Region-of-interest highlighting method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a region-of-interest highlighting method and device, equipment and a storage medium, relates to the technical field of infrared thermal imaging, and is used for highlighting a region-of-interest in a to-be-highlighted infrared image so that a user can check the region-of-interest. The highlighting method comprises the following steps: in response to a region determination operation based on an image display interface, taking a determined interface region as a region of interest; the image display interface is used for displaying an infrared image acquired by the image acquisition equipment; and in response to a highlighting operation for the region of interest, enhancing the contrast of the local infrared image corresponding to the region of interest.

Description

Technical Field

[0001] The present application relates to the field of infrared thermal imaging technology, and in particular to a method, device, equipment and storage medium for highlighting a region of interest. Background Art

[0002] Thermal images are mostly single-channel grayscale images without color information. In practical applications, the search for targets mostly relies on temperature information, and the grayscale distribution effect of the image is limited by the scene content. The richer the scene, the easier it is for the target to be submerged in the complex background, which is not conducive to target discovery and observation. This phenomenon is particularly obvious in infrared thermal imaging. Therefore, after obtaining the thermal imaging image, the target in the thermal imaging image can be highlighted for user reference.

[0003] The highlighting in related technologies is mostly based on the parameter adjustment of the digital image signal processor (ISP) of the whole frame, which has requirements on the grayscale amplitude of the target, that is, highlighting the high-temperature target. If the target is in the low temperature or medium temperature range, the highlighting scheme design has no prior knowledge and cannot highlight the target. Another scheme is the highlighting scheme based on the target detection method. This scheme relies on the target detection algorithm and has high requirements on the power consumption of the resource platform. Summary of the invention

[0004] The present application provides a method, device, equipment and storage medium for highlighting a region of interest, which is used to provide a solution with low computational cost and capable of highlighting a region of interest in an infrared image to be highlighted, so that users can easily view the content in the region of interest.

[0005] A first aspect of an embodiment of the present application provides a method for highlighting a region of interest, comprising: in response to a region determination operation based on an image display interface, taking a determined interface region as a region of interest; the image display interface is used to display infrared images acquired by an image acquisition device; in response to the highlighting operation on the region of interest, enhancing the contrast of a local infrared image corresponding to the region of interest.

[0006] The method for highlighting the region of interest provided in the embodiment of the present application does not rely on the target detection algorithm or the prior knowledge of the target when highlighting the infrared image displayed in the image display interface, but determines the region of interest through the region determination operation, and the determination method is simple and more applicable in practical applications. Then, by enhancing the contrast of the local infrared image corresponding to the region of interest, the effect of highlighting the region of interest can be achieved, and the highlighting method is simple, and does not require a large amount of computing resources to facilitate users to check the region of interest.

[0007] In combination with the first implementation manner of the first aspect, in response to the area determination operation based on the image display interface, the area determined in the area determination operation is used as the area of ​​interest, including: the interface center area of ​​the image display interface is used as the area of ​​interest.

[0008] In combination with the second implementation manner of the first aspect, the central area of ​​the interface is an area of ​​a preset size in the center of the interface, or is a central area of ​​the interface where the grayscale difference is within a preset threshold range.

[0009] In combination with the third implementation manner of the first aspect, in the process of enhancing the contrast of the local infrared image, the enhancement degree of the local infrared image gradually decreases from the center to the periphery of the local infrared image.

[0010] In combination with the fourth implementation method of the first aspect, the contrast of the local infrared image corresponding to the region of interest is enhanced, including: counting the number of times each gray value appears in the local infrared image to obtain a statistical result corresponding to the local infrared image; correcting the statistical result according to the weight corresponding to the region of interest to obtain a corrected statistical result; wherein the weight corresponding to the region of interest gradually decreases from the center of the region of interest to the periphery; and performing histogram equalization processing on the local infrared image based on the corrected statistical result to obtain a target local infrared image.

[0011] In combination with the fifth implementation method of the first aspect, the contrast of the local infrared image corresponding to the region of interest is enhanced, including: determining image processing parameters corresponding to the region of interest; the image processing parameters include noise reduction parameters and / or sharpening parameters; based on the image processing parameters corresponding to the region of interest, the parameters of the local infrared image are adjusted to enhance the contrast of the local infrared image, so as to obtain a target local infrared image.

[0012] In combination with the sixth implementation manner of the first aspect, the method further includes: fusing the target local infrared image with the infrared image to obtain a fused image; and displaying the fused image in an image display interface.

[0013] In combination with the seventh implementation method of the first aspect, the contrast of the local infrared image corresponding to the region of interest is enhanced, including: counting the number of occurrences of each grayscale value in the infrared image displayed in the image display interface to obtain the statistical results corresponding to the infrared image; correcting the statistical results according to the weight corresponding to the region of interest to obtain the corrected statistical results; wherein the weight corresponding to the region of interest is greater than 1, and the weight corresponding to the region of interest gradually decreases from the center of the region of interest to the periphery of the region of interest; and performing histogram equalization processing on the infrared image displayed in the image display interface based on the corrected statistical results.

[0014] In combination with the eighth implementation method of the first aspect, the contrast of the local infrared image corresponding to the region of interest is enhanced, including: determining the target dynamic range of the local infrared image; determining the target response rate corresponding to the target dynamic range based on the correspondence between the preset dynamic range and the response rate; adjusting the response rate of the image acquisition device to the target response rate; reacquiring the infrared image through the adjusted image acquisition device, and enhancing the contrast of the local infrared image corresponding to the region of interest in the newly acquired infrared image.

[0015] In combination with the ninth implementation method of the first aspect, the method also includes: determining the image processing parameters corresponding to the target response rate based on the corresponding relationship between the preset response rate and the image processing parameters; the image processing parameters include sharpening parameters and / or noise reduction parameters; and adjusting the parameters of the newly acquired infrared image based on the image processing parameters corresponding to the target response rate.

[0016] A second aspect of an embodiment of the present application provides a device for highlighting a region of interest, comprising: a determination module for determining one or more regions in an infrared image to be highlighted in response to an operation by a user to determine one or more regions and to set the one or more regions as regions of interest; a highlighting module for enhancing the contrast of the region of interest in response to the highlighting operation on the region of interest so as to highlight the region of interest.

[0017] A third aspect of an embodiment of the present application provides an electronic device, comprising: one or more processors; one or more memories; wherein the one or more memories are used to store computer program codes, the computer program codes include computer instructions, and when the one or more processors execute the computer instructions, the electronic device executes the method for highlighting a region of interest provided by the first aspect and its possible implementation methods.

[0018] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, which stores computer execution instructions. When the computer execution instructions are run on a computer, the computer executes the method for highlighting a region of interest provided by the first aspect and its possible implementation methods.

[0019] A fifth aspect of an embodiment of the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the method for highlighting a region of interest provided in the first aspect and its possible implementation methods.

