Thermal infrared imager multi-temperature and regional target detection method
By using solid circular array pattern calibration plate and affine transformation model in infrared thermal image cameras, the problem of lack of heat source texture details in infrared images is solved. Accurate detection and efficient analysis of targets within a specific temperature range are achieved.
Patent Information
- Application Number
- CN202411450015.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-17
- Publication Date
- 2025-01-07
AI Technical Summary
When an infrared thermal imager generates infrared images, the heat source lacks texture details and cannot effectively present target texture information within a specific temperature range, making it difficult to accurately locate the fault points in power systems and other fields.
The solid circular array pattern calibration plate and affine transformation model can be used to register the visible light image and infrared image, obtain the infrared image within a specific temperature range, and obtain the target infrared image of the ROI area through the area box selection, and finally register it with the The subsequent visible light images are fused to generate multi-temperature and area target detection images.
The synchronous highlighting of temperature information and image details is achieved, the temperature information analysis efficiency of infrared thermal imagers is improved, redundant information interference is avoided, and accurate detection of the target temperature section in the fixed area is achieved.
Smart Images
Figure CN119273896A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of image processing technology, and in particular to a multi-temperature and regional target detection method of an infrared thermal imager. Background Art
[0002] Infrared thermal imager is a device that uses infrared thermal imaging technology to detect the infrared radiation of the target object and convert the image of the temperature distribution of the target object into a visible image through signal processing, photoelectric conversion, etc. The infrared thermal imager accurately quantifies the actual detected heat and images the entire target object in real time in the form of a surface, so it can accurately identify the suspected fault area that is heating up.
[0003] When an infrared thermal imager generates an infrared image, it is unable to effectively present the target texture information within a specific temperature range due to the lack of texture details of the heat source in the infrared imaging, which makes it inconvenient to use in some power systems, medical and other fields. For example, in the field of power systems, infrared thermal imaging technology is used to detect unusual heat points of the target through infrared images based on the thermal information of the object. However, due to the lack of prominence in the detailed texture, the specific problem of the fault point cannot be effectively located. In the prior art, a temperature threshold is set in the infrared imaging to display information within a specific temperature range, and the image portion that exceeds the temperature range is set to a fixed color to attempt to highlight the detailed texture information. However, the visualization effect of this solution is poor, and it is difficult to achieve the simultaneous highlighting of temperature information and image details. Summary of the invention
[0004] In view of the above problems, a multi-temperature and regional target detection method of infrared thermal imager is proposed, which aims to solve the technical problem that the heat source lacks texture details in infrared imaging in the prior art and cannot effectively present the target texture information within a specific temperature range.
[0005] The present invention provides a method for detecting multiple temperature and regional targets using an infrared thermal imager, the method comprising:
[0006] Step S1: realizing registration of visible light image and infrared image through solid circle array pattern calibration plate and affine transformation model;
[0007] Step S2: Detecting and imaging the same range within the same time to obtain a corresponding first visible light image and a first infrared image;
[0008] Step S3: According to the temperature range set by the user, inversely calculate the corresponding Y16 format brightness maximum value, traverse the first infrared image, and obtain the second infrared image within a specific temperature range;
[0009] Step S4: Based on the second infrared image within the specific temperature range, a target infrared image of the ROI area is obtained by selecting the area;
[0010] Step S5: Fusing the target infrared image in the ROI area with the registered first visible light image background to obtain a multi-temperature and regional target detection image.
[0011] Furthermore, in step S1, the registration of the visible light image and the infrared image is realized by using the solid circle array pattern calibration plate and the affine transformation model as follows:
[0012] Based on the solid circle array pattern calibration plate, the affine matrix at each calibration distance is obtained by aligning the centers of each circle of the visible light image with the centers of each circle of the infrared image at each calibration distance;
[0013] The average value of all affine matrices is calculated, and the X-direction offset component and the Y-direction offset component at each distance are obtained by interpolation to obtain the registration parameters at each distance.
[0014] Through various distance registration parameters, the visible light image is transformed through an affine matrix to achieve registration of the visible light and infrared images.
[0015] Furthermore, the average value of all affine matrices is calculated, and the X-direction offset component and the Y-direction offset component at each distance are obtained by interpolation, and the registration parameters at each distance are obtained as follows:
[0016] Calculate the average value of the rotation and scaling components in the X and Y directions of the affine matrix at all calibration distances;
[0017] According to the average values of the rotation and scaling components in the X and Y directions in the affine matrix at all calibration distances, the X-direction offset component and the Y-direction offset component of the affine matrix at each calibration distance are corrected;
[0018] According to the corrected X-direction offset component and Y-direction offset component of the affine matrix at each calibration distance, the X-direction offset component and Y-direction offset component of the affine matrix at any distance are calculated by interpolation method to generate the affine matrix at any distance.
