine the target pixel intensity value of the target feature point relative to the second image frame.

[0101] The relative intensity data between the third image frame and the target reference frame includes third difference relative data and third minimum value relative data.

[0102] Based on the relative intensity data between the third image frame and the target reference frame, the relative intensity data between the second image frame and the target reference frame is determined. The principle of solving the relative intensity data between the first image frame and the target reference frame is the same and will not be repeated here.

[0103] Based on the relative intensity data between the second image frame and the target reference frame and the current pixel intensity value of the target feature point in the second image frame, the target pixel intensity value of the target feature point relative to the second image frame is determined, as shown in formula (14).

[0104]

[0105] In formula (14), I2 is the current pixel intensity value of the target feature point in the second image frame; o b2 and are the relative intensity data between the second image frame and the target reference frame respectively.

[0106] In some embodiments, the present invention further comprises:

[0107] Obtain a spatial position offset of the target feature point in the second image frame; determine a spatial position offset difference of the target feature point relative to the second image frame based on the spatial position offset of the target feature point in the second image frame and the spatial position offset of the target feature point in the target reference frame; and update a target pixel intensity value of the target feature point relative to the second image frame based on the spatial position offset difference of the target feature point relative to the second image frame.

[0108] Among them, the spatial position offset difference of the target feature point relative to the second image frame is o r2=r2-r o , r2 is the spatial position offset of the target feature point in the second image frame.

[0109] Based on the spatial position offset difference of the target feature point relative to the second image frame, the target pixel intensity value of the target feature point relative to the second image frame is updated by adding the spatial position offset difference of the target feature point relative to the second image frame to the target pixel intensity value of the target feature point relative to the second image frame. For details, see formula (15).

[0110]

[0111] Therefore, by adding the spatial position offset difference of the target feature point relative to the second image frame to the target pixel intensity value of the target feature point relative to the second image frame, the accuracy of the target pixel intensity value of the target feature point relative to the second image frame can be effectively improved.

[0112] S140. Based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, perform photometric calibration on the current pixel intensity value of the target feature point in the first image frame and the current pixel intensity value of the target feature point in the second image frame.

[0113] Among them, after the current pixel intensity value of the target feature point in the first image frame and the current pixel intensity value of the target feature point in the second image frame are photometrically calibrated, the current pixel intensity value of the target feature point in the first image frame after calibration is the same as the current pixel intensity value of the target feature point in the second image frame after calibration.

[0114] In some embodiments, photometrically calibrating a current pixel intensity value of the target feature point in the first image frame and a current pixel intensity value of the target feature point in the second image frame based on a target pixel intensity value of the target feature point relative to the first image frame and a target pixel intensity value of the target feature point relative to the second image frame includes:

[0115] Based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, the pixel calibration intensity value corresponding to the target feature point is determined; based on the pixel calibration intensity value corresponding to the target feature point, the current pixel intensity value of the target feature point in the first image frame is photometrically calibrated; based on the pixel calibration intensity value corresponding to the target feature point, the current pixel intensity value of the target feature point in the second image frame is photometrically calibrated.

[0116] When photometrically calibrating the current pixel intensity value of a target feature point in a first image frame based on the pixel calibration intensity value corresponding to the target feature point, the pixel calibration intensity value corresponding to the target feature point can be used to replace the current pixel intensity value of the target feature point in the first image frame. When photometrically calibrating the current pixel intensity value of a target feature point in a second image frame based on the pixel calibration intensity value corresponding to the target feature point, the pixel calibration intensity value corresponding to the target feature point can be used to replace the current pixel intensity value of the target feature point in the second image frame. This ensures that the same feature point has the same intensity response in two adjacent image frames.

