Target enhanced image display method, device, equipment and storage medium

Abstract

The application provides an image display method, device and equipment for target enhancement, and a storage medium. The method comprises the following steps: segmenting an original image to form a target image template containing only target information; performing enhancement processing on the target image template to obtain a target enhanced image; and fusing the target enhanced image corresponding to a target of interest with the original image according to a current fusion mode type to obtain a display image of the target of interest. Therefore, in the display image obtained by the image display method for target enhancement, the details and contours of the target of interest are clearer, or the target of interest is enlarged, so that the target is easier to observe, and the information of the background area in the display image remains the information of the background area in the original image, so that the display of the overall picture is not affected while the target is observed.

Description

Technical Field

[0001] This application relates to the field of image display technology, and in particular to a target-enhanced image display method, apparatus, device, and storage medium. Background Technology

[0002] With the continuous development of infrared technology, people are constantly increasing their demands for the display quality of infrared images. However, some targets that observers need to observe are often obscured by complex environmental backgrounds with low contrast and low signal-to-noise ratios. Therefore, how to make targets stand out more clearly in the image has become a hot topic.

[0003] Currently, many outdoor observation products highlight targets using picture-in-picture or zoom methods. However, both of these methods significantly impact the field of view, making it difficult to observe the target while simultaneously taking in the overall scene. Summary of the Invention

[0004] To address the existing technical problems, this application provides a method, apparatus, device, and storage medium for target-enhanced image display.

[0005] A method for displaying an image with enhanced target features, comprising:

[0006] Obtain the original image;

[0007] The original image is segmented to extract the target from the original image and form a target image template;

[0008] The target image template is enhanced to obtain the target enhanced image;

[0009] Based on the current fusion mode type, the enhanced image of the target of interest is fused with the original image to obtain an enhanced display image of the target of interest.

[0010] A target-enhanced image display device, comprising:

[0011] The image acquisition module is used to acquire the original image;

[0012] The image segmentation module is used to segment the original image and extract the target in the original image to form a target image template;

[0013] The target enhancement module is used to enhance the target image template to obtain a target enhanced image;

[0014] The fusion display module is used to fuse the enhanced image of the target of interest with the original image according to the current fusion mode type, so as to obtain an enhanced display image of the target of interest.

[0015] A target-enhanced image display device, including a memory and a processor;

[0016] When the processor executes the computer program instructions stored in the memory, it performs the steps of the image display method.

[0017] A computer-readable storage medium storing computer program instructions;

[0018] When the computer program instructions are executed by the processor, the steps of the image display method are implemented.

[0019] As can be seen from the above, the target enhancement image display method, apparatus, device, and storage medium provided in this application segment the original image to form a target image template containing only target information, then enhance the target image template to obtain a target enhancement image, and finally, according to the current fusion mode type, fuse the target enhancement image corresponding to the target of interest with the original image to obtain a display image enhanced by the target of interest. Therefore, in the display image obtained by the target enhancement image display method, the details and outlines of the target of interest are clearer, or the target of interest is magnified, making the target easier to observe, while the background information in the display image remains the same as the background information in the original image, so that the overall display of the screen is not affected while observing the target. Attached Figure Description

[0020] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0021] Figure 1 This is a flowchart illustrating the target enhancement image display method according to Embodiment 1 of this application;

[0022] Figure 2 This is a flowchart illustrating the target enhancement image display method according to Embodiment 2 of this application;

[0023] Figure 3 This is a flowchart illustrating the target enhancement image display method according to Embodiment 3 of this application;

[0024] Figure 4 This is a flowchart illustrating the target enhancement image display method according to Embodiment 4 of this application;

[0025] Figure 5 This is a schematic diagram illustrating the process of displaying a target-enhanced image according to some embodiments of this application;

[0026] Figure 6 The original image before target augmentation;

[0027] Figure 7 The image is a target-enhanced display image based on the target enhancement image display method provided in some embodiments of this application;

