Intelligent assembling method and system suitable for low-illumination environment

Abstract

The invention provides an intelligent assembly method and system suitable for a low-illumination environment, and the method comprises the steps: obtaining an image in an airplane belly, and carrying out the enhancement processing of the obtained image in the airplane belly, and obtaining an enhanced image; performing pose detection on the assembly hook and the assembly rack based on the enhanced image to obtain pose data; based on the obtained pose data, trajectory planning of bomb hanging in the belly of the aircraft is carried out, and trajectory data are output; and based on the output track data, the platform is controlled to drive the assembling hook to hang the projectile body on the assembling frame.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent assembly, and particularly relates to an intelligent assembly method and system applicable to low-illumination environments. Background Technique

[0002] The statements in this part only provide background technical information related to the present invention and do not necessarily constitute prior art.

[0003] Internal belly weapon hanging on an aircraft refers to the configuration method of mounting missiles, bombs or other weapons inside the belly of the aircraft fuselage. At present, the operation of internal belly weapon hanging on an aircraft still mainly relies on manual visual inspection, and the existing problems are prominent problems such as long weapon hanging time, many personnel occupied, and low operation efficiency.

[0004] With the continuous maturity of perception technologies such as machine vision, it shows broad application prospects in the military field. By integrating vision positioning and motion control technologies, the automation degree of the weapon hanging process can be significantly improved, the burden on personnel can be reduced, risks can be lowered, and the overall operation efficiency can be increased. However, due to the complex internal environment structure and harsh lighting conditions in the belly, it brings severe challenges to the stable recognition and precise control of the intelligent assembly system. There is an urgent need to construct an intelligent assembly solution with environmental adaptability, strong recognition accuracy, and high control precision.

[0005] Currently, the key difficulties in the belly environment include:

[0006] (1) Complex structure and difficult feature recognition. The internal structure of the belly is complex, and the bottom structure of the assembly rack is hidden. Generally, it consists of two separated rectangular notches. The structural features of the visual target are weak, and the background interference is strong. Such an environment poses challenges to traditional image processing methods, easily leading to unstable feature recognition. Deep learning or point cloud recognition methods often have false detection phenomena, and it is difficult to achieve high-precision target positioning and alignment control.

[0007] (2) Harsh lighting conditions and limited image quality. The belly area is often in a low-illumination state and is easily interfered by factors such as shadows and reflections. Especially in the actual usage background, the light source is strictly controlled, and the imaging quality cannot be improved by means of supplementary lighting, resulting in low contrast and high noise in the images collected by the visual sensor, seriously affecting the accuracy of target edge extraction and pose estimation. Among them, a low-illumination environment refers to an environment with a low light intensity, an environment with an illuminance lower than 30 lux. Dusk illuminance: 10–100 lux. In addition, it should be noted that active lighting is strictly restricted in military scenarios, which forms a fundamental conflict with the sensitivity requirements of visual sensors.

[0008] In summary, existing image enhancement algorithms focus on the overall effect of images and do not focus on enhancing based on the characteristics of ArUco code recognition. In addition, the current recognition of the bomb - hanging system uses templates or deep learning, which is not suitable for the complex environment inside the aircraft belly. Summary of the Invention

[0009] To overcome the deficiencies of the above - mentioned prior art, the present invention provides an intelligent assembly method applicable to low - illumination environments, realizing automatic and intelligent operation of bomb - hanging inside the aircraft belly, and significantly reducing labor input and potential safety hazards.

[0010] To achieve the above object, one or more embodiments of the present invention provide the following technical solutions:

[0011] In a first aspect, an intelligent assembly method applicable to low - illumination environments is disclosed, including:

[0012] Obtain an image inside the aircraft belly. If the image inside the aircraft belly is obtained under low illumination and the ArUco code cannot be recognized, perform enhancement processing on the obtained image inside the aircraft belly to obtain an enhanced image for recognizing the ArUco code;

[0013] Based on the enhanced image with the recognized ArUco code, perform pose detection of the assembly hook and the assembly rack to obtain pose data;

[0014] Based on the obtained pose data, perform trajectory planning for bomb - hanging inside the aircraft belly and output trajectory data;

[0015] Based on the output trajectory data, control the platform to drive the assembly hook to hang the bomb body on the assembly rack.