[0117] In some embodiments, determining a pixel calibration intensity value corresponding to a target feature point based on a target pixel intensity value of the target feature point relative to a first image frame and a target pixel intensity value of the target feature point relative to a second image frame includes:

[0118] Based on the photometric calibration data of the target feature point in the first image frame and the photometric calibration data of the target feature point in the second image frame, determine the calibration weight of the target feature point relative to the first image frame and the calibration weight of the target feature point relative to the second image frame; based on the calibration weight of the target feature point relative to the first image frame, the calibration weight of the target feature point relative to the second image frame, the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, determine the pixel calibration intensity value corresponding to the target feature point.

[0119] The photometric calibration data of the target feature point in the first image frame can be used to describe the number of photometric calibrations of the target feature point in the first image frame. The photometric calibration data of the target feature point in the second image frame can be used to describe the number of photometric calibrations of the target feature point in the second image frame.

[0120] Based on the photometric calibration data of the target feature point in the first image frame and the photometric calibration data of the target feature point in the second image frame, determining the calibration weight of the target feature point relative to the first image frame and the calibration weight of the target feature point relative to the second image frame may include: if the photometric calibration data of the target feature point in the first image frame and the photometric calibration data of the target feature point in the second image frame are the same, then determining that the calibration weight of the target feature point relative to the first image frame and the calibration weight of the target feature point relative to the second image frame are both 0.5; if the photometric calibration data of the target feature point in the first image frame and the photometric calibration data of the target feature point in the second image frame are different, then the image frame with a larger photometric calibration data has a larger calibration weight. Therefore, it is convenient to formulate corresponding calibration weights for the target feature points based on the photometric calibration data in different image frames, so as to effectively improve the accuracy of photometric calibration.

[0121] In addition, the average of the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame may be determined as the pixel calibration intensity value corresponding to the target feature point.

[0122] In this embodiment, pixel data of a first image frame, pixel data of a second image frame, and pixel data of a third image frame captured by a thermal infrared camera are obtained, where the first image frame is the previous image frame of the second image frame, and the second image frame is the previous image frame of the third image frame; based on the pixel data of the first image frame and the pixel data of the second image frame, a target pixel intensity value of a target feature point relative to the first image frame is determined, where the target feature point is a pixel point contained in both the first image frame and the second image frame; based on the pixel data of the second image frame and the pixel data of the third image frame, a target pixel intensity value of the target feature point relative to the second image frame is determined; based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, photometric calibration is performed on the current pixel intensity value of the target feature point in the first image frame and the current pixel intensity value of the target feature point in the second image frame. In this way, the corresponding pixel intensity value is determined by the current frame image data and the next frame image data, thereby realizing the photometric calibration of two adjacent frames of images, so that the same feature points in adjacent frame images share the same pixel intensity, ensuring the contrast equivalence of adjacent frame images and effectively improving the efficiency of feature point tracking.

[0123] In addition, considering any pair of (t, t+1) frames, instead of estimating all unknown parameters about the hypothetical frame o ( o a t , o b t , o a t+1 , o b t+1), but rather estimates its relative parameter term ( t a t+1 , t b t+1 ), as shown in the following formulas (16) and (17).

[0124]

[0125]

[0126] Combining formula (10), formula (16) and formula (17), while ignoring hp t， P s , as shown in the following formula (18).

[0127]

[0128] The above are all continuous image frames (t, t+1) to show the meaning of sequential and gradual process. However, in the case of corresponding pixel relationship, it can be extended to any two image frames i, j, and O is used in formula (11). Τ (g'p' t ,C i,j ) to estimate the relative parameter P′ i,j ={ i a j , i b j}.

[0129] In fact, the current frame t can have pixel correspondences with multiple previous frames t-1, t-2, tk, ..., all of which can be used to obtain P' t-1,t ={ t-1 a t , t-1 b t Therefore, we redefine C t =C t-1,t ∪C t-2,t ∪C t-k,t ∪… represents the set of all corresponding pixel relationships from multiple previous frames to the current frame t.

[0130] set up is the set of all parameters of N frames relative to the first frame, where P′ 1,1 ={ 1 a1=1, 1 b1=0} For other frames x≠1, P′ 1,x It can be calculated by the chain rule using the following formulas (19) and (20).

[0131]

[0132]

[0133] Consider the estimated time parameter P t 'Think it is robust enough to estimate P s Therefore, for P t ' is known, similar to formula (18), using formula (10), formula (17), formula (18) and not neglected, we can get the value of P s Linear function of As shown in the following formula (21).

[0134]

[0135] Figure 2 This is a structural diagram of a photometric calibration device for a thermal infrared camera provided in this embodiment. The photometric calibration device for a thermal infrared camera may include: an acquisition module 210 , a first determination module 220 , a second determination module 230 and a calibration module 240 .

[0136] The acquisition module 210 is used to obtain pixel data of the first image frame, pixel data of the second image frame and pixel data of the third image frame captured by the thermal infrared camera, where the first image frame is the previous image frame of the second image frame and the second image frame is the previous image frame of the third image frame.

[0137] The first determination module 220 is used to determine the target pixel intensity value of the target feature point relative to the first image frame based on the pixel data of the first image frame and the pixel data of the second image frame. The target feature point is a pixel point contained in both the first image frame and the second image frame.

[0138] The second determining module 230 is configured to determine a target pixel intensity value of the target feature point relative to the second image frame based on the pixel data of the second image frame and the pixel data of the third image frame.

[0139] The calibration module 240 is used to perform photometric calibration on the current pixel intensity value of the target feature point in the first image frame and the current pixel intensity value of the target feature point in the second image frame based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame.

[0140] In this embodiment, optionally, the pixel point data of the first image frame includes: the current pixel intensity value of the target feature point in the first image frame, and the pixel point data of the second image frame includes: the intensity difference representation data and minimum intensity representation data corresponding to the second image frame.

[0141] The first determining module 220 is specifically configured to:

[0142] Obtain intensity difference characterization data and minimum intensity characterization data corresponding to the target reference frame, wherein the target reference frame includes target feature points, and the target feature points have no intensity deviation in the target reference frame; determine the intensity relative data between the second image frame and the target reference frame based on the intensity difference characterization data and minimum intensity characterization data corresponding to the second image frame, and the intensity difference characterization data and minimum intensity characterization data corresponding to the target reference frame; determine the intensity relative data between the first image frame and the target reference frame based on the intensity relative data between the second image frame and the target reference frame; determine the target pixel intensity value of the target feature point relative to the first image frame based on the intensity relative data between the first image frame and the target reference frame and the current pixel intensity value of the target feature point in the first image frame.

[0143] In this embodiment, optionally, it further includes: a third determination module and an update module.

[0144] The acquisition module 210 is further configured to acquire the spatial position offset of the target feature point in the first image frame and the spatial position offset of the target feature point in the target reference frame.

[0145] The third determining module is used to determine the spatial position offset difference of the target feature point relative to the first image frame based on the spatial position offset of the target feature point in the first image frame and the spatial position offset of the target feature point in the target reference frame.

[0146] The updating module is configured to update a target pixel intensity value of the target feature point relative to the first image frame based on a spatial position offset difference of the target feature point relative to the first image frame.

[0147] In this embodiment, optionally, the pixel point data of the second image frame also includes: the current pixel intensity value of the target feature point in the second image frame, and the pixel point data of the third image frame includes: the intensity difference characterization data and minimum intensity characterization data corresponding to the third image frame.

[0148] The second determining module 230 is specifically configured to:

[0149] Based on the intensity difference characterization data and minimum intensity characterization data corresponding to the third image frame, and the intensity difference characterization data and minimum intensity characterization data corresponding to the target reference frame, determine the intensity relative data between the third image frame and the target reference frame; based on the intensity relative data between the third image frame and the target reference frame, determine the intensity relative data between the second image frame and the target reference frame; based on the intensity relative data between the second image frame and the target reference frame and the current pixel intensity value of the target feature point in the second image frame, determine the target pixel intensity value of the target feature point relative to the second image frame.

