AUV (Autonomous Underwater Vehicle) underwater dynamic docking visual positioning method using vector line light source

Abstract

The invention relates to the technical field of underwater docking, and discloses an AUV (Autonomous Underwater Vehicle) underwater dynamic docking visual positioning method using a vector line light source, which comprises the following steps: constructing a visual marker consisting of the vector line light source consisting of four groups of lasers with changeable emission angles; obtaining the relative distance between the docking AUV and the target AUV, determining an emission angle adjustment rule based on the relative distance, and adjusting the emission angles of the four groups of lasers according to the rule; acquiring a reference image of the vector line light source by using a camera carried by the docking AUV, and performing adaptive enhancement on the reference image by taking a relative distance as an adaptive condition; performing information completion on the enhanced image, and extracting key points from the enhanced image after information completion; and carrying out relative position and attitude calculation on the extracted key points by using a PNP algorithm to obtain a final result of underwater visual positioning. According to the method, the underwater dynamic docking visual positioning precision is improved, and the docking dynamics and the fault-tolerant rate are improved in dynamic docking.

Description

Technical Field

[0001] Embodiments of the present application relate to the technical field of underwater docking, and particularly to an AUV underwater dynamic docking vision positioning method using a vector line light source. Background Art

[0002] With the gradual increase in the demand for ocean exploration by humans, rapid exploration and long-time navigation have become research hotspots. Autonomous Underwater Vehicles (AUVs) have gradually become important devices for ocean exploration and safeguarding marine rights and interests. In the latest research, significant breakthroughs have been made in terms of speed, depth, and autonomy of single-body small AUVs. However, their prominent drawbacks still exist, namely limited detection range, relatively short voyage, and difficulty in real-time data transmission for detecting a wider area.

[0003] To improve the performance of AUVs, the currently common solution is to use an underwater dock or a surface mother ship for static docking and recovery of AUVs. After docking, battery charging and detection data transmission are carried out. The key problem in this process is how to obtain the underwater relative position information between the AUV and the docking station. The traditional method is to use a point light source matrix as a marker, use a camera to obtain images, and obtain the position information after image processing. The point light source matrix has a small afterimage and high brightness in the static state, and has a good performance effect in the docking recognition process.

[0004] Static docking requires a fixed docking station, and additional time is required for both recovery and redeployment. How to achieve the effect similar to an air refueling tanker when the AUV is in operation is a research direction worthy of in-depth study. Without changing its own motion state, dynamic docking can be achieved by a large AUV to realize energy and data transmission. This technology is called dynamic docking. Dynamic docking is more complex than static docking. How to obtain the position of the AUV in the motion state is the key. The point light source marker used in static docking will have a large afterimage in actual use, which leads to a significant decrease in recognition accuracy and even positioning failure. That is to say, the point light source marker can meet the requirements of static docking, but in dynamic docking, both the target AUV and the docking AUV are in a moving state, and the point light source marker cannot play a role. In mechanical design, when the point light source marker is set on the AUV, a larger tail needs to be designed, which increases the resistance of the AUV itself, consumes more energy, and reduces the energy use efficiency in actual use. Summary of the Invention

[0005] To solve the above technical problems, an embodiment of the present application proposes an AUV underwater dynamic docking vision positioning method using a vector line light source. By using the vector line light source, the perception range is increased, the accuracy of the positioning result can be improved in static docking, and the dynamics and fault tolerance of docking can be improved in dynamic docking.

[0006] To achieve the above object, an embodiment of the present application proposes an AUV underwater dynamic docking vision positioning method, including the following steps: constructing a visual marker composed of vector line light sources, where the vector line light source is composed of four groups of lasers with changeable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servos inside the target AUV housing and form a rhombus. The emission angle of the lasers can be changed by changing the angle of the servos; obtaining the relative distance between the docking AUV and the target AUV, determining the emission angle adjustment rule based on the relative distance, and adjusting the emission angles of the four groups of lasers according to the determined emission angle adjustment rule; using the camera carried by the docking AUV itself to obtain the reference image of the vector line light source, and adaptively enhancing the reference image with the relative distance as the adaptive condition to obtain an enhanced image; complementing the information of the enhanced image to make up for the dead zone existing in the docking process and the missing key points caused by occlusion, and extracting the key points from the enhanced image after information complementation; using the PNP algorithm to solve the relative position and attitude of the extracted key points to obtain the final result of underwater vision positioning.

