Thermal infrared image processor, system, method and device

Abstract

The present application discloses a thermal infrared image processor, system, method and device. The thermal infrared image processor (20) comprises a preprocessing module (210) and an artificial intelligence processing module (220), wherein the preprocessing module (210) is configured to generate a second thermal infrared image suitable for detection by the artificial intelligence processing module (220) based on a first thermal infrared image received by the thermal infrared image processor (20); and the artificial intelligence processing module (220) is configured to detect a target object in the second thermal infrared image.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and more specifically, to a thermal infrared image processor, system, method and device. Background Art

[0002] As people have more and more demands for temperature monitoring of objects in specified scenes, many temperature measurement systems have appeared on the market for users to use. The current temperature measurement systems all use thermal infrared cameras for image acquisition, and then derive the temperature values ​​of each part of the image based on the pixel information of the thermal infrared image. However, the existing high-resolution thermal infrared cameras are expensive, and although the low-resolution thermal infrared cameras are cheap, the captured thermal infrared images have low resolution, blurred images, and unclear contours, which can easily lead to problems such as missed detection, false detection, low accuracy, and low effective detection rate when detecting objects in the image. In addition, the existing thermal infrared cameras do not have artificial intelligence detection functions, so it is necessary to retrain the model based on the collected thermal infrared images, which is time-consuming and laborious.

[0003] There are technical problems in the above-mentioned prior art that although the high-resolution thermal infrared images captured by the high-resolution thermal infrared cameras can detect target objects, they are very expensive, and although the low-resolution thermal infrared cameras are cheap, the thermal infrared images they capture have low resolution, blurred images, and unclear contours, which makes it easy to cause missed detections, false detections, low accuracy, and low effective detection rates when detecting target objects in images. No effective solution has been proposed yet. Summary of the invention

[0004] The present disclosure provides a thermal infrared image processor, system, method and device to at least solve the technical problems existing in the prior art that high-resolution thermal infrared images acquired by high-resolution thermal infrared cameras can detect target objects but are very expensive, while low-resolution thermal infrared cameras are cheap but the acquired thermal infrared images have low resolution, blurred images and unclear contours, which easily lead to missed detections, wrong detections, low accuracy and low effective detection rate when detecting target objects in images.

[0005] According to one aspect of an embodiment of the present disclosure, there is provided a thermal infrared image processor, comprising a preprocessing module and an artificial intelligence processing module, wherein the preprocessing module is configured to generate a second thermal infrared image suitable for detection by the artificial intelligence processing module based on a first thermal infrared image received by the thermal infrared image processor; and the artificial intelligence processing module is configured to detect a target object in the second thermal infrared image.

[0006] According to another aspect of an embodiment of the present disclosure, a thermal infrared image processing system is provided, comprising: an image acquisition device; and a thermal infrared image processor according to the above, wherein the thermal infrared image processor is connected to the image acquisition device to receive a thermal infrared image acquired by the image acquisition device.

[0007] According to another aspect of the embodiments of the present disclosure, there is also provided a thermal infrared image processing system, including: an image acquisition device, a high-definition display module and a network interface module; and a thermal infrared image processor as described above, wherein the thermal infrared image processor is connected to the image acquisition device to receive the thermal infrared image acquired by the image acquisition device; the high-definition display module is connected to the image fusion module in the thermal infrared image processor to display the third thermal infrared image generated by the image fusion module in high definition; and the network interface module is connected to the image fusion module in the thermal infrared image processor to send target object temperature, target object position and related data of the third thermal infrared image to a remote server.

[0008] According to another aspect of an embodiment of the present disclosure, a thermal infrared image processing method is provided, including: generating a second thermal infrared image suitable for image detection according to a preset preprocessing algorithm and a first thermal infrared image; and detecting a target object in the second thermal infrared image.

[0009] According to another aspect of the embodiments of the present disclosure, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, the above method is executed by a processor.

[0010] According to another aspect of an embodiment of the present disclosure, a thermal infrared image processing device is provided, including: a processor; and a memory connected to the processor, for providing the processor with instructions for processing the following processing steps: generating a second thermal infrared image suitable for image detection based on a preset preprocessing algorithm and a first thermal infrared image; and detecting a target object in the second thermal infrared image.