[0016] As a further technical solution, performing enhancement processing on the obtained image inside the aircraft belly to obtain an enhanced image specifically includes:

[0017] The obtained image inside the aircraft belly is an RGB image. Convert the RGB image to the HSV space, extract the V component as the main target for subsequent enhancement, and keep the H and S components unchanged;

[0018] Process the extracted luminance V component to enhance the image brightness; process the extracted luminance V component through a Retinex algorithm improved based on guided filtering;

[0019] For the enhanced luminance V component, increase the contrast and improve the visibility of image details;

[0020] Optimize the overall brightness distribution and adjust the overall brightness;

[0021] Synthesize the enhanced V component with the original H and S components, and then convert it to the enhanced RGB image.

[0022] As a further technical solution, an image inside the belly of the aircraft is acquired. The image inside the belly of the aircraft contains ArUco codes, where the ArUco codes are respectively pasted on the assembly hook and the assembly rack;

[0023] The corner pixel coordinates and depth information of the ArUco codes are recognized, and their world coordinate system coordinates are obtained through coordinate system conversion, and the relative pose relationship between the assembly hook and the assembly rack is acquired.

[0024] As a further technical solution, the corner pixel coordinates of the ArUco codes are recognized, specifically including:

[0025] The image is grayscaled, filtered, then threshold segmented, and then edge detected;

[0026] The ArUco code contours are screened, perspective transformation of the ArUco codes and ArUco code encoding recognition are performed, and finally the corner pixel coordinates of the ArUco codes are obtained.

[0027] As a further technical solution, trajectory planning for bomb hanging inside the belly of the aircraft is performed based on the obtained pose data and trajectory data is output, specifically including:

[0028] Based on the relative pose relationship between the acquired assembly hook and the assembly rack, the piecewise polynomial interpolation method in the joint space is adopted, the joint positions of the starting point, waypoints, and end point are input, and the speed and acceleration of the joint movement are calculated and output through piecewise polynomial.

[0029] As a further technical solution, it also includes a trajectory optimization step:

[0030] The goal of time optimization for the six - degree - of - freedom platform trajectory is to minimize the movement time under the premise of meeting the speed and acceleration limits: the trajectory after piecewise polynomial interpolation planning is divided into three segments, and the time used for each segment of the trajectory is T1, T2, and T3. The improved particle swarm optimization algorithm is used to optimize the trajectory to find the shortest time for each segment of the trajectory, and thus the optimal time for the trajectory movement is obtained. Its objective function is expressed as:

[0031] f(t) = min(T1 + T2 + T3)

[0032] This function is also the fitness value function, which is used to measure the quality of the particles. The smaller the fitness value of the particle, that is, the smaller the objective function, the more excellent the particle.

[0033] In the second aspect, an intelligent assembly system applicable to low - illumination environments is disclosed, including:

[0034] The image processing module is configured to: obtain an image inside the belly of an aircraft. If the image inside the belly of the aircraft is obtained under low illumination and the ArUco code cannot be recognized, perform enhancement processing on the obtained image inside the belly of the aircraft to obtain an enhanced image so as to recognize the ArUco code;

[0035] The pose data detection module is configured to: perform pose detection of the assembly hook and the assembly rack based on the enhanced image with the recognized ArUco code to obtain pose data;

[0036] The trajectory planning module is configured to: perform trajectory planning for the ammunition hanging inside the belly of the aircraft based on the obtained pose data and output trajectory data;

[0037] The assembly module is configured to: control the platform based on the output trajectory data to drive the assembly hook to hang the projectile on the assembly rack.

[0038] It should be noted that if the image inside the belly of the aircraft is obtained under normal light conditions, image enhancement processing is no longer required.

[0039] The above one or more technical solutions have the following beneficial effects:

[0040] After the technical solution of the present invention obtains the image inside the belly of the aircraft, since ArUco codes are provided on both the assembly hook and the assembly rack, it is first determined whether the ArUco code can be recognized. If not, enhancement processing is performed, and recognition and pose estimation between the assembly hook and the assembly rack are realized for the enhanced image, which is helpful for subsequent trajectory planning between the assembly hook and the assembly rack.