[0007] To achieve the above object, an embodiment of the present application further provides an AUV underwater dynamic docking vision positioning system using a vector line light source. The system includes: a vision marker construction module, a transmission angle adjustment module, an image acquisition and enhancement module, an information completion module, and a solution positioning execution module; the vision marker construction module is used to construct a vision marker composed of vector line light sources. The vector line light source is composed of four groups of lasers with adjustable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servos inside the target AUV housing. The four groups of lasers form a rhombus, and the emission angle of the lasers can be changed by changing the angle of the servos; the transmission angle adjustment module is used to obtain the relative distance between the docking AUV and the target AUV, determine the transmission angle adjustment rule based on the relative distance, and adjust the emission angles of the four groups of lasers according to the determined transmission angle adjustment rule; the image acquisition and enhancement module is used to use the camera carried by the docking AUV itself to acquire the reference image of the vector line light source, and perform adaptive enhancement on the reference image with the relative distance between the docking AUV and the target AUV as the adaptive condition to obtain an enhanced image; the information completion module is used to complete the information of the enhanced image, make up for the dead zone existing in the docking process and the missing key points caused by occlusion, and extract the key points from the enhanced image after information completion; the solution positioning execution module is used to perform relative position and attitude solution on the extracted key points using the PNP algorithm to obtain the final result of underwater vision positioning.

[0008] To achieve the above object, an embodiment of the present application further provides an electronic device. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute an AUV underwater dynamic docking vision positioning method using a vector line light source as described above.

[0009] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, which when executed by a processor, can implement an AUV underwater dynamic docking vision positioning method using a vector line light source as described above.

[0010] An AUV underwater dynamic docking vision positioning method using a vector line light source proposed in an embodiment of the present application constructs a vision marker composed of vector line light sources considering the highly linear characteristics of lasers underwater. The vector line light source consists of four groups of lasers with variable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servos inside the target AUV housing and form a rhombus. By changing the angles of the servos, the emission angles of the lasers can be changed. Such a vision marker can reduce the resistance of the docking AUV itself, improve the energy utilization rate, and increase the voyage of the docking AUV. The linear laser contains more information than the point light source. When some parts of the linear laser are missing in visual perception, limited information can still be used for completion, that is, using some pixel points to predict the line of the laser. During the docking process, the adjustment of the emission angle of the laser adopts a combined adjustment method of discrete and continuous to meet the requirements of detection range and detection accuracy. In addition, considering that the vector line light source has a concentrated and relatively small brightness compared to the point light source marker, the present application designs an adaptive enhancement of the image with relative distance as the adaptive condition to make up for the deficiencies of the line light source compared to the point light source. Such a vision positioning method is suitable for complex docking tasks, can improve the accuracy of the positioning result in static docking, and improve the dynamics and fault tolerance rate of docking in dynamic docking.

[0011] Optionally, constructing a vision marker composed of vector line light sources includes: fixing the bottom of the servo and installing a green laser emission device on the top, and changing the angle of the green laser emission device by changing the angle of the servo itself, so as to form four groups of lasers with variable emission angles; forming a rhombus with variable area by the four groups of lasers with variable emission angles, and using the rhombus with variable area as the vision marker, and the area of the vision marker changes with the change of the emission angles of the four groups of lasers; among them, the servos are divided into two groups and fixed at the upper and lower vertices of the rhombus, with the center point of the rhombus as the origin, and there is a vector line light source in each of the four quadrants.

[0012] Optionally, determine the emission angle adjustment rule based on the relative distance, and adjust the emission angles of the four groups of lasers according to the determined emission angle adjustment rule, including: judging whether the relative distance is greater than a first preset threshold; if the relative distance is greater than or equal to the first preset threshold, classify the relative distance as medium and long distance, and adopt a segmented emission angle adjustment rule to adjust the emission angles of the four groups of lasers. Among them, when the relative distance is greater than or equal to a second preset threshold, adjust the emission angles of the four groups of lasers to 60 degrees, and when the relative distance is less than the second preset threshold, adjust the emission angles of the four groups of lasers to 45 degrees; where the second preset threshold is greater than the first preset threshold; if the relative distance is less than the first preset threshold, classify the relative distance as short distance, and adopt a continuous emission angle adjustment rule to adjust the emission angles of the four groups of lasers. The emission angle adjustment range of the continuous emission angle adjustment rule is from 10 degrees to 30 degrees, and the adjustment step size is 1 degree. For medium and long distances, the real-time requirement of visual positioning is greater than the accuracy requirement, so a segmented emission angle adjustment rule is adopted. For short distances, the accuracy of visual positioning is the most important, so a continuous emission angle adjustment rule is adopted.