[0028] Figure 8 This application provides a target-enhanced image display device according to some embodiments;

[0029] Figure 9 This is a currently enhanced image display device provided according to some embodiments of this application. Detailed Implementation

[0030] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to limit the ways in which this application may be implemented. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0032] In the following description, the expression “some embodiments” is used, which describes a subset of possible embodiments. However, it should be understood that “some embodiments” can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0033] To address the problem that existing infrared image displays cannot simultaneously observe the target and maintain the overall image for an extended period of time, this application provides a target-enhanced image display method, apparatus, device, and storage medium. Figures 1 to 5 The images shown are schematic diagrams in different embodiments of the target enhancement image display method and process provided in this application. The target enhancement image display method provided in this application can be used in, for example... Figure 8 The target-enhanced image display device and Figure 9 This is implemented in the image display device that enhances the target shown. The following is in conjunction with... Figures 1 to 7 The present application provides a relatively detailed description of the target-enhanced image display method, apparatus, device, and storage medium.

[0034] Please see Figure 1 This is a flowchart illustrating the target enhancement image display method according to Embodiment 1 of this application. In Embodiment 1, the target enhancement image display method provided by this application includes S2, S4, S6 and S8.

[0035] S2: Obtain the original image.

[0036] S2 can be derived from Figure 8 The image acquisition module 101 in the target-enhanced image display device shown is implemented, or is implemented by... Figure 9 The memory 202 in the target-enhanced image display device shows the corresponding image acquisition program, which is then used by... Figure 9 The processor 201 in the target-enhanced image display device is implemented when executing the image acquisition program stored in the memory 202.

[0037] In Embodiment 1, the original image is an infrared image captured by an infrared camera. In some other embodiments, the original image may also be a visible light image captured by a visible light camera.

[0038] S4: Segment the original image to extract the target from the original image and form a target image template.

[0039] S4 can be derived from Figure 8 The image segmentation module 102 in the target-enhanced image display device shown is implemented, or by... Figure 9 The memory 202 in the target-enhanced image display device shows the corresponding image segmentation program, which is then used by... Figure 9 The processor 201 in the target-enhanced image display device is implemented when executing the image segmentation program stored in the memory 202.

[0040] In Embodiment 1, the size of the target image template is the same as the size of the original image. The original image is segmented to determine the target region and the background region. Then, the pixel values ​​of the target region are kept unchanged, while the pixel values ​​of the background region are all set to 0, to obtain a target image template that masks the background region and only displays the target region. In other embodiments, the original image can also be segmented first to determine the target region and the background region. Then, the pixel values ​​of the target region are mapped to the corresponding positions in a preset image with the same size as the original image and all pixel values ​​of 0, to obtain the target image template.

[0041] Specifically, in Embodiment 1, the PSPNet (Pyramid Scene Parsing Network) algorithm is used to segment the original image to extract the highlighted target regions, forming the target image template. The PSPNet algorithm can fuse appropriate global features, combining local and global information to segment the complete target, thus obtaining a complete target image template. In other embodiments, an image thresholding method can be used to determine the segmentation points between the target and background regions in the original image. Then, pixel values ​​smaller than the segmentation points are set to 0, while pixel values ​​larger than the segmentation points remain unchanged, thus obtaining the target image template. Furthermore, in other embodiments, a deep learning-based image segmentation model can be used to segment the original image to obtain the target image template. The image segmentation model is a model trained using original image samples and corresponding labeled target image template samples as a training set; the image segmentation model can be the Unet image segmentation model.

[0042] S6: Enhance the target image template to obtain the target enhanced image.

[0043] S6 can be generated by Figure 8 The target enhancement module 103 in the target enhancement image display device shown is used to implement it, or it is implemented by... Figure 9 The memory 202 in the target enhancement image display device shown stores the corresponding target enhancement program, and then... Figure 9 The processor 201 in the target enhancement image display device shown implements this when executing the target enhancement program stored in the memory 202.

