CN115294606B - Millimeter wave image dark target enhancement method - Google Patents

Abstract

The invention discloses a dark target enhancement method of a millimeter-wave image. Firstly, the center axis position, the top position and the shoulder position of the human body are calculated in the millimeter-wave image of the human body, the processing area is limited, and the average gray value of the human body is calculated to create a complementary image. In the complement image, the complement of pixels whose gray value is lower than the average gray value in the original image is stored; the area of the dark target in the complement image is extracted, the wrong enhancement part caused by the body structure is excluded, and only the dark target is retained enhanced area. Finally, the complement image is weighted and fused with the original image, the dark target texture features are preserved and the gray features of the dark target are enhanced, and the enhanced millimeter-wave image of the dark target is obtained. The method of the invention combines the grayscale feature of the dark object and the positional relationship between the dark object and the human body area, effectively enhances the grayscale feature of the dark object and at the same time effectively retains the texture feature of the dark object.

Description

A Dark Target Enhancement Method for Millimeter Wave Images

technical field

The invention belongs to the field of human body millimeter wave image target detection, in particular to a millimeter wave image dark target enhancement method.

Background technique

Millimeter-wave image target detection is the key to realize the detection of contraband on the human body surface. It can be widely used in security checks such as airports and stations, and is an effective replacement for existing human security checks. The use of millimeter waves to image the human body is a prerequisite for the realization of millimeter wave image target detection. Active millimeter wave imaging technology irradiates millimeter waves to the human body and uses millimeter wave radar to receive millimeter wave echoes to generate images based on the difference in the strength of the echoes. According to the effect on the incident millimeter wave, the properties of contraband targets carried by the human body can be divided into two categories: one kind has a stronger reflection effect on the incident millimeter wave than absorption effect, and the gray value in the millimeter wave image is higher than that of the human body area (Fig. 1(a) rectangular frame, hereinafter referred to as bright target); one type has a stronger absorption effect on the incident millimeter wave than reflection, and the gray value in the millimeter wave image is much lower than that of the human body area (Fig. 1(b) rectangular frame, hereinafter referred to as the dark target).

At present, most millimeter-wave image target detection methods use machine learning technology, and its training and testing principles can be briefly summarized as follows: After learning a large number of features of the required target, look for positions similar to the learned features in the test image. Among them, the "features of the target" refer to the unique texture, grayscale and other characteristics of the target area (relative to the human body area). It can be seen from Figure 1 that the bright target has richer textures than the dark target, while the target features of the dark target are similar to the black background outside the human body area. The detection rate is poor.

Aiming at this problem, the present invention combines the grayscale characteristics of the dark object and the positional relationship between the dark object and the human body area, effectively enhancing the grayscale characteristics of the dark object while effectively retaining the texture characteristics of the dark object.

Contents of the invention

The present invention aims at the problem that the detection rate of the dark target is not good due to the inconspicuous target features of the dark target compared with the bright target in the millimeter-wave image of the human body. Combining the grayscale characteristics of the dark target and the positional relationship between the dark target and the human body area, While effectively enhancing the gray features of the dark target, the texture feature of the dark target is effectively preserved.

A method for enhancing a dark target in a millimeter wave image, comprising the steps of:

Step 1. Calculate the central axis position, head position and shoulder position of the human body in the millimeter wave image of the human body, and limit the processing area;

Step 2, calculate the average gray value of the human body;

Step 3, creating a complementary set image, and storing a complementary set of pixels whose gray value in the original image is lower than the average gray value in the complementary set image;

Step 4. Extract the region of the dark target in the complement image, exclude the wrong enhanced part caused by the body structure, and only keep the enhanced region of the dark target.

Step 5. The complement image is weighted and fused with the original image, the texture feature of the dark object is preserved and the grayscale feature of the dark object is enhanced, and the enhanced millimeter wave image of the dark object is obtained.

Further, the specific method of step 1 is as follows;

Since the background gray value of the millimeter-wave human body image is almost 0, the maximum inter-class variance method can be used to segment the human body region to obtain a binary image of the human body region. A plane Cartesian coordinate system is established with the upper left corner of the image as the origin O, and the downward and rightward directions of the origin are the positive directions of the x-axis and y-axis respectively.

