Alignment method, device, underwater vehicle and storage medium

Abstract

The present invention discloses an alignment method for an underwater vehicle, the method comprising the following steps: acquiring a target image of a target area, the target area including a luminous laser light source; extracting a region of interest corresponding to the laser light source in the target image; performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest; and controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest. The present invention also discloses an alignment device, an underwater vehicle, and a computer-readable storage medium. Using the alignment method of the present invention, the underwater vehicle has a larger range of motion.

Description

Technical Field

[0001] The present invention relates to the field of underwater positioning, and in particular to an alignment method, a device, an underwater vehicle and a computer-readable storage medium. Background Art

[0002] Underwater laser communication has the characteristics of long distance, high accuracy and good real-time performance, and dynamic precise alignment and precise tracking of the laser beam are the basic guarantee for achieving stable underwater communication.

[0003] At present, in order to achieve precise underwater alignment, the existing alignment methods usually adopt the method of placing fixed reference objects underwater, and using the positional relationship between the mobile node (such as an underwater vehicle) and the fixed reference objects to control the mobile node to achieve the alignment of the mobile node.

[0004] However, using existing alignment methods, the motion range of the mobile node is small. Summary of the invention

[0005] The main purpose of the present invention is to provide an alignment method, device, underwater vehicle and computer-readable storage medium, aiming to solve the technical problem of the existing alignment method in the prior art using the small motion range of the mobile node.

[0006] To achieve the above object, the present invention provides an alignment method for an underwater vehicle, the method comprising the following steps:

[0007] Acquire a target image of a target area, wherein the target area includes a light emitting laser light source;

[0008] Extracting a region of interest corresponding to the laser light source in the target image;

[0009] Performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest;

[0010] Based on the shape recognition result and the region of interest, the underwater vehicle is controlled to align with the laser light source.

[0011] Optionally, the step of extracting the region of interest corresponding to the laser light source in the target image includes:

[0012] Obtaining a grayscale value of the target image;

[0013] Determine an area in the target image where the grayscale value is greater than or equal to a preset grayscale threshold as an initial region of interest;

[0014] Determine a connected domain boundary in the initial region of interest;

[0015] The area within the boundary of the connected domain is determined as the region of interest.

[0016] Optionally, the step of extracting the region of interest corresponding to the laser light source in the target image includes:

[0017] Determine a growth pixel point in a light spot area corresponding to the laser light source in the target image;

[0018] The growing pixels are expanded using a preset region growing rule to obtain the region of interest.

[0019] Optionally, the step of performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest includes:

[0020] Drawing a circumscribed circle for the region of interest to obtain a reference circumscribed circle;

[0021] determining an area ratio of the area of ​​the region of interest to the area of ​​the reference circumscribed circle;

[0022] Based on the comparison result of the preset ratio and the area ratio, the shape recognition result of the region of interest is obtained.

[0023] Optionally, before the step of controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest, the method further includes:

[0024] Performing halo and background removal on the region of interest to obtain a final light spot area;

[0025] The step of controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest comprises:

[0026] Based on the shape recognition result and the final light spot area, the underwater vehicle is controlled to align with the laser light source.

[0027] Optionally, the step of controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the final light spot area includes:

[0028] When the shape recognition result is that the region of interest is circular, filtering the final light spot area to obtain a final light spot area after filtering; determining the light spot centroid in the final light spot area after filtering; determining first position information of the laser light source and the underwater vehicle based on the light spot centroid; and controlling the underwater vehicle to align with the laser light source based on the first position information; or,

[0029] When the shape recognition result is that the region of interest is strip-shaped, the final light spot area is fitted to obtain a fitted ellipse; the major axis of the fitted ellipse is determined as the centerline of the light beam; selected pixel points corresponding to the centerline of the light beam are determined in the final light spot area; and based on the grayscale values ​​of the selected pixel points, second position information of the laser light source and the underwater vehicle is determined; and based on the second position information, the underwater vehicle is controlled to align with the laser light source.