[0041] When the technical solution of the present invention performs enhancement processing on low-illumination images, based on the improved Retinex image enhancement algorithm of guided filtering, illuminance estimation and enhancement processing are performed on the V channel in the HSV space, realizing high-robustness object recognition and pose estimation under complex illumination and structural backgrounds, effectively improving the recognition success rate of ArUco codes under low illumination, and enhancing the reliability of system operation in dark environments at night. The technical solution of this embodiment uses guided filtering improvement and focuses on improving the recognition effect of ArUco codes after enhancement. This system uses a depth camera to recognize ArUco codes and has strong robustness.

[0042] The technical solution of the present invention improves the trajectory smoothness and execution efficiency of the assembly platform. The closed-loop control based on visual feedback significantly improves the hanging accuracy and reduces the risk of misalignment. The technical solution of the present invention realizes automatic and intelligent operation of ammunition hanging inside the belly of the aircraft through visual positioning and trajectory planning means, significantly reducing the labor input and improving the operation efficiency.

[0043] Advantages of additional aspects of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through practice of the present invention. Description of the Drawings

[0044] The accompanying drawings of the specification, which form a part of the present invention, are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention.

[0045] Figure 1 Schematic diagram of the camera installation position and working area in this embodiment;

[0046] Figure 2 Schematic diagram of the camera field of view and the use of ArUco codes in this embodiment;

[0047] Figure 3 Schematic diagram of the ArUco code recognition process;

[0048] Figure 4 Schematic diagram of coordinate system conversion;

[0049] Figure 5 Schematic diagram of low-light image enhancement based on improved Retinex;

[0050] Figure 6 Flowchart of the improved particle swarm optimization algorithm;

[0051] Figure 7 Overall schematic diagram of this embodiment;

[0052] Figure 8 Schematic diagram of the method assembly of this embodiment;

[0053] Figure 9 Schematic diagram of 3-5-3 piecewise polynomial trajectory planning simulation, where (a) position change curve; (b) speed change curve; (c) acceleration change curve;

[0054] Figure 10 Schematic diagram of the use method of ArUco codes and the movement of the bomb rack hook;

[0055] Figure 11 Schematic diagram of the change in the position of the bomb rack hook caused by the change in the platform angle. Detailed implementation manners

[0056] It should be noted that the following detailed description is exemplary and is intended to provide a further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0057] It should be noted that the terms used herein are only for describing the specific implementation manners and are not intended to limit the exemplary embodiments according to the present invention.

[0058] Without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other.

[0059] Term Explanation:

[0060] ArUco code: A square binary marker image based on Hamming code, used for visual positioning and pose detection.

[0061] Retinex algorithm: An image enhancement algorithm based on the human visual system, used for image processing in low-light environments.

[0062] 3-5-3 polynomial interpolation: A piecewise polynomial interpolation method, used to improve the smoothness of the trajectory.

[0063] Particle Swarm Optimization Algorithm (PSO): An optimization algorithm based on swarm intelligence, used to solve complex optimization problems.

[0064] Embodiment 1

[0065] Currently, the operation of hanging bombs inside the aircraft belly in low-light environments lacks an intelligent assembly strategy suitable for the low-light environment inside the aircraft belly. There are problems such as insufficient accuracy in visual recognition and detection in complex environments. The problem that the ArUco code cannot be recognized under low-light conditions. When hanging bombs inside the aircraft belly, a six-degree-of-freedom platform is used to lift the bomb body. The assembly hook is on the bomb body, and the assembly rack is inside the aircraft belly. Hanging the assembly hook on the bomb body onto the assembly rack. Currently, the trajectory planning efficiency of the six-degree-of-freedom platform is low.

[0066] This embodiment discloses an intelligent assembly method applicable to low-light environments. Using this method, joint space trajectory planning is performed on the motors of the six-degree-of-freedom platform. The motors move according to the planned speed and acceleration. Stick the ArUco code near the assembly hook and the assembly rack. The overall steps are shown in the appendix Figure 7 as follows, including:

[0067] Step 1: Obtain a photo of the low-light environment inside the aircraft belly, which is an RGB image. If the ArUco code cannot be recognized in the photo of the low-light environment, perform enhancement processing. If the ArUco code can be recognized, directly detect the pose between the assembly hook and the assembly rack. Among them, the depth camera is installed on the platform body of the six-degree-of-freedom platform. The installation of the camera is shown in the appendix Figure 1 as follows, and the field of view of the camera is shown in the appendix Figure 2 as follows, to ensure that the perspective containing the assembly hook and the assembly rack can be collected and the ArUco code can be photographed.