[0011] In an embodiment of the present invention, firstly, a second thermal infrared image for image detection is generated based on the first thermal infrared image, and then the target object is detected in the second thermal infrared image. The technical effect of being able to effectively detect the target object in the thermal infrared image captured by a low-resolution thermal infrared camera, avoiding the occurrence of missed detection and wrong detection, and greatly improving the accuracy of detection is achieved. This solves the technical problem that the high-resolution thermal infrared image captured by a high-resolution thermal infrared camera in the prior art can detect the target object but is very expensive, while the low-resolution thermal infrared camera, although cheap, has a low resolution of the captured thermal infrared image, a blurred image, and unclear contours, which makes it easy to cause missed detection, wrong detection, low accuracy, and low effective detection rate when detecting the target object in the image.

[0012] Based on the detailed description of the specific embodiments of the present application in combination with the accompanying drawings below, those skilled in the art will become more aware of the above and other objects, advantages and features of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Hereinafter, some specific embodiments of the present application will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the accompanying drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the accompanying drawings:

[0014] Figure 1 is a schematic diagram of a thermal infrared image processor according to the first aspect of Embodiment 1 of the present disclosure;

[0015] Figure 2 is a schematic diagram of a thermal infrared image processor according to the second aspect of Embodiment 1 of the present disclosure;

[0016] Figure 3 is a schematic diagram of a thermal infrared image processing system according to the third aspect of Embodiment 1 of the present disclosure;

[0017] Figure 4 is a schematic diagram of a thermal infrared image processing system according to the fourth aspect of Embodiment 1 of the present disclosure;

[0018] Figure 5 is a schematic diagram of a thermal infrared image processing system according to the fifth aspect of Embodiment 1 of the present disclosure;

[0019] Figure 6 is a flowchart of the thermal infrared image processing method according to the sixth aspect of Embodiment 1 of the present disclosure; and

[0020] Figure 7 It is a schematic diagram of an image processing device according to Embodiment 2 of the present disclosure. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0025] Example 1

[0026] Figure 1 is a schematic diagram of a thermal infrared image processor 20 according to the first aspect of Embodiment 1 of the present application. Figure 1 As shown, the present application provides a thermal infrared image processor 20, including a preprocessing module 210 and an artificial intelligence processing module 220, wherein the preprocessing module 210 is configured to generate a second thermal infrared image suitable for detection by the artificial intelligence processing module 220 based on a first thermal infrared image received by the thermal infrared image processor 20; and the artificial intelligence processing module 220 is configured to detect a target object in the second thermal infrared image.

[0027] As described in the background technology, with the increasing demand for temperature monitoring of objects in a specified scene, many temperature measurement systems have appeared on the market for users to use. The current temperature measurement systems all use thermal infrared cameras to capture images, and then derive the temperature values ​​of each part of the image based on the pixel information of the thermal infrared image. However, the existing high-resolution thermal infrared cameras are expensive, and although the low-resolution thermal infrared cameras are cheap, the captured thermal infrared images have low resolution, blurred images, and unclear contours, which can easily lead to problems such as missed detection, wrong detection, low accuracy, and low effective detection rate when detecting objects in the image. In addition, the existing thermal infrared cameras do not have artificial intelligence detection functions, so it is necessary to retrain the model based on the captured thermal infrared images, which is time-consuming and laborious.

[0028] In view of the problems existing in the above-mentioned prior art, Figure 1 As shown, when the thermal infrared image processor 20 in this embodiment receives a low-resolution thermal infrared image (corresponding to the first thermal infrared image mentioned above), it is unable to effectively detect the target object in the first thermal infrared image due to the low resolution of the first thermal infrared image (for example, but not limited to, a low-resolution image with a resolution of 160*120 to 384*288). Therefore, in this embodiment, the received first thermal infrared image is preprocessed by the preprocessing module 210 to generate a second thermal infrared image suitable for detection by the artificial intelligence processing module 220. Then, the target object in the second thermal infrared image is detected by the artificial intelligence processing module 220.

[0029] In a specific embodiment, the preprocessing module 210 includes at least one of the following units: an upsampling unit 211 and an image enhancement unit 212, wherein the upsampling unit 211 is configured to perform an upsampling operation on the first thermal infrared image to generate a second thermal infrared image; the image enhancement unit 212 is configured to perform an image enhancement operation on the first thermal infrared image according to a preset algorithm to generate a second thermal infrared image; and the image enhancement unit 212 is also configured to enhance the detail information in the high-resolution thermal infrared image output by the upsampling unit 211 according to a preset image enhancement algorithm to generate a second thermal infrared image.

