A water interference removal method for deep-sea binocular camera terrain reconstruction

Abstract

The present invention belongs to the field of deep-sea image processing technology, and specifically relates to a method for removing water interference for deep-sea binocular camera terrain reconstruction. First, two different deep learning networks are used to constrain the images captured by the binocular camera and output a disparity matrix constrained by the deep learning network. Then, a threshold method is used in Lab color space to remove the seawater area to obtain an initial valid area. Morphological operations such as dilation, hole filling, and corrosion are performed on the initial valid area in sequence to obtain a final valid area and an invalid area. The final valid area is mapped to the constrained disparity matrix, and the disparity values ​​corresponding to the invalid area are set to invalid values, thereby achieving the removal of water interference. This solution removes interference caused by pure seawater areas in binocular images through processes such as dual deep learning network constraints, color space conversion and thresholding operations, and morphological operations, ensuring the continuity and integrity of the image area and effectively improving segmentation accuracy.

Description

Technical Field

[0001] The present invention belongs to the technical field of deep-sea image processing, and in particular relates to a method for removing water interference for deep-sea binocular camera terrain reconstruction. Background Art

[0002] With the continuous advancement of deep-sea scientific research and marine resource development, the application of underwater visual sensing technology in topographic surveys, deep-sea environmental monitoring, and marine life observation has become increasingly important. As one of the core devices in underwater visual sensing, binocular cameras can achieve three-dimensional reconstruction through stereo vision technology, providing scientists and engineers with accurate deep-sea topographic information.

[0003] Ideally, 3D reconstruction from a binocular camera should focus on the actual surface of objects. However, due to the optical properties of water, pure seawater areas are sometimes mistakenly identified as sources of reconstructible depth information, leading to unnecessary 3D reconstruction. This phenomenon stems from the transparency, reflective properties, or light refraction effects of water bodies, which interfere with the camera's depth estimation and introduce unnecessary "false depth information" into the 3D model. Misreconstructing pure seawater areas as objects with depth can affect reconstruction accuracy and scene understanding. For example, planes or areas that should not exist may appear in the 3D model, blurring the shape and position of actual objects and adversely affecting deep-sea exploration missions.

[0004] Therefore, there is an urgent need for a technology that can effectively distinguish between pure seawater areas and actual object surfaces, reduce or remove the impact of pure seawater areas in three-dimensional terrain reconstruction, improve the three-dimensional reconstruction accuracy of binocular cameras, and thereby improve the accuracy of deep-sea exploration and research. Summary of the Invention

[0005] To address the problem in the prior art that pure seawater areas in images captured by binocular cameras introduce a large amount of noise, affecting the accuracy of three-dimensional reconstruction, the present invention proposes a water interference removal method for deep-sea binocular camera terrain reconstruction. The method is used to separate the pure seawater areas in the image from the effective information areas. This method can not only accurately identify the pure seawater areas in the image, but also effectively reduce the noise caused by deep-sea water interference, greatly improving the accuracy of three-dimensional terrain reconstruction.

[0006] The present invention is implemented by adopting the following technical solution: a method for removing water interference for deep-sea binocular camera terrain reconstruction, comprising the following steps:

[0007] Step A: Use two different deep learning networks to constrain the images collected by the binocular camera and output the disparity matrix D constrained by the deep learning network;

[0008] Step B: for the image captured by the binocular camera, use the threshold method in the Lab color space to remove the seawater area to obtain the initial effective area BW;

[0009] Step B1: Convert the image captured by the binocular camera from RGB color space to Lab color space. Use the threshold method to preliminarily constrain the images of the L channel, a channel, and b channel. Assume that the distribution of most pure seawater areas in the three channels is as follows:

[0010] Step B2: Depending on different application scenarios and requirements, there are several ways to obtain the initial effective area:

[0011] (1) In situations where the requirements are high, the brightness channel and the color channel are constrained, and the segmentation method that retains the effective area to the greatest extent is:

[0012]

[0013] (2) For applications with low requirements, the operation to remove seawater areas to the greatest extent possible is:

[0014]

[0015] (3) For the first two cases, since the image is more sensitive to brightness during the segmentation process, a dynamic threshold based on statistical principles is used. replace As shown below:

[0016]