Calculate the center axis position:

Take points at the outermost edge of the left calf and right calf of the human body under the same ordinate, and record the two abscissas as legLeft and legRight respectively. Note that the abscissa of the central axis of the human body is axis, then axis is expressed as:

Calculate the overhead position:

Use the axis to calculate the head position, record the vertical coordinate of the top of the head as headTop, the binary image of the human body as I _OTSU , and the total number of rows in the image as imgRows. The specific steps of the calculation method of headTop are as follows:

1-1: At the point (axis,0) in I _OTSU , traverse along the positive direction of the y-axis.

1-2: When traversing to the first pixel whose gray value is not 0, record the ordinate of the pixel as headTop and stop traversing, and the calculation ends.

Calculate the shoulder position:

First, in the binary image I _OTSU , traverse from the position of the top of the head (coordinates (axis, headTop)) along the negative direction of the x-axis to the first point that is not 0, and the abscissa is marked as leftArm. For the axis-leftArm pixel points within (leftArm, headTop) to (axis, headTop), traverse along the positive direction of the y-axis to the first point that is not 0, and record the ordinate of this point as leftShoulder _i , i∈[ 0,axis-leftArm).

Similarly, in the binary image I _OTSU , traverse from the position of the top of the head (coordinates (axis, headTop)) along the positive direction of the x-axis to the first point that is not 0, and the abscissa is marked as rightArm. For the rightArm-axis pixels from (axis, headTop) to (rightArm, headTop), traverse along the positive direction of the y-axis to the first point that is not 0, and record the ordinate of this point as rightShoulder _j , j∈[ 0, rightArm-axis).

Finally, find the maximum value of the ordinate in the ordinate set leftShoulder _i ∩ rightShoulder _j as the ordinate of the shoulder position, which is recorded as Shoulder.

Further, the specific method of step 2 is as follows;

Since the background gray value of the millimeter wave image of the human body is 0, the average gray value of non-zero pixels is the average gray value of the human body area. Record the average gray value of the human body as avgGrey, record the millimeter-wave image of the human body as I _src , and record the total number of rows and columns of I _src as imgRows and imgCols. The specific steps of the calculation method of avgGrey are as follows:

2-1: Start traversing all pixels of I _src from the origin, record the total gray value of all pixels of I _src and the number of pixels whose gray value is not 0.

2-2: After the traversal is completed, calculate the ratio of the total gray value of all pixels in I _src to the number of pixels whose gray value is not 0, and record the ratio as avgGrey of I _src , and the calculation ends.

Further, the specific method of step 3 is as follows;

Note that the complement image is I _enhance , and the maximum gray value that can be stored by a single pixel in the complement image file is maxGrey. The specific steps for generating I _enhance are as follows:

3-1: Create a complement image I _enhance with the same size as I _src , and the initial gray value of all pixels in I _enhance is 0.

3-2: Traverse all the pixels below the shoulders of the human body in I _src , take avgGray as the complement threshold, and for pixels whose gray value is lower than avgGray in I _src , use the gray value of the pixel in I _enhance The complement value is assigned to the pixel at the position corresponding to I _enhance .

3-3: After the traversal is completed, the calculation ends.

Explanation of the complementary value in step 3-2: Take an 8-bit unsigned single-channel grayscale image as an example: the maximum grayscale value that can be stored in a single pixel is 255, assuming that one pixel has a grayscale value of 20, then The complementary value of this pixel is 255-20=235.

Further, the specific method of step 4 is as follows;

In the human body binary image I _OTSU , traverse upward from the bottom of the image along the axis axis of the human body, and stop when encountering the first point that is not 0, record the ordinate of this point as buttDown, and the ordinate of this point is the crotch of the human body Y-axis. Therefore, the ordinate interval of the human leg is [buttDown,imgRows), and the left leg of the human body is located on the left side of the axis of the human body, and the right leg of the human body is located on the right side of the axis axis of the human body. The inner and outer edge complement area of the leg is used to obtain the complement image I′ _enhance after the complement area of the outer edge of the human body is removed.

In the horizontal direction, the image pixels are traversed from the outside of the human body to the inside of the human body, and the traversal termination condition is set to ensure that the complement of dark objects will not be removed together. Taking the removal of the outer edge complement area on the left side of the human body as an example, the specific removal method of the outer edge complement area on the left side of the human body is as follows:

4-1: In the area of x∈[0,axis], start from the position x=0, traverse each row of pixels in I _enhance along the positive direction of the x-axis, and set the non-zero pixels in the traversal process The gray value is set to zero. When the current pixel is non-zero and the gray value of the next pixel at the traversal position is 0, set the non-zero pixel at the current position to zero, end the traversal of the row and jump to the beginning of the next row of pixels Positions continue to traverse according to the above rules.