[0030] Optionally, before the step of acquiring the target image of the target area, the method further includes:

[0031] capturing real-time video of the target area;

[0032] The step of acquiring the target image of the target area comprises:

[0033] The target image satisfying a preset condition is acquired in the real-time video.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also proposes an alignment device for an underwater vehicle, the device comprising:

[0035] An acquisition module, used to acquire a target image of a target area, wherein the target area includes a light emitting laser light source;

[0036] An extraction module, used for extracting a region of interest corresponding to the laser light source in the target image;

[0037] A recognition module, used for performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest;

[0038] A control module is used to control the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest.

[0039] In addition, to achieve the above-mentioned purpose, the present invention also proposes an underwater vehicle, which includes: a memory, a processor, and an alignment program stored in the memory and running on the processor, and when the alignment program is executed by the processor, the steps of the alignment method described in any one of the above items are implemented.

[0040] In addition, to achieve the above objectives, the present invention also proposes a computer-readable storage medium, on which an alignment program is stored, and when the alignment program is executed by a processor, the steps of the alignment method as described in any one of the above items are implemented.

[0041] The technical solution of the present invention proposes an alignment method, which includes acquiring a target image of a target area, wherein the target area includes a luminous laser light source; extracting a region of interest corresponding to the laser light source in the target image; performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest; and controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest.

[0042] Because, in the existing alignment method, in order to accurately obtain the positional relationship between the underwater vehicle and the fixed reference object, the underwater vehicle can only navigate around the fixed reference object, so that the underwater vehicle has a small range of motion. In the present invention, the region of interest in the target image corresponding to the laser light source is identified to obtain a shape recognition result, and based on the shape recognition result and the region of interest, the underwater vehicle is controlled to align with the laser light source, and the direction and position of the laser emission are not restricted, so that when the underwater vehicle is aligned using the method of the present invention, the navigation area of ​​the underwater vehicle is not restricted. Therefore, using the alignment method of the present invention, the underwater vehicle has a larger range of motion. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0044] Figure 1 A schematic diagram of the underwater vehicle structure of the hardware operating environment involved in the embodiment of the present invention;

[0045] Figure 2 It is a schematic diagram of the flow chart of the first embodiment of the alignment method of the present invention;

[0046] Figure 3a and Figure 3b All are schematic diagrams of the regions of interest of the present invention;

[0047] Figure 4a and Figure 4b All of them are schematic diagrams of the relationship between the region of interest and the reference circumscribed circle of the present invention;

[0048] Figure 5 It is a schematic diagram of the final light spot area of ​​the present invention;

[0049] Figure 6 It is a schematic diagram of the structure of the underwater navigation system of the present invention;

[0050] Figure 7It is a structural block diagram of the first embodiment of the alignment device of the present invention.

[0051] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Reference Figure 1 , Figure 1 A schematic diagram of the underwater vehicle structure of the hardware operating environment involved in the embodiment of the present invention.

[0054] Typically, the underwater vehicle comprises: at least one processor 301, a memory 302, and an alignment program stored in the memory and executable on the processor, wherein the alignment program is configured to implement the steps of the alignment method as described above.

[0055] The processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may also include an AI (Artificial Intelligence) processor, which is used to process operations related to the alignment method, so that the alignment method model can be trained and learned autonomously to improve efficiency and accuracy.

[0056] The memory 302 may include one or more computer-readable storage media, which may be non-transitory. The memory 302 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices, flash memory storage devices, etc.

[0057] In some embodiments, the underwater vehicle may further include: a communication interface 303 and at least one peripheral device. The processor 301, the memory 302 and the communication interface 303 may be connected via a bus or a signal line. Each peripheral device may be connected to the communication interface 303 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 304, a display screen 305 and a power supply 306.

[0058] The communication interface 303 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 301 and the memory 302. In some embodiments, the processor 301, the memory 302, and the communication interface 303 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 301, the memory 302, and the communication interface 303 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0059] The radio frequency circuit 304 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 304 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 304 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals.