[0068] In the present patent implementation, when it is necessary to perform enhancement processing due to the inability to recognize the ArUco code, an improved Retinex image enhancement algorithm based on guided filtering is introduced for low-illumination environments, and the illuminance of the V channel in the HSV color space is estimated and enhanced. Combining CLAHE and Gamma correction further improves the image contrast and enhances the target visibility.

[0069] See the appendix Figure 5 As shown, the basic steps of the low-illumination image enhancement algorithm based on improved Retinex are as follows:

[0070] Step (1-1) Image color space conversion. Convert the RGB image to the HSV color space, extract the V component as the main target for subsequent enhancement, and keep the H and S components unchanged.

[0071] Step (1-2) Brightness component enhancement. Apply the improved Retinex algorithm to the extracted brightness V component, and improve the illumination image estimation through guided filtering to enhance the image brightness.

[0072] It should be noted that Gaussian filtering is used inside the Retinex algorithm. Here, according to the characteristics of ArUco code detection, guided filtering is improved. Among them, guided filtering is an edge-preserving filtering method based on a local linear model. Compared with Gaussian filtering, guided filtering has better effects in retaining image edges and details and is more suitable for the recognition of images inside the aircraft belly in the low-illumination scenario of this implementation example.

[0073] Step (1-3) Contrast enhancement. For the enhanced brightness V component, further use the CLAHE algorithm to improve the contrast and improve the visibility of image details.

[0074] Step (1-4) Overall brightness adjustment. Use Gamma correction to further optimize the overall brightness distribution, ensure clear details in the dark areas, and avoid the over-enhancement problem that may be caused by CLAHE.

[0075] Step (1-5) Image reconstruction. Synthesize the enhanced V component with the original H and S components, and then convert it into the enhanced RGB image.

[0076] It should be noted that using CLAHE and Gamma correction to further improve the image contrast, the above means belong to existing correction technologies and will not be elaborated in detail here.

[0077] Step two: Perform visual positioning on the enhanced image: Obtain the corner pixel coordinates and depth information through ArUco code recognition, and calculate its world coordinate system coordinates through coordinate system conversion.

[0078] Use ArUco codes to detect the pose of the assembly hook and the assembly rack, and optimize the accuracy of the target three-dimensional position and attitude estimation by combining depth information. Through coordinate system transformation and hand-eye calibration, obtain the relative pose relationship between the assembly hook and the assembly rack, that is, the output of coordinate transformation.

[0079] The corner pixel coordinates of the ArUco code are obtained through recognition, as shown in the appendix Figure 3 shown. Coordinate system transformation is shown in the appendix Figure 4 shown. The relevant formula is:

[0080]

[0081] In the above formula, f x and f y respectively represent the camera focal lengths in units of row and column pixels. K1 represents the internal parameter matrix of the camera, which contains information such as the optical center position and focal length. K2 represents the external parameter matrix of the camera, where R is the rotation matrix and T is the translation vector, obtained through hand-eye calibration. (u, v) are pixel coordinates, and Z c is the depth value of the ArUco code corner in the camera coordinate system, obtained by the depth camera. (x w , y w , z w ) are the coordinates of the ArUco code corner in the world coordinate system.

[0082] Step 3: Trajectory planning: Adopt the 3-5-3 piecewise polynomial interpolation method in the joint space. Based on the pose, determine the joint positions of the input starting point, waypoints, and ending point, and calculate and output the speed and acceleration of the joint movement through piecewise polynomials to ensure that the assembly platform trajectory is continuous and smooth at the position, speed, and acceleration levels and meets the platform dynamic constraint conditions. The specific simulation of the 3-5-3 piecewise polynomial trajectory planning is shown in the appendix Figure 9 shown.

[0083] Step 4: Trajectory optimization: Introduce an improved particle swarm optimization algorithm to optimize the trajectory execution time, adopt an adaptive inertia weight update strategy to accelerate the convergence speed and improve the trajectory efficiency.