[0020] Among them, the beneficial effects described in the second to fifth aspects can refer to the beneficial effect analysis of the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0022] Figure 1 A method flow of a method for highlighting a region of interest provided in an embodiment of the present application Figure 1 ;

[0023] Figure 2 A schematic diagram of determining a region of interest provided in an embodiment of the present application;

[0024] Figure 3 A schematic diagram of an infrared image to be highlighted provided in an embodiment of the present application;

[0025] Figure 4 A schematic diagram of a highlighted infrared image provided in an embodiment of the present application;

[0026] Figure 5 A schematic diagram of a method for highlighting a region of interest provided in an embodiment of the present application Figure 1 ;

[0027] Figure 6 A schematic diagram of a method for highlighting a region of interest provided in an embodiment of the present application Figure 2 ;

[0028] Figure 7 An infrared image after unweighted histogram equalization processing provided in an embodiment of the present application;

[0029] Figure 8 An infrared image after weighted histogram equalization processing provided in an embodiment of the present application;

[0030] Fig. 9 A method flow of a method for highlighting a region of interest provided in an embodiment of the present application Figure 2 ;

[0031] Fig.10 A schematic diagram of the structure of a device for highlighting a region of interest provided in an embodiment of the present application;

[0032] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0035] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "connected" and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances. In addition, when describing a pipeline, the "connected" and "connection" used in this application have the meaning of conduction. The specific meaning needs to be understood in conjunction with the context.

[0036] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0037] Infrared thermal imaging telescopes or infrared image acquisition equipment can passively receive infrared radiation emitted by objects through optical lenses and infrared detectors, and then convert the temperature distribution image of the target object into a video image through means such as photoelectric conversion, electrical signal processing and digital image processing. Specifically, the infrared lens will filter out visible light, allowing only infrared rays to pass through, and collect the radiation within the working band and focus it on the detector. The detector then converts the collected infrared radiation into a weak electrical signal, the size of which can reflect the strength of the infrared radiation. The hardware circuits carried in the movement will amplify and reduce the noise of these weak electrical signals, so as to clearly collect the temperature distribution of the target object. Finally, the software will process, optimize, and enhance the amplified and noise-reduced electrical signals, and obtain electronic video signals, which can be output to the display to obtain thermal imaging images visible to the human eye.

[0038] The thermal images collected are mostly single-channel grayscale images, lacking color information, and the grayscale distribution is limited by the scene content, which makes it easy for the target to be submerged in the complex background, which indeed brings difficulties to target search and is not conducive to target discovery. Therefore, in order to facilitate users to observe the targets in the area of ​​interest, after obtaining the thermal imaging image, the targets in the thermal imaging image need to be highlighted for easy viewing by users.

[0039] The highlighting in related technologies is mostly based on the ISP parameter adjustment of the entire frame, that is, a series of algorithms and technical processing are performed on the original image signal output by the image sensor, aiming to enhance the image quality, contrast, color accuracy, noise reduction, white balance adjustment, sharpening and other aspects. Its main functions include linear correction, noise removal, bad pixel removal, interpolation, white balance adjustment, automatic exposure control, etc. However, this method has requirements on the grayscale amplitude of the target, that is, to highlight high-temperature targets. If the target is in the low or intermediate temperature range, its grayscale value may be close to the background, making it difficult to highlight. Moreover, in the absence of prior knowledge, this highlighting scheme is difficult to accurately judge the grayscale range and characteristics of the target, and it is impossible to highlight any target.

[0040] Another solution is a highlighting solution based on target detection methods, which relies on target detection algorithms, such as deep learning models such as convolutional neural networks. These algorithms can automatically learn the characteristics of targets and accurately identify and locate targets in images. Through target detection algorithms, automatic highlighting of targets can be achieved, improving the visual effect and readability of images. However, target detection algorithms usually involve a large number of matrix operations and convolution operations, which have high computational complexity. This may lead to a significant increase in the power consumption of resource platforms, especially when processing high-resolution images or real-time video streams, which in turn increases the cost of infrared thermal imaging telescopes and leads to poor user experience.

[0041] Based on this, an embodiment of the present application provides a method for highlighting a region of interest. According to the method, a user can select one or more regions in an infrared image to be highlighted as a region of interest (ROI); then, after receiving a highlighting operation on the region of interest, the contrast of the region of interest is enhanced to highlight the region of interest.

[0042] It can be seen that the solution provided by the embodiment of the present application does not rely on the target detection algorithm or prior knowledge of the target when highlighting the infrared image to be highlighted, but the area where the target is located is manually determined by the user and is used as the area of ​​interest. The determination method is simple and more applicable in practical applications. Then, by enhancing the contrast of the area of ​​interest, the effect of highlighting the area of ​​interest can be achieved, and it does not require a large amount of computing resources to facilitate users to check the area of ​​interest.

[0043] It should be understood that the method for highlighting the region of interest provided in the present application is applied to a device with an infrared image acquisition function, which may be an infrared thermal imaging telescope or an infrared image acquisition device, etc. For ease of description, the embodiment of the present application takes an infrared thermal imaging telescope as an example to illustrate the solution of the present application.

[0044] The infrared thermal imaging telescope can be used for outdoor observation and target observation at night and in low light conditions. It can clearly display infrared images of the surrounding conditions to help see people, objects and animals. The infrared thermal imaging telescope can be used in outdoor activities, outdoor search and rescue, wildlife observation or rescue and other application scenarios, so that users can observe the surrounding area in real time through the infrared thermal imaging telescope.

[0045] In some embodiments, the human visual system has a natural tendency to give priority to focusing on and processing the central area of ​​the visual scene. This is called "center bias" or "visual attention concentration effect". When faced with a complex visual scene, the user's eyes and brain will first lock onto the center of the screen to obtain the most critical information. In other words, when the user consults an infrared image, he or she will also be more inclined to consult the center of the infrared image. Therefore, as a feasible implementation method, a cross cursor can be set at the center of the infrared image, that is, the center of the screen display of the infrared thermal imaging telescope, so that the cross cursor can be used to align with the target to be observed during application, and then the user can set the area where the target is located as the area of ​​interest.

[0046] The method for highlighting the region of interest provided in the present application is described below with reference to the accompanying drawings.

[0047] See also Figure 1 The method for highlighting a region of interest provided in this application comprises the following steps:

[0048] S101 . In response to an area determination operation based on an image display interface, a determined interface area is used as an area of ​​interest.

[0049] Among them, the image display interface is used to display the infrared images collected by the image acquisition device.

[0050] It should be understood that infrared acquisition equipment such as infrared thermal imaging telescopes usually have an image display interface, which can display the acquired infrared images in real time. When the user determines that there is a target object that he wants to focus on in the infrared image, that is, when a certain area of ​​the infrared image needs to be highlighted, he can perform a region determination operation in the image display interface, and then the infrared thermal imaging telescope can use the interface area corresponding to the region determination operation as the area of ​​interest.

[0051] This application does not limit the region determination operation. Exemplarily, as a feasible implementation method, the user can directly define one or more regions in the image display interface and use them as regions of interest. As another feasible implementation method, in response to the user's operation of determining the target object in the image display interface, a prompt message is output, and the prompt message is used to prompt the user whether to use the region where the target object is located as the region of interest; in response to receiving the user's confirmation operation, the region of a preset size where the target object is located is used as the region of interest.

[0052] In some embodiments, since the human visual system has a selective attention mechanism, that is, it automatically pays attention to certain information and ignores other information, it tends to focus on the central area of ​​the visual scene. This effect also exists in image viewing, making the center of the picture easily become the focus of user vision. Therefore, in order to better enhance the user's attention to the area of ​​interest, the area of ​​interest can be set in the central area of ​​the image display interface.

[0053] Specifically, as a feasible implementation method, S101 can be implemented as: taking the central area of ​​the image display interface as the region of interest.

[0054] It is understandable that if Figure 2 As shown in FIG. 1 , when the user finds the target object within the field of view, he usually moves the infrared thermal imaging telescope to align the cross cursor located at the center of the image display interface with the target object, that is, the object that the user wants to focus on. Then, the user can use the physical buttons set on the infrared thermal imaging telescope machine or the display controls in the image display interface (such as Figure 2 The confirmation control shown in the figure) triggers the area confirmation operation, and the center area of ​​the image display interface ( Figure 2 The region of interest is shown in bold.

[0055] As a feasible implementation method, the center area of ​​the image display interface may be an area of ​​a preset size in the center of the interface.

[0056] Among them, the preset size can be preset by the system or the user, and can be set according to the needs in the actual application process. Exemplarily, as a feasible implementation method, the correspondence between the triggering number of physical buttons and the preset size can be preset, so that the user can touch the physical button according to their own needs to obtain the size of the area of ​​interest that meets the user's needs. As another feasible implementation method, the user can set the size of the area of ​​interest in the image display interface. The embodiment of the present application is not limited to this.

[0057] As a feasible implementation manner, the central area of ​​the interface may also be the central area of ​​the interface where the grayscale difference is within a preset threshold range.

[0058] That is, in the central area of ​​the image display interface, the grayscale value difference between each pixel point, or the grayscale value difference between this area and other parts of the interface is determined to obtain the grayscale difference, and then the central area of ​​the interface where the grayscale difference is within the preset threshold range is taken as the area of ​​interest.

[0059] It is understandable that infrared images capture the thermal radiation of the surface of an object, and the body temperature and surface characteristics of a person or animal (such as hair, skin, etc.) will affect its infrared radiation characteristics. However, due to the self-regulation mechanism of organisms, their body temperature is usually maintained in a relatively stable range. Therefore, in infrared images, the overall grayscale values ​​of these organisms may be relatively close.

[0060] Therefore, the central area of ​​the interface where the grayscale difference is within the preset threshold range can be identified as the area where a target object is located and used as the region of interest. The amount of data required for subsequent highlighting of the region of interest can be significantly reduced. This helps to speed up processing and reduce computing costs. At the same time, after the highlighting process, it can make it easier for users to view the region of interest, improving the user experience.

[0061] In other embodiments, if the image acquisition device remains stationary while the user is using it to observe, it may mean that it is steadily capturing an image of a specific area, which means that the user is locking onto an important area for continuous observation, that is, the user is observing the object or information in the area in detail. In addition, since users tend to focus more on the central area of ​​the picture, the central area is the natural focus of the user's vision.

[0062] Based on this, as a feasible implementation method, when the image acquisition device is in the current posture for a period exceeding a preset period, the central area of ​​the image display interface can be used as the region of interest.

[0063] It should be understood that the specific method for determining the region of interest can refer to the above embodiments, and this application will not go into details here.

[0064] For example, when the image acquisition device is in the current position for more than 3 seconds, the central area of ​​the image display interface may be used as the region of interest.

[0065] It can be understood that when the image acquisition device is in the current position for longer than the preset time, it indicates that the user is observing in detail the object or information presented in the center of the infrared image. Since the central area is the natural focus of the user's vision, the central area of ​​the image display interface can be automatically used as the area of ​​interest.

[0066] Alternatively, as another feasible implementation method, the grayscale value corresponding to the center of the image display interface can be obtained. When the grayscale value does not change within a preset time period or is within a preset grayscale range, the center area of ​​the image display interface is taken as the area of ​​interest.

[0067] It is understandable that due to the different materials, structures and thermal characteristics of different objects, the intensity of infrared radiation they emit will also be different, that is, the grayscale difference of different objects in infrared images is usually large. However, the surface temperature distribution of the same object is relatively uniform, that is, in the infrared image, the grayscale of the object will also be relatively uniform, and the grayscale difference of the same object is small. Therefore, it is possible to determine whether the user is observing a certain object by the change of the grayscale value corresponding to the center of the interface of the image display interface.

[0068] If the grayscale value corresponding to the center of the interface does not change within a preset time or is within a preset grayscale range, it can be determined that the user is observing an object. To facilitate user browsing, the center area of ​​the image display interface can be used as the area of ​​interest.

[0069] S102 : In response to the highlighting operation on the region of interest, the contrast of the local infrared image corresponding to the region of interest is enhanced.

[0070] After determining one or more regions of interest, the user can perform a highlighting operation on the regions of interest. The highlighting operation can be a user touching a control corresponding to the highlighting operation, or a physical button on a touch device, or issuing a voice command related to the highlighting. The embodiments of the present application do not limit the specific content of the highlighting operation.

[0071] Upon receiving the highlighting operation of the occlusion on the area of ​​interest, the contrast of the local infrared image displayed in the area of ​​interest is enhanced, so that the local infrared image can be more prominent relative to other parts of the infrared image, thereby improving the efficiency and accuracy of the user's interpretation of the infrared image displayed in the image display interface.

[0072] In some embodiments, if contrast enhancement processing is performed on a local infrared image in a region of interest, a relatively obvious boundary may be generated at the junction of the region of interest and other regions, resulting in a poor viewing experience for the user.

[0073] Therefore, in order to avoid unnatural boundary effects at the edge of the ROI, as a feasible implementation method, in the process of enhancing the contrast of the local infrared image, the enhancement degree of the local infrared image can be gradually reduced from the center of the local infrared image to the periphery.

[0074] In this way, the central area of ​​the local infrared image has the highest degree of enhancement. This usually means that the pixel values ​​in this area will be retained or enhanced the most in subsequent processing. The degree of enhancement gradually decreases from the center of the local infrared image to the periphery, that is, the degree of enhancement in other areas gradually decreases to ensure a smooth transition between the local infrared image and other infrared images to avoid sudden changes causing boundary effects.