[0013] Optionally, the adaptive enhancement of the reference image with the relative distance as the adaptive condition to obtain the enhanced image includes: based on the MSRCR image enhancement algorithm, taking the relative distance as the adaptive condition, constructing an adaptive MSRCR image enhancement algorithm. In the adaptive MSRCR image enhancement algorithm, different relative distances correspond to different gain values, and the magnitude of the gain value is directly proportional to the magnitude of the relative distance; using the adaptive MSRCR image enhancement algorithm, based on the relative distance, perform adaptive enhancement on the reference image to obtain the enhanced image. The MSRCR image enhancement algorithm can achieve enhanced processing of specific colors and can well achieve enhanced processing of underwater green lasers. Transforming the MSRCR image enhancement algorithm into an adaptive MSRCR image enhancement algorithm with the relative distance as the adaptive condition can better improve the enhancement effect.

[0014] Optionally, the information completion of the enhanced image to make up for the dead zone existing in the docking process and the missing key points caused by occlusion, and extract the key points from the enhanced image after information completion, including: using the combination method of layer and least squares to perform linear fitting on the known pixel points in the enhanced image to obtain the line after information completion; based on the line after information completion, perform expansion of the image space to find the intersection points of the four groups of lasers, and take the intersection points of the four groups of lasers as the key points of visual perception.

[0015] Optionally, the known pixel points in the enhanced image are linearly fitted using the layer and least squares combination method, including: performing preprocessing operations on the enhanced image, including underwater marker feature fusion, Gaussian filtering, and adaptive threshold segmentation, to obtain the preprocessed enhanced image; performing improved Caddy edge detection on the preprocessed enhanced image to obtain edge detection points; linearly fitting the edge detection points using the layer and least squares combination method to complete the linear information and angle information, obtaining a line with completed information; expanding the image space based on the line with completed information to find the intersection points of four groups of lasers, and using the intersection points of the four groups of lasers as the key points for visual perception, including: extending the line with completed information using the unidirectional linearity of the line to find the four intersection points of the four groups of lasers, and using the Bayesian estimation algorithm to estimate the accuracy rate of the intersection points; if the accuracy rate of the intersection points is greater than the preset accuracy rate threshold, then using the intersection points as the key points for visual perception; if the accuracy rate of the intersection points is less than or equal to the preset accuracy rate threshold, then discarding the current reference image. Estimating the accuracy rate of the intersection points and only retaining the intersection points greater than the preset accuracy rate threshold as key points can improve the accuracy and scientific nature of the key points, thereby better improving the accuracy of visual positioning and docking.

[0016] Optionally, the PNP algorithm is used to calculate the relative position and attitude of the extracted key points to obtain the final result of underwater visual positioning, including: based on the position coordinates of the key points in the completed enhanced image and the actual position coordinates of the visual markers, using the PNP algorithm to calculate the relative position and attitude to obtain the final result of underwater visual positioning. The PNP algorithm is used to obtain the position matrix and rotation matrix. Using the PNP algorithm can quickly and accurately calculate the final result of underwater visual positioning, thereby providing a standard and basis for subsequent underwater dynamic docking. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the following will briefly introduce the drawings required to be used in the description of the embodiments of the present application or the related art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 is a flowchart of an AUV underwater dynamic docking visual positioning method using a vector line light source provided in an embodiment of the present application;

[0019] Figure 2 is a design schematic diagram of a vector line light source provided in an embodiment of the present application;

[0020] Figure 3It is a schematic diagram for determining the emission angle adjustment rule provided in an embodiment of the present application;

[0021] Figure 4 It is a flowchart of image enhancement, information completion, and relative position and attitude calculation provided in an embodiment of the present application;