[0060] The display screen 305 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof.

[0061] The power supply 306 is used to power various components in the electronic device. The power supply 306 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 306 includes a rechargeable battery, the rechargeable battery can support wired charging or wireless charging. The rechargeable battery can also be used to support fast charging technology.

[0062] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the underwater vehicle, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0063] In addition, an embodiment of the present invention further proposes a computer-readable storage medium, on which an alignment program is stored, and when the alignment program is executed by a processor, the steps of the alignment method described above are implemented. Therefore, it will not be described in detail here. In addition, the description of the beneficial effects of adopting the same method will not be described in detail. For technical details not disclosed in the computer-readable storage medium embodiment involved in this application, please refer to the description of the method embodiment of this application. As an example, the program instructions can be deployed to be executed on an underwater vehicle, or on multiple underwater vehicles located at one location, or on multiple underwater vehicles distributed at multiple locations and interconnected by a communication network.

[0064] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the above-mentioned program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the above-mentioned computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0065] Based on the above hardware structure, an embodiment of the alignment method of the present invention is proposed.

[0066] Reference Figure 2 , Figure 2 This is a flow chart of a first embodiment of an alignment method of the present invention, wherein the method is applied to an underwater vehicle, and the method further comprises the following steps:

[0067] Step S11: Acquire a target image of a target area, where the target area includes a luminous laser light source.

[0068] It should be noted that the executor of the present invention is an underwater vehicle, and the underwater vehicle is equipped with an alignment program. When the underwater vehicle executes the alignment program, the alignment method of the present invention is implemented. In another embodiment, the underwater vehicle can send the target image to the terminal device, and the terminal device executes steps S11-S14, obtains the control instruction based on the shape recognition result, and sends the control instruction to the underwater vehicle through a wired network, a wireless network or Bluetooth, etc., and the underwater vehicle controls the underwater vehicle to align with the laser light source based on the control instruction. The area corresponding to the laser emitted by the laser light source is the alignment area, and the underwater vehicle is aligned with the laser light source, which means that the underwater vehicle is sailing in the alignment area; the underwater vehicle determines whether the underwater vehicle is in the alignment area based on the shape recognition result, and then determines the control action of the underwater vehicle.

[0069] The target area may refer to an area where a laser light source is set, the laser light source emits laser, and the target area is photographed by a camera (such as a monocular camera) of the underwater vehicle to obtain a target image of the target area, the target image has a light spot, and the light spot in the target image is an image corresponding to the laser emitted by the laser light source in the target area. It can be understood that the target image of the target area includes a partial image corresponding to the laser emitted by the laser light source, and also includes a partial image corresponding to the area outside the laser light source. Among them, the camera of the underwater vehicle can be an external camera, that is, the underwater vehicle and the camera are combined into an underwater vehicle group.

[0070] Furthermore, before step S11, the method further includes: shooting a real-time video of the target area. Accordingly, step S11 includes: acquiring the target image that meets a preset condition in the real-time video.

[0071] It should be noted that the underwater vehicle shoots real-time video through a camera and extracts the target image from the real-time video. Each frame of the real-time video needs to perform the steps of the alignment method of the present invention, but the image of the laser light source in some video frames in the real-time video may not be clear, and the information contained is invalid information, and it is not necessary to perform the steps of the alignment method of the present invention.

[0072] The preset condition may be that the video frame has a complete laser light source image. For example, in a certain video frame, there is only 1 / 2 of the laser light source image (the laser light source may be blocked), then the video frame is unusable and cannot be determined as the target image. For video frames that meet the preset conditions, the alignment method of the present invention can be executed.

[0073] Step S12: extracting a region of interest corresponding to the laser light source in the target image.

[0074] Specifically, step S12 includes: obtaining the gray value of the target image; determining a region in the target image whose gray value is greater than or equal to a preset gray threshold as an initial region of interest; determining a connected domain boundary in the initial region of interest; determining a region within the connected domain boundary as the region of interest; or,

[0075] A growth pixel point is determined in the spot area corresponding to the laser light source in the target image; and the growth pixel point is expanded using a preset regional growth rule to obtain the region of interest.