[0075] It can be seen that the solution provided by the embodiment of the present application does not rely on the target detection algorithm or prior knowledge of the target when highlighting the infrared image displayed in the image display interface, but is based on the area determination operation of the image display interface, and the determined interface area is used as the area of ​​interest. The determination method is simple and has stronger applicability in practical applications. Then, by enhancing the contrast of the local infrared image corresponding to the area of ​​interest, the effect of highlighting the local infrared image can be achieved, and it does not require a large amount of computing resources to facilitate users to view the area of ​​interest.

[0076] For example, see Figure 3 and Figure 4 , Figure 3 This is the infrared image before highlighting. Figure 4 The area indicated by the bold frame in the figure is the area of ​​interest. Figure 4 That is, the infrared image is obtained by highlighting the local infrared image corresponding to the region of interest. It can be seen that the solution of the present application enhances the contrast of the region of interest, so that when the user views the infrared image, he or she can focus on the content in the region of interest, which is convenient for the user to use.

[0077] In some embodiments, only the local infrared image in the region of interest may be processed to enhance the contrast of the local infrared image, which may be achieved by performing histogram equalization processing on the local infrared image, adjusting parameters, and the like.

[0078] It should be understood that histogram equalization is a technique for enhancing image contrast by adjusting the distribution of image grayscale values. The core idea of ​​histogram equalization is to change the grayscale histogram of the original image from a relatively concentrated grayscale interval to a uniform distribution in the entire grayscale range. This can make the pixel values ​​in the image more evenly distributed, thereby enhancing the image contrast. Therefore, the contrast of the local infrared image in the region of interest can be enhanced by histogram equalization.

[0079] For details, please refer to Figure 5 , S102 can be specifically implemented as follows:

[0080] S201 , counting the number of occurrences of each gray value in a local infrared image, and obtaining a statistical result corresponding to the local infrared image.

[0081] It should be understood that counting the number of occurrences of each gray value in the local infrared image is to understand the gray distribution of the image and provide basic data for the subsequent calculation of the cumulative histogram and the mapping function.

[0082] Specifically, when counting the grayscale histogram of a local infrared image, it is necessary to traverse the entire image and obtain the grayscale value of each pixel. Then, for each grayscale value, use an array (or hash table, etc.) to record the number of times it appears. Among them, the index of the array corresponds to the grayscale value, and the value of the array corresponds to the number of times the grayscale value appears. Then, the statistical result corresponding to the local infrared image is obtained.

[0083] It should be understood that Figure 5 As shown in FIG. 1 , the statistical results corresponding to the local infrared image can be displayed by the grayscale histogram corresponding to the local infrared image. The grayscale histogram is used to display the relationship between each grayscale level in the local infrared image and its corresponding pixel number (or frequency). In the histogram equalization process, counting the number of occurrences of each grayscale value in the image and obtaining the grayscale histogram is an important step in the histogram equalization process. Counting the number of occurrences of each grayscale value can help determine the grayscale distribution of the image.

[0084] Moreover, in the process of histogram equalization, a grayscale mapping relationship needs to be established to map the grayscale value of the original image to the new grayscale value. This mapping relationship can be determined based on the grayscale histogram of the local original image. By counting the number of occurrences of each grayscale value, we can calculate the cumulative distribution function of each grayscale value in the histogram to determine the mapping relationship.

[0085] S202: Correct the statistical result according to the weight corresponding to the region of interest to obtain a corrected statistical result.

[0086] Among them, the weight corresponding to the region of interest gradually decreases from the center of the region of interest to the periphery.

[0087] Specifically, as a feasible implementation method, the weight corresponding to each region can be converted into a two-dimensional array (mask) of the same size as the image, where the value of each element represents the weight of the corresponding image position. Then, an array can be created to store the grayscale value statistics, and then for each pixel in the image, the position of its grayscale value in the statistics array is found, and the statistics of the position are corrected according to the weight of the current pixel to obtain the corrected statistics.

[0088] It should be understood that if the region of interest uses a uniform weight, then a more obvious boundary may be generated at the junction of the region of interest and other regions, resulting in a poor user experience. Therefore, in order to avoid unnatural boundary effects at the edge of the ROI, the weight of the region of interest can be set to gradually decrease from the center to the periphery.

[0089] In this way, the central area of ​​the ROI (or "focus area") is given the highest weight. This usually means that the pixel values ​​in this area will be retained or enhanced the most in subsequent processing. The weights decrease from the central area of ​​the picture to the surrounding areas, that is, more weight is assigned to the central area of ​​the ROI, and the weights of other areas are gradually reduced to ensure a smooth transition between the region of interest and other areas to avoid sudden changes causing boundary effects.

[0090] Specifically, in practical applications, a preset weight value can be set for the central area of ​​the ROI, and then a suitable function such as a linear function or a Gaussian function is used to calculate the weights of other areas except the central area, ensuring that the weight value decreases smoothly with increasing distance to prevent boundary effects.

[0091] For example, the weight value may be gradually reduced from the central area of ​​the ROI to the periphery, so as to ensure a smooth transition between the region of interest and other regions, thereby improving the user's viewing experience of the image.

[0092] It can be seen that the solution of this embodiment adopts a strategy of decreasing weights from the central area of ​​the picture to the surrounding areas, which can effectively avoid the boundary effect and improve the effect of histogram equalization processing.

[0093] S203 . Perform histogram equalization processing on the local infrared image based on the corrected statistical result to obtain a target local infrared image.

[0094] It should be understood that histogram equalization is an image enhancement technique based on the statistical characteristics of image grayscale values. The core idea of ​​this method is to transform the histogram (i.e., grayscale value distribution) of the original image into a more uniform or nearly uniform form. In this way, the grayscale values ​​that were originally concentrated in the histogram will be stretched or expanded to cover a wider grayscale range, while the grayscale values ​​that were originally sparsely distributed will be compressed or merged to reduce their occupied range.

[0095] That is to say, the histogram equalization process will widen the grayscale values ​​with a large number of pixels in the corrected statistical results (i.e., the grayscale values ​​that play a major role in the picture), and merge the grayscale values ​​with a small number of pixels (i.e., the grayscale values ​​that do not play a major role in the picture). As a result, the grayscale values ​​that originally dominated the local infrared image will be given a wider grayscale range, making them more prominent visually; while the grayscale values ​​that were originally uncommon will be compressed into a smaller grayscale range, and may even be merged.

[0096] In this embodiment, the statistical results of the local infrared image are corrected based on the region of interest, that is, the number of pixels corresponding to the grayscale value at the center of the local infrared image is adjusted according to the weight, that is, the frequency of these grayscale levels in the image is increased. In this way, in the process of histogram equalization, these high-frequency grayscale levels will be stretched to a wider grayscale range, which may enhance the contrast of the area to a certain extent.