4-2: After traversing all the lines of I _enhance , the calculation ends.

Use the morphological opening operation to eliminate the clutter in the non-dark target complement area that may exist: record the highest bit of the shorter side length of the image as m, and use the rectangular structure element pair I' with the origin at the center of the size m×m _Enhance morphological opening operation processing, record the complement image processed by morphological opening operation as I″ _enhance .

Further, the specific method of step 5 is as follows.

Use the same method in step 2 to calculate the average gray value of I″ _enhance , which is recorded as avgGrey _enhance . In order to enhance the gray feature of the dark target while retaining the original texture features of the dark target, use the average gray value of avgGrey _enhance and I _src avgGrey calculates the weighting coefficient, and the weighting is fused with I _src and I″ _enhance . Note that the fused image is I _fusion , and the fusion process of I _fusion is expressed as:

I _fusion is the final enhancement result of the dark target in the human millimeter wave image, which effectively preserves the texture feature of the dark target while effectively enhancing the gray feature of the dark target.

The beneficial effects of the present invention are as follows:

Aiming at the poor detection rate of dark targets caused by the inconspicuous target features of dark targets compared with bright targets in human millimeter-wave images, combined with the grayscale features of dark targets and the positional relationship between dark targets and human body areas, it effectively enhances the The texture features of the dark target are effectively preserved while the gray features of the dark target are preserved.

Description of drawings

Figure 1 is a schematic diagram of a bright target and a dark target in a millimeter wave image of a human body;

Fig. 2 is a schematic diagram of the OTSU segmentation result of the millimeter-wave image of the human body;

Fig. 3 is a schematic diagram of the airspace coordinate system of the present invention;

Fig. 4 is a schematic diagram of shoulder position calculation;

Fig. 5 is a schematic diagram of the enhancement flow of the present invention.

Detailed ways

The method of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

A method for enhancing a dark target in a millimeter-wave image specifically includes the following steps:

Step 1. Calculate the position of the central axis of the human body, the position of the top of the head and the position of the shoulder;

Since the background gray value of the millimeter-wave human body image is almost 0, the maximum inter-class variance method (OTSU, Otsu N.A Threshold Selection Method from Gray-Level Histograms[J].IEEETransactions on Systems Man&Cybernetics,2007,9(1): 62-66.) Segment the human body region to obtain the binary image of the human body region as shown in Figure 2. As shown in Figure 3, a plane Cartesian coordinate system is established with the upper left corner of the image as the origin O, and the downward and rightward points of the origin are the positive directions of the x-axis and y-axis respectively. The schematic diagram of the coordinate system and the key points below are marked in Figure 3 out.

Calculate the center axis position:

Take points at the outermost edge of the left calf and right calf of the human body under the same ordinate, and record the two abscissas as legLeft and legRight respectively. Note that the abscissa of the central axis of the human body is axis, then axis is expressed as:

Calculate the overhead position:

Use the axis to calculate the head position, record the vertical coordinate of the top of the head as headTop, the binary image of the human body as I _OTSU , and the total number of rows in the image as imgRows. The specific steps of the calculation method of headTop are as follows:

1-1: At the point (axis,0) in I _OTSU , traverse along the positive direction of the y-axis.

1-2: When traversing to the first pixel whose gray value is not 0, record the ordinate of the pixel as headTop and stop traversing, and the calculation ends.

The pseudocode of the headTop calculation algorithm is as follows:

Calculate the shoulder position:

First, in the binary image I _OTSU , traverse from the position of the top of the head (coordinates (axis, headTop)) along the negative direction of the x-axis to the first point that is not 0, and the abscissa is marked as leftArm. For the axis-leftArm pixel points within (leftArm, headTop) to (axis, headTop), traverse along the positive direction of the y-axis to the first point that is not 0, and record the ordinate of this point as leftShoulder _i , i∈[ 0,axis-leftArm).

Similarly, in the binary image I _OTSU , traverse from the position of the top of the head (coordinates (axis, headTop)) along the positive direction of the x-axis to the first point that is not 0, and the abscissa is marked as rightArm. For the rightArm-axis pixels from (axis, headTop) to (rightArm, headTop), traverse along the positive direction of the y-axis to the first point that is not 0, and record the ordinate of this point as rightShoulder _j , j∈[ 0, rightArm-axis).