[0076] It should be noted that the target image includes the region of interest (ROI region, which is reflected as a spot region on the target image) corresponding to the laser emitted by the laser light source, and also includes the region corresponding to the non-laser light source (the region has no laser emitted by the laser light source, which is reflected as a non-spot region on the target image). At this time, it is necessary to extract the region of interest corresponding to the laser emitted by the laser light source in the target image and name it the region of interest. There are two specific extraction methods, refer to the description above.

[0077] Among them, the first method is the threshold segmentation method. Since the brightness of the spot area is obviously higher than the surrounding environment, a fixed threshold (the preset grayscale threshold) can be used to roughly locate the approximate area where the spot is located, that is, the initial region of interest, and then the region of interest is generated by finding the boundary through the connected domain, that is, the region of interest. Specifically, the preset grayscale threshold can be set by the user according to needs, and the present invention does not limit it. The area corresponding to the grayscale value greater than or equal to the preset grayscale threshold in the target image is determined as the initial area.

[0078] Another method is a region growing method, which first determines the growing pixel points in the spot area corresponding to the laser light source in the target image, selects the pixel point with the highest gray value as the growing pixel point, expands the growing pixel point according to the preset region growing rule, and finally stops growing to obtain the region of interest. The preset region growing rule and the various parameters in the preset region growing rule can be set by the user according to the needs, and the present invention does not limit it.

[0079] Reference Figure 3a and Figure 3b , Figure 3a and Figure 3b All of them are schematic diagrams of the regions of interest of the present invention. Figure 3a This is a schematic diagram of the region of interest (or ROI region) obtained by the threshold segmentation method. Figure 3b Schematic diagram of the region of interest (or ROI region) obtained by the region growing method, where: Figure 3a and Figure 3b The left side is a schematic diagram of the region of interest extracted from the target image, and the right side is a grayscale image corresponding to the region of interest. It can be seen that through the above two methods, the region of interest can be located, thereby discarding a large area of ​​background area, which is conducive to the efficient extraction of the light spot.

[0080] Step S13: performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest.

[0081] Specifically, step S13 includes: drawing a circumscribed circle for the region of interest to obtain a reference circumscribed circle; determining an area ratio between the area of ​​the region of interest and the area of ​​the reference circumscribed circle; and obtaining a shape recognition result of the region of interest based on a comparison result of a preset ratio and the area ratio.

[0082] It should be noted that the preset ratio can be set by the user according to the needs, and the present invention does not limit it. When the comparison result is that the area ratio reaches the preset ratio, the region of interest can be approximately a circular spot, and when the comparison result is that the area ratio does not reach the preset ratio, the region of interest is approximately a strip spot.

[0083] Reference Figure 4a and Figure 4b , Figure 4a and Figure 4b All of them are schematic diagrams of the relationship between the region of interest and the reference circumscribed circle of the present invention; Figure 4a is a schematic diagram of a circular light spot. Figure 4b It is a schematic diagram of a strip light spot. It can be seen that the actual spot area of ​​the circular light spot is close to the area of ​​the reference circumscribed circle, with a small difference, reaching the preset ratio, while the actual spot area of ​​the strip light spot is greatly different from the area of ​​the reference circumscribed circle, failing to reach the preset ratio.

[0084] Step S14: Based on the shape recognition result and the region of interest, the underwater vehicle is controlled to align with the laser light source.

[0085] Furthermore, before step S14, the method further includes: performing halo and background removal on the region of interest to obtain a final light spot area; correspondingly, step S14 includes: controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the final light spot area.