[0022] Figure 5 It is a schematic structural diagram of an AUV underwater dynamic docking vision positioning system using a vector line light source provided in another embodiment of the present application;

[0023] Figure 6 It is a schematic structural diagram of an electronic device provided in another embodiment of the present application. Detailed implementation manners

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will elaborate on each embodiment of the present application with reference to the accompanying drawings. However, those of ordinary skill in the art can understand that in each embodiment of the present application, many technical details are provided for readers to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solutions claimed in the present application can still be implemented. The following division of each embodiment is for convenience of description and should not constitute any limitation to the specific implementation manner of the present application. Each embodiment can be combined and cross-referenced with each other on the premise of not conflicting.

[0025] An embodiment of the present application proposes an AUV underwater dynamic docking vision positioning method using a vector line light source, which is applied to an electronic device. The following specifically describes the implementation details of an AUV underwater dynamic docking vision positioning method using a vector line light source proposed in this embodiment. The following content is only implementation details provided for convenient understanding and is not necessary for implementing this solution.

[0026] The specific process of an AUV underwater dynamic docking vision positioning method using a vector line light source proposed in this embodiment can be as Figure 1 shown and includes:

[0027] Step 101: Construct a visual marker composed of vector line light sources. The vector line light source consists of four groups of lasers with changeable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servo motors inside the target AUV housing and form a rhombus. By changing the angles of the servo motors, the emission angles of the lasers can be changed.

[0028] In a specific implementation, the prerequisite for realizing underwater dynamic docking visual positioning is to construct and deploy visual markers in the target AUV. The visual markers are composed of vector line light sources, and the vector line light sources are composed of four groups of lasers with variable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servos inside the target AUV housing and form a rhombus. By changing the angles of the servos, the emission angles of the lasers can be changed.

[0029] In one example, the design principle of the vector line light source is as Figure 2 shown. Fix the bottom of the servo of the target AUV and install a green laser emission device on the top. By changing the angle of the servo itself, the angle change of the green laser emission device can be realized, thus forming four groups of lasers with variable emission angles. Through position design, the four groups of lasers with variable emission angles are combined into a rhombus with variable area, and the rhombus with variable area is used as the visual marker. The area of the visual marker (the area of the rhombus) changes with the change of the emission angles of the four groups of lasers. Among them, the servos are divided into two groups and fixed at the upper and lower vertices of the rhombus. Taking the center point of the rhombus as the origin, there is a vector line light source in each of the four quadrants.

[0030] Step 102, obtain the relative distance between the docking AUV and the target AUV, determine the emission angle adjustment rule based on the relative distance, and adjust the emission angles of the four groups of lasers according to the determined emission angle adjustment rule.

[0031] In a specific implementation, when there is a docking requirement, the target AUV will obtain the relative distance between itself and the docking AUV, determine the emission angle adjustment rule based on the relative distance, and adjust the emission angles of the four groups of lasers according to the determined emission angle adjustment rule, thereby adjusting the visual marker.

[0032] In one example, the determination process of the emission angle adjustment rule can be as Figure 3 shown. The target AUV determines whether the relative distance between itself and the docking AUV is greater than the first preset threshold, and the specific value of the first preset threshold can be set by those skilled in the art according to actual needs.

[0033] If the detected relative distance is greater than or equal to the first preset threshold, the relative distance can be classified as a medium-to-long distance. At this time, the emission angles of the four groups of lasers are adjusted using a segmented emission angle adjustment rule. The medium-to-long distance also needs to be further divided based on the second preset threshold. When the relative distance is greater than or equal to the second preset threshold, the relative distance is classified as a long distance, and at this time, the emission angles of the four groups of lasers are adjusted to 60 degrees. When the relative distance is less than the second preset threshold, the relative distance is classified as a medium distance, and at this time, the emission angles of the four groups of lasers are adjusted to 45 degrees. It should be noted that the second preset threshold is greater than the first preset threshold, and the specific value of the first preset threshold can be set by those skilled in the art according to actual needs.

[0034] If the detected relative distance is less than the first preset threshold, the relative distance can be classified as a short distance. At this time, the emission angles of the four groups of lasers are adjusted using a continuous emission angle adjustment rule. The emission angle adjustment range of the continuous emission angle adjustment rule is from 10 degrees to 30 degrees, and the adjustment step size is 1 degree. That is, the emission angles of the four groups of lasers are gradually adjusted from 30 degrees to 10 degrees at an adjustment step size of 1 degree.