[0017] in, Indicates the minimum threshold of the L channel, which is used to determine the lower limit of the brightness of the seawater area. Indicates the maximum threshold of the L channel, which is used to determine the upper limit of the brightness of the seawater area. L(i,j) represents the brightness value of the pixel in the Lab color space. a(i,j) represents the a channel value of the pixel in the Lab color space, representing the range from green to red. Indicates the minimum threshold of channel a, which is used to determine the lower limit of the green to red range of the seawater area. Indicates the maximum threshold of the a channel, which is used to determine the upper limit of the green to red range of the seawater area. b(i,j) represents the b channel value of the pixel in the Lab color space, representing the range from blue to yellow. Indicates the minimum threshold of the b channel, which is used to determine the lower limit of the blue to yellow range of the seawater area. Indicates the maximum threshold of the b channel, which is used to determine the upper limit of the blue to yellow range of the seawater area, μ 海水统计 and σ海水统计 is the mean and standard deviation of the cumulative statistical pixel values ​​of the L channel of the pure seawater area in more than ten pictures of different scenes, μ 全图 and σ 全图 is the mean and standard deviation of all pixel values ​​in the L channel of the image to be segmented, W1 and W2 are weights, k is a coefficient, M is the binary mask of the segmented seawater area, M(i, j) is the element in the binary mask of the segmented seawater area, and the initial valid area is the opposite part, which is expressed as:

[0018]

[0019] Where BW is the initial valid area, and BW(i,j) is the element in the initial valid area;

[0020] Step C: perform dilation, hole filling, and erosion morphological operations on the initial valid area BW in sequence to obtain the final valid area BW3 and the invalid area;

[0021] Step D: Map the final valid area BW3 to the constrained disparity matrix D obtained in step A, and set the disparity values ​​corresponding to the invalid areas to invalid values, thereby removing water interference.

[0022] Furthermore, the step C is specifically implemented in the following manner:

[0023] (1) First, the initial effective area is expanded, and the mathematical description is as follows:

[0024]

[0025] Among them, BW1 is the area after the dilation operation, and B1 is the structural element;

[0026] (2) Then fill the holes in the area after the dilation operation. If the captured target contains holes, skip this step and assume that the output after filling the holes in the BW1 area is BW2;

[0027] (3) Finally, the output after filling the holes is corroded to restore the image to its original size before expansion:

[0028]

[0029] Among them, BW3 is the final valid area after the corrosion operation, BW2 is the area after the hole filling operation, and B2 is the structural element.

[0030] Furthermore, in step D, the specific mapping formula is expressed as:

[0031]

[0032] Among them, DNoWater The disparity matrix D is the final one that removes the interference of pure seawater area. NoWater (i, j) is the final disparity value after removing the interference of the pure seawater area, D(i, j) is the disparity value constrained by the dual deep learning network, and BW3(i, j) is the element in the final effective area. Combined with the internal parameters of the camera, the final 3D terrain point cloud is obtained. The point cloud restored by multiple frames of images is stitched together to restore the deep-sea 3D terrain map without the interference of the pure seawater area. Similarly, the segmented area can be mapped to the image to obtain an image with the seawater area removed.

[0033] Furthermore, step A is specifically implemented in the following manner:

[0034] Assume that D1 and D2 are the disparity matrices generated by two deep learning networks based on the same pair of binocular camera stereo images, then their disparity difference ΔD(i,j) is expressed as follows;

[0035] ΔD(i,j)=|D1(i,j)-D2(i,j)|

[0036] If ΔD(i,j)>T, mark D1(i,j) and D2(i,j) as invalid values

[0037] Where T is a fixed threshold, D1(i, j) and D2(i, j) are the disparity values ​​generated by the two deep learning networks at the image pixel point (i, j), and either of the marked D1 or D2 is used as the disparity matrix D constrained by the dual deep learning network.

[0038] Furthermore, in step A, the original disparity matrix is ​​obtained through a single deep learning network to replace the constrained disparity matrix. After the threshold method and morphological operation of the Lab color space, BW3 is directly mapped to the original disparity matrix to also achieve the removal of water interference.