[0086] Specifically, step S14 includes: when the shape recognition result is that the region of interest is circular, filtering the final light spot area to obtain a final light spot area after filtering; determining the light spot centroid in the final light spot area after filtering; determining first position information of the laser light source and the underwater vehicle based on the light spot centroid; and controlling the underwater vehicle to align with the laser light source based on the first position information; or,

[0087] When the shape recognition result is that the region of interest is strip-shaped, the final light spot area is fitted to obtain a fitted ellipse; the major axis of the fitted ellipse is determined as the centerline of the light beam; selected pixel points corresponding to the centerline of the light beam are determined in the final light spot area; and based on the grayscale values ​​of the selected pixel points, second position information of the laser light source and the underwater vehicle is determined; and based on the second position information, the underwater vehicle is controlled to align with the laser light source.

[0088] It should be noted that, since the halo and background around the light spot are easily confused with the light spot, it is necessary to extract the final light spot area in the region of interest, that is, the area in the region of interest that does not include the halo and background. The present invention adopts a Gaussian mixture model (GMM), the core idea of ​​which is clustering. A reasonable number of clustering areas is set in advance, and the optimal solution of the parameters is obtained by maximizing the probability density function. The area corresponding to the optimal solution is the final light spot area. For the parameter estimation of the probability density function, the EM algorithm is repeatedly iterated. The algorithm has convergence, and the optimal solution can be found when the number of iterations is sufficient.

[0089] Reference Figure 5 , Figure 5 is a schematic diagram of the final light spot area of ​​the present invention, Figure 5 The left side is a grayscale image corresponding to the region of interest in the target image, and the right side is a schematic diagram of the final light spot region, where the dark light spot is the final light spot region.

[0090] For the approximately circular spot, that is, the recognition result of the region of interest is a circular spot, the centroid of the final spot area is used as a feature. In order to reduce the influence of scattered light around the final spot area on the centroid extraction, an effective filtering strategy (such as open operation or median filtering, etc.) is used to filter out the scattered light to obtain the final spot area after filtering, and further a circle fitting is performed on the contour of the final spot area after filtering, so as to extract the center of the circle as the centroid of the final spot area after filtering, that is, the spot centroid. At the same time, when the shape detection result of the region of interest is a circle, it means that the underwater vehicle is near the alignment area (that is, the first position information is that the underwater vehicle is in the alignment area). At this time, when controlling the alignment of the underwater vehicle with the laser light source, it is only necessary to fine-tune the position so that it is dynamically stable in the alignment area.

[0091] For the light spot with beam, that is, the recognition result of the region of interest is a strip light spot, according to the characteristic that the final light spot area is conically divergent along the direction of the light beam, the major axis of the ellipse is found by fitting an ellipse to the final light spot area. The major axis of the ellipse is the center line of the light beam. According to the principle that the more concentrated the brightness is, the closer it is to the center of mass, a number of adjacent pixels are taken from the center of the ellipse along both sides of the center line of the light beam. These pixels are the selected pixels, and the emission direction of the light emitted by the laser light source is determined according to the grayscale mean of the selected pixels. Then, based on the emission direction, the second position information (i.e., the specific deviation direction of the underwater vehicle from the alignment area) is determined. At the same time, when the recognition result of the region of interest is a strip light spot, it means that the underwater vehicle has obviously deviated from the alignment area. At this time, when controlling the underwater vehicle to align with the laser light source, the underwater vehicle needs to move back to the alignment area along the direction of the light beam based on the emission direction.

[0092] In one embodiment, a highly maneuverable underwater agile robot (BlueROV) is used as the underwater vehicle, and a monocular camera for sensing the external environment is integrated in the BlueROV. The BlueROV is connected to a host computer (which may be a personal computer, etc.) for communication. The host computer is used to perform most of the steps in the present invention. The BlueROV is only used to obtain the target image and perform the alignment action. The other data analysis processes are all performed by the host computer, and the control instructions are obtained (the control instructions may include the control actions described above: fine-tuning the position to make it dynamically stable in the alignment area, or moving back to the alignment area along the direction of the light beam, etc.), and the BlueROV executes the control instructions.