[0019] Furthermore, the step S2 is specifically as follows:
[0020] Using the non-infrared mode of the infrared thermal imager within a certain viewing angle range within a period of time to obtain a first visible light image;
[0021] In the same time and for the same viewing angle range, the first infrared image is acquired using the cold detection mode, the hot detection mode or the medium temperature detection mode of the infrared thermal imager.
[0022] Furthermore, the step S3 is specifically as follows:
[0023] According to the maximum and minimum temperature values set by the user, the corresponding maximum and minimum values of the 16-bit brightness data are calculated inversely;
[0024] The first infrared image is traversed using the inversely calculated maximum and minimum values of the 16-bit brightness data to obtain a second infrared image within a specific temperature range set by the user.
[0025] Furthermore, the shape of the ROI region in step S4 can be freely set as needed, and the shape of the ROI region can be regular or irregular.
[0026] Furthermore, the number of ROI regions in step S4 may be one or more.
[0027] Furthermore, in step S5, the target infrared image in the ROI area is fused with the registered first visible light image background by directly superimposing the target infrared image in the ROI area on the registered first visible light image to completely cover the visible light information of the target.
[0028] Furthermore, in step S5, the target infrared image in the ROI area is fused with the registered first visible light image background by setting the target infrared image in the ROI area to a fixed color, superimposing it on the registered first visible light image and merging it with the visible light image.
[0029] Furthermore, in step S5, the target infrared image in the ROI region is fused with the registered first visible light image background by assigning different weights to the target infrared image in the ROI region and the registered first visible light image background.
[0030] Compared with the prior art, the present invention has the following beneficial effects:
[0031] (1) Realize the precise detection function of the temperature range of the target in a fixed area based on the infrared thermal imager. First, through the registration of the visible light image and the infrared image; detect and image the same range at the same time to obtain the corresponding first visible light image and first infrared image; then, based on the second infrared image in a specific temperature range, obtain the target infrared image of the ROI area by selecting the area; finally, fuse the target infrared image of the ROI area with the background of the registered first visible light image to obtain a multi-temperature and regional target detection image. In this way, the visible light and infrared information are effectively combined, the detection information of the target is more prominent, the temperature information and image details are highlighted simultaneously, and the precise detection function of the temperature range of the target in a fixed area based on the infrared thermal imager is realized.
[0032] (2) Improve the analysis efficiency of temperature information based on infrared thermal imagers and avoid interference from redundant information. When infrared detection of targets in a fixed area is performed, if the field of view is large or the thermal imager is far from the target, the target infrared image of the ROI area is obtained by selecting the area, and temperature analysis is performed only on the ROI area image to avoid redundant information in other areas, improve the analysis efficiency of temperature information, and avoid interference from redundant information. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.
[0034] Figure 1 A flow chart of a method for detecting multi-temperature and regional targets using an infrared thermal imager provided by an embodiment of the present invention;
[0035] Figure 2 A schematic diagram of the order of the centers of infrared images of the calibration plate provided in an embodiment of the present invention;
[0036] Figure 3 A schematic diagram of the arrangement of the centers of visible light images of the calibration plate provided in an embodiment of the present invention;
[0037] Figure 4 A schematic diagram of a first infrared image provided by an embodiment of the present invention;
[0038] Figure 5 A schematic diagram of a second infrared image provided by an embodiment of the present invention;
[0039] Figure 6 A schematic diagram of a second infrared image frame selection provided by an embodiment of the present invention;
[0040] Figure 7 A schematic diagram of an infrared image of a target in a ROI area provided by an embodiment of the present invention;
[0041] Figure 8 A schematic diagram of a first multi-temperature and regional target detection image fused with visible light and infrared information provided by an embodiment of the present invention;
[0042] Fig. 9 A schematic diagram of a second multi-temperature and regional target detection image fused with visible light and infrared information provided by an embodiment of the present invention;
[0043] Fig.10 A schematic diagram of a third multi-temperature and regional target detection image that fuses visible light and infrared information provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0044] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. Obviously, the specific embodiments described herein are only used to explain the present invention and are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0045] See also Figure 1-Figure 9 ,like Figure 1 A flow chart of a multi-temperature and regional target detection method of an infrared thermal imager provided in an embodiment of the present invention, the flow chart specifically includes:
[0046] Step S1: realize the registration of visible light image and infrared image through solid circle array pattern calibration plate and affine transformation model.
[0047] Among them, the registration of the visible light image and the infrared image by using the solid circle array pattern calibration plate and the affine transformation model in step S1 is specifically as follows: based on the solid circle array pattern calibration plate, by aligning the centers of each circle of the visible light image and each center of each circle of the infrared image at each calibration distance (see Figure 2 and Figure 3 ), obtain the affine matrix at each calibration distance; calculate the average value of all affine matrices, use interpolation to obtain the X-direction offset component and the Y-direction offset component at each distance, and obtain the registration parameters of each distance; through the registration parameters of each distance, transform the visible light image through the affine matrix to realize the registration of visible light and infrared images.