Finally, find the maximum value of the ordinate in the ordinate set leftShoulder _i ∩ rightShoulder _j as the ordinate of the shoulder position, which is recorded as Shoulder.

The schematic diagram of calculating the shoulder position is shown in FIG. 4 , where the direction of the arrow indicates the direction of pixel traversal.

Step 2, calculate the average gray value of the human body;

Since the background gray value of the millimeter wave image of the human body is 0, the average gray value of non-zero pixels is the average gray value of the human body area. Record the average gray value of the human body as avgGrey, record the millimeter-wave image of the human body as I _src , and record the total number of rows and columns of I _src as imgRows and imgCols. The specific steps of the calculation method of avgGrey are as follows:

2-1: Start traversing all pixels of I _src from the origin, record the total gray value of all pixels of I _src and the number of pixels whose gray value is not 0.

2-2: After the traversal is completed, calculate the ratio of the total gray value of all pixels in I _src to the number of pixels whose gray value is not 0, and record the ratio as avgGrey of I _src , and the calculation ends.

The pseudocode of the avgGrey calculation algorithm is as follows:

Step 3, create a complementary set image, and store a complementary set of pixels whose grayscale value in I _src is lower than the average grayscale value in the complementary set image;

Note that the complement image is I _enhance , and the maximum gray value that can be stored by a single pixel in the complement image file is maxGrey. The specific steps for generating I _enhance are as follows:

3-1: Create a complement image I _enhance with the same size as I _src , and the initial gray value of all pixels in I _enhance is 0.

3-2: Traverse all the pixels below the shoulders of the human body in I _src , take avgGray as the complement threshold, and for pixels whose gray value is lower than avgGray in I _src , use the gray value of the pixel in I _enhance The complement value is assigned to the pixel at the position corresponding to I _enhance .

3-3: After the traversal is completed, the calculation ends.

Explanation of the complementary value in step 3-2: Take an 8-bit unsigned single-channel grayscale image as an example: the maximum grayscale value that can be stored in a single pixel is 255, assuming that one pixel has a grayscale value of 20, then The complementary value of this pixel is 255-20=235.

The pseudocode of the complement image generation algorithm is as follows:

An example of a complement image is shown in Figure 5(a).

Step 4, extracting the region that is the dark target in the complement image;

As shown in Figure 5(a), the outer edge of the human body has similar grayscale features to the dark object, so there will be complements of the outer edge of the human body and the dark object in the complementary image, so it is necessary to remove the complementary area of the non-dark object .

In the binary image I _OTSU of the human body, traverse upward from the bottom of the image along the axis axis of the human body, and stop when encountering the first point that is not 0 (see Figure 3, record the ordinate of this point as buttDown), the ordinate of this point is is the vertical coordinate of the human crotch. Therefore, the ordinate interval of the human leg is [buttDown,imgRows), and the left leg of the human body is located on the left side of the axis of the human body, and the right leg of the human body is located on the right side of the axis axis of the human body. The inner and outer edge complement area of the leg is used to obtain the complement image I′ _enhance after the complement area of the outer edge of the human body is removed.

In the horizontal direction, the image pixels are traversed in the direction from the outside of the human body to the inside of the human body, and the traversal termination condition is set to ensure that the complement of dark objects will not be removed together. Taking the removal of the outer edge complement area on the left side of the human body as an example, the specific removal method of the outer edge complement area on the left side of the human body is as follows:

4-1: In the area of x∈[0,axis], start from the position x=0, traverse each row of pixels in I _enhance along the positive direction of the x-axis, and set the non-zero pixels in the traversal process The gray value is set to zero. When the current pixel is non-zero and the gray value of the next pixel at the traversal position is 0, set the non-zero pixel at the current position to zero, end the traversal of the row and jump to the beginning of the next row of pixels The location (the location of x=0) continues to traverse according to the above rules.

4-2: After traversing all the lines of I _enhance , the calculation ends.