[0039] Compared with the prior art, the advantages and positive effects of the present invention are:

[0040] This solution not only removes some water interference in seawater through dual neural network constraints, but also removes most random noise and incorrectly matched points, eliminating the subsequent point cloud denoising process; through the image segmentation algorithm, combined with the brightness and color channel characteristics of the Lab color space, it can accurately identify and segment pure seawater areas in the image, thereby significantly reducing the noise interference caused by these areas. The algorithm of this solution is simple and has a very high running speed; by performing morphological operations on the effective area, the continuity and integrity of the image area are ensured, thereby improving the segmentation accuracy; it provides a reliable and efficient solution for removing water interference for binocular camera 3D reconstruction in deep-sea environments, and has broad application prospects and practical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of the interference removal method according to an embodiment of the present invention;

[0042] Figure 2 Schematic diagram of the statistical results of seawater area according to an embodiment of the present invention, (a) is the brightness distribution of the L channel, (b) is the color distribution of the a channel, and (c) is the color distribution of the b channel;

[0043] Figure 3 This is a schematic diagram of global brightness statistics results according to an embodiment of the present invention;

[0044] Figure 4 Schematic diagram of the original image and original point cloud according to an embodiment of the present invention, (a) is the original image, (b) is the original point cloud image;

[0045] Figure 5 Schematic diagram of an image and point cloud after removing seawater interference according to an embodiment of the present invention, (a) is the image after removing interference, and (b) is the point cloud image after removing interference;

[0046] Figure 6 Schematic diagram of the effect of image segmentation according to an embodiment of the present invention; (a) is the unsegmented image, and (b) is the segmented image;

[0047] Figure 7 This is a three-dimensional topographic map without removing seawater interference in an embodiment of the present invention;

[0048] Figure 8 This is a three-dimensional topographic map with seawater interference removed according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described below with reference to the accompanying drawings and embodiments. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can also be implemented in other ways than those described herein. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0050] A water interference removal method for deep-sea binocular camera terrain reconstruction, combining Figure 1 As shown, the following steps are included:

[0051] Step 1: Use two different deep learning networks to constrain the images captured by the binocular camera and output the disparity matrix constrained by the deep learning network;

[0052] Pure seawater areas typically lack distinct texture features, which can easily lead to noise and errors in disparity estimation. When a single network performs depth prediction in these areas, it may generate false depth points, affecting the overall structure of the 3D reconstruction. In this example, two different deep learning networks are used for constraint filtering. False depth points are filtered out due to inconsistent predictions between the two networks, effectively reducing the generation of false depth points and avoiding the appearance of unnecessary surfaces or structures in the 3D model. The disparity difference ΔD(i,j) is described by the following formula:

[0053] ΔD(i,j)=|D1(i,j)-D2(i,j)|

[0054] If ΔD(i,j)>T, mark D1(i,j) and D2(i,j) as invalid values

[0055] Here, D1(i, j) and D2(i, j) are the disparity values ​​generated by the two deep learning networks at the image pixel (i, j), respectively. T is a fixed threshold, typically set to <5. The smaller the value, the smaller the difference allowed between the two disparity matrices. The disparity matrices generated by the two deep learning networks should be the same. Points with disparity differences greater than the threshold are set to invalid values. Finally, either the labeled matrix D1 or D2 is used as the output of the dual neural network constraint, D.

[0056] Step 2: For the image captured by the binocular camera, use the threshold method in the Lab (CIE Lab) color space to remove the seawater area and obtain the initial effective area;

[0057] The image captured by the binocular camera is converted from RGB color space to Lab (CIE Lab) color space. The image is initially constrained using the threshold method of three channels (L channel, a channel, and b channel), and the image is roughly divided into a pure seawater area and an initial valid area.

[0058] Extensive statistical analysis of deep-sea imagery reveals two key differences between pure seawater areas and normal target areas: 1) Pure seawater areas are typically lower in brightness because they lack reflected light from valid targets; 2) Due to the inherent properties of seawater, pure seawater areas often appear bluish-green. These two properties are most pronounced in the Lab (CIELab) color space, making thresholding the optimal approach in this space.