[0084] The flow of the improved particle swarm optimization algorithm is shown in the appendix Figure 6 shown.

[0085] In order to improve the search performance and convergence speed of the particle swarm, this paper studies an adaptive inertia weight adjustment method based on the change of the optimal fitness value. The specific formula is as follows:

[0086]

[0087] In the formula, ω(t) is the inertia weight at the current time t; ω max is the maximum inertia weight at the initial time; ωmin is the minimum inertia weight; f best (t) is the optimal fitness value at the current time t; f best (0) is the optimal fitness value at the initial time.

[0088] The corresponding particle velocity update formula is improved to:

[0089]

[0090] In the formula, each particle i represents a possible solution, and its position is represented by the decision variable to represent, where k represents the number of updates, and d represents the d-dimensional search space. Each particle has a velocity vector indicating the direction and step size of its movement in the d-dimensional search space. In each iteration, the particle needs to update its individual optimal position P id and the global optimal position P gd of the entire population. ω represents the inertia weight, which is dynamically variable, and its usual value range is (0.4, 0.9), representing the ability of the particle to maintain its current velocity. The smaller its value, the stronger the individual optimization ability; c1 and c2 represent learning factors, usually both taking the value of 2, representing the degree of dependence of the particle on the individual optimal position and the group optimal position respectively; r1 and r2 represent random factors, which are random numbers between [0, 1], used to increase the randomness of the search.

[0091] In this method, the inertia weight is not a fixed value, but is dynamically adjusted according to the current fitness of the particle swarm. This self-adaptive adjustment method can better balance global and local searches. A larger inertia weight is maintained at the initial stage of the search process to enhance the global exploration ability of the particles and avoid falling into the local optimum prematurely. In the later stage of the optimization process, as the optimal fitness value increases, the inertia weight gradually decreases, prompting the particle swarm to focus more on the vicinity of the current optimal solution for fine search, effectively improving the convergence speed and accuracy of the algorithm.

[0092] The goal of time optimization for the six-degree-of-freedom platform trajectory is to minimize the movement time under the premise of meeting the speed and acceleration limits. The trajectory after 3-5-3 piecewise polynomial interpolation planning is divided into three segments, and the time used for each segment of the trajectory is T1, T2, and T3. The improved particle swarm optimization algorithm is used to optimize the trajectory to find the shortest time for each segment of the trajectory, and thus the optimal time for the trajectory movement is obtained. Its objective function is expressed as:

[0093] f(t) = min(T1 + T2 + T3)

[0094] This function is also the fitness value function, used to measure the quality of the particles. The smaller the fitness value of the particle (the smaller the objective function), the better the particle.

[0095] Step 5: Control and Feedback: The system uses the visual detection result as feedback. When moving to the waypoint, it performs a visual positioning again to feedback the current pose, dynamically correct the assembly pose error, achieve multi-stage segmented control, and improve the docking success rate and operation stability.

[0096] During assembly, for the docking of the assembly hook and the assembly rack, multi-stage segmented control means setting a position for secondary visual positioning, obtaining the poses of both, and moving the assembly hook to make its pose the same as that of the assembly rack, thus completing the docking.

[0097] Regarding the usage method of ArUco codes:

[0098] Stick an ArUco code with a size of 6×6 at each end of the bomb rack to obtain the coordinates of the center points of the two slots of the bomb rack. Stick an ArUco code with a size of 7×7 at each end of the bomb hook to obtain the coordinates of the center points of the two lugs of the bomb hook. The center points of the two slots of the bomb rack are j1 and j2 respectively, and the center points of the two lugs of the bomb hook are g1 and g2 respectively. Measure their three-dimensional coordinates in the coordinate system of their respective adjacent ArUco codes. When the camera detects the pose of the ArUco code, the transformation matrix between the ArUco code coordinate system {M} and the world coordinate system {B} can be obtained from the coordinate transformation relationship. The coordinates of points j1, j2, g1, and g2 in the world coordinate system can be solved as follows:

[0099]

[0100] According to the principle that two points determine a line, the line (j1, j2) with J as the midpoint and the line (g1, g2) with G as the midpoint can be obtained in the world coordinate system. The attitude difference and the coordinate difference of the midpoints of the two lines are the required movement amounts of the bomb hook. The usage method of ArUco codes and the schematic diagram of the movement of the bomb hook are as Figure 10 shown.