[0097] Moreover, in this embodiment, the weight corresponding to the region of interest gradually decreases from the center to the periphery of the region of interest, that is, the enhancement degree of the local infrared image gradually decreases from the center to the periphery of the local infrared image.

[0098] It should be understood that histogram equalization stretches the distribution range of grayscale values, making similar grayscale values ​​that were originally difficult to distinguish in the image easier to distinguish. This stretching effect is particularly obvious in areas where grayscale values ​​were originally concentrated, because the grayscale values ​​in these areas will be distributed into a wider grayscale range after equalization. In addition, after histogram equalization, more grayscale levels are used to represent different brightness in the image, which can enhance the dynamic range of the image, that is, the grayscale difference between the brightest and darkest parts of the image, making the details in the image clearer.

[0099] Histogram equalization expands the grayscale value distribution and stretches the grayscale value distribution range, so that the grayscale values ​​with a larger number in the local infrared image will be given a wider grayscale range, making them more prominent visually. At the same time, it can enhance the dynamic range of the image, thereby improving the contrast of the local infrared image and making the edges and textures in the image more prominent.

[0100] It can be seen that the scheme provided by this embodiment corrects the grayscale statistical results of the local infrared image through the weight corresponding to the region of interest, and the weight corresponding to the region of interest gradually decreases from the center of the region of interest to the periphery, so that while enhancing the contrast of the local infrared image, the degree of enhancement of the local infrared image gradually decreases from the center of the local infrared image to the periphery. In other words, the scheme of this embodiment enhances the contrast of the local infrared image through histogram equalization processing, and at the same time, during the processing, it can ensure that the degree of enhancement of the local infrared image gradually decreases from the center of the local infrared image to the periphery, so that the transition between the local infrared image and other parts of the infrared image is more natural, that is, it can ensure a smooth transition between the region of interest and other regions, so as to enhance the user's viewing experience of the image.

[0101] As another feasible implementation method, the contrast of the region of interest can be enhanced by local image processing, that is, only the image processing parameters of the region of interest in the image are adjusted, so that the processing method of the region of interest is different from that of other regions, and thus the display effect is also different. It should be noted that the solution of this embodiment and the histogram equalization processing solution in the above embodiment can be used simultaneously to enhance the contrast of the local infrared image, or they can be used separately, and the embodiment of the present application does not limit this.

[0102] Specifically, S102 may also be implemented as S1021 and S1022 as follows:

[0103] S1021. Determine image processing parameters corresponding to the region of interest.

[0104] The image processing parameters include noise reduction parameters and / or sharpening parameters.

[0105] It should be understood that sharpening parameters are mainly used to enhance the clarity and edge sharpness of an image. Common sharpening parameters include: strength, which determines the strength of sharpening, that is, the degree of edge contrast enhancement. By adjusting the strength, you can control the obviousness of the edges in the image, making the image look clearer; fineness, which controls the frequency of the sharpening effect, that is, the richness of the details. The higher the fineness, the richer the details in the image, but it may also cause the image to look too sharp or produce noise; critical value, which sets the edge contrast that will be sharpened. It is the threshold for distinguishing edges from non-edges. By adjusting the critical value, you can control which edges are sharpened and which edges are retained in their original state.

[0106] Denoising parameters are used to reduce noise in images and improve image clarity and quality. Common denoising parameters include: filter type, such as median filter, adaptive Wiener filter, etc. Different filter types have different processing effects on different types of noise; filter strength, which determines the degree of denoising. The higher the strength, the more obvious the denoising effect, but it may also lead to loss of image details; denoising algorithms, such as non-local means (NLM) algorithm, block matching based 3D filtering (BM3D) algorithm, etc. These algorithms remove noise by using similar blocks in the image, and the effect is usually better than simple filters.

[0107] Specifically, as a feasible implementation method, the grayscale histogram, color distribution, texture features, etc. of the region of interest can be analyzed to extract key parameters for contrast enhancement. These parameters may include grayscale range, mean, standard deviation, contrast, etc. Then, the noise reduction parameters and / or sharpening parameters corresponding to the region of interest can be determined according to the parameters of the region of interest and the image characteristics.

[0108] As another feasible implementation method, image processing parameters matching the resolution may be determined according to the resolution of the region of interest.

[0109] It should be understood that resolution is an important indicator to measure the ability of an image to express details. Images with different resolutions differ in terms of detail richness, clarity, etc. Therefore, determining processing parameters based on the resolution of the image can ensure that important details are not lost during the processing, while avoiding the introduction of unnecessary blur or noise, thereby maintaining the overall quality of the image.

[0110] S1022: Adjust the parameters of the local infrared image based on the image processing parameters corresponding to the region of interest to enhance the contrast of the local infrared image and obtain a target local infrared image.

[0111] After the image processing parameters corresponding to the region of interest are obtained, the parameters of the local infrared image can be adjusted based on the image processing parameters corresponding to the region of interest.

[0112] Exemplarily, when the image processing parameter is a noise reduction parameter, a suitable filtering algorithm such as median filtering, Gaussian filtering, bilateral filtering, etc. can be selected for the local infrared image according to the noise reduction parameter to remove noise in the local infrared image. It should be understood that the noise reduction parameter can also include: filter window size, number of iterations, etc., which will also affect the noise reduction effect.

[0113] It should be understood that infrared images are easily disturbed by various noises during the imaging process, such as thermal noise, electronic noise, etc. These noises will reduce the clarity and contrast of the image, making it difficult to identify the target object. Through noise reduction processing, these noises can be effectively removed to improve the purity and contrast of the local infrared image.

[0114] Sharpening is another effective method to enhance the contrast of infrared images. The purpose of sharpening is to enhance the edge and detail information in the image, making the boundary between the target object and the background clearer. Through sharpening, the clarity and contrast of local infrared images can be improved.

[0115] It can be seen that the method provided in this embodiment performs noise reduction and / or sharpening processing on the local infrared image by determining the noise reduction parameters and / or sharpening parameters corresponding to the region of interest, so that the contrast of the obtained target local infrared image is higher.

[0116] In some embodiments, after contrast enhancement is performed on the local infrared image, it needs to be displayed in an image display interface for easy viewing by users.

[0117] As a feasible implementation method, the method provided in the embodiment of the present application also includes: fusing the local infrared image of the target with the infrared image to obtain a fused image; and displaying the fused image in an image display interface.

[0118] The target infrared image and the unprocessed infrared image to be highlighted are image fused, and the pixels of the target infrared image and the infrared image to be highlighted can be processed and combined one by one. Commonly used methods include weighted average method, maximum method, minimum method, etc. A high-quality image containing complementary information of the two is obtained. The fused image can simultaneously contain the enhanced area of ​​interest information in the target local infrared image and other background information in the unprocessed infrared image. This helps to better identify and analyze infrared images and improve the efficiency and accuracy of image processing.