[0059] Assume that most (but not all) of the pure seawater area is distributed among the three channels as follows:

[0060]

[0061] Constrain the brightness channel and color channel separately, and the segmentation method that retains the valid area to the greatest extent is:

[0062]

[0063] In some cases where the requirements are not high, using only the L (brightness) channel and the a (green-red) channel or the L (brightness) channel and the b (blue-yellow) channel can also achieve a better segmentation effect. The operation to remove the seawater area to the greatest extent is:

[0064]

[0065] Since the image is more sensitive to brightness during the segmentation process, a dynamic threshold based on statistical principles can be used in situations with higher requirements. replace As shown below:

[0066]

[0067] Among them, μ 海水统计 and σ 海水统计 is the mean and standard deviation of the cumulative statistical pixel values ​​of the L channel of the pure seawater area in more than ten pictures of different scenes, μ 全图 and σ 全图 is the mean and standard deviation of all pixel values ​​in the L channel of the image to be segmented. The formula represents the dynamic threshold The bright part in the seawater area (μ 海水统计 +2σ 海水统计 ) and the darker part (μ 全图 -kσ 全图 ) are jointly restricted. The coefficient k in the formula is generally set to 1.28 (the darker 10% in the normal distribution), and can also be adjusted according to actual conditions. W1 and W2 are weights. The smaller the value of W1, the higher the dynamic threshold. The greater the effect of the image brightness, the greater the effect. Usually W1 is set to 0.7, and the solution formula for W2 is as follows:

[0068] W1(μ 海水统计 +2σ 海水统计 )+W2(μ 全图统计 -1.28σ 全图统计 )=(μ 海水统计 +2σ 海水统计 )

[0069] where μ 全图统计 and σ 全图统计 is the cumulative statistical mean and standard deviation of all pixel values ​​of the L channel in more than ten pictures of different scenes, so that In (μ 海水统计 +2σ海水统计 ) fluctuates around .

[0070] The M(i,j) in the formula is the binary mask of the segmented seawater area, and the initial valid area should be the opposite part, that is:

[0071]

[0072] The BW(i,j) part is the initial effective area.

[0073] Step 3: Perform morphological operations on the initial valid area BW, including dilation, hole filling, and erosion.

[0074] (1) First, dilate the initial valid area: In a binary image, some small gaps or broken areas in the foreground may cause the segmentation result to be inconsistent. These discontinuous areas can be connected through the dilation operation. Dilation can fill the small discontinuous areas and make the entire area more continuous. The mathematical description is as follows:

[0075]

[0076] Wherein, BW1 is the area after the dilation operation, B1 is the structural element, and a disk is selected in the present invention. The radius is adjusted according to the image resolution. At a resolution of 1920x1080, the radius is usually set to 5.

[0077] (2) Hole filling is then performed on the region after the dilation operation. Hole filling is performed to eliminate some holes within the BW1 region. Usually, the seabed topography in deep-sea images does not have holes. Filling holes can make the entire region in the image more continuous. However, in some special cases, the imaged target itself contains holes, so this step should be skipped. Assume that the output of the BW1 region after hole filling is BW2.

[0078] (3) Finally, the output after filling the holes is corroded to return the image to its original size before expansion, ensuring that the image does not over-expand after filling the gaps and holes. Finally, the segmented area can be output:

[0079]

[0080] Among them, BW3 is the final effective area after the corrosion operation, BW2 is the area after the hole filling operation, and B2 is a structural element. In the present invention, a disk is selected, and the radius is the same as or slightly larger than B1.

[0081] Step 4: Map the final valid area obtained by segmentation in step 3 to the disparity matrix D after the dual deep learning network constraint obtained in step 1, and set the disparity value corresponding to the invalid area (the area where BW3(i,j)=0) to an invalid value, thereby effectively removing most of the noise interference caused by deep sea water or distant dark areas.

[0082] Since the segmentation based on the threshold method and morphological operation is not in the disparity matrix, the segmentation result is mapped to the disparity matrix, and the disparity values ​​of the invalid areas in the segmented area are all set to invalid values. The specific mapping formula is as follows:

[0083]

[0084] By combining the disparity matrix D that finally removes the interference of pure seawater area NoWater The final 3D terrain point cloud (the point cloud is formed by 3D reconstruction of the disparity matrix) can be obtained by combining the internal parameters of the camera. By stitching the point clouds restored from multiple frames of images, the deep-sea 3D terrain map without the interference of pure seawater areas can be restored. Similarly, the segmented area can be mapped into the image to obtain an image without the seawater area.