[0048] Among them, the X-direction offset component and the Y-direction offset component at each distance are obtained by interpolation, and the registration parameters at each distance are obtained specifically as follows: the average value of the rotation and scaling components in the X and Y directions in the affine matrix at all calibration distances is calculated; according to the average value of the rotation and scaling components in the X and Y directions in the affine matrix at all calibration distances, the X-direction offset component and the Y-direction offset component of the affine matrix at each calibration distance are corrected; according to the corrected X-direction offset component and the Y-direction offset component of the affine matrix at each calibration distance, the X-direction offset component and the Y-direction offset component of the affine matrix at any distance are calculated by interpolation method to generate the affine matrix at any distance.
[0049] Step S2: Detecting and imaging the same range within the same time to obtain a corresponding first visible light image and a first infrared image.
[0050] Among them, step S2 is specifically: using the infrared thermal imager in a non-infrared mode for a certain viewing angle range within a period of time to obtain a first visible light image; using the infrared thermal imager in a cold detection mode, a hot detection mode, or a medium temperature detection mode for the same viewing angle range within the same period of time to obtain a first infrared image, such as Figure 4 shown.
[0051] In this embodiment, an infrared thermal imager is used to introduce a cold detection mode, a hot detection mode and a medium-temperature detection mode. At the same time, the cold detection mode, the hot detection mode and the medium-temperature detection mode can be switched as needed, so that the system can adapt to the target detection needs within different temperature ranges and improve the flexibility and accuracy of detection.
[0052] Step S3: According to the temperature range set by the user, inversely calculate the corresponding Y16 format brightness maximum value, traverse the first infrared image, and obtain the second infrared image within the specific temperature range.
[0053] Among them, the step S3 is specifically as follows: according to the maximum temperature value and the minimum temperature value set by the user, the corresponding 16-bit brightness data maximum value and minimum value are calculated inversely; the first infrared image is traversed using the inversely calculated 16-bit brightness data maximum value and minimum value to obtain the second infrared image within the specific temperature range set by the user.
[0054] In this embodiment, after obtaining the first infrared image, the user can freely set the temperature range parameters required for the first infrared image. In order to ensure higher brightness accuracy and wider dynamic range of image processing, in this embodiment, the maximum and minimum values of the inversely calculated 16-bit brightness data are used to traverse the first infrared image to obtain a second infrared image within a specific temperature range, such as Figure 5 shown.
[0055] Step S4: Based on the second infrared image within the specific temperature range, a target infrared image of the ROI area is obtained by selecting the area.
[0056] The form of area selection is as follows: Figure 6 As shown, the target infrared image reference of the ROI area Figure 7 As shown, the shape of the ROI region in step S4 can be freely set as needed, and the shape of the ROI region can be regular or irregular. Moreover, the number of ROI regions can be one or more.
[0057] Step S5: Fusing the target infrared image in the ROI area with the registered first visible light image background to obtain a multi-temperature and regional target detection image.
[0058] In step S5, the target infrared image of the ROI area is fused with the first visible light image background after registration, which can be: the target infrared image of the ROI area is directly superimposed on the first visible light image after registration, and the visible light information of the target is completely covered. Figure 8 This single infrared overlay mode fusion strategy can simultaneously display the target temperature information and other image detail information of the image without increasing the system's computing power requirements.
[0059] Furthermore, in step S5, the target infrared image of the ROI region is fused with the background of the first visible light image after registration, and the target infrared image of the ROI region is set to a fixed color and superimposed on the first visible light image after registration and fused with the visible light image. Fig. 9 This fixed color overlay mode fusion strategy can highlight the target temperature information of the displayed image for the user at the first time, and avoid the interference of other visible light image detail information.
[0060] Furthermore, in step S5, the target infrared image of the ROI region is fused with the first visible light image background after registration. Different weights are assigned to the target infrared image of the ROI region and the first visible light image after registration for fusion. Fig.10 As shown. This transparent overlay mode fusion strategy enables the target area to reflect the infrared thermal image information while retaining the texture details of the visible light. The actual weight ratio can be set as needed. For example, in order to highlight the temperature information, the target infrared image in the ROI area and the first registered visible light image can be configured with a weight of 7:3; for another example, in order to highlight the texture detail information, the target infrared image in the ROI area and the first registered visible light image can be configured with a weight of 3:7.