[0150] In this embodiment, optionally, it further includes: a fourth determining module.

[0151] The acquisition module 210 is further configured to acquire the spatial position offset of the target feature point in the second image frame.

[0152] The fourth determining module is used to determine the spatial position offset difference of the target feature point relative to the second image frame based on the spatial position offset of the target feature point in the second image frame and the spatial position offset of the target feature point in the target reference frame.

[0153] The updating module is further configured to update the target pixel intensity value of the target feature point relative to the second image frame based on the spatial position offset difference of the target feature point relative to the second image frame.

[0154] In this embodiment, optionally, the calibration module 240 is specifically configured to:

[0155] Based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, the pixel calibration intensity value corresponding to the target feature point is determined; based on the pixel calibration intensity value corresponding to the target feature point, the current pixel intensity value of the target feature point in the first image frame is photometrically calibrated; based on the pixel calibration intensity value corresponding to the target feature point, the current pixel intensity value of the target feature point in the second image frame is photometrically calibrated.

[0156] In this embodiment, optionally, the calibration module 240 is specifically configured to:

[0157] Based on the photometric calibration data of the target feature point in the first image frame and the photometric calibration data of the target feature point in the second image frame, determine the calibration weight of the target feature point relative to the first image frame and the calibration weight of the target feature point relative to the second image frame; based on the calibration weight of the target feature point relative to the first image frame, the calibration weight of the target feature point relative to the second image frame, the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, determine the pixel calibration intensity value corresponding to the target feature point.

[0158] The photometric calibration device for a thermal infrared camera provided in the present disclosure can execute the above method embodiments. Its specific implementation principles and technical effects can be found in the above method embodiments, and the present disclosure will not elaborate on them here.

[0159] The present application also provides a computer device. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0160] The computer device includes a memory 310 and a processor 320 that are interconnected and communicate with each other via a system bus. It should be noted that the figure only shows a computer device with a memory 310 and a processor 320, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0161] Computer devices can be desktop computers, laptops, PDAs, cloud servers, etc. Computer devices can interact with users through keyboards, mice, remote controls, touchpads, or voice-activated devices.

[0162] The memory 310 includes at least one type of readable storage medium, including non-volatile memory or volatile memory, such as flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, magnetic disk, optical disk, etc. The RAM may include static RAM or dynamic RAM. In some embodiments, the memory 310 may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory 310 may also be an external storage device of the computer device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, or a Flash Card equipped on the computer device. Of course, the memory 310 may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the memory 310 is generally used to store the operating system and various application software installed on the computer device, such as the program code of the above-mentioned method. In addition, the memory 310 may also be used to temporarily store various types of data that have been output or are about to be output.

[0163] The processor 320 is generally used to perform the overall operation of the computer device. In this embodiment, the memory 310 is used to store program code or instructions, which include computer operating instructions. The processor 320 is used to execute the program code or instructions stored in the memory 310 or process data, such as the program code for running the above method.

[0164] In this document, a bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. This bus system can be divided into address buses, data buses, and control buses. For ease of illustration, the figure uses only one thick line, but this does not mean that there is only one bus or only one type of bus.

[0165] Another embodiment of the present application further provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads the computer-readable program code stored in the computer-readable medium, enabling the processor to execute the functional actions specified in each step or combination of steps in the above method, and to generate a device that implements the functional actions specified in each block or combination of blocks in the block diagram.

[0166] Computer-readable media include but are not limited to electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any appropriate combination of the foregoing, the memory is used to store program codes or instructions, the program codes include computer operating instructions, and the processor is used to execute the program codes or instructions of the above-mentioned methods stored in the memory.

[0167] For the definitions of memory and processor, please refer to the description of the aforementioned computer device embodiment and will not be repeated here.

[0168] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0169] Each functional unit or module in each embodiment of the present application may be integrated into a processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The above-mentioned integrated units may be implemented in the form of hardware or software functional units.