[0093] In a specific application, the underwater vehicle transmits the real-time video of the monocular camera to the host computer through the gstreamer module (a multimedia development framework for video processing). The host computer executes the data analysis steps of the present invention and publishes a "\vision\pose" message, which includes position deviation information. After obtaining the information, the control module can send a control input signal to the propeller of the underwater vehicle. At the same time, the underwater vehicle will feedback the depth information "\vfr_hud" at this time to the control module through the internal depth sensor to achieve stable control of the underwater vehicle.

[0094] In addition, the underwater vehicle of the present invention may include a BlueROV and a laser transmitter and receiver. The BlueROV may be connected to the laser transmitter and receiver through a fixed frame. The laser receiver is used to receive the laser emitted by the laser light source, and the laser transmitter is used to emit the laser. The laser light source may be a BlueROV equipped with a laser transmitter, which is fixed to the target area and used as the laser light source of the present invention.

[0095] It is understandable that, in other embodiments, all steps of the alignment method of the present invention may be completed by the underwater vehicle without the need to communicate with the host computer.

[0096] Reference Figure 6 , Figure 6 The schematic diagram of the underwater navigation system structure of the present invention includes an underwater vehicle and a laser light source. Figure 6 The largest frame in the figure is a pool (or lake, etc.), a laser light source is fixedly suspended on the right side of the pool (it can be a BlueROV equipped with a laser transmitter), the dotted line corresponding to the laser light source is the emitted laser light, and the left side is a movable underwater vehicle (which can include a BlueROV and a laser receiver). The underwater vehicle is at a certain distance from the laser light source, Xw, Yw and Zw are the horizontal coordinate, vertical coordinate and vertical coordinate of the world coordinate system, respectively, and Xb, Yb and Zb are the horizontal coordinate, vertical coordinate and vertical coordinate of the body coordinate system (the coordinate system of the underwater vehicle), respectively. At the same time, using the method of the present invention, when the distance between the underwater vehicle and the laser light source is 15m, the accuracy of the final spot area obtained by the method of the present invention can reach <±0.5m, which is a high accuracy.

[0097] The technical solution of the present invention proposes an alignment method, which includes acquiring a target image of a target area, wherein the target area includes a luminous laser light source; extracting a region of interest corresponding to the laser light source in the target image; performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest; and controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest.

[0098] Because, in the existing alignment method, in order to accurately obtain the positional relationship between the underwater vehicle and the fixed reference object, the underwater vehicle can only navigate around the fixed reference object, so that the underwater vehicle has a small range of motion. In the present invention, the region of interest in the target image corresponding to the laser light source is identified to obtain a shape recognition result, and based on the shape recognition result and the region of interest, the underwater vehicle is controlled to align with the laser light source, and the direction and position of the laser emission are not restricted, so that when the underwater vehicle is aligned using the method of the present invention, the navigation area of ​​the underwater vehicle is not restricted. Therefore, using the alignment method of the present invention, the underwater vehicle has a larger range of motion.

[0099] At the same time, by extracting the region of interest in the target image, only the region of interest is analyzed to improve the efficiency of image processing; through the step-by-step processing of coarse extraction (determination of the region of interest) and fine positioning (determination of the final spot area), the final spot area can be accurately extracted. In addition, a spot shape classification strategy is formulated, and the corresponding feature parameters are extracted according to the shape category of the spot, and the node is controlled to move, and finally a stable alignment is achieved.

[0100] In addition, by using the alignment method of the present invention, the navigation area of ​​the underwater vehicle does not need to set up fixed reference objects. The underwater vehicle is not only suitable for known underwater areas, but also for unknown underwater areas. The applicable environment of the underwater vehicle is more diverse and the adaptability is better.

[0101] Reference Figure 7 , Figure 7 This is a structural block diagram of a first embodiment of an alignment device of the present invention, the device is used for an underwater vehicle, and the device comprises:

[0102] An acquisition module 10 is used to acquire a target image of a target area, wherein the target area includes a light emitting laser light source;

[0103] An extraction module 20, used to extract a region of interest corresponding to the laser light source in the target image;

[0104] The recognition module 30 is used to perform shape recognition on the region of interest to obtain a shape recognition result of the region of interest;

[0105] The control module 40 is used to control the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest.