[0030] Specifically, regarding the reason why the target object cannot be effectively detected in the low-resolution first thermal infrared image, this application mainly considers two factors. The first aspect is that due to the limitation of computing resources, the current image detection and recognition algorithms usually support the recognition of images with a limited range of resolutions (for example, a resolution of 512*512, 640*360, 640*480 or others); the second aspect is that the image in the low-resolution first thermal infrared image is blurred, the outline is not clear, and the various features of the target object cannot be presented in detail. For example, when the target object is a person, the first thermal infrared image cannot clearly present features such as the human body outline, head, and limbs.

[0031] Further, in response to the problem in the first aspect mentioned above, the preprocessing module 210 of this embodiment upsamples the first thermal infrared image through the upsampling unit 211, and converts the resolution of the first thermal infrared image into a second thermal infrared image suitable for detection by the artificial intelligence processing module 220. Among them, the resolution of the first thermal infrared image is lower than the resolution of the second thermal infrared image. For example: the received first thermal infrared image may be a low-resolution image with a resolution of 160*120 to 384*288, and the resolution of the second thermal infrared image suitable for detection by the artificial intelligence processing module 220 is, for example, 512*512, 640*360, 640*480 or others. Therefore, the preprocessing module 210 may, for example, use a multi-phase filter or a linear filter for upsampling to complete the upgrade from low resolution to high resolution. Thus, it is no longer necessary to retrain the model based on the collected thermal infrared image, but to use the existing artificial intelligence detection function to effectively detect the low-resolution thermal infrared image.

[0032] Furthermore, in order to solve the problem in the second aspect mentioned above, the preprocessing module 210 of this embodiment performs an image enhancement operation on the first thermal infrared image according to a preset algorithm through the image enhancement unit 212, thereby generating a second thermal infrared image.

[0033] In a specific embodiment, due to the imaging characteristics of the thermal infrared sensor itself and the low resolution, the thermal infrared image often has high noise, which causes the edge information of the object to be disturbed. In order to solve the problem of high noise, the image enhancement unit 212 uses a preset denoising filter algorithm to perform denoising to suppress the noise in the image without destroying the edge of the object. Among them, common denoising filter algorithms include bilateral filtering algorithm and guided filtering algorithm.

[0034] In another specific embodiment, since the thermal infrared image is formed based on the surface temperature of the object, and the temperature difference between the object and the background in the actual scene is not very large, the edge details of the object are not obvious in the thermal infrared image. To address this problem, the image enhancement unit 212 uses a preset edge sharpening algorithm to perform edge enhancement to enhance the detail information of the object. Among them, common edge sharpening algorithms include, for example, the Laplace filter algorithm and the Sobel filter algorithm.

[0035] In addition, it should be noted that the image enhancement unit 212 is not limited to including a denoising filtering algorithm and an edge sharpening algorithm, and may also include other algorithms that can enhance image quality.

[0036] Preferably, in view of the problem in the first aspect mentioned above, the preprocessing module 210 of this embodiment may also first perform an upsampling operation on the first thermal infrared image through the upsampling unit 211 to complete the upgrade from low resolution to high resolution. Then, the image enhancement unit 212 performs an image enhancement operation on the high-resolution thermal infrared image output by the upsampling unit 211 to suppress the noise in the high-resolution thermal infrared image and enhance the detail information in the high-resolution thermal infrared image, thereby generating a second thermal infrared image suitable for detection by the artificial intelligence processing module 220. Among them, the image enhancement unit 212 may use the above-mentioned preset denoising filter algorithm for denoising to suppress the noise in the high-resolution thermal infrared image output by the upsampling unit 211 without destroying the edge of the object. In addition, the image enhancement unit 212 may also use the above-mentioned preset image enhancement algorithm for edge enhancement to enhance the detail information of the object in the high-resolution thermal infrared image output by the upsampling unit 211.