[0101] In this embodiment, perform a visual positioning again to feedback the current pose, that is, secondary detection and pose adjustment:

[0102] When the poses of the ArUco codes of the bomb rack and the bomb hook are detected, the required movement amount of the bomb hook can be obtained, and this movement amount is achieved by the movement of the six-degree-of-freedom platform. Due to the offset between the bomb hook and the end of the six-degree-of-freedom platform, when the six-degree-of-freedom platform changes its angle, it will not only cause the bomb hook to change its angle, but also cause a position change. The schematic diagram of the position change of the bomb hook caused by the platform angle change is as Figure 11 shown.

[0103] Taking the change in the rotation angle as an example, assume that the vertical distance between the bomb hanger and the rotation axis of the six-degree-of-freedom platform is d. When the platform drives the bomb hanger to rotate by an angle of α, the resulting position change of the bomb hanger is:

[0104]

[0105] Due to the differences in the bomb bodies and the deviation of the bomb release position each time, the offset between the bomb hanger and the end of the six-degree-of-freedom platform is not fixed. Coupled with the fact that the movement angle during the bomb hanging operation is not large, the resulting position change is small. In this embodiment, a secondary detection and pose adjustment are designed during the automatic bomb hanging operation. A path point is set directly below the bomb hanger, and a pose detection is performed again at this point. At this time, the angle adjustment has been completed, and the six-degree-of-freedom platform moves according to the new position difference. Through the secondary detection and pose adjustment, not only can complex position change calculations be avoided, but also various system errors can be effectively eliminated, improving the operation accuracy.

[0106] In some embodiments, the ArUco code can be replaced by other visual marker systems such as AprilTag, ARTag, etc.

[0107] In addition, the image enhancement algorithm can adopt deep learning methods or Retinex variant models according to requirements. And for the trajectory optimization part, other intelligent optimization methods such as genetic algorithms and immune algorithms can be selected according to the platform performance. During specific assembly, refer to the appendix Figure 9 as shown.

[0108] Embodiment 2

[0109] The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of the above method are implemented.

[0110] Embodiment 3

[0111] The purpose of this embodiment is to provide a computer-readable storage medium.

[0112] A computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are executed.

[0113] Embodiment 4

[0114] The purpose of this embodiment is to provide an intelligent assembly system suitable for low-light environments, including:

[0115] An image processing module, configured to: acquire an image inside the belly of an aircraft, and perform enhancement processing on the acquired image inside the belly of the aircraft to obtain an enhanced image;

[0116] The pose data detection module is configured to: perform pose detection on the assembly hook and the assembly rack based on the enhanced image to obtain pose data;

[0117] The trajectory planning module is configured to: perform trajectory planning for the internal bomb suspension in the belly of the aircraft based on the obtained pose data and output trajectory data;

[0118] The assembly module is configured to: control the platform to drive the assembly hook to hang the bomb body on the assembly rack based on the output trajectory data.

[0119] Embodiment 5

[0120] The purpose of this embodiment is to provide a computer program product containing instructions, which, when running on a computer, enables the computer to execute the methods and functions involved in any one of the above embodiments.

[0121] Each step involved in the device of the above embodiments corresponds to the first method embodiment. For the specific implementation manner, reference may be made to the relevant description part of the first embodiment. The term "computer-readable storage medium" should be understood to include a single medium or multiple media containing one or more instruction sets; it should also be understood to include any medium that can store, encode, or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0122] Those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computer device. Optionally, they can be implemented by program codes executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0123] Although the specific implementation manner of the present invention has been described above in conjunction with the drawings, it is not a limitation to the protection scope of the present invention. Those skilled in the art should understand that, based on the technical solution of the present invention, various modifications or deformations that can be made without creative efforts by those skilled in the art are still within the protection scope of the present invention.

Claims

1. An intelligent assembly method applicable to low-illumination environments, characterized in that, including: Obtain an image inside the belly of the aircraft. If the image inside the belly of the aircraft is obtained under low illumination and the ArUco code cannot be recognized, