An airborne infrared image-based method and system for identifying high-brightness targets on water

Abstract

The present invention discloses a method and system for identifying high-brightness targets on water based on airborne infrared images, which relates to the technical field of target identification. The technical key points of the present invention include: acquiring an image containing high-brightness targets on water; calculating the perimeter logarithm feature of the image; calculating a first segmentation threshold based on the image gray value, and using the first segmentation threshold to perform a first threshold segmentation on the perimeter logarithm feature map; calculating the number of pixel points of each independent target in the image after the first threshold segmentation, and determining the independent target with the number of pixel points less than the preset number threshold as the high-brightness target area; calculating a second segmentation threshold based on the image gray value, and using the second segmentation threshold to perform a second threshold segmentation on the image retaining the high-brightness target area, and determining the area greater than the second segmentation threshold as the high-brightness target. The present invention has stronger detail recognition ability, can accurately distinguish high-brightness targets from the background, and effectively reduces the false recognition rate.

Description

Technical Field

[0001] The present invention relates to the technical field of target recognition, and particularly relates to a method and system for identifying waterborne high-brightness targets based on airborne infrared images. Background Art

[0002] With the continuous development of infrared imaging technology and image feature extraction technology, the applications of the two in the field of high-brightness target recognition are gradually integrated. By applying image feature extraction technology to airborne infrared images, more accurate and efficient recognition of high-brightness targets can be achieved. At present, scholars at home and abroad have carried out a large number of studies on the recognition of high-brightness targets in airborne infrared images. These studies mainly focus on the optimization of feature extraction algorithms, the research on multi-feature fusion methods, and the application of machine learning and deep learning algorithms. Image feature extraction technology can be applied to fields such as maritime traffic monitoring, high-brightness target safety detection, and fishery resource investigation, providing strong technical support for maritime safety and resource management. Summary of the Invention

[0003] Therefore, the present invention proposes a method and system for identifying waterborne high-brightness targets based on airborne infrared images to meet the actual demand for accurate extraction of waterborne high-brightness targets in the field of aerial infrared image high-brightness target recognition.

[0004] According to one aspect of the present invention, a method for identifying waterborne high-brightness targets based on airborne infrared images is proposed. The method includes:

[0005] Obtaining an image containing waterborne high-brightness targets;

[0006] Calculating the explicit perimeter logarithmic feature of the image; the explicit perimeter logarithmic feature is defined as the logarithm ratio of image saliency to the perimeter of a sliding window;

[0007] Calculating a first segmentation threshold based on the image gray value, and performing a first threshold segmentation on the feature map formed by the explicit perimeter logarithmic feature by using the first segmentation threshold, marking the region greater than the first segmentation threshold as an independent target, and marking the region less than or equal to the first segmentation threshold as the background;

[0008] Calculating the number of pixel points of each independent target in the image after the first threshold segmentation, deleting the independent targets with the number of pixel points greater than or equal to a preset number threshold, and determining the independent targets with the number of pixel points less than the preset number threshold as high-brightness target regions;

[0009] Calculating a second segmentation threshold based on the image gray value, and performing a second threshold segmentation on the image retaining the high-brightness target region by using the second segmentation threshold, and determining the region greater than the second segmentation threshold as the high-brightness target.

[0010] Further, the calculating the explicit perimeter logarithmic feature of the image includes:

[0011] Set the sliding window size, and calculate the segmentation threshold within the sliding window based on the mean and standard deviation of all pixel values within the sliding window; count the number of pixel points within the sliding window whose pixel values are greater than the segmentation threshold N T ; Calculate the number of perimeter pixel points of the sliding window N C ; Then the display perimeter logarithm feature corresponding to the pixel point (i,j) at the location is: F ( i , j ) = log( N T ) / log( N C ).

[0012] Furthermore, the calculation formula for the segmentation threshold within the sliding window is:

[0013] T’ = μ + k σ’

[0014] Wherein, μ is the mean of all pixel values within the sliding window, σ’ is the standard deviation of all pixel values within the sliding window, k is an adjustment constant greater than 1.

[0015] Furthermore, the calculation formula for the first segmentation threshold is:

[0016] T f = I min + m ×( I max – I mean )

[0017] Wherein, I max is the maximum gray value of the display perimeter logarithm feature map, I min is the minimum gray value of the display perimeter logarithm feature map, I mean is the mean gray value of the display perimeter logarithm feature map, m is an adjustment constant.