[0119] For example, see Figure 6 After contrast enhancement processing is performed on the local infrared image corresponding to the region of interest in the infrared image to obtain the target local infrared image, the target local infrared image can be fused with the infrared image and then displayed in the image display interface.

[0120] In some embodiments, since the acquired infrared images may be affected by noise, blur, lack of contrast, etc., it is usually necessary to improve the image quality through image processing techniques such as filtering, enhancement and sharpening before displaying the infrared images, so as to make them easier to observe and interpret. Based on this, the contrast of the local infrared images can be enhanced while the infrared images are processed as a whole.

[0121] Specifically, as a feasible implementation method, S102 can be specifically implemented as follows:

[0122] S11. Count the number of occurrences of each gray value in the infrared image displayed in the image display interface to obtain a statistical result corresponding to the infrared image.

[0123] The specific statistical process can be referred to the description in S201 above, and this application will not go into details here.

[0124] S12. Correct the statistical result according to the weight corresponding to the region of interest to obtain a corrected statistical result.

[0125] The weight corresponding to the region of interest is greater than 1, and the weight corresponding to the region of interest gradually decreases from the center of the region of interest to the periphery of the region of interest.

[0126] It should be understood that when the weight assigned to the pixels of the region of interest is greater than 1, it indicates that the pixels of the region of interest are more significantly stretched or expanded during the histogram equalization process in the subsequent processing, thereby enhancing the contrast of the region. This helps to make the details in the ROI clearer.

[0127] When counting the number of occurrences of each grayscale value, if a pixel is located in an area with a weight greater than 1, the contribution of the grayscale value of the pixel in the statistical result will be amplified accordingly. In other words, in the corrected statistical results, the grayscale values ​​with higher weights will appear more often than they actually appear in the image. Because the histogram equalization process will widen the grayscale values ​​with a large number of pixels (i.e., the grayscale values ​​that play a major role in the picture), and merge the grayscale values ​​with a small number of pixels (i.e., the grayscale values ​​that do not play a major role in the picture). In other words, a larger number of grayscale values ​​will be given a wider grayscale range, making them more prominent visually.

[0128] The solution of this embodiment sets the weight of the region of interest to be greater than 1, that is, the number of occurrences of the grayscale value of the region of interest is increased, and then when performing subsequent grayscale mapping, a wider grayscale range is allocated to the region of interest, so that the contrast of the region of interest can be enhanced to a higher degree than that of other regions.

[0129] Furthermore, it can be seen from the above embodiments that the weight corresponding to the region of interest gradually decreases from the center of the region of interest to the periphery of the region of interest, that is, during the processing, it can be ensured that the enhancement degree of the local infrared image gradually decreases from the center of the local infrared image to the periphery, so that the transition between the local infrared image and other parts of the infrared image is more natural, that is, a smooth transition between the region of interest and other regions can be guaranteed to enhance the user's viewing experience of the image.

[0130] S13. Performing histogram equalization processing on the infrared image displayed in the image display interface based on the corrected statistical result.

[0131] Specifically, after obtaining the corrected statistical results, the CDF value of each gray level can be calculated based on the corrected gray level histogram. The CDF value is used to calculate the ratio of the total number of pixels from the lowest gray level to the current gray level to the total number of pixels. That is, the larger the CDF value corresponding to the gray value with a large number of pixels, the higher the frequency of these gray values ​​appearing in the image. In the process of histogram equalization, these high-frequency gray values ​​will be assigned to a wider gray range, and then the visual of this part of the content in the processed image will be more prominent, that is, the degree of contrast enhancement is higher.

[0132] That is to say, in the process of histogram equalization, the areas with higher weights will be given more attention in the statistical and mapping processes, so the contrast of the areas with higher weights in the final image may be further enhanced.

[0133] For example, see Figure 7 and Figure 8 , Figure 7 is the infrared image after unweighted histogram equalization processing, Figure 8 For the region of interest ( Figure 7 and Figure 8 The infrared image is weighted by the unweighted histogram equalization (the central area of ​​the ROI), and then processed by histogram equalization. It can be seen that the overall visual effect of the image after unweighted histogram equalization is enhanced, but some important details or features of the ROI area may not be highlighted. The weighted image can highlight the details and features of the ROI area, making the information in this area clearer and easier to observe.

[0134] It can be seen that the solution provided in this embodiment, when applying the corrected statistical results to histogram equalization, is actually performing a "weighted" processing on the standard equalization process. This weighted processing can adjust the distribution of gray values ​​according to the importance or attention of different regions in the image. Specifically, by increasing the distribution range of the gray values ​​of the region of interest in the histogram, the details of the region of interest are made more prominent, thereby enhancing the contrast of the region of interest. The region of interest in the image will receive more attention and thus be more prominent visually. This helps to guide the attention of the observer or analyst and improve the efficiency of transmitting image information.

[0135] In some embodiments, the contrast of the region of interest can also be enhanced by adjusting the device responsivity. The device responsivity generally refers to the input-output gain of the detection system, that is, how responsive the system is to an input signal (such as infrared radiation). In infrared imaging, the responsivity is generally related to the sensitivity of the detector. It is understood that increasing the responsivity generally makes the difference between light and dark areas in the image more obvious, thereby enhancing the contrast of the image. This helps to visually highlight the details in the image, making the image more vivid and clear.

[0136] Based on this, as a feasible implementation method, please refer to Fig. 9 , enhancing the contrast of the region of interest, and can also include:

[0137] S401, determining a target dynamic range of a local infrared image.

[0138] Determine the distribution range of infrared radiation intensity in the region of interest in the infrared image to be highlighted. This can be achieved by calculating the gray value histogram of the pixels in the region of interest. Then, according to the distribution range of infrared radiation intensity in the region of interest, set a target dynamic range. This range should be able to cover most of the infrared radiation intensity in the ROI while avoiding overexposure or underexposure.

[0139] S402: Determine a target response rate corresponding to the target dynamic range based on a preset correspondence relationship between the dynamic range and the response rate.

[0140] It is understandable that the correspondence between the preset dynamic range and the response rate is usually obtained through experimental data, system parameters or image processing algorithms, etc. The correspondence may be expressed in the form of a table, a curve or a mathematical function to describe the response rate of the system under different dynamic ranges.

[0141] Furthermore, if the correspondence between the preset dynamic range and the response rate is expressed in a table, the response rate corresponding to the target dynamic range can be directly searched in the table. If the preset relationship is expressed in the form of a curve, the response rate corresponding to the target dynamic range can be estimated by interpolation or curve fitting. If the preset relationship is expressed in the form of a mathematical function, the target dynamic range can be substituted into the function for calculation to obtain the corresponding target response rate. The embodiments of the present application are not limited to this.

[0142] S403: Adjust the response rate of the image acquisition device to the target response rate.