[0035] It can be understood that for medium-to-long distances, the real-time requirement of visual positioning is much greater than the accuracy requirement. Therefore, a segmented emission angle adjustment rule is adopted. For short distances, the accuracy of visual positioning is the most important. Therefore, a continuous emission angle adjustment rule is adopted.

[0036] Step 103: Use the camera carried by the docking AUV to obtain the reference image of the vector line light source, and perform adaptive enhancement on the reference image with the relative distance as the adaptive condition to obtain the enhanced image.

[0037] In specific implementation, when there is a docking requirement, the docking AUV will use the camera carried by itself to obtain the reference image of the vector line light source, and then perform adaptive enhancement on the reference image with the relative distance as the adaptive condition to obtain the enhanced image. Underwater imaging is restricted by the environment, and the quality of the imaging result is limited. Performing image enhancement can well improve the accuracy of visual positioning.

[0038] In one example, the docking AUV is based on the MSRCR image enhancement algorithm and uses the relative distance as the adaptive condition to construct an adaptive MSRCR image enhancement algorithm. In the adaptive MSRCR image enhancement algorithm, different relative distances correspond to different gain values, and the magnitude of the gain value is directly proportional to the magnitude of the relative distance. The farther the relative distance, the greater the gain value. The docking AUV uses the adaptive MSRCR image enhancement algorithm to adaptively enhance the reference image based on the relative distance to obtain an enhanced image. The MSRCR image enhancement algorithm can achieve the enhancement processing of specific colors and can well achieve the enhancement processing of underwater green lasers. Transforming the MSRCR image enhancement algorithm into an adaptive MSRCR image enhancement algorithm with the relative distance as the adaptive condition can better improve the enhancement effect.

[0039] Step 104: Complement the information of the enhanced image to make up for the dead zones existing in the docking process and the missing key points caused by occlusion, and extract the key points from the enhanced image after information complementation.

[0040] In a specific implementation, after obtaining the enhanced image, the docking AUV needs to complement the information of the enhanced image to make up for the dead zones existing in the docking process and the missing key points caused by occlusion, and extract the key points from the enhanced image after information complementation.

[0041] In one example, the information complementation process can be as Figure 4 shown. The docking AUV uses the layer and least squares combination method to perform linear fitting on the known pixel points in the enhanced image to obtain a line after information complementation. Subsequently, based on the line after information complementation, the image space is expanded to find the intersection points of four groups of lasers, and the intersection points of the four groups of lasers are used as the key points for visual perception.

[0042] In one example, before performing linear fitting, the docking AUV needs to perform preprocessing operations on the enhanced image, including underwater marker feature fusion, Gaussian filtering, and adaptive threshold segmentation, to obtain a preprocessed enhanced image. Subsequently, improved Caddy edge detection is performed on the preprocessed enhanced image to obtain edge detection points. Finally, the layer and least squares combination method is used to perform linear fitting on the edge detection points to complement the linear information and angular information and obtain a line after information complementation.

[0043] In one example, when the docking AUV extracts key points, it extends the line after information completion using the unidirectional linearity of the line, so as to find the four intersection points (cross points) of the four groups of lasers. At the same time, the Bayesian estimation algorithm is used to estimate the accuracy rate of the intersection points. If the accuracy rate of the intersection points is greater than the preset accuracy rate threshold (which can generally be set to 0.9, and the intersection points with an accuracy rate greater than 0.9 are considered reliable), then the four intersection points are used as the key points for visual perception. If the accuracy rate of the intersection points is less than or equal to the preset accuracy rate threshold, the reference image of the current frame needs to be discarded, and the reference image of the next frame is used to perform image enhancement, information completion, and key point extraction again.

[0044] Step 105: Use the PNP algorithm to calculate the relative position and attitude of the extracted key points to obtain the final result of underwater visual positioning.

[0045] In a specific implementation, after the docking AUV extracts the key points, it can use the PNP algorithm to calculate the relative position and attitude of the extracted key points to obtain the final result of underwater visual positioning.