[0018] Furthermore, the calculation formula for the second segmentation threshold is:

[0019]

[0020] Wherein, and to retain the maximum and minimum image gray values of the highlighted target area; σ is the standard deviation of all gray values of the image of the highlighted target area; p is an adjustment constant greater than 1.

[0021] According to another aspect of the present invention, a waterborne highlighted target recognition system based on airborne infrared images is proposed. The system includes:

[0022] An image acquisition module configured to acquire an image containing a waterborne highlighted target;

[0023] A feature calculation module configured to calculate the explicit perimeter logarithmic feature of the image; the explicit perimeter logarithmic feature is defined as the ratio of the image saliency to the logarithm of the perimeter of the sliding window;

[0024] A first segmentation module configured to calculate a first segmentation threshold based on the image gray value, and perform a first threshold segmentation on the feature map formed by the explicit perimeter logarithmic feature by using the first segmentation threshold, marking the area greater than the first segmentation threshold as an independent target, and marking the area less than or equal to the first segmentation threshold as the background;

[0025] A highlighted area extraction module configured to calculate the number of pixel points of each independent target in the image after the first threshold segmentation, delete the independent targets with the number of pixel points greater than or equal to the preset number threshold, and determine the independent targets with the number of pixel points less than the preset number threshold as the highlighted target area;

[0026] A second segmentation module configured to calculate a second segmentation threshold based on the image gray value, and perform a second threshold segmentation on the image retaining the highlighted target area by using the second segmentation threshold, and determining the area greater than the second segmentation threshold as the highlighted target.

[0027] Further, calculating the explicit perimeter logarithmic feature of the image in the feature calculation module includes:

[0028] Set the size of the sliding window, and calculate the segmentation threshold within the sliding window based on the mean and standard deviation of all pixel values within the sliding window; count the number of pixel points within the sliding window whose pixel values are greater than the segmentation threshold N T ; calculate the number of perimeter pixel points of the sliding window N C ; then the explicit perimeter logarithmic feature corresponding to the pixel point (i,j) is: F ( i , j ) = log( N T ) / log( N C)。

[0029] Further, the calculation formula for the segmentation threshold within the sliding window in the feature calculation module is:

[0030] T’ = μ + k σ’

[0031] Wherein, μ is the mean value of all pixel values within the sliding window, σ’ is the standard deviation of all pixel values within the sliding window, k is an adjustment constant greater than 1.

[0032] Further, the calculation formula for the first segmentation threshold in the first segmentation module is:

[0033] T f = I min + m ×( I max – I mean )

[0034] Wherein, I max is the maximum gray value of the explicit perimeter logarithmic feature map, I min is the minimum gray value of the explicit perimeter logarithmic feature map, I mean is the mean gray value of the explicit perimeter logarithmic feature map, m is an adjustment constant.

[0035] Further, the calculation formula for the second segmentation threshold in the second segmentation module is:

[0036]

[0037] Wherein, and are the maximum and minimum gray values of the image for retaining the highlighted target area; σ is the standard deviation of all gray values of the image for retaining the highlighted target area; p is an adjustment constant greater than 1.

[0038] The beneficial technical effects of the present invention are:

[0039] The present invention provides a method and system for identifying waterborne high-brightness targets based on airborne infrared images. First, an image containing waterborne high-brightness targets is acquired; then, the perimeter logarithm feature of the image is calculated; the perimeter logarithm feature is defined as the ratio of the image saliency to the logarithm of the perimeter of the sliding window; then, a first segmentation threshold is calculated based on the image gray value, and the feature map formed by the perimeter logarithm feature is subjected to the first threshold segmentation using the first segmentation threshold, and the regions greater than the first segmentation threshold are marked as independent targets, and the regions less than or equal to the first segmentation threshold are marked as the background; then, the number of pixel points of each independent target in the image after the first threshold segmentation is calculated, and the independent targets with the number of pixel points greater than or equal to the preset number threshold are deleted, and the independent targets with the number of pixel points less than the preset number threshold are determined as the high-brightness target regions; then, a second segmentation threshold is calculated based on the image gray value, and the image retaining the high-brightness target regions is subjected to the second threshold segmentation using the second segmentation threshold, and the regions greater than the second segmentation threshold are determined as the high-brightness targets. The present invention has stronger detail recognition ability, can accurately distinguish high-brightness targets from the background by analyzing the thermal information in the infrared image, and can accurately extract the features of the high-brightness targets under complex backgrounds; the present invention can adapt to various different environmental and noise conditions, and effectively reduce the false recognition rate. The present invention realizes a high degree of automation, and can still accurately identify even in a dynamically changing or low-contrast environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown by way of example and not limitation, wherein:

[0041] Figure 1 is a flowchart of a method for identifying waterborne high-brightness targets based on airborne infrared images according to an embodiment of the present invention.