[0044] Enhancing the target image template includes contrast enhancement and / or magnification. Since the pixels in the background area of ​​the target image have been set to 0, during the enhancement process of the target image template, only the target area is subjected to corresponding contrast enhancement and / or magnification, while the pixel values ​​of the background area remain 0.

[0045] S8: Based on the current fusion mode type, fuse the enhanced image of the target of interest with the original image to obtain the enhanced display image of the target of interest.

[0046] S2 can be derived from Figure 8 The target enhancement image display device shown implements the fusion display module 104, or is implemented by... Figure 9 The memory 202 in the target-enhanced image display device shows the corresponding fusion display program, which is then stored by... Figure 9The processor 201 in the target-enhanced image display device is implemented when executing the fusion display program stored in the memory 202.

[0047] The fusion mode types can be divided into selected fusion mode and all-target fusion mode. Selected fusion mode refers to fusing the enhanced image of the target currently selected by the user with the original image, enhancing the user-selected target before displaying it. Selected target fusion mode can be further divided into single-target selected fusion mode and multi-target selected fusion mode. In single-target selected fusion mode, only one target is selected at a time; when the target is selected, the enhanced image of that target is fused with the original image, enhancing the user-selected target before displaying it. In multi-target selected fusion mode, multiple targets are selected at a time; when multiple targets of interest are selected, the enhanced images of these multiple targets are fused with the original image, enhancing the multiple targets of interest selected by the user before displaying them.

[0048] As can be seen from the above, in the target enhancement image display method provided in this application, the original image is segmented to form a target image template containing only target information. Then, the target image template is enhanced to obtain a target-enhanced image. Finally, according to the current fusion mode type, the target-enhanced image corresponding to the target of interest is fused with the original image to obtain a display image enhanced with the target of interest. Therefore, in the display image obtained through the target enhancement image display method, the details and contours of the target of interest are clearer, or the target of interest is magnified, making the target easier to observe. Meanwhile, the background information in the display image remains the same as the background information in the original image, so the overall display of the image is not affected while observing the target.

[0049] Please see Figure 2 This is a flowchart illustrating the target enhancement image display method according to Embodiment 2 of this application. In Embodiment 2, the target enhancement image display method provided by this application includes S2, S41a, S42a, S6, and S8. That is, the difference between Embodiment 2 and Embodiment 1 is that S4 further includes S41a and S42a. S2, S6, and S8 are the same as in Embodiment 1, and therefore will not be described again.

[0050] In Example 2, S4: Segmenting the original image to extract targets from the original image and form a target image template, including:

[0051] S41a: Determine the target of interest in the original image based on the current fusion mode type.

[0052] The fusion mode type can be divided into selected fusion mode and all fusion mode. Different fusion mode types can determine the target of interest (ROI) in the original image in different ways. When the fusion mode type is selected fusion mode, the ROI in the original image can be determined based on the current position of the partition in the original image. When the fusion mode type is selected fusion mode, all targets in the original image are directly used as the ROI, without the need for partitioning to select the ROI.

[0053] When a user has a target of interest, the reticle (such as a crosshair) can be moved to the location of the target of interest in the original image to select it. Then, when segmenting the original image, the position of the corresponding target of interest can be determined based on the current position of the reticle within the original image. Of course, in other embodiments, other methods can be used to select the position of the target of interest; for example, the position can be determined based on the location selected by the user with the mouse. The target of interest can be one or more.

[0054] S42a: Segment the original image to extract the target of interest from the original image and form a target image template.

[0055] After determining the target of interest and its corresponding position, the pixel value of the target of interest at its corresponding position in the original image can be kept unchanged, while the pixel values ​​of other areas can be set to 0, thereby achieving the segmentation of the original image to obtain an image template containing only the target of interest, i.e., the target image template.

[0056] In Example 2, image segmentation is performed after the target of interest is selected. That is, each time a target of interest is selected, the original image needs to be segmented once. The segmented target image template contains only the target of interest. Subsequently, the target image template is enhanced, and the enhanced target image is fused with the original image according to the position of the target of interest.

[0057] Please see Figure 3 This is a flowchart illustrating the target enhancement image display method according to Embodiment 3 of this application. In Embodiment 3, the target enhancement image display method provided by this application includes S2, S41b, S6, and S81a, S81a. That is, the difference between Embodiment 3 and Embodiment 1 is that S4 includes S41b and S8 includes S81a, S82a. S2 and S6 are the same as in Embodiment 1, and therefore will not be described again.

[0058] In Embodiment 3, S4: Segmenting the original image to extract targets from the original image and form a target image template, including:

[0059] S41b: Segment the original image to extract each target in the original image and form a target image template corresponding to each target.

[0060] Furthermore, in Embodiment 3, S8: Based on the current fusion mode type, the enhanced image of the target of interest is fused with the original image to obtain an enhanced display image of the target of interest, including:

[0061] S81a: Determine the target of interest corresponding to the current position based on the current fusion mode type.

[0062] S82a: The enhanced image of the target of interest is fused with the original image to obtain an enhanced display image of the target of interest.

[0063] The difference between Embodiment 3 and Embodiment 2 is that in Embodiment 2, the original image is segmented based on the location of the target of interest after the target of interest is selected, resulting in a target image template that only displays the target of interest. In Embodiment 3, however, all targets in the original image are segmented before the target of interest is selected, resulting in target image templates that display each target. These target image templates are then enhanced to obtain corresponding enhanced images. The location of the target of interest is then determined from the enhanced target image based on the current position of the segment in the original image. Based on the location of the target of interest, the enhanced target image is fused with the original image. In this method, the user determines the target of interest after the original image has been segmented and enhanced sequentially. That is, after each determination of the target of interest, the user does not need to perform segmentation and enhancement again; they only need to fuse the enhanced target image with the original image according to the location of the target of interest and the current fusion mode type. In some embodiments, the target image template corresponding to each target can be a single target image template that includes all targets in the original image. In other embodiments, the target image template corresponding to each target may also be a target image template corresponding to each target in the original image, and each target image template in each target image includes a corresponding target in the original image.

[0064] Please see Figure 4This is a flowchart illustrating the target enhancement image display method according to Embodiment 4 of this application. Embodiment 4 differs from Embodiment 1 in that, in Embodiment 4, before step S8: according to the current fusion mode type, the target enhancement image corresponding to the target of interest is fused with the original image to obtain the enhanced display image of the target of interest, the target enhancement image display method further includes steps S71, S72, S73, and S9, as detailed below:

[0065] S71: Get mode selection command.

[0066] S72: Determine whether the image display mode is a blending mode according to the mode selection instruction. If yes, execute S73; otherwise, execute S9.

[0067] S73: Determine the current fusion mode type.

[0068] S9: Use the original image as the display image.

[0069] When a user needs to enhance the display of a target of interest, they will select whether to enable the fusion mode through the human-computer interaction interface. A corresponding mode selection command will be sent to the image display device or equipment displaying the enhanced target image provided in this application. The user will then judge the mode selection command to determine whether to enter fusion mode. If fusion mode is entered, it indicates that fusion output is currently in progress, and the enhanced target display image needs to be output. Therefore, the next step after determining that fusion mode has been entered is to determine the current fusion mode type before proceeding to step S8. If it is determined that the current mode is non-fusion mode, meaning the user does not need to enhance the target display, then normal output is performed, i.e., the original image is output as the display image.

[0070] It should be noted that in Embodiment 4, the original image is first segmented and enhanced, and then S71: obtaining the mode selection instruction is executed. Therefore, in S4, the original image needs to be segmented to extract a target image template that only displays each target object in the original image. That is, in Embodiment 4, S4 includes S41b in Embodiment 3. Then S8 includes S81a and S82a in Embodiment 3. In other embodiments, S71 can also be executed before the target segmentation and enhancement of the corresponding original image. In that case, S42 further includes S41a and S42a.