[0037] Thus, in this embodiment, the provided thermal infrared image processor 20 first preprocesses the received first thermal infrared image through the preprocessing module 210 to generate a second thermal infrared image suitable for detection by the artificial intelligence processing module 220, and then detects the target object in the second thermal infrared image through the artificial intelligence processing module 220. The target object in the thermal infrared image captured by the low-resolution thermal infrared camera can be effectively detected, avoiding the occurrence of missed detection and wrong detection, and greatly improving the technical effect of the accuracy of detection. In addition, the high-resolution thermal infrared image captured by the high-resolution thermal infrared camera in the prior art is solved, although the high-resolution thermal infrared image can detect the target object, the price is very expensive, and the low-resolution thermal infrared camera is low in price but the captured thermal infrared image has low resolution, blurred image, and unclear outline, which makes it easy to cause missed detection, wrong detection, low accuracy and low effective detection rate when detecting the target object in the image.

[0038] In addition, reference Figure 2 As shown, according to the second aspect of this embodiment 1, a schematic diagram of a thermal infrared image processor 20 is provided. Specifically, Figure 1 On the basis of this, the thermal infrared image processor 20 also includes a temperature detection module 230, the temperature detection module 230 includes a positioning unit 231 and a temperature detection unit 232, wherein the positioning unit 231 is configured to determine the second position information of the target object in the first thermal infrared image according to the first position information of the target object in the second thermal infrared image; and the temperature detection unit 232 is configured to determine the temperature distribution information corresponding to the target object according to the pixel information corresponding to the second position information in the first thermal infrared image.

[0039] Specifically, after receiving a low-resolution thermal infrared image from a low-resolution thermal infrared camera, the thermal infrared image processor usually needs to convert the low-resolution thermal infrared image into a high-resolution thermal infrared image suitable for the existing image detection and recognition algorithm by upsampling, image enhancement, or a combination of the two, and then detect the target object. In this case, the temperature information will be lost, making the temperature distribution information of the target object in the converted high-resolution thermal infrared image inaccurate.

[0040] For the above problems, refer to Figure 2 As shown, on the basis of the first aspect of the present embodiment, the thermal infrared image processor 20 provided in the second aspect first determines the second position information of the target object in the first thermal infrared image according to the first position information of the target object in the second thermal infrared image through the positioning unit 231 in the temperature detection module 230. Among them, the positioning unit 231 can use a preset coordinate conversion algorithm to convert the first position information in the second thermal infrared image into the corresponding second position information in the first thermal infrared image. Then, the temperature detection unit 232 in the temperature detection module 230 obtains the corresponding temperature value according to the pixel information corresponding to the second position information, thereby determining the temperature distribution information corresponding to the target object. In this way, the effect of the temperature distribution information of the target object can be accurately determined. The problem of inaccurate temperature distribution information of the target object in the high-resolution thermal infrared image obtained by the conversion mentioned above is solved.

[0041] Optionally, an image fusion module 240 is also included, which is configured to add a mark at the position of the target object in the second thermal infrared image based on the first position information and temperature distribution information, generate a third thermal infrared image, and cache the target object temperature, target object position and related data of the third thermal infrared image.

[0042] In practice, monitoring staff usually monitors the target object by watching the monitoring video. Therefore, if it is possible to add a mark for identifying the target object and the temperature distribution information of the target object in the video (for example, using a color rectangular frame to mark the target object, relative face temperature information, forehead temperature information, etc.), it will be more conducive to the monitoring staff to observe the monitoring video. However, as mentioned above, if the target object is to be detected in a low-resolution thermal infrared image, the low-resolution thermal infrared image must be converted into a high-resolution thermal infrared image suitable for the artificial intelligence processing module 220.

[0043] In this case, reference Figure 2As shown, the thermal infrared image processor 20 also includes an image fusion module 240, through which the first position information detected by the artificial intelligence processing module 220 and the temperature distribution information determined by the temperature detection module 230 are fused with the second thermal infrared image generated by the preprocessing module 210, and a mark of the position information and the temperature information is added at the position of the target object in the second thermal infrared image. For example, a color rectangular frame is added around the target object to mark the position of the detected target object in the thermal infrared image, and specific temperature information can be added to the specific parts of the target object (for example, the forehead, face, and limbs, etc.), and a high-resolution third thermal infrared image with a mark of the position information and temperature information of the target object is generated, and the target object temperature, target object position, and relevant data of the third thermal infrared image of the target object are cached. Thus, in this way, a high-definition and marked monitoring video can be provided to the monitoring staff, which is conducive to the monitoring of the monitoring staff.