[0042] Figure 2 is an example diagram of an image containing waterborne high-brightness targets in an embodiment of the present invention.

[0043] Figure 3 is an example diagram of the perimeter logarithm feature calculated in an embodiment of the present invention.

[0044] Figure 4 is an example diagram of the feature after the first threshold segmentation in an embodiment of the present invention.

[0045] Figure 5 is an example diagram of the retained high-brightness target regions in an embodiment of the present invention.

[0046] Figure 6 is an example diagram of the image obtained by multiplying the image of the region where the high-brightness target is located by the original image in an embodiment of the present invention.

[0047] Figure 7 This is a high - light target example diagram identified in the embodiments of the present invention.

[0048] Figure 8 This is a schematic structural diagram of a water - based high - light target recognition system based on airborne infrared images according to the embodiments of the present invention. Detailed implementation manners

[0049] Next, the principles and spirit of the present invention will be described with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and then implement the present invention, rather than limiting the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to be able to fully convey the scope of the present disclosure to those skilled in the art.

[0050] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, equipment, method, or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms: completely hardware, completely software (including firmware, resident software, micro - code, etc.), or a combination of hardware and software. In this article, it should be understood that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0051] The embodiments of the present invention propose a method for recognizing water - based high - light targets based on airborne infrared images, as Figure 1 shown, the method includes:

[0052] S1. Obtain an image containing water - based high - light targets;

[0053] S2. Calculate the explicit - perimeter logarithm feature of the image; the explicit - perimeter logarithm feature is defined as the ratio of the image saliency to the logarithm of the perimeter of the sliding window;

[0054] S3. Calculate a first segmentation threshold based on the image gray - scale value, and use the first segmentation threshold to perform the first threshold segmentation on the feature map formed by the explicit - perimeter logarithm feature, marking the region greater than the first segmentation threshold as an independent target, and marking the region less than or equal to the first segmentation threshold as the background;

[0055] S4. Calculate the number of pixel points of each independent target in the image after the first threshold segmentation, delete the independent targets with the number of pixel points greater than or equal to the preset number threshold, and determine the independent targets with the number of pixel points less than the preset number threshold as the high - light target regions;

[0056] S5. Calculate the second segmentation threshold based on the image gray value, and use the second segmentation threshold to perform a second threshold segmentation on the image with the highlighted target area retained, and determine the area greater than the second segmentation threshold as the highlighted target.

[0057] In this embodiment, preferably, calculating the apparent perimeter logarithmic feature of the image in S2 includes:

[0058] Set the sliding window size, and calculate the segmentation threshold within the sliding window based on the mean and standard deviation of all pixel values within the sliding window; count the number of pixel points within the sliding window whose pixel values are greater than the segmentation threshold N T ; calculate the number of perimeter pixel points of the sliding window N C ; then the apparent perimeter logarithmic feature corresponding to the pixel point (i,j) is: F ( i , j ) = log( N T ) / log( N C ). Among them, the calculation formula for the segmentation threshold within the sliding window is:

[0059] T’ = μ + k σ’

[0060] Among them, μ is the mean of all pixel values within the sliding window, σ’ is the standard deviation of all pixel values within the sliding window, k is an adjustment constant greater than 1.

[0061] In this embodiment, preferably, the calculation formula for the first segmentation threshold in S3 is:

[0062] T f = I min + m ×( I max – I mean )

[0063] Among them, I max is the maximum gray value of the apparent perimeter logarithmic feature map, I min is the minimum gray value of the apparent perimeter logarithmic feature map, I mean is the mean gray value of the apparent perimeter logarithmic feature map, m is an adjustment constant.

[0064] In this embodiment, preferably, the calculation formula of the second segmentation threshold in S5 is as follows:

[0065]

[0066] Wherein, and are the maximum and minimum image gray values for retaining the highlighted target area; σ is the standard deviation of all gray values of the image for retaining the highlighted target area; p is an adjustment constant greater than 1.

[0067] The embodiments of the present invention will be described in detail below.