[0061] The present embodiment provides a method for detecting multi-temperature and regional targets using an infrared thermal imager, which is achieved by registering visible light images with infrared images; detecting and imaging the same range at the same time to obtain a corresponding first visible light image and a first infrared image; then, based on a second infrared image within a specific temperature range, obtaining a target infrared image in the ROI region by selecting a region; finally, fusing the target infrared image in the ROI region with the registered first visible light image background to obtain a multi-temperature and regional target detection image. In this way, visible light and infrared information are effectively combined, the detection information of the target is more prominent, the temperature information and image details are highlighted simultaneously, and the accurate detection function of the fixed regional target temperature segment based on the infrared thermal imager is realized. At the same time, the analysis efficiency of the image temperature and texture detail information is improved to avoid interference from redundant information.
[0062] The above embodiments only express the preferred implementation mode of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
Claims
1. A method for detecting multiple temperatures and regional targets using an infrared thermal imager, characterized in that: The following steps are involved: Step S1: realizing registration of visible light image and infrared image through solid circle array pattern calibration plate and affine transformation model; Step S2: Detecting and imaging the same range within the same time to obtain a corresponding first visible light image and a first infrared image; Step S3: According to the temperature range set by the user, inversely calculate the corresponding Y16 format brightness maximum value, traverse the first infrared image, and obtain the second infrared image within a specific temperature range; Step S4: Based on the second infrared image within the specific temperature range, a target infrared image of the ROI area is obtained by selecting the area; Step S5: Fusing the target infrared image in the ROI area with the registered first visible light image background to obtain a multi-temperature and regional target detection image.
2. The infrared thermal imager multi-temperature and regional target detection method according to claim 1, characterized in that: In step S1, the registration of the visible light image and the infrared image is realized by using the solid circle array pattern calibration plate and the affine transformation model as follows: Based on the solid circle array pattern calibration plate, the affine matrix at each calibration distance is obtained by aligning the centers of each circle of the visible light image with the centers of each circle of the infrared image at each calibration distance; The average value of all affine matrices is calculated, and the X-direction offset component and the Y-direction offset component at each distance are obtained by interpolation to obtain the registration parameters at each distance. Through various distance registration parameters, the visible light image is transformed through an affine matrix to achieve registration of the visible light and infrared images.
3. The infrared thermal imager multi-temperature and regional target detection method according to claim 2, characterized in that: The average value of all affine matrices is calculated, and the X-direction offset component and the Y-direction offset component at each distance are obtained by interpolation. The specific distance registration parameters are: Calculate the average value of the rotation and scaling components in the X and Y directions of the affine matrix at all calibration distances; According to the average values of the rotation and scaling components in the X and Y directions in the affine matrix at all calibration distances, the X-direction offset component and the Y-direction offset component of the affine matrix at each calibration distance are corrected; According to the corrected X-direction offset component and Y-direction offset component of the affine matrix at each calibration distance, the X-direction offset component and Y-direction offset component of the affine matrix at any distance are calculated by interpolation method to generate the affine matrix at any distance.
4. The infrared thermal imager multi-temperature and regional target detection method according to claim 1, characterized in that: The step S2 is specifically as follows: Using the non-infrared mode of the infrared thermal imager within a certain viewing angle range within a period of time to obtain a first visible light image; In the same time and for the same viewing angle range, the first infrared image is acquired using the cold detection mode, the hot detection mode or the medium temperature detection mode of the infrared thermal imager.
5. The infrared thermal imager multi-temperature and regional target detection method according to claim 1, characterized in that: The step S3 is specifically as follows: According to the maximum and minimum temperature values set by the user, the corresponding maximum and minimum values of the 16-bit brightness data are calculated inversely; The first infrared image is traversed using the inversely calculated maximum and minimum values of the 16-bit brightness data to obtain a second infrared image within a specific temperature range set by the user.
6. The infrared thermal imager multi-temperature and regional target detection method according to claim 1, characterized in that: The shape of the ROI region in step S4 can be freely set as needed, and the shape of the ROI region can be regular or irregular.
7. The infrared thermal imager multi-temperature and regional target detection method according to claim 6, characterized in that: The number of ROI regions in step S4 may be one or more.
8. The infrared thermal imager multi-temperature and regional target detection method according to claim 1, characterized in that: In step S5, the target infrared image in the ROI area is fused with the registered first visible light image background by directly superimposing the target infrared image in the ROI area on the registered first visible light image to completely cover the visible light information of the target.
9. The infrared thermal imager multi-temperature and regional target detection method according to claim 1, characterized in that: In step S5, the target infrared image in the ROI area is fused with the registered first visible light image background by setting the target infrared image in the ROI area to a fixed color, superimposing it on the registered first visible light image and merging it with the visible light image.
10. The infrared thermal imager multi-temperature and regional target detection method according to claim 1, characterized in that: In step S5, the target infrared image in the ROI region is fused with the registered first visible light image background by assigning different weights to the target infrared image in the ROI region and the registered first visible light image background.