[0085] In addition, it should be noted that in the solution of the present invention, step 1 does not require the use of two different deep learning networks to constrain the images captured by the binocular camera. Instead, the original disparity matrix is ​​obtained through a single deep learning network. After using the threshold method and morphological operations in the Lab color space, BW3 is directly mapped to the original disparity matrix, which can also achieve better results.

[0086] In order to better understand the solution of the present invention, the advantages of this solution are described in detail below using a practical application case as an example:

[0087] Example 1: Using Lab color space thresholding and morphological operations to remove seawater from a deep-sea hydrothermal vent image:

[0088] Step 1: Dynamic threshold preparatory work: Count the pixel values ​​of Lab space of deep sea pictures taken at the same time. This embodiment counts the sea water area of ​​25 pictures and obtains (μ 海水统计 +2σ 海水统计 ) is about 35. At the same time, the L channel of 12 deep-sea images of different scenes taken during the same period was statistically analyzed, and (μ 全图统计 -1.28σ 全图统计 ) is approximately 9.55.

[0089] Taking W1 as 0.7, we can calculate that W2 is about 1.1, so

[0090] Step 2: Take the left camera image and convert it to Lab color space for segmentation using the threshold method. In this example, the values ​​are:

[0091]

[0092] Pick As the initial effective area.

[0093] Step 3: Perform morphological operations of dilation, hole filling, and erosion on the initial valid area BW. In this example, the disk radius of B1 in the dilation operation is 5, and the disk radius of B2 in the erosion operation is 5, to obtain the final valid area BW3 after segmentation.

[0094] Step 4: Map the final valid area to the image and disparity matrix to obtain the image and point cloud with the seawater area removed. The final result is as follows: Figure 4 、 Figure 5 shown.

[0095] Example 2: 3D terrain reconstruction using a binocular camera in the Haima cold spring area:

[0096] Preparatory work: Complete underwater system calibration, distortion correction, and stereo calibration of the deep-sea binocular camera. Obtain the camera's internal parameters and the corrected left and right images to improve the accuracy of 3D reconstruction.

[0097] Step 1: Pass the left and right images from the binocular camera into two deep learning networks with different architectures to obtain two different disparity matrices (based on the left camera). This example uses two public networks, MC-Stereo and RAFT-Stereo. The formula ΔD(i,j) = |D1(i,j) - D2(i,j)| is used to determine the difference in the disparity values ​​of the two disparity matrices. When ΔD(i,j) > T, the value of D1(i,j) is set to an invalid value. The marked D1 is then output as D, where T = 2.

[0098] Step 2: Take the left camera image and convert it to Lab color space for segmentation using the threshold method. In this example, the values ​​are:

[0099] M(i,j)=(0≤L(i,j)≤38)∧((-25≤a(i,j)≤0)∧(-60≤b(i,j)≤0))

[0100] Thus, pure seawater is roughly separated from the dark area, and the As the initial effective area.

[0101] Step 3: Perform morphological operations of dilation, hole filling, and erosion on the initial valid area BW in sequence. In this example, the disk radius of B1 in the dilation operation is 5, and the disk radius of B2 in the erosion operation is 5, to obtain the final valid area BW3 after segmentation.

[0102] like Figure 6 As shown, by applying BW3 directly to the left camera image, you can see that the segmented image not only removes the pure seawater area and the dark area, but also retains the cold spring bubbles, which is very necessary in the observation of cold springs.

[0103] Step 4: Set the disparity values ​​of the invalid areas in the segmented area to invalid values, and stitch the point clouds restored from multiple frames to restore the deep sea 3D topographic map without the interference of pure sea water areas. Figure 7 As shown in the figure, the topographic map after removing the interference of seawater is shown in the figure. Figure 8 shown.