[0170] If the integrated unit is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0171] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In the device claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used to advantage. The use of relative terms such as "first", "second" and "third", etc. does not connote any prioritization, but such terms are used to distinguish a certain feature from another feature with the same name. The steps of the methods described in the above embodiments should not be understood as necessarily limited in their sequence, except when this is explicitly specified.

[0172] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; even though the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still make modifications to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A photometric calibration method for a thermal infrared camera, characterized in that: include: Obtaining pixel data of a first image frame, pixel data of a second image frame, and pixel data of a third image frame captured by the thermal infrared camera, where the first image frame is a previous image frame of the second image frame, and the second image frame is a previous image frame of the third image frame; The pixel data of the first image frame includes: the current pixel intensity value of the target feature point in the first image frame, the pixel data of the second image frame includes: intensity difference representation data, minimum intensity representation data and the current pixel intensity value of the target feature point in the second image frame corresponding to the second image frame; the target feature point is a pixel point included in both the first image frame and the second image frame; the pixel data of the third image frame includes: intensity difference representation data and minimum intensity representation data corresponding to the third image frame; the intensity difference representation data is the difference between the maximum pixel intensity value and the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the corresponding image frame; the minimum intensity representation data is the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the corresponding image frame; Obtaining intensity difference characterization data and minimum intensity characterization data corresponding to a target reference frame, wherein the target reference frame includes the target feature point, and the target feature point has no intensity deviation in the target reference frame; determining intensity relative data between the second image frame and the target reference frame based on the intensity difference characterization data and minimum intensity characterization data corresponding to the second image frame, and the intensity difference characterization data and minimum intensity characterization data corresponding to the target reference frame; determining intensity relative data between the first image frame and the target reference frame based on the intensity relative data between the second image frame and the target reference frame; determining a target pixel intensity value of the target feature point relative to the first image frame based on the intensity relative data between the first image frame and the target reference frame and a current pixel intensity value of the target feature point in the first image frame; determining intensity relative data between the third image frame and the target reference frame based on the intensity difference characterization data and the minimum intensity characterization data corresponding to the third image frame, and the intensity difference characterization data and the minimum intensity characterization data corresponding to the target reference frame; determining intensity relative data between the second image frame and the target reference frame based on the intensity relative data between the third image frame and the target reference frame; and determining a target pixel intensity value of the target feature point relative to the second image frame based on the intensity relative data between the second image frame and the target reference frame and a current pixel intensity value of the target feature point in the second image frame; Based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, the current pixel intensity value of the target feature point in the first image frame and the current pixel intensity value of the target feature point in the second image frame are photometrically calibrated.

2. The method according to claim 1, characterized in that Also includes: Acquire a spatial position offset of the target feature point in the first image frame and a spatial position offset of the target feature point in the target reference frame; determining a spatial position offset difference of the target feature point relative to the first image frame based on a spatial position offset of the target feature point in the first image frame and a spatial position offset of the target feature point in the target reference frame; Based on the spatial position offset difference of the target feature point relative to the first image frame, the target pixel intensity value of the target feature point relative to the first image frame is updated.

3. The method according to claim 1, characterized in that Also includes: Obtaining a spatial position offset of the target feature point in the second image frame; determining a spatial position offset difference of the target feature point relative to the second image frame based on a spatial position offset of the target feature point in the second image frame and a spatial position offset of the target feature point in the target reference frame; Based on the spatial position offset difference of the target feature point relative to the second image frame, the target pixel intensity value of the target feature point relative to the second image frame is updated.