[0046] In one example, the PNP algorithm is used to obtain the position matrix and rotation matrix. Based on the position coordinates of the key points in the enhanced image after completion and the actual position coordinates of the visual markers, the docking AUV uses the PNP algorithm to calculate the relative position and attitude, and can quickly and accurately calculate the final result of underwater visual positioning, thus providing a standard and basis for subsequent underwater dynamic docking.

[0047] An AUV underwater dynamic docking vision positioning method using a vector line light source proposed in this embodiment constructs a vision marker composed of vector line light sources considering the highly linear characteristics of lasers underwater. The vector line light source consists of four groups of lasers with variable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servos inside the target AUV hull and form a rhombus. By changing the angles of the servos, the emission angles of the lasers can be changed. Such a vision marker can reduce the resistance of the docking AUV itself, improve the energy utilization rate, and increase the voyage of the docking AUV. Linear lasers contain more information than point light sources. When some parts of the linear lasers are missing in visual perception, limited information can still be used to complete them, that is, to predict the line of the laser using some pixel points. During the docking process, the adjustment of the emission angle of the laser adopts a combined adjustment method of discrete and continuous to meet the requirements of detection range and detection accuracy. In addition, considering that the vector line light source has a concentrated and relatively small brightness compared to the point light source marker, this application designs an adaptive enhancement of the image with relative distance as the adaptive condition to make up for the deficiencies of the line light source compared to the point light source. Such a vision positioning method is suitable for complex docking tasks and can improve the accuracy of the positioning result in static docking and the dynamics and fault tolerance of docking in dynamic docking.

[0048] The step division of the above various methods is only for clear description. When implemented, they can be combined into one step, or some steps can be split into multiple steps. As long as the same logical relationship is included, it is within the protection scope of this application; adding insignificant modifications to the algorithm or process or introducing insignificant designs, but not changing the core design of its algorithm and process, are within the protection scope of this application.

[0049] Another embodiment of this application proposes an AUV underwater dynamic docking vision positioning system using a vector line light source. The implementation details of an AUV underwater dynamic docking vision positioning system using a vector line light source proposed in this embodiment will be specifically described below. The following content is only implementation details provided for easy understanding and is not necessary for implementing this solution. The specific structure of an AUV underwater dynamic docking vision positioning system using a vector line light source proposed in this embodiment can be as Figure 5 shown, including: a vision marker construction module 201, an emission angle adjustment module 202, an image acquisition and enhancement module 203, an information completion module 204, and a solution and positioning execution module 204.

[0050] The vision marker construction module 201 is used to construct a vision marker composed of vector line light sources. The vector line light source consists of four groups of lasers with variable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servos inside the target AUV hull, and the four groups of lasers form a rhombus. By changing the angles of the servos, the emission angles of the lasers can be changed.

[0051] The emission angle adjustment module 202 is configured to obtain the relative distance between the docking AUV and the target AUV, determine the emission angle adjustment rule based on the relative distance, and adjust the emission angles of the four groups of lasers according to the determined emission angle adjustment rule.

[0052] The image acquisition and enhancement module 203 is configured to use the camera carried by the docking AUV itself to acquire the reference image of the vector line light source, and perform adaptive enhancement on the reference image with the relative distance between the docking AUV and the target AUV as the adaptive condition to obtain the enhanced image.

[0053] The information completion module 204 is configured to complete the information of the enhanced image, make up for the dead zone existing in the docking process and the missing key points caused by occlusion, and extract the key points from the enhanced image after information completion.

[0054] The solution positioning execution module 205 is configured to use the PNP algorithm to perform relative position and attitude solution on the extracted key points to obtain the final result of underwater vision positioning.

[0055] It should be noted that each module and module group involved in this embodiment are all logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or can be implemented by a combination of multiple physical units. In addition, in order to highlight the innovative part of this application, units not closely related to solving the technical problems proposed in this application are not introduced in this embodiment, but this does not mean that there are no other units in this embodiment.

[0056] It is not difficult to find that this embodiment is a system embodiment corresponding to the above method embodiment, and this embodiment can be implemented in cooperation with the above method embodiment. The relevant technical details and technical effects mentioned in the above method embodiment are still valid in this embodiment. To avoid repetition, they are not elaborated here. Correspondingly, the relevant technical details mentioned in this embodiment can also be applied to the above method embodiment.