The pseudo code for removing the complement area of the outer edge of the human body is as follows:

Mathematical Morphology (Serra J.Image Analysis and Mathematical Morphology-VolumeI.Academic, 1982.) The opening operation can eliminate small connected domains and retain larger connected domains (connected domain: a piece of interconnected valuable pixels in the image gather). Use the morphological opening operation to eliminate the clutter in the non-dark target complement area that may exist: record the highest bit of the shorter side length of the image as m, and use the rectangular structure element pair I' with the origin at the center of the size m×m _Enhance morphological opening operation processing, record the complement image processed by morphological opening operation as I "_enhance" . For example, the size of _I'enhance in Fig. 5(b) is 400×768, so m=4. Fig. 5(c) is The I″ _enhance obtained by the operation processing in Fig. 5(b) is performed.

Step 5. Weighted fusion of the complement image and the original image.

Use the same method in step 2 to calculate the average gray value of I″ _enhance , which is recorded as avgGrey _enhance . In order to enhance the gray feature of the dark target while retaining the original texture features of the dark target, use the average gray value of avgGrey _enhance and I _src avgGrey calculates the weighting coefficient, and the weighting is fused with I _src and I″ _enhance . Note that the fused image is I _fusion , and the fusion process of I _fusion is expressed as:

I _fusion is the final enhancement result of the dark target in the human millimeter-wave image (that is, the millimeter-wave image after the dark target is enhanced, as shown in Figure 5(d)), which effectively preserves the dark target while effectively enhancing the gray feature of the dark target. Texture features of the target.

Claims (4)

1. A method for enhancing a dark target in a millimeter wave image is characterized by comprising the following steps:

step 1, calculating the axis position, the vertex position and the shoulder position in the human body in the millimeter wave image of the human body, and limiting a processing area;

step 2, calculating the average gray value of the human body;

step 3, creating a complementary set image, and storing a complementary set of pixel points with gray values lower than the average gray value in the original image in the complementary set image;

step 4, extracting the area which is the dark target in the complementary image, excluding the error enhancement part caused by the body structure, and only reserving the enhancement area of the dark target;

step 5, weighting and fusing the complementary set image and the original image, reserving texture features of the dark target, enhancing gray features of the dark target, and obtaining a millimeter wave image after the dark target is enhanced;

the specific method of the step 1 is as follows;

because the background gray value of the millimeter wave human body image is almost 0, the human body region can be segmented by using the maximum inter-class variance method to obtain a binary image of the human body region; establishing a plane rectangular coordinate system by taking the upper left corner point of the image as an original point O, wherein the downward direction and the rightward direction of the original point are respectively the positive directions of an x axis and a y axis;

calculating the position of the middle shaft:

respectively taking points at the outermost edges of the left shank and the right shank of the human body under the same ordinate, and respectively recording the abscissa of the left shank and the abscissa of the right shank as legLeft and legRight; let the abscissa of the medial axis of the human body be axis, then axis is expressed as:

calculating the head top position:

calculating the position of the head by means of axis, recording the vertical coordinate of the top of the head as headTop and the binary image of the human body as I _OTSU Image lineThe method for calculating headTop with imgRows comprises the following specific steps:

1-1: in I _OTSU At point (axis, 0), traversing in the positive y-axis direction;

1-2: when traversing to a pixel point with a first gray value not being 0, recording the vertical coordinate of the pixel point as a headTop and stopping traversing, and finishing the calculation;

calculating the shoulder position:

firstly, in a binary image I _OTSU Traversing from the vertex position to the first point which is not 0 along the negative direction of the x-axis, and recording the abscissa as leftArm, wherein the coordinate of the vertex position is (axis, headTop); traversing to a first point which is not 0 sequentially along the positive direction of the y axis aiming at the axis-leftArm pixel points from (leftArm, headTop) to (axis, headTop), and recording the ordinate of the point as leftShoulder _i ,i∈[0,axis-leftArm)；

Similarly, in the binary image I _OTSU Traversing from the vertex position to the first point which is not 0 along the positive direction of the x-axis, and marking the abscissa as rightArm, wherein the coordinate of the vertex position is (axis, headTop); sequentially traversing to a first point which is not 0 along the positive direction of the y axis aiming at the rightArm-axis pixel points from (axis, headTop) to (rightArm, headTop), and recording the ordinate of the point as rightShoulder _j ,j∈[0,rightArm-axis)；