[0071] In S73, the corresponding type selection instruction can be obtained based on the user's current selection. Therefore, S73 further includes S731 and S732.

[0072] S731: Get type selection instruction.

[0073] S732: Determine the current fusion mode type based on the type selection instruction.

[0074] As described above, if the fusion mode type includes a selected fusion mode and all fusion modes, the selected fusion mode further includes a single-target selected fusion mode and a multi-target selected fusion mode. Each of the fusion modes can be selected from the corresponding type menu in the human-computer interaction interface. The user selects the desired fusion mode type according to the type menu, and the target-enhanced image display device or equipment obtains the corresponding type selection instruction based on the user's selection.

[0075] Specifically, in some embodiments, when the current fusion mode type is a selected fusion mode type, S8: fusing the target enhancement image corresponding to the target of interest with the original image according to the current fusion mode type to obtain a display image enhanced by the target of interest includes: determining the position of the target of interest based on the current position of the segment in the original image, and then fusing the target enhancement image corresponding to the target of interest with the original image according to the position of the target of interest to obtain a display image enhanced by the target of interest. In the selected target fusion mode, the target of interest needs to be selected before fusion to determine the position of the target of interest, and the fusion is performed at the position of the target of interest to obtain a display image enhanced by the target of interest.

[0076] When the selected fusion mode is single-target fusion mode, only one target is selected at a time, and the enhanced display image of the selected target is obtained after fusion; when the selected fusion mode is multi-target fusion mode, multiple targets are selected at a time, and the enhanced display image of the selected multiple targets is obtained after fusion.

[0077] In some application scenarios, the target of interest can be a stationary target or a moving target. If the target is stationary, it can be selected directly when the reticle moves to its current position and is no longer selected when the reticle moves away from the target's position. However, for a moving target of interest, or when selecting a target of interest from multiple targets, the position of the target of interest differs in different frames of the original images captured by the camera device. Therefore, in some embodiments, determining the position of the target of interest based on the current position of the reticle in the original image specifically includes:

[0078] Based on the current position of the segment in the original image, a target of interest (ROI) is determined. A target tracking algorithm is then used to track the ROI and determine its position. Therefore, even after the segment leaves the ROI, the tracking algorithm can continuously acquire the ROI's position within the frame for subsequent fusion, until the ROI leaves the frame, at which point the selection process is complete. For moving ROIs, selection can be achieved by first using segmentation and then continuously tracking the selected ROI across different frames of the original image.

[0079] In some scenarios, the target of interest (ROI) in the original image is so small that it is difficult to move the reticle to its location. Therefore, in some embodiments, before determining the location of the ROI based on the current position of the reticle in the original image, the image display method further includes: setting a corresponding magnifiable region in the original image for small targets with a size less than or equal to a preset size. Then, determining the location of the ROI based on the current position of the reticle in the original image includes: determining the location of the magnifiable region selected by the reticle based on the current position of the reticle in the original image, and determining the location of the small target within the magnifiable region as the location of the ROI based on the location of the magnifiable region.

[0080] The small-sized target, whose size is less than or equal to a preset size, is located in the magnifiable region. When the reticle moves to the magnifiable region corresponding to the small-sized target, the position of the small-sized target in the magnifiable region is determined as the position of the target of interest. That is, the position of the magnifiable region is used to determine the position of the corresponding smaller target of interest. In subsequent fusion, a display image is obtained that enhances the position corresponding to the small-sized target in the magnifiable region, thereby achieving enhanced display of the small-sized target. The area of ​​the magnifiable region is set as small as possible to avoid affecting the overall display of the image after enhancing its display. Therefore, in some embodiments, the magnifiable region is the smallest magnifiable region, which only needs to be selected by the reticle.