[0143] The response rate of the image acquisition device that acquires the infrared image to be highlighted is adjusted to the target response rate, so that the response rate of the image acquisition device matches the target dynamic range of the region of interest. It can be understood that the matching of the image response rate and the target dynamic range can ensure that the target object is accurately highlighted in the image and reduce the interference of background information. That is, by adjusting the response rate, the contrast of the infrared image of the region of interest can be enhanced, so that the target object in the region of interest can be more easily identified and highlighted.

[0144] In addition, proper adjustment of the response rate can also reduce the noise in the image and improve the image clarity and signal-to-noise ratio.

[0145] Specifically, as a feasible implementation method, the response rate of the image acquisition device can be indirectly adjusted by adjusting the gain parameter, bias parameter or exposure time of the image acquisition device.

[0146] S404: reacquire the infrared image through the adjusted image acquisition device, and enhance the contrast of the local infrared image corresponding to the region of interest in the newly acquired infrared image.

[0147] It can be understood that the adjustment of the device response rate is an adjustment of the hardware device, and the effect of the adjustment occurs on the newly acquired image. Therefore, after the response rate adjustment, it is necessary to use the adjusted device to re-capture the infrared image and enhance the contrast of the local infrared image corresponding to the area of ​​interest in the newly acquired infrared image to highlight the area of ​​interest.

[0148] It should be understood that the method of enhancing the contrast of the local infrared image in the newly acquired infrared image may adopt the method in the above embodiment, and the present application will not elaborate on it here.

[0149] In some embodiments, since the response rate is adjusted for the hardware device and the target response rate is determined based on the dynamic range of the region of interest, the adjustment usually affects the image's brightness, contrast, and dynamic range. If only the response rate is adjusted without adjusting other processing parameters, it may cause problems such as uneven brightness, unbalanced contrast, or loss of details in some parts of the image. Therefore, in order to maintain consistency in image quality, other processing parameters need to be adjusted accordingly to ensure that the visual effect of the entire image is optimal.

[0150] Specifically, as a feasible implementation method, the method for highlighting the region of interest provided in the embodiment of the present application also includes: determining the image processing parameters corresponding to the target response rate according to the corresponding relationship between the preset response rate and the image processing parameters; and adjusting the parameters of the newly acquired infrared image based on the image processing parameters corresponding to the target response rate.

[0151] As a feasible implementation manner, the image processing parameters include sharpening parameters and / or noise reduction parameters.

[0152] It is understandable that adjusting the response rate may introduce some side effects, such as increased noise, loss of detail, or color distortion. These side effects may affect the quality and readability of the image. In order to reduce the impact of these side effects, other processing parameters need to be adjusted to compensate. For example, if the adjustment of the response rate leads to increased noise, the effect of the noise can be reduced by noise reduction processing; if it leads to loss of detail, the detail can be enhanced by sharpening processing.

[0153] It can be seen that it is necessary to adjust the sharpening parameters and / or noise reduction parameters of the entire image after adjusting the response rate. This can not only maintain the consistency of image quality and optimize the efficiency of image processing, but also adapt to different application scenarios and reduce the side effects of image processing.

[0154] In some embodiments, in order to facilitate the user to check the effect of highlighting the region of interest, it is necessary to output the highlighted image for the user to view.

[0155] Specifically, as a feasible implementation method, the method for highlighting the region of interest provided in the embodiment of the present application further includes: outputting a target infrared image, wherein the target infrared image is an infrared image with enhanced contrast of a local infrared image in the region of interest.

[0156] The processed target infrared image can be directly output so that users can check the area of ​​interest. Directly outputting the target infrared image can omit the image fusion step and simplify the processing flow. The target infrared image has enhanced the contrast of the area of ​​interest, so it can be directly used for target detection, recognition and other tasks. It can be seen that compared with image fusion, directly outputting the target infrared image can reduce the consumption of computing resources and improve processing efficiency.

[0157] The embodiment of the present application can divide the functional modules of the highlighting device or image acquisition device of the region of interest according to the above method. For example, the highlighting device or image acquisition device of the region of interest can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0158] The present application also provides a device for highlighting an area of ​​interest. Fig.10 The device 60 for highlighting a region of interest includes: a determination module 61 and a highlighting module 62 .

[0159] Among them, the determination module 61 is used to respond to the area determination operation based on the image display interface, and use the determined interface area as the area of ​​interest; the image display interface is used to display the infrared image captured by the image acquisition device; the highlighting module 62 is used to respond to the highlighting operation on the area of ​​interest, and enhance the contrast of the local infrared image corresponding to the area of ​​interest.

[0160] As a feasible implementation method, the determination module 61 is specifically configured to use the central area of ​​the image display interface as the region of interest.

[0161] As a feasible implementation method, the central area of ​​the interface is an area of ​​a preset size in the center of the interface, or is a central area of ​​the interface where the grayscale difference is within a preset threshold range.

[0162] As a feasible implementation method, in the process of enhancing the contrast of the local infrared image, the enhancement degree of the local infrared image is gradually reduced from the center of the local infrared image to the periphery.

[0163] As a feasible implementation method, the highlighting module 62 is specifically used to count the number of times each gray value appears in the local infrared image to obtain the statistical results corresponding to the local infrared image; correct the statistical results according to the weights corresponding to the region of interest to obtain the corrected statistical results; wherein the weights corresponding to the region of interest gradually decrease from the center of the region of interest to the periphery; and perform histogram equalization processing on the local infrared image based on the corrected statistical results to obtain the target local infrared image.

[0164] As a feasible implementation method, the highlighting module 62 is specifically used to determine the image processing parameters corresponding to the region of interest; the image processing parameters include noise reduction parameters and / or sharpening parameters; based on the image processing parameters corresponding to the region of interest, the parameters of the local infrared image are adjusted to enhance the contrast of the local infrared image to obtain the target local infrared image.

[0165] As a feasible implementation method, the device 60 for highlighting the region of interest also includes a fusion module for fusing the target local infrared image with the infrared image to obtain a fused image; and a display module for displaying the fused image in an image display interface.

[0166] As a feasible implementation method, the highlighting module 62 is specifically used to count the number of times each grayscale value appears in the infrared image displayed in the image display interface to obtain the statistical results corresponding to the infrared image; correct the statistical results according to the weights corresponding to the regions of interest to obtain the corrected statistical results; wherein the weights corresponding to the regions of interest are greater than 1, and the weights corresponding to the regions of interest gradually decrease from the center of the regions of interest to the periphery of the regions of interest; and perform histogram equalization processing on the infrared image displayed in the image display interface based on the corrected statistical results.

[0167] As a feasible implementation method, the highlighting module 62 is specifically used to determine the target dynamic range of the local infrared image; based on the corresponding relationship between the preset dynamic range and the response rate, determine the target response rate corresponding to the target dynamic range; adjust the response rate of the image acquisition device to the target response rate; re-acquire the infrared image through the adjusted image acquisition device, and enhance the contrast of the local infrared image corresponding to the area of ​​interest in the newly acquired infrared image.