4. The method according to claim 1, wherein The performing photometric calibration on a current pixel intensity value of the target feature point in the first image frame and a current pixel intensity value of the target feature point in the second image frame based on a target pixel intensity value of the target feature point relative to the first image frame and a target pixel intensity value of the target feature point relative to the second image frame, comprising: Determining a pixel calibration intensity value corresponding to the target feature point based on a target pixel intensity value of the target feature point relative to the first image frame and a target pixel intensity value of the target feature point relative to the second image frame; performing photometric calibration on a current pixel intensity value of the target feature point in the first image frame based on a pixel calibration intensity value corresponding to the target feature point; Based on the pixel calibration intensity value corresponding to the target feature point, photometric calibration is performed on the current pixel intensity value of the target feature point in the second image frame.

5. The method according to claim 4, characterized in that The determining, based on the target pixel intensity value of the target feature point relative to the first image frame and the target pixel intensity value of the target feature point relative to the second image frame, a pixel calibration intensity value corresponding to the target feature point includes: Determining, based on photometric calibration data of the target feature point in the first image frame and photometric calibration data of the target feature point in the second image frame, a calibration weight of the target feature point relative to the first image frame and a calibration weight of the target feature point relative to the second image frame; Based on the calibration weight of the target feature point relative to the first image frame, the calibration weight of the target feature point relative to the second image frame, the target pixel intensity value of the target feature point relative to the first image frame, and the target pixel intensity value of the target feature point relative to the second image frame, determine the pixel calibration intensity value corresponding to the target feature point.

6. A photometric calibration device for a thermal infrared camera, characterized in that: include: an acquisition module, configured to acquire pixel data of a first image frame, pixel data of a second image frame, and pixel data of a third image frame captured by the thermal infrared camera, wherein the first image frame is a previous image frame of the second image frame, and the second image frame is a previous image frame of the third image frame; The pixel data of the first image frame includes: the current pixel intensity value of the target feature point in the first image frame, the pixel data of the second image frame includes: intensity difference representation data, minimum intensity representation data and the current pixel intensity value of the target feature point in the second image frame corresponding to the second image frame; the target feature point is a pixel point included in both the first image frame and the second image frame; the pixel data of the third image frame includes: intensity difference representation data and minimum intensity representation data corresponding to the third image frame; the intensity difference representation data is the difference between the maximum pixel intensity value and the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the corresponding image frame; the minimum intensity representation data is the minimum pixel intensity value among the current pixel intensity values ​​of all feature points included in the corresponding image frame; a first determination module, configured to obtain intensity difference characterization data and minimum intensity characterization data corresponding to a target reference frame, wherein the target reference frame includes the target feature point and the target feature point has no intensity deviation in the target reference frame; determine intensity relative data between the second image frame and the target reference frame based on the intensity difference characterization data and minimum intensity characterization data corresponding to the second image frame and the intensity difference characterization data and minimum intensity characterization data corresponding to the target reference frame; determine intensity relative data between the first image frame and the target reference frame based on the intensity relative data between the second image frame and the target reference frame; and determine a target pixel intensity value of the target feature point relative to the first image frame based on the intensity relative data between the first image frame and the target reference frame and a current pixel intensity value of the target feature point in the first image frame; a second determining module, configured to determine relative intensity data between the third image frame and the target reference frame based on the intensity difference characterization data and the minimum intensity characterization data corresponding to the third image frame, and the intensity difference characterization data and the minimum intensity characterization data corresponding to the target reference frame; determine relative intensity data between the second image frame and the target reference frame based on the relative intensity data between the third image frame and the target reference frame; and determine a target pixel intensity value of the target feature point relative to the second image frame based on the relative intensity data between the second image frame and the target reference frame and a current pixel intensity value of the target feature point in the second image frame; A calibration module is used to perform photometric calibration on a current pixel intensity value of the target feature point in the first image frame and a current pixel intensity value of the target feature point in the second image frame based on a target pixel intensity value of the target feature point relative to the first image frame and a target pixel intensity value of the target feature point relative to the second image frame.

7. A computer device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the photometric calibration method for a thermal infrared camera as claimed in any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the photometric calibration method for a thermal infrared camera as claimed in any one of claims 1 to 5 is implemented.

Images