[0044] In addition, reference Figure 3 As shown, according to the third aspect of this embodiment 1, a thermal infrared image processing system is provided, including: an image acquisition device 10; and a thermal infrared image processor 20 according to the above-mentioned, the thermal infrared image processor 20 is connected to the image acquisition device 10 to receive the thermal infrared image acquired by the image acquisition device 10.

[0045] Thus, the thermal infrared image (corresponding to Figure 3 The first thermal infrared image in the image acquisition device 10 is then sent by the image acquisition device 10 to the thermal infrared image processor 20. After receiving the thermal infrared image acquired by the image acquisition device 10, the thermal infrared image processor 20 performs corresponding processing on the thermal infrared image.

[0046] In addition, reference Figure 4 As shown, according to the fourth aspect of the present embodiment 1, a thermal infrared image processing system is provided, comprising: a high-definition display module 30 and a network interface module 31; and the thermal infrared image processor 20 described above, wherein the high-definition display module 30 is connected to the image fusion module 240 in the thermal infrared image processor 20, and is used to display the third thermal infrared image generated by the image fusion module 240. The network interface module 31 is connected to the image fusion module 240 in the thermal infrared image processor 20, and is used to send the target object temperature, the target object position and the relevant data of the third thermal infrared image to the remote server.

[0047] Specifically, referring to the above, the third thermal infrared image generated by the image fusion module 240 is a high-resolution image with a mark of the location information and temperature information of the target object. Figure 4As shown, the thermal infrared image processing system not only includes the above Figure 3 The thermal infrared image processor 20 shown in the figure also includes a high-definition display module 30 and a network interface module 31, which are connected to the image fusion module 240 and are respectively used to display the third thermal infrared image and send the collected target object temperature, target object position and related data of the third thermal infrared image to the remote server. Therefore, not only can the third thermal infrared image with high resolution and marked with the position information and temperature information of the target object be displayed to the relevant staff, but also the remote server can perform further data analysis.

[0048] In addition, reference Figure 5 As shown, according to the fifth aspect of this embodiment 1, a thermal infrared image processing system is provided, including: an image acquisition device 10, a high-definition display module 30 and a network interface module 31; and a thermal infrared image processor 20 as described above, wherein the thermal infrared image processor 20 is connected to the image acquisition device 10 to receive the thermal infrared image acquired by the image acquisition device 10; the high-definition display module 30 is connected to the image fusion module 240 in the thermal infrared image processor 20, for displaying the third thermal infrared image generated by the image fusion module 240; and the network interface module 31 is connected to the image fusion module 240 in the thermal infrared image processor 20, for sending target object temperature, target object position and related data of the third thermal infrared image to a remote server.

[0049] Specifically, combined Figures 1 to 4 As shown, the thermal infrared image processing system includes an image acquisition device 10, a high-definition display module 30, a network interface module 31, and a thermal infrared image processor 20 as described above. The thermal infrared image (corresponding to Figure 5 The first thermal infrared image in the image acquisition device 10 is then sent to the thermal infrared image processor 20 by the image acquisition device 10. After receiving the first thermal infrared image acquired by the image acquisition device 10, the thermal infrared image processor 20 performs corresponding processing on the first thermal infrared image, and generates a third thermal infrared image through the image fusion module 240 in the thermal infrared image processor 20. The generated third thermal infrared image is high-resolution and marked with the location information and temperature information of the target object. Finally, the generated third thermal infrared image is displayed by the high-definition display module 30, and the target object temperature, target object location and related data of the third thermal infrared image are sent to the remote server through the network interface module 31 for further data analysis.

[0050] In addition, reference Figure 6 As shown, according to the sixth aspect of this embodiment 1, a thermal infrared image processing method is provided, including:

[0051] S602: generating a second thermal infrared image suitable for image detection according to a preset preprocessing algorithm and the first thermal infrared image; and

[0052] S604: Detect a target object in the second thermal infrared image.

[0053] Specifically, the specific description of the method described in the sixth aspect of this embodiment can refer to the relevant description of the thermal infrared image processor described in the first aspect of this embodiment. Thus, the method first generates a second thermal infrared image for image detection according to a preset preprocessing algorithm and a first thermal infrared image, and then detects the target object in the second thermal infrared image. The technical effect of being able to effectively detect the target object in the thermal infrared image captured by a low-resolution thermal infrared camera, avoiding the occurrence of missed detection and wrong detection, and greatly improving the accuracy of detection is achieved. In addition, the technical problem that the high-resolution thermal infrared image captured by a high-resolution thermal infrared camera in the prior art can detect the target object but is very expensive, and the low-resolution thermal infrared camera, although low in price, has a low resolution of the captured thermal infrared image, a blurred image, and unclear contours, makes it easy to cause missed detection, wrong detection, low accuracy, and low effective detection rate when detecting the target object in the image.