[0168] As a feasible implementation method, the determination module 61 is also used to determine the image processing parameters corresponding to the target response rate based on the corresponding relationship between the preset response rate and the image processing parameters; the image processing parameters include sharpening parameters and / or noise reduction parameters; the device 60 for highlighting the region of interest also includes an adjustment module for adjusting the parameters of the newly acquired infrared image based on the image processing parameters corresponding to the target response rate.

[0169] An embodiment of the present application also provides an infrared image acquisition device, including: one or more processors; one or more memories; wherein the one or more memories are used to store computer program codes, and the computer program codes include computer instructions. When the one or more processors execute the computer instructions, the infrared image acquisition device executes the method for highlighting the area of ​​interest provided in the above embodiment.

[0170] In some embodiments, the infrared image acquisition device may be an infrared thermal imaging telescope, an infrared thermal imager, an infrared camera, etc., and this embodiment of the present application does not impose any limitation on this.

[0171] The present application also provides an electronic device. Fig.11 The electronic device 201 includes: one or more memories 121, one or more processors 122, a communication bus 123 and a communication interface 124. The processor 122 is connected to the memory 121 via the bus 123; the one or more memories 121 are used to store computer program codes, and the computer program codes include computer instructions; when the one or more processors 122 execute the computer instructions, the electronic device 201 executes the method for highlighting the region of interest provided in the above embodiment.

[0172] Optionally, the memory 121 may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a tape, a floppy disk, and an optical data storage device, etc. The embodiments of the present application do not impose any restrictions on this.

[0173] The processor 122 can be a central processing unit (CPU), a general-purpose processor network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD) or any combination thereof, and the embodiments of the present application do not impose any restrictions on this.

[0174] The communication bus 123 may be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus. The communication bus 123 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.11 Just one thick line is used, but it does not mean that there is only one bus or one type of communication bus.

[0175] The communication interface 124 uses any transceiver or other device for communicating with other devices or communication networks, such as control systems, radio access networks (RAN), wireless local area networks (WLAN), etc.

[0176] The embodiments of the present application also provide a computer program product including one or more instructions, where the one or more instructions are stored in a memory of a computer device and executed by a processor to complete the various processes of the above embodiments.

[0177] An embodiment of the present application further provides a computer-readable storage medium, which includes computer-executable instructions. When the computer-executable instructions are executed on a computer, the computer executes the method for highlighting a region of interest provided in the above embodiment.

[0178] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0179] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, 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.

[0180] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0181] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0182] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device or processor to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0183] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto, and any changes or substitutions 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 method for highlighting a region of interest, characterized in that: include: In response to the region determination operation based on the image display interface, the determined interface region is used as a region of interest; The image display interface is used to display the infrared image collected by the image acquisition device; In response to the highlighting operation on the region of interest, the contrast of the local infrared image corresponding to the region of interest is enhanced.

2. The method according to claim 1, characterized in that In response to the region determination operation based on the image display interface, taking the region determined in the region determination operation as the region of interest includes: The central area of ​​the image display interface is used as the region of interest.

3. The method according to claim 1, characterized in that The central area of ​​the interface is an area of ​​a preset size in the center of the interface, or is a central area of ​​the interface where the grayscale difference is within a preset threshold range.

4. The method according to any one of claims 1 to 3, characterized in that: In the process of enhancing the contrast of the local infrared image, the enhancement degree of the local infrared image gradually decreases from the center to the periphery of the local infrared image.

5. The method according to claim 1, characterized in that The step of enhancing the contrast of the local infrared image corresponding to the region of interest includes: Counting the number of occurrences of each gray value in the local infrared image to obtain a statistical result corresponding to the local infrared image; The statistical result is corrected according to the weight corresponding to the region of interest to obtain a corrected statistical result; wherein the weight corresponding to the region of interest gradually decreases from the center of the region of interest to the periphery; Based on the corrected statistical result, a histogram equalization process is performed on the local infrared image to obtain a target local infrared image.

6. The method according to claim 1, characterized in that The step of enhancing the contrast of the local infrared image corresponding to the region of interest includes: Determining image processing parameters corresponding to the region of interest; the image processing parameters include noise reduction parameters and / or sharpening parameters; The local infrared image is adjusted based on the image processing parameters corresponding to the region of interest to enhance the contrast of the local infrared image and obtain a target local infrared image.

7. The method according to claim 5 or 6, characterized in that: The method further comprises: fusing the local infrared image of the target with the infrared image to obtain a fused image; The fused image is displayed in the image display interface.

8. The method according to any one of claims 1 to 3, characterized in that: The step of enhancing the contrast of the local infrared image corresponding to the region of interest includes: Counting the number of occurrences of each grayscale value in the infrared image displayed in the image display interface to obtain a statistical result corresponding to the infrared image; The statistical result is corrected according to the weight corresponding to the region of interest to obtain a corrected statistical result; wherein the weight corresponding to the region of interest is greater than 1, and the weight corresponding to the region of interest gradually decreases from the center of the region of interest to the periphery of the region of interest; Based on the corrected statistical result, histogram equalization processing is performed on the infrared image displayed in the image display interface.

9. The method according to any one of claims 1 to 3, characterized in that: The step of enhancing the contrast of the local infrared image corresponding to the region of interest includes: determining a target dynamic range of the local infrared image; Based on a preset correspondence between a dynamic range and a response rate, determining a target response rate corresponding to the target dynamic range; adjusting the response rate of the image acquisition device to the target response rate; The infrared image is reacquired through the adjusted image acquisition device, and the contrast of the local infrared image corresponding to the region of interest in the newly acquired infrared image is enhanced.

10. The method according to claim 9, characterized in that The method further comprises: Determining the image processing parameters corresponding to the target response rate according to the preset correspondence between the response rate and the image processing parameters; the image processing parameters include sharpening parameters and / or noise reduction parameters; The newly acquired infrared image is subjected to parameter adjustment based on the image processing parameters corresponding to the target response rate.

11. A device for highlighting a region of interest, characterized in that: include: A determination module, configured to respond to an area determination operation based on the image display interface and use the determined interface area as an area of ​​interest; The image display interface is used to display the infrared image collected by the image acquisition device; The highlighting module is used to enhance the contrast of the local infrared image corresponding to the region of interest in response to the highlighting operation on the region of interest.

12. An infrared image acquisition device, characterized in that: include: one or more processors; one or more memories; Wherein, the one or more memories are used to store computer program codes, and the computer program codes include computer instructions. When the one or more processors execute the computer instructions, the infrared image acquisition device executes the method for highlighting the area of ​​interest as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed on a computer, the computer is enabled to execute the method for highlighting a region of interest according to any one of claims 1 to 10.

Images