[0081] In some embodiments, when the current fusion mode type is determined to be the all-fusion mode type according to the type selection instruction, S8: according to the current fusion mode type, the target enhancement image corresponding to the target of interest is fused with the original image to obtain a display image enhanced by the target of interest, including: determining the position of the target of interest based on the positions of all targets in the original image; and fusion the target enhancement image corresponding to the target of interest with the original image based on the position of the target of interest to obtain a display image enhanced by the target of interest. That is, in this case, if the target of interest is all targets in the original image, then before fusion, it is not necessary to select the corresponding target of interest by segmentation. During the fusion process, all enhancement regions in the target enhancement image replace the corresponding regions in the original image to obtain a display image enhanced by all targets.

[0082] Continue reading Figure 4 In Embodiment 4, after S2 is executed and before S72 is executed, the target enhancement image display method further includes S31 and S32, which are executed sequentially.

[0083] S31: Denoise the original image.

[0084] After S31 is executed, S32 and S4 are executed respectively, but the order in which S32 and S4 are executed is not limited. In S4, the denoised original image is segmented to extract the target from the original image and form a target image template.

[0085] Specifically, the denoising process for the original image includes temporal denoising and spatial denoising. For temporal denoising, an FIR (Finite Impulse Response) filter can be selected, which offers higher stability and lower computational error. For spatial denoising, a bilateral filtering algorithm is used, which preserves edges while removing noise, retaining as much detail as possible.

[0086] S32: Perform contrast enhancement processing on the original image after denoising.

[0087] S32 is performed before S72. That is, after completing S32, it is necessary to determine whether it is necessary to enter the fusion mode. If so, the fusion mode type is determined. Finally, in S8, the target enhanced image is fused with the original image after denoising and contrast enhancement to obtain the display image. If not, S9 is executed: the original image after denoising and contrast enhancement is used as the display image.

[0088] Specifically, a dual-platform histogram algorithm can be used to enhance the contrast of the denoised original image. This algorithm is simple, efficient, and highly adaptable to various scenarios.

[0089] In some embodiments, S8, fusing the enhanced image of the target of interest with the original image to obtain an enhanced display image of the target of interest, includes: reassigning the pixel values ​​at the corresponding positions in the original image based on the pixel values ​​at the location of the target of interest in the enhanced image, thereby obtaining the enhanced display image of the target of interest. Therefore, based on the fused display image, only the location of the target of interest is enhanced as required by the user, while other areas retain the pixel values ​​of the corresponding areas in the original image during normal display, thus not affecting the display of the entire screen.

[0090] In some embodiments, the pixel at the corresponding position in the original image is reassigned according to the pixel value at the position of the target of interest in the enhanced image to obtain the display image. This further includes: assigning the pixel value at the position of the target of interest in the enhanced image to the pixel at the corresponding position in the original image to obtain the display image.

[0091] In some embodiments, in order to make the target of interest more prominent in the displayed image, pseudo-color mapping is also performed on the fused image in S8. That is, in this embodiment, S8 includes: fusing the target enhancement image corresponding to the target of interest with the original image according to the current fusion mode type to obtain a fused image, and then performing pseudo-color mapping on the fused image according to the selected pseudo-color mapping type to obtain the enhanced display image of the target of interest.

[0092] Specifically, the fusion mode type further includes a pseudo-color fusion mode. When the user selects the pseudo-color fusion mode type according to the menu, in S8, the fused image is pseudo-color mapped according to different preset pseudo-colors, making the target easier to observe in the picture.

[0093] Please see Figure 5 This is a schematic diagram of the display process implemented by the target enhancement image display method provided in some embodiments of this application, wherein the original image is an infrared image as an example.

[0094] The target enhancement image display method includes S01 to S08.

[0095] S01: Acquire an infrared image. The infrared image is input into the target-enhanced image display device provided in this application, and the image display device acquires the infrared image.

[0096] S02: Denoising Processing. The input infrared image is denoised to remove noise while preserving as much detail as possible. S03 and S05 are executed after denoising the input infrared image.

[0097] S03: Target Image Segmentation. The denoised infrared image is segmented to obtain a target image template that displays only the individual targets in the infrared image. The next step after S03 is S04.