Finally, in the ordinate set leftSholder _i ∩rightShoulder _j Finding the maximum value of the vertical coordinate as the vertical coordinate of the Shoulder position, and recording as Shoulder;

the specific method of the step 2 is as follows;

since the background gray value of the human millimeter wave image is 0, the average gray value of the non-0 pixel points is the average gray value of the human body area; recording the average gray value of the human body as avgGrey and the millimeter wave image of the human body as I _src Respectively record I _src The total row and column numbers of imgRows and imgCols; the calculation method of the avgGrey comprises the following specific steps:

2-1: traverse I from origin _src All pixel points of (1), record I _src The total gray value of all the pixel points and the number of the pixel points with the gray values not being 0;

2-2: after the traversal is finished, calculating I _src The ratio of the total gray value of all the pixels to the number of pixels with gray values not 0 is marked as I _src Avggley, the calculation ends.

2. The method for enhancing the dark objects in the millimeter wave images according to claim 1, wherein the step 3 is as follows;

the complementary set of images is I _enhance The maximum gray value which can be stored by a single pixel point of the complementary set image file is maxGrey, I _enhance The specific steps of the generation are as follows:

3-1: creating a sheet and I _src Complementary set image I of the same size _enhance ，I _enhance The initial gray values of all the internal pixel points are 0;

3-2: traverse I _src All pixel points of the part below the shoulders of the middle human body take the avgGray as a complementary threshold value for I _src Pixel points with internal gray value lower than avgGray are shown in I _enhance In which the complement value of the gray value of the pixel point is taken as I _enhance Assigning the pixel points of the corresponding positions;

3-3: after traversing, finishing calculation;

for the interpretation of the complement in step 3-2: take an 8-bit unsigned single-channel grayscale map as an example: the maximum gray value that a single pixel can store is 255, and if the gray value of a pixel is 20, the complement value of the pixel is 255-20=235.

3. The method for enhancing the dark target in the millimeter wave image according to claim 2, wherein the step 4 is as follows;

in a binary image I of a human body _OTSU Traversing the inner edge human body central axis from the bottom of the image upwards, stopping when meeting a first point which is not 0, recording the vertical coordinate of the point as button Down, and the vertical coordinate of the point is the vertical coordinate of the human body crotch; therefore, the human body leg vertical coordinate interval is [ button Down, imgRows ], the human body left leg is positioned at the left side of the human body central axis, the human body right leg is positioned at the right side of the human body central axis, and the human body legs are positioned by utilizing the informationSide position, and removing the complementary region at the inner outer edge of the two legs to obtain a complementary image I after the complementary region at the outer edge of the human body is removed _e ′ _nhance ；

Traversing image pixels in the transverse direction from the outer side of the human body to the inner side of the human body, and setting a traversing termination condition to ensure that the complementary sets of the dark targets cannot be removed together; taking the removal of the outer edge complementary region on the left side of the human body as an example, a specific removal method of the outer edge complementary region on the left side of the human body is as follows:

4-1: in the case where x is equal to 0]In the region, starting from the position of x =0, traversing I in rows in the positive direction of the x axis _enhance Setting the gray value of the non-zero pixel point to zero in the traversal process; when the current pixel point is nonzero and the gray value of the next pixel point at the traversal position is 0, zeroing the nonzero pixel point at the current position, ending the traversal of the line and jumping to the initial position of the pixel point at the next line to continue the traversal according to the rule;

4-2: finish traversing I _enhance All the rows of (2) are calculated;

the morphological opening operation is used to eliminate the possible presence of clutter in the non-dark target complement region: let m be the highest bit of the shorter edge length of the image, use the rectangular structural element pair I with the origin at the center and the size of m × m _e ′ _nhance Morphological opening operation processing, recording the complementary set image after the morphological opening operation processing as I _e ″ _nhance 。

4. The method for enhancing the dark objects in the millimeter wave images according to claim 3, wherein the step 5 is as follows;

i was calculated using the same method as in step 2 _e ″ _nhance Is recorded as avgGrey _enhance (ii) a In order to enhance the gray scale characteristics of the dark target and simultaneously retain the original texture characteristics of the dark target, avgGrey is used _enhance And I _src Calculating a weighting coefficient by using the average gray value avgGrey, and performing weighted fusion I _src And I _enhance (ii) a The fused image is recorded as I _fusion Then, I _fusion The fusion process of (a) is represented as:

I _fusion the method has the advantages that the texture features of the dark target are effectively reserved while the gray features of the dark target are effectively enhanced for the final enhancement result of the dark target in the human millimeter wave image.

Images