[0104] The above description is merely a preferred embodiment of the present invention and does not constitute any other form of limitation to the present invention. Any person skilled in the art may utilize the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes for application in other fields. However, any simple modification, equivalent change, and modification of the above embodiments made in accordance with the technical essence of the present invention without departing from the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A method for removing water interference for deep-sea binocular camera terrain reconstruction, characterized in that: The following steps are involved: Step A: Use two different deep learning networks to constrain the images collected by the binocular camera and output the disparity matrix D constrained by the deep learning network; Step B: for the image captured by the binocular camera, use the threshold method in the Lab color space to remove the seawater area to obtain the initial effective area BW; Step B1: Convert the image captured by the binocular camera from RGB color space to Lab color space. Use the threshold method to perform preliminary constraints on the images of the L channel, a channel, and b channel. Assume that the distribution of pure seawater areas in the three channels is as follows: Step B2: Depending on different application scenarios and requirements, there are several ways to obtain the initial effective area: (1) In situations where the requirements are high, the brightness channel and the color channel are constrained, and the segmentation method that retains the effective area to the greatest extent is: (2) For applications with low requirements, the operation to remove seawater areas to the greatest extent possible is: (3) For the first two cases, since the image is more sensitive to brightness during the segmentation process, a dynamic threshold based on statistical principles is used. replace As shown below: in, Indicates the minimum threshold of the L channel, Indicates the maximum threshold of the L channel, L(i,j) represents the brightness value of the pixel in the Lab color space, a(i,j) represents the a channel value of the pixel in the Lab color space, Indicates the minimum threshold of channel a, represents the maximum threshold of the a channel, b(i,j) represents the b channel value of the pixel in the Lab color space, Indicates the minimum threshold of the b channel, Indicates the maximum threshold of the b channel, μ 海水统计 and σ 海水统计 is the mean and standard deviation of the cumulative statistical pixel values ​​of the L channel of the pure seawater area in more than ten pictures of different scenes, μ 全图 and σ 全图 is the mean and standard deviation of all pixel values ​​in the L channel of the image to be segmented, W1 and W2 are weights, k is a coefficient, M is the binary mask of the segmented seawater area, M(i, j) is the element in the binary mask of the segmented seawater area, and the initial valid area is the opposite part, which is expressed as: Where BW is the initial valid area, and BW(i,j) is the element in the initial valid area; Step C: perform dilation, hole filling, and erosion morphological operations on the initial valid area BW in sequence to obtain the final valid area BW3 and the invalid area; Step D: Map the final valid area BW3 to the constrained disparity matrix D obtained in step A, and set the disparity values ​​corresponding to the invalid areas to invalid values, thereby removing water interference; The specific mapping formula is: Among them, D NoWater The disparity matrix D is the final one that removes the interference of pure seawater area. NoWater (i, j) is the final disparity value after removing the interference of the pure seawater area, D(i, j) is the disparity value constrained by the dual deep learning network, and BW3(i, j) is the element in the final effective area. Combined with the internal parameters of the camera, the final 3D terrain point cloud is obtained. The point cloud restored by multiple frames of images is stitched together to restore the deep-sea 3D terrain map without the interference of the pure seawater area. Similarly, the segmented area can be mapped to the image to obtain an image with the seawater area removed.

2. The method for removing water interference for deep-sea binocular camera terrain reconstruction according to claim 1, characterized in that: The step C is specifically implemented in the following manner: (1) First, the initial effective area is expanded, and the mathematical description is as follows: BW1=BW⊕B1 Among them, BW1 is the area after the dilation operation, and B1 is the structural element; (2) Then fill the holes in the area after the dilation operation. If the captured target contains holes, skip this step and assume that the output after filling the holes in the BW1 area is BW2; (3) Finally, the output after filling the holes is corroded to restore the image to its original size before expansion: Among them, BW3 is the final valid area after the corrosion operation, BW2 is the area after the hole filling operation, and B2 is the structural element.

3. The method for removing water interference for deep-sea binocular camera terrain reconstruction according to claim 1, characterized in that: The step A is specifically implemented in the following manner: Assume that D1 and D2 are the disparity matrices generated by two deep learning networks based on the same pair of binocular camera stereo images, then their disparity difference ΔD(i,j) is expressed as follows; ΔD(i,j)=|D1(i,j)-D2(i,j)| If ΔD(i,j)>T, mark D1(i,j) and D2(i,j) as invalid values Where T is a fixed threshold, D1(i, j) and D2(i, j) are the disparity values ​​generated by the two deep learning networks at the image pixel point (i, j), and either of the marked D1 or D2 is used as the disparity matrix D constrained by the dual deep learning network.

4. The method for removing water interference for deep-sea binocular camera terrain reconstruction according to claim 1, characterized in that: In step A, the original disparity matrix is ​​obtained through a single deep learning network to replace the constrained disparity matrix. After the threshold method and morphological operation of the Lab color space, BW3 is directly mapped to the original disparity matrix to also achieve the removal of water interference.

Images