[0098] S04: Target Enhancement Processing. Enhancement processing is performed on the target image template to obtain an enhanced target image. The next step after S04 is S06.

[0099] S05: Contrast Enhancement Processing. The infrared image after denoising is subjected to contrast enhancement processing to obtain the infrared image after both denoising and contrast enhancement processing.

[0100] S06: Determine whether the target of interest should be enhanced in display. If yes, proceed to S07; otherwise, proceed to S08.

[0101] S07: Fusion Output. When entering fusion mode, depending on the current fusion mode type, the enhanced image of the target of interest is fused with the infrared image after denoising and contrast enhancement. The fused image is then displayed as the fusion output image.

[0102] S08: Normal Output. When there is no need to enter the fusion mode, i.e., when there is no need to enhance the display of the target of interest, the infrared image after noise reduction and contrast enhancement will be used as the normal output display image.

[0103] To facilitate a more intuitive understanding of the target enhancement effect achieved by the target-enhanced image display method provided in this application, Figure 6 Provide the original image before target augmentation. Figure 7 The image after target enhancement according to the target enhancement image display method provided in this application is given. Figure 6 and Figure 7 The black circles in the diagram represent the corresponding targets of interest. (Through...) Figure 6 and Figure 7 The comparison shows that the target enhancement image display method provided in this application only enhances or magnifies the target of interest without affecting the normal observation of other images. It maintains global image contrast, improves the detail and contrast of the target area, and does not cause excessive stretching of the overall image, thus affecting the viewing experience. Furthermore, in some embodiments, it can also... Figure 7 The enhanced target of interest is subjected to pseudo-color mapping to color the enhanced target of interest, which can further enhance the target of interest.

[0104] Please refer to Figure 8 In some embodiments, this application also provides a target-enhanced image display device. The target-enhanced image display device includes an image acquisition module 101, an image segmentation module 102, a target enhancement module 103, and a fusion display module 104. The image acquisition module 101 is used to acquire an original image; the image segmentation module 102 is used to segment the original image to extract targets from the original image and form target image templates; the target enhancement module 103 is used to enhance the target image templates to obtain a target-enhanced image; and the fusion display module 104 is used to fuse the target-enhanced image corresponding to the target of interest with the original image according to the current fusion mode type to obtain a display image enhanced by the target of interest.

[0105] Please refer to Figure 9 In some embodiments, this application also provides a target-enhanced image display device, which includes a memory 202 and a processor 201. When the processor 201 executes computer program instructions stored in the memory 202, it performs the steps of the target-enhanced image display method according to any embodiment of this application.

[0106] Furthermore, this application also provides a computer-readable storage medium storing computer program instructions; when executed by a processor, the computer program instructions implement the steps of the target enhancement image display method provided according to any embodiment of this application.

[0107] The aforementioned processor may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The moving target detection device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0108] The aforementioned memory may include high-speed RAM (Random Access Memory) and may also include NVM (Non-Volatile Memory), such as at least one disk storage device.

[0109] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for displaying an image with enhanced target features, characterized in that, include: Acquire and display the original image; the original image is an infrared image; The original image is segmented to extract the target from the original image and form a target image template; The target image template is enhanced to obtain an enhanced target image; the enhancement of the target image template includes contrast enhancement processing and magnification processing of the target image template; When the current fusion mode is selected, the target of interest at the current position is selected according to the current position of the partition in the original image; or, in the original image, a corresponding magnifiable region is set for small targets with a size less than or equal to a preset size, the position of the magnifiable region selected by the partition is determined according to the current position of the partition in the original image, and the small target in the magnifiable region is selected as the target of interest according to the position of the magnifiable region. Based on the location of the target of interest, the enhanced image of the target of interest is fused with the original image to obtain a fused image; The magnified target of interest in the fused image is subjected to pseudo-color mapping according to the selected pseudo-color mapping type to obtain an enhanced display image of the target of interest; If the target is a static target, when the segment moves away from the current position, the target of interest is no longer selected, and the target of interest will no longer be enhanced in display.