[0057] Another embodiment of the present application proposes an electronic device, as Figure 6 shown, including: at least one processor 301; and a memory 302 communicatively connected to the at least one processor 301; wherein, the memory 302 stores instructions executable by the at least one processor 301, and the instructions are executed by the at least one processor 301 so that the at least one processor 301 can execute a method for AUV underwater dynamic docking vision positioning using a vector line light source as described in the above method embodiment.

[0058] Among them, the memory and the processor are connected in a bus manner. The bus can include any number of interconnected buses and bridges, which connect various circuits of one or more processors and the memory together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, etc., which are well known in the art, so they will not be further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on the transmission medium.

[0059] The processor is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. The memory can be used to store data used by the processor when executing operations.

[0060] Another embodiment of the present application proposes a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it can implement a method for underwater dynamic docking vision positioning of an AUV using a vector line light source as described in the above method embodiment.

[0061] That is, those skilled in the art can understand that all or part of the steps in implementing the above embodiment methods can be completed by instructing relevant hardware through a program. This program is stored in a storage medium, including several instructions to enable a device (such as a single-chip microcomputer, chip) or a processor to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, or optical discs, etc., which can store program codes.

[0062] Those of ordinary skill in the art can understand that the above embodiments are all specific embodiments for implementing the technical solutions of the present application, and in practical applications, various changes can be made in form and details without departing from the spirit and scope of the present application.

Claims

1. An AUV underwater dynamic docking vision positioning method using a vector line light source, characterized in that The method includes: Construct a visual marker composed of vector line light sources. The vector line light sources are composed of four groups of lasers with variable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servos inside the target AUV housing and form a rhombus. By changing the angles of the servos, the emission angles of the lasers can be changed; Obtain the relative distance between the docking AUV and the target AUV, determine the emission angle adjustment rule based on the relative distance, and adjust the emission angles of the four groups of lasers according to the determined emission angle adjustment rule; Use the camera carried by the docking AUV itself to obtain the reference image of the vector line light source, and perform adaptive enhancement on the reference image with the relative distance as the adaptive condition to obtain the enhanced image; Perform information completion on the enhanced image to make up for the dead zone existing in the docking process and the missing key points caused by occlusion, and extract the key points from the enhanced image after information completion; Use the PNP algorithm to calculate the relative position and attitude of the extracted key points to obtain the final result of underwater visual positioning.

2. A method for visual positioning of AUV underwater dynamic docking using a vector line light source according to claim 1, characterized in that, Construct a visual marker composed of vector line light sources, including: Fix the bottom of the servo and install a green laser emission device on the top. By changing the angle of the servo itself, the angle change of the green laser emission device can be realized, thereby forming four groups of lasers with variable emission angles; Form a rhombus with variable area by the four groups of lasers with variable emission angles, and use the rhombus with variable area as the visual marker. The area of the visual marker changes with the change of the emission angles of the four groups of lasers; among them, the servos are divided into two groups and fixed at the upper and lower vertices of the rhombus. Taking the center point of the rhombus as the origin, there is a vector line light source in each of the four quadrants.

3. A method for underwater dynamic docking vision positioning of an AUV using a vector line light source according to claim 1, characterized in that, Determine the emission angle adjustment rule based on the relative distance, and adjust the emission angles of the four groups of lasers according to the determined emission angle adjustment rule, including: Judge whether the relative distance is greater than the first preset threshold; If the relative distance is greater than or equal to the first preset threshold, classify the relative distance as medium and long distance, and use a segmented emission angle adjustment rule to adjust the emission angles of the four groups of lasers. Among them, when the relative distance is greater than or equal to the second preset threshold, adjust the emission angles of the four groups of lasers to 60 degrees, and when the relative distance is less than the second preset threshold, adjust the emission angles of the four groups of lasers to 45 degrees; among them, the second preset threshold is greater than the first preset threshold; If the relative distance is less than the first preset threshold, classify the relative distance as short distance, and use a continuous emission angle adjustment rule to adjust the emission angles of the four groups of lasers. The emission angle adjustment range of the continuous emission angle adjustment rule is 10 degrees to 30 degrees, and the adjustment step is 1 degree.