[0054] Optionally, the operation of generating a second thermal infrared image suitable for image detection based on a preset preprocessing algorithm and the first thermal infrared image includes at least one of the following operations: upsampling the first thermal infrared image to generate a second thermal infrared image; and performing an image enhancement operation on the first thermal infrared image according to a preset algorithm to generate a second thermal infrared image.

[0055] Optionally, performing an image enhancement operation on the first thermal infrared image according to a preset algorithm to generate a second thermal infrared image includes: suppressing noise in the first thermal infrared image according to a preset denoising filtering algorithm to generate a second thermal infrared image; or suppressing noise in a high-resolution thermal infrared image obtained by an upsampling operation according to a preset denoising filtering algorithm to generate a second thermal infrared image.

[0056] Optionally, performing an image enhancement operation on the first thermal infrared image according to a preset algorithm to generate a second thermal infrared image includes: enhancing detail information in the first thermal infrared image according to a preset image enhancement algorithm to generate a second thermal infrared image; or enhancing detail information in a high-resolution thermal infrared image obtained by an upsampling operation according to a preset image enhancement algorithm to generate a second thermal infrared image.

[0057] Optionally, it also includes: determining the second position information of the target object in the first thermal infrared image based on the first position information of the target object in the second thermal infrared image; and determining the temperature distribution information corresponding to the target object based on the pixel information corresponding to the second position information in the first thermal infrared image.

[0058] Optionally, it also includes: adding a mark at the position of the target object in the second thermal infrared image according to the first position information and the temperature distribution information, generating a third thermal infrared image while caching the target object temperature, target object position and related data of the third thermal infrared image.

[0059] In addition, according to a seventh aspect of this embodiment, a storage medium is provided, wherein the storage medium includes a stored program, wherein when the program is run, a processor executes any one of the above methods.

[0060] Example 2

[0061] Figure 7 FIG. 7 shows a thermal infrared image processing device 700 according to this embodiment, which corresponds to the method described in the sixth aspect of Embodiment 1. Figure 7 As shown, the device 700 includes: a processor 710; and a memory 720, which is connected to the processor 710 and is used to provide the processor 710 with instructions for processing the following processing steps: generating a second thermal infrared image suitable for image detection based on a preset preprocessing algorithm and a first thermal infrared image; and detecting a target object in the second thermal infrared image.

[0062] Optionally, the operation of generating a second thermal infrared image suitable for image detection based on a preset preprocessing algorithm and the first thermal infrared image includes at least one of the following operations: upsampling the first thermal infrared image to generate a second thermal infrared image; and performing an image enhancement operation on the first thermal infrared image according to a preset algorithm to generate a second thermal infrared image.

[0063] Optionally, performing an image enhancement operation on the first thermal infrared image according to a preset algorithm to generate a second thermal infrared image includes: suppressing noise in the first thermal infrared image according to a preset denoising filtering algorithm to generate a second thermal infrared image; or suppressing noise in a high-resolution thermal infrared image obtained by an upsampling operation according to a preset denoising filtering algorithm to generate a second thermal infrared image.

[0064] Optionally, performing an image enhancement operation on the first thermal infrared image according to a preset algorithm to generate a second thermal infrared image includes: enhancing detail information in the first thermal infrared image according to a preset image enhancement algorithm to generate a second thermal infrared image; or enhancing detail information in a high-resolution thermal infrared image obtained by an upsampling operation according to a preset image enhancement algorithm to generate a second thermal infrared image.

[0065] Optionally, the memory 720 is also used to provide instructions for the processor 710 to process the following processing steps: determining the second position information of the target object in the first thermal infrared image based on the first position information of the target object in the second thermal infrared image; and determining the temperature distribution information corresponding to the target object based on the pixel information corresponding to the second position information in the first thermal infrared image.

[0066] Optionally, the memory 720 is also used to provide instructions for the processor 710 to process the following processing steps: adding a mark at the position of the target object in the second thermal infrared image based on the first position information and temperature distribution information, generating a third thermal infrared image while caching the target object temperature, target object position and related data of the third thermal infrared image.