2. The image display method according to claim 1, characterized in that, The step of segmenting the original image to extract targets from the original image and form target image templates includes: Based on the current fusion mode type, determine the target of interest in the original image; The original image is segmented to extract the target of interest from the original image, forming a target image template.

3. The image display method according to claim 1, characterized in that, The step of segmenting the original image to extract targets from the original image and form target image templates includes: The original image is segmented to extract each target in the original image, forming a target image template corresponding to each target. Based on the current fusion mode type, the enhanced image of the target of interest is fused with the original image to obtain an enhanced display image of the target of interest, including: Based on the current fusion mode type, determine the target of interest in the original image; The enhanced image of the target of interest is fused with the original image to obtain an enhanced display image of the target of interest.

4. The image display method according to claim 1, characterized in that, Before fusing the enhanced image of the target of interest with the original image according to the current fusion mode type to obtain the enhanced display image of the target of interest, the process includes: Get the mode selection command; The image display mode is determined to be a blending mode based on the mode selection instruction. If so, determine the current fusion mode type; If not, the original image will be used as the display image.

5. The image display method according to claim 1, characterized in that, The method further includes: If the target is a dynamic target, a target tracking algorithm is used to track the target of interest and continuously obtain the position of the target of interest.

6. The image display method according to claim 1, characterized in that, When the current fusion mode type is full fusion mode, Based on the locations of all targets in the original image, determine the location of the target of interest; Based on the location of the target of interest, the enhanced image corresponding to the target of interest is fused with the original image to obtain an enhanced display image of the target of interest.

7. The image display method according to claim 4, characterized in that, Before determining whether the image display mode is a fusion mode according to the mode selection instruction, the image display method further includes: performing noise reduction processing and contrast enhancement processing on the original image respectively; The step of using the original image as the display image includes: The original image after denoising and contrast enhancement is used as the display image; The step of fusing the enhanced image of the target of interest with the original image according to the current fusion mode type to obtain an enhanced display image of the target of interest includes: Based on the current fusion mode type, the enhanced image of the target of interest is fused with the original image after denoising and contrast enhancement to obtain the enhanced display image of the target of interest.

8. The image display method according to claim 1, characterized in that, The enhanced image corresponding to the target of interest is fused with the original image to obtain an enhanced display image of the target of interest, including: Based on the pixel value at the location of the target of interest in the enhanced image, the corresponding pixel in the original image is re-assigned to obtain the enhanced display image of the target of interest.

9. A target enhancement image display device, characterized in that, include: The image acquisition module is used to acquire and display the original image; the original image is an infrared image. The image segmentation module is used to segment the original image and extract the target in the original image to form a target image template; The target enhancement module is used to enhance the target image template to obtain a target enhanced image; the enhancement of the target image template includes contrast enhancement processing and magnification processing of the target image template; The fusion display module is used to select the target of interest at the current position of the segment in the original image when the current fusion mode type is selected fusion mode; or, in the original image, a corresponding magnifiable region is set for small targets with a size less than or equal to a preset size, the position of the magnifiable region selected by the segment is determined according to the current position of the segment in the original image, and the small target in the magnifiable region is selected as the target of interest according to the position of the magnifiable region. Based on the location of the target of interest, the enhanced image of the target of interest is fused with the original image to obtain a fused image; The magnified target of interest in the fused image is subjected to pseudo-color mapping according to the selected pseudo-color mapping type to obtain an enhanced display image of the target of interest; If the target is a static target, when the segment moves away from the current position, the target of interest is no longer selected, and the target of interest will no longer be enhanced in display.

10. A target-enhanced image display device, characterized in that, Including memory and processor; When the processor executes the computer program instructions stored in the memory, it performs the steps of the image display method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions; When the computer program instructions are executed by the processor, they implement the steps of the image display method according to any one of claims 1 to 8.

Images