[0068] First, in S1, an image containing a water highlight target is acquired.

[0069] According to the embodiments of the present invention, a drone can be used to carry an infrared camera to fly close to the sea surface to shoot a video containing a highlight target, the water surface, and the sky; video frames are extracted to obtain an image containing a water highlight target. An example is as Figure 2 shown.

[0070] Then, in S2, the explicit perimeter logarithm feature of the image is calculated; the explicit perimeter logarithm feature is defined as the ratio of the image saliency to the logarithm of the perimeter of the sliding window.

[0071] According to the embodiments of the present invention, the detailed calculation process of the explicit perimeter logarithm feature is as follows:

[0072] 1) Set the size of the sliding window to 15×15;

[0073] 2) Calculate the segmentation threshold within the sliding window as:

[0074] T’ = μ + k σ’

[0075] Where μ is the mean value of all pixel values within the sliding window, σ’ is the standard deviation of all pixel values within the sliding window, k is an adjustment constant greater than 1. In this embodiment, k takes 2.3.

[0076] 3) Count the number of pixel points within the sliding window whose pixel values are greater than of T’ the number of pixel points N T .

[0077] 4) Calculate the number of pixel points of the perimeter of the sliding window N C :

[0078] N C = 4*(L - 1)

[0079] Where L is the number of pixel points of the side length of the sliding window.

[0080] 5) Calculate the image (i,j) The sliding window image feature at F ( i , j ) is:

[0081] F ( i , j ) = log( N T ) / log( N C )

[0082] The finally formed explicit perimeter logarithmic feature diagram is shown as an example Figure 3 as follows.

[0083] Then, in S3, calculate the first segmentation threshold based on the image gray value, and use the first segmentation threshold to perform the first threshold segmentation on the feature map formed by the explicit perimeter logarithmic feature, mark the area greater than the first segmentation threshold as an independent target, and mark the area less than or equal to the first segmentation threshold as the background.

[0084] According to the embodiment of the present invention, for the threshold segmentation of the explicit perimeter logarithmic feature map, the segmentation threshold T f is:

[0085] T f = I min + m ⋅ ( I max – I mean )

[0086] Where I max is the maximum value of the image gray value, I min is the minimum value of the image gray value, I mean is the average value of the image gray value, m is an adjustment constant within the range of [0, 0.5]. The feature diagram after the first threshold segmentation is shown as an example Figure 4 as follows.

[0087] Then, in S4, calculate the number of pixel points of each independent target in the image after the first threshold segmentation, delete the independent targets with the number of pixel points greater than or equal to the preset number threshold, and determine the independent targets with the number of pixel points less than the preset number threshold as the highlighted target areas.

[0088] According to the embodiment of the present invention, calculate the number of pixel points of each independent target in the airborne infrared image T B , and eliminate the independent targets with the number of pixel points greater than T B , such as the coastline, so as to obtain the area where the highlighted target is located. In this embodiment, set T B to be 2000.

[0089] An example of the area where the retained highlighted target is located is shown in Figure 5 as shown.

[0090] Further, the area map of the highlighted target can be multiplied by the pixel points of the original image containing the highlighted target on the water ( Figure 2 ), and the obtained image is shown in Figure 6 as shown.

[0091] Then, in S5, calculate the second segmentation threshold based on the image gray value, and use the second segmentation threshold to perform a second threshold segmentation on the image retaining the highlighted target area, and determine the area greater than the second segmentation threshold as the highlighted target.

[0092] According to the embodiment of the present invention, perform threshold segmentation on the image again, and the segmentation threshold T is:

[0093]

[0094] Among them, and are the maximum and minimum values of all pixel (gray) values in the image; σ is the standard deviation of the image pixel values, p is an adjustment constant greater than 1. In this embodiment, p takes 2.5. After the second threshold segmentation, the highlighted target part in the image can be more accurately highlighted. An example of the recognized highlighted image is shown in Figure 7 as shown.

[0095] The present invention proposes a method for identifying high - light targets on water based on airborne infrared images, which has stronger detail recognition ability. By analyzing the thermal information in the infrared images, this method can accurately distinguish high - light targets from the background and accurately extract the features of high - light targets under complex backgrounds. In addition, this method can adapt to various different environmental and noise conditions, effectively reducing the false recognition rate. It also achieves a high degree of automation and can still accurately identify even in dynamic or low - contrast environments.