[0067] Therefore, according to this embodiment, the thermal infrared image processing device 700 first generates a second thermal infrared image for image detection according to a preset preprocessing algorithm and the first thermal infrared image, and then detects the target object in the second thermal infrared image. The technical effect of being able to effectively detect the target object in the thermal infrared image captured by a low-resolution thermal infrared camera, avoiding the occurrence of missed detection and wrong detection, and greatly improving the accuracy of detection is achieved. This solves the technical problem that the high-resolution thermal infrared image captured by a high-resolution thermal infrared camera in the prior art can detect the target object but is very expensive, while the low-resolution thermal infrared camera, although low in price, has a low resolution of the captured thermal infrared image, a blurred image, and unclear contours, which makes it easy to cause missed detection, wrong detection, low accuracy, and low effective detection rate when detecting the target object in the image.

[0068] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0069] Unless otherwise specifically stated, the relative arrangement of the parts and steps described in these embodiments, numerical expressions and numerical values ​​do not limit the scope of the present disclosure. At the same time, it should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. The technology, methods and equipment known to ordinary technicians in the relevant field may not be discussed in detail, but in appropriate cases, the technology, methods and equipment should be regarded as a part of the authorization specification. In all examples shown and discussed here, any specific value should be interpreted as being merely exemplary, rather than as a limitation. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0070] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used here to describe the spatial positional relationship between a device or feature and other devices or features as shown in the figure. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figure. For example, if the device in the accompanying drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" can include both "above" and "below". (The device can also be positioned in other different ways, rotated 90 degrees or in other orientations), and the spatially relative descriptions used here are interpreted accordingly.

[0071] In the description of the present disclosure, it is necessary to understand that the orientation or positional relationship indicated by directional words such as "front, back, up, down, left, right", "lateral, vertical, perpendicular, horizontal" and "top, bottom" are usually based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present disclosure and simplifying the description. Unless otherwise specified, these directional words do not indicate or imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the scope of protection of the present disclosure; the directional words "inside and outside" refer to the inside and outside relative to the outline of each component itself.

[0072] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A thermal infrared image processor (20), characterized in that: It includes a pre-processing module (210) and an artificial intelligence processing module (220), wherein The pre-processing module (210) is configured to generate a second thermal infrared image suitable for detection by the artificial intelligence processing module (220) based on the first thermal infrared image received by the thermal infrared image processor (20); The artificial intelligence processing module (220) is configured to detect a target object in the second thermal infrared image, wherein The preprocessing module (210) comprises at least one of the following units: an upsampling unit (211) and an image enhancement unit (212), wherein The upsampling unit (211) is configured to perform an upsampling operation on the first thermal infrared image, thereby generating the second thermal infrared image; The image enhancement unit (212) is configured to perform an image enhancement operation on the first thermal infrared image according to a preset algorithm, thereby generating the second thermal infrared image, and wherein It also includes a temperature detection module (230), wherein the temperature detection module (230) includes a positioning unit (231) and a temperature detection unit (232), wherein The positioning unit (231) is configured to convert the first position information of the target object in the second thermal infrared image into the second position information of the target object in the first thermal infrared image according to a preset coordinate conversion algorithm; as well as The temperature detection unit (232) is configured to obtain temperature value information corresponding to the pixel information corresponding to the second position information in the first thermal infrared image, thereby determining temperature distribution information corresponding to the target object, wherein The apparatus further comprises an image fusion module (240), wherein the image fusion module (240) is configured to fuse the first position information, the temperature distribution information and the second thermal infrared image, add a mark of the position information and the temperature information at the position of the target object in the second thermal infrared image, and generate a third thermal infrared image marked with the position information and the temperature information of the target object; as well as The image fusion module (240) is further configured to cache the target object temperature, the target object position and the relevant data of the third thermal infrared image while generating the third thermal infrared image, wherein The image enhancement unit (212) is configured to suppress noise in the first thermal infrared image according to a preset denoising filtering algorithm, and the image enhancement unit (212) is also configured to suppress noise in the high-resolution thermal infrared image output by the upsampling unit (211) according to the preset denoising filtering algorithm, thereby generating the second thermal infrared image.