[0106] The above descriptions are only optional embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent structural changes made using the contents of the present invention's specification and drawings, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. An alignment method, characterized in that: For an underwater vehicle, the method comprises the following steps: Acquire a target image of a target area, wherein the target area includes a light emitting laser light source; Extracting a region of interest corresponding to the laser light source in the target image; Performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest; Based on the shape recognition result and the region of interest, controlling the underwater vehicle to align with the laser light source; The step of performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest comprises: Drawing a circumscribed circle for the region of interest to obtain a reference circumscribed circle; determining an area ratio of the area of ​​the region of interest to the area of ​​the reference circumscribed circle; Based on the comparison result of the preset ratio and the area ratio, the shape recognition result of the region of interest is obtained.

2. The method according to claim 1, characterized in that The step of extracting the region of interest corresponding to the laser light source in the target image comprises: Obtaining the grayscale value of the target image; Determine an area in the target image where the grayscale value is greater than or equal to a preset grayscale threshold as an initial region of interest; Determine a connected domain boundary in the initial region of interest; The area within the boundary of the connected domain is determined as the region of interest.

3. The method according to claim 1, characterized in that The step of extracting the region of interest corresponding to the laser light source in the target image comprises: Determine a growth pixel point in a light spot area corresponding to the laser light source in the target image; The growing pixels are expanded using a preset region growing rule to obtain the region of interest.

4. The method according to claim 2 or 3, characterized in that Before the step of controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest, the method further includes: Performing halo and background removal on the region of interest to obtain a final light spot area; The step of controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest comprises: Based on the shape recognition result and the final light spot area, the underwater vehicle is controlled to align with the laser light source.

5. The method according to claim 4, characterized in that The step of controlling the underwater vehicle to align with the laser light source based on the shape recognition result and the final light spot area comprises: When the shape recognition result is that the region of interest is circular, filtering the final light spot area to obtain a final light spot area after filtering; determining a light spot centroid in the final light spot area after filtering; determining first position information of the laser light source and the underwater vehicle based on the light spot centroid; and controlling the underwater vehicle to align with the laser light source based on the first position information; or, When the shape recognition result is that the region of interest is strip-shaped, the final light spot area is fitted to obtain a fitted ellipse; the major axis of the fitted ellipse is determined as the centerline of the light beam; selected pixel points corresponding to the centerline of the light beam are determined in the final light spot area; and based on the grayscale values ​​of the selected pixel points, second position information of the laser light source and the underwater vehicle is determined; and based on the second position information, the underwater vehicle is controlled to align with the laser light source.

6. The method according to claim 5, characterized in that Before the step of acquiring the target image of the target area, the method further includes: capturing real-time video of the target area; The step of acquiring the target image of the target area comprises: The target image satisfying a preset condition is acquired in the real-time video.

7. An alignment device, characterized in that: For underwater vehicles, the device includes: An acquisition module, used to acquire a target image of a target area, wherein the target area includes a light emitting laser light source; An extraction module, used for extracting a region of interest corresponding to the laser light source in the target image; A recognition module, used for performing shape recognition on the region of interest to obtain a shape recognition result of the region of interest; A control module, configured to control the underwater vehicle to align with the laser light source based on the shape recognition result and the region of interest; The recognition module is also used to draw a circumscribed circle for the region of interest to obtain a reference circumscribed circle; determine the area ratio of the area of ​​the region of interest to the area of ​​the reference circumscribed circle; and obtain a shape recognition result of the region of interest based on a comparison result of a preset ratio and the area ratio.

8. An underwater vehicle, characterized in that: The underwater vehicle comprises: a memory, a processor, and an alignment program stored in the memory and running on the processor, wherein the alignment program implements the steps of the alignment method according to any one of claims 1 to 6 when executed by the processor.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an alignment program, and when the alignment program is executed by a processor, the steps of the alignment method according to any one of claims 1 to 6 are implemented.

Images