[0096] Another embodiment of the present invention proposes a system for identifying high - light targets on water based on airborne infrared images. As Figure 8 shown, the system includes:

[0097] An image acquisition module 810 configured to acquire an image containing high - light targets on water;

[0098] A feature calculation module 820 configured to calculate the explicit perimeter logarithm feature of the image; the explicit perimeter logarithm feature is defined as the ratio of the image saliency to the logarithm of the perimeter of the sliding window;

[0099] A first segmentation module 830 configured to calculate a first segmentation threshold based on the image gray - scale value, and use the first segmentation threshold to perform a first threshold segmentation on the feature map formed by the explicit perimeter logarithm feature, marking the area greater than the first segmentation threshold as independent targets and the area less than or equal to the first segmentation threshold as the background;

[0100] A high - light area extraction module 840 configured to calculate the number of pixel points of each independent target in the image after the first threshold segmentation, deleting the independent targets with the number of pixel points greater than or equal to a preset number threshold, and determining the independent targets with the number of pixel points less than the preset number threshold as high - light target areas;

[0101] A second segmentation module 850 configured to calculate a second segmentation threshold based on the image gray - scale value, and use the second segmentation threshold to perform a second threshold segmentation on the image retaining the high - light target areas, determining the area greater than the second segmentation threshold as high - light targets.

[0102] In this embodiment, preferably, the calculation of the explicit perimeter logarithm feature of the image in the feature calculation module 820 includes:

[0103] Setting the size of the sliding window, and calculating the segmentation threshold within the sliding window based on the mean and standard deviation of all pixel values within the sliding window; counting the number of pixel points within the sliding window whose pixel values are greater than the segmentation threshold N T ; calculating the number of perimeter pixel points of the sliding window N C ; then the explicit perimeter logarithm feature corresponding to the pixel point (i,j) is:F ( i , j ) = log( N T ) / log( N C )。

[0104] In this embodiment, preferably, the calculation formula for the segmentation threshold within the sliding window in the feature calculation module 820 is:

[0105] T’ = μ + k σ’

[0106] Wherein, μ is the mean value of all pixel values within the sliding window, σ’ is the standard deviation of all pixel values within the sliding window, k is an adjustment constant greater than 1.

[0107] In this embodiment, preferably, the calculation formula for the first segmentation threshold in the first segmentation module 830 is:

[0108] T f = I min + m × ( I max – I mean )

[0109] Wherein, I max is the maximum gray value of the explicit circumference logarithmic feature map, I min is the minimum gray value of the explicit circumference logarithmic feature map, I mean is the mean gray value of the explicit circumference logarithmic feature map, m is an adjustment constant.

[0110] In this embodiment, preferably, the calculation formula for the second segmentation threshold in the second segmentation module 850 is:

[0111]

[0112] Wherein, and are the maximum and minimum gray values of the image for retaining the highlighted target area; σ is the standard deviation of all gray values of the image for retaining the highlighted target area; p is an adjustment constant greater than 1.

[0113] It should be noted that the functions of the waterborne high-brightness target recognition system based on airborne infrared images described in this embodiment can be illustrated by the foregoing method for recognizing waterborne high-brightness targets based on airborne infrared images. For the parts not detailed in the system embodiment, reference may be made to the above method embodiment.

[0114] It should be noted that although several units, modules or sub-modules are mentioned in the foregoing detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described modules can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0115] In addition, although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the shown operations must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

[0116] Although the spirit and principles of the present invention have been described with reference to several specific embodiments, it should be understood that the present invention is not limited to the specific embodiments disclosed, and the division of each aspect does not mean that the features in these aspects cannot be combined for benefit. This division is only for convenience of expression. The present invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.