2. The thermal infrared image processor (20) according to claim 1, characterized in that: The image enhancement unit (212) is configured to enhance detail information in the first thermal infrared image according to a preset image enhancement algorithm, thereby generating the second thermal infrared image; or The image enhancement unit (212) is configured to enhance detail information in the high-resolution thermal infrared image output by the upsampling unit (211) according to the preset image enhancement algorithm, thereby generating the second thermal infrared image.

3. A thermal infrared image processing system, characterized in that: include: Image acquisition device (10); And according to the thermal infrared image processor (20) according to any one of claims 1 to 2, the thermal infrared image processor (20) is connected to the image acquisition device (10) to receive the thermal infrared image acquired by the image acquisition device (10).

4. A thermal infrared image processing system, characterized in that: include: An image acquisition device (10), a high-definition display module (30) and a network interface module (31); and the thermal infrared image processor (20) according to claim 1, wherein The thermal infrared image processor (20) is connected to the image acquisition device (10) to receive the thermal infrared image acquired by the image acquisition device (10); The high-definition display module (30) is connected to the image fusion module (240) in the thermal infrared image processor (20) and is used to display the third thermal infrared image generated by the image fusion module (240) in high definition; as well as The network interface module (31) is connected to the image fusion module (240) in the thermal infrared image processor (20) and is used to send the target object temperature, the target object position and relevant data of the third thermal infrared image to a remote server.

5. A thermal infrared image processing method, characterized in that: include: Generate a second thermal infrared image suitable for image detection according to a preset preprocessing algorithm and the first thermal infrared image, wherein the first thermal infrared image is a low-resolution thermal infrared image; as well as Detecting a target object in the second thermal infrared image, wherein The operation of generating a second thermal infrared image suitable for image detection according to a preset preprocessing algorithm and the first thermal infrared image includes: Performing an upsampling operation on the first thermal infrared image to generate the second thermal infrared image; The first thermal infrared image is enhanced according to a preset algorithm to generate the second thermal infrared image. The operation of detecting a target object in the second thermal infrared image includes: converting the first position information of the target object in the second thermal infrared image into the second position information of the target object in the first thermal infrared image according to a preset coordinate conversion algorithm; and According to the pixel information corresponding to the second position information in the first thermal infrared image, the temperature value information corresponding to the pixel information is acquired, so as to determine the temperature distribution information corresponding to the target object; The method further includes: fusing the first position information, the temperature distribution information, and the second thermal infrared image, adding a mark of position information and temperature information at the position of the target object in the second thermal infrared image, and generating a third thermal infrared image marked with the position information and temperature information of the target object; and The target object temperature, the target object position and the related data of the third thermal infrared image are cached while generating the third thermal infrared image, wherein The operation of performing an image enhancement operation on the first thermal infrared image according to a preset algorithm to generate the second thermal infrared image includes: According to a preset denoising filter algorithm, the noise in the first thermal infrared image is suppressed to generate the second thermal infrared image, and according to the preset denoising filter algorithm, the noise in the high-resolution thermal infrared image output by the upsampling unit (211) is suppressed to generate the second thermal infrared image.

6. A thermal infrared image processing device, characterized in that: include: processor; as well as A memory, connected to the processor, configured to provide the processor with instructions for processing the following processing steps: Generating a second thermal infrared image suitable for image detection according to a preset preprocessing algorithm and the first thermal infrared image; Detecting a target object in the second thermal infrared image, wherein Performing an upsampling operation on the first thermal infrared image to generate the second thermal infrared image; performing an image enhancement operation on the first thermal infrared image according to a preset algorithm, thereby generating the second thermal infrared image; Determining second position information of the target object in the first thermal infrared image according to the first position information of the target object in the second thermal infrared image; as well as Determine temperature distribution information corresponding to the target object according to pixel information corresponding to the second position information in the first thermal infrared image, wherein The system further comprises an image fusion module (240), wherein the image fusion module (240) is configured to add a mark at the position of the target object in the second thermal infrared image according to the first position information and the temperature distribution information, and to generate a third thermal infrared image while caching the target object temperature, the target object position and relevant data of the third thermal infrared image, wherein The image enhancement unit (212) is configured to suppress noise in the first thermal infrared image according to a preset denoising filtering algorithm, thereby generating the second thermal infrared image; or The image enhancement unit (212) is configured to suppress noise in the high-resolution thermal infrared image output by the upsampling unit (211) according to the preset denoising filtering algorithm, thereby generating the second thermal infrared image.

Images