4. A method for underwater dynamic docking vision positioning of an AUV using a vector line light source according to claim 3, characterized in that Perform adaptive enhancement on the reference image with the relative distance as the adaptive condition to obtain the enhanced image, including: Based on the MSRCR image enhancement algorithm, with the relative distance as the adaptive condition, construct an adaptive MSRCR image enhancement algorithm. In the adaptive MSRCR image enhancement algorithm, different relative distances correspond to different gain values, and the size of the gain value is directly proportional to the size of the relative distance; Using the adaptive MSRCR image enhancement algorithm, based on the relative distance, adaptively enhance the reference image to obtain the enhanced image.

5. A method for underwater dynamic docking vision positioning of an AUV using a vector line light source according to claim 4, characterized in that, Perform information completion on the enhanced image to make up for the dead zones existing in the docking process and the missing key points caused by occlusion, and extract key points from the enhanced image after information completion, including: Use the combination method of layer and least squares to perform linear fitting on the known pixel points in the enhanced image to obtain the line after information completion; Based on the line after information completion, expand the image space, find the intersection points of the four groups of lasers, and use the intersection points of the four groups of lasers as the key points for visual perception.

6. A method for underwater dynamic docking vision positioning of an AUV using a vector line light source according to claim 5, characterized in that, Use the combination method of layer and least squares to perform linear fitting on the known pixel points in the enhanced image, including: Perform preprocessing operations on the enhanced image, including underwater marker feature fusion, Gaussian filtering, and adaptive threshold segmentation, to obtain the preprocessed enhanced image; Perform improved Caddy edge detection on the preprocessed enhanced image to obtain edge detection points; Use the combination method of layer and least squares to perform linear fitting on the edge detection points to complete the linear information and angular information, and obtain the line after information completion; Based on the line after information completion, expand the image space, find the intersection points of the four groups of lasers, and use the intersection points of the four groups of lasers as the key points for visual perception, including: Use the unidirectional linearity of the line to extend the line after information completion, so as to find the four intersection points of the four groups of lasers, and use the Bayesian estimation algorithm to estimate the accuracy rate of the intersection points; If the accuracy rate of the intersection points is greater than the preset accuracy rate threshold, then use the intersection points as the key points for visual perception; If the accuracy rate of the intersection points is less than or equal to the preset accuracy rate threshold, then discard the current reference image.

7. A method for visual positioning of AUV underwater dynamic docking using a vector line light source according to claim 6, characterized in that, Use the PNP algorithm to perform relative position and attitude calculation on the extracted key points to obtain the final result of underwater visual positioning, including: Based on the position coordinates of the key points in the enhanced image after completion and the actual position coordinates of the visual marker, use the PNP algorithm to perform relative position and attitude calculation to obtain the final result of underwater visual positioning.

8. An AUV underwater dynamic docking vision positioning system using a vector line light source, characterized in that, The system includes: a visual marker construction module, a transmission angle adjustment module, an image acquisition and enhancement module, an information completion module, and a calculation and positioning execution module; The visual marker construction module is used to construct a visual marker composed of vector line light sources. The vector line light sources are composed of four groups of lasers with adjustable emission angles. The four groups of lasers are fixed on a rotating mechanism composed of servos inside the target AUV housing. The four groups of lasers form a rhombus, and the emission angle of the lasers can be changed by changing the angle of the servos; The transmission angle adjustment module is used to obtain the relative distance between the docking AUV and the target AUV, determine the transmission angle adjustment rule based on the relative distance, and adjust the emission angles of the four groups of lasers according to the determined transmission angle adjustment rule; The image acquisition and enhancement module is used to use the camera carried by the docking AUV itself to acquire the reference image of the vector line light source, and adaptively enhance the reference image with the relative distance between the docking AUV and the target AUV as the adaptive condition to obtain the enhanced image; An information completion module, which is used to complete the information of the enhanced image, make up for the dead zone existing in the docking process and the missing key points caused by occlusion, and extract the key points from the enhanced image after information completion; A solution positioning execution module, which is used to calculate the relative position and attitude of the extracted key points by using the PNP algorithm to obtain the final result of underwater vision positioning.

9. An electronic device, characterized in that, Comprising: At least one processor; And, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for AUV underwater dynamic docking vision positioning using a vector line light source according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it can implement a method for AUV underwater dynamic docking vision positioning using a vector line light source according to any one of claims 1 to 7.

Images