Claims

1. A method for identifying highlighted targets on water based on airborne infrared images, characterized in that: include: Acquire an image containing a highlighted target above water; Calculating the logarithmic feature of the image; The logarithmic feature of the saliency of the image is defined as the logarithmic ratio of the saliency of the image to the circumference of the sliding window; including: setting the size of the sliding window, and calculating the segmentation threshold in the sliding window based on the mean and standard deviation of all pixel values ​​in the sliding window; counting the number of pixel points in the sliding window whose pixel values ​​are greater than the segmentation threshold N T ; Calculate the number of pixels around the sliding window N C ; then the pixel (i,j) The corresponding logarithmic characteristics of the location are: F ( i , j )=log( N T ) / log( N C );Wherein, the calculation formula of the segmentation threshold in the sliding window is: T’ = μ + k σ' ； in, μ is the mean value of all pixel values ​​in the sliding window, σ' is the standard deviation of all pixel values ​​in the sliding window, k is a regulation constant greater than 1; Calculating a first segmentation threshold based on the gray value of the image, using the first segmentation threshold to perform a first threshold segmentation on the feature map formed by the logarithmic feature of the peripheral image, marking an area greater than the first segmentation threshold as an independent target, and marking an area less than or equal to the first segmentation threshold as a background; Calculate the number of pixels of each independent target in the image after the first threshold segmentation, delete the independent targets whose number of pixels is greater than or equal to the preset number threshold, and determine the independent targets whose number of pixels is less than the preset number threshold as the highlighted target area; A second segmentation threshold is calculated based on the grayscale value of the image, so as to perform a second threshold segmentation on the image retaining the highlighted target area using the second segmentation threshold, and determine the area greater than the second segmentation threshold as the highlighted target.

2. The method for identifying highlighted targets on water based on airborne infrared images according to claim 1, characterized in that: The calculation formula of the first segmentation threshold is: T f = I min + m ×( I max – I mean )； in, I max is the maximum grayscale value of the logarithmic feature map of the visible period, I min is the minimum grayscale value of the logarithmic feature map of the visible period, I mean is the grayscale mean of the logarithmic feature map of the visible period, m is the adjustment constant.

3. The method for identifying highlighted targets on water based on airborne infrared images according to claim 1, characterized in that: The calculation formula of the second segmentation threshold is: ； in, and To retain the maximum and minimum grayscale values ​​of the image in the highlighted target area; σ The standard deviation of all gray values ​​of the image to retain the highlighted target area; p is a regulation constant greater than 1.

4. A water highlight target recognition system based on airborne infrared images, characterized in that: include: An image acquisition module, configured to acquire an image containing a highlighted target above water; A feature calculation module, configured to calculate a logarithmic feature of the image; The logarithmic feature of the saliency of the image is defined as the logarithmic ratio of the saliency of the image to the circumference of the sliding window; including: setting the size of the sliding window, and calculating the segmentation threshold in the sliding window based on the mean and standard deviation of all pixel values ​​in the sliding window; counting the number of pixel points in the sliding window whose pixel values ​​are greater than the segmentation threshold N T ; Calculate the number of pixels around the sliding window N C ; then the pixel (i,j) The corresponding logarithmic characteristics of the location are: F ( i , j )=log( N T ) / log( N C ); The calculation formula of the segmentation threshold in the sliding window is: T’ = μ + k σ' ； in, μ is the mean value of all pixel values ​​in the sliding window, σ' is the standard deviation of all pixel values ​​in the sliding window, k is a regulation constant greater than 1; A first segmentation module is configured to calculate a first segmentation threshold based on the image gray value, so as to perform a first threshold segmentation on the feature map formed by the logarithmic feature of the peripheral display using the first segmentation threshold, mark the area greater than the first segmentation threshold as an independent target, and mark the area less than or equal to the first segmentation threshold as a background; A highlight region extraction module is configured to calculate the number of pixels of each independent target in the image after the first threshold segmentation, delete the independent targets whose number of pixels is greater than or equal to a preset number threshold, and determine the independent targets whose number of pixels is less than the preset number threshold as highlight target regions; The second segmentation module is configured to calculate a second segmentation threshold based on the image grayscale value, so as to perform a second threshold segmentation on the image retaining the highlighted target area using the second segmentation threshold, and determine the area greater than the second segmentation threshold as the highlighted target.

5. The water highlight target recognition system based on airborne infrared imaging according to claim 4 is characterized in that: The calculation formula of the first segmentation threshold in the first segmentation module is: T f = I min + m ×( I max – I mean )； in, I max is the maximum grayscale value of the logarithmic feature map of the visible period, I min is the minimum grayscale value of the logarithmic feature map of the visible period, I mean is the grayscale mean of the logarithmic feature map of the visible period, m is the adjustment constant.

6. The water highlight target recognition system based on airborne infrared imaging according to claim 4 is characterized in that: The calculation formula of the second segmentation threshold in the second segmentation module is: ； in, and To retain the maximum and minimum grayscale values ​​of the image in the highlighted target area; σ The standard deviation of all gray values ​​of the image to retain the highlighted target area; p is a regulation constant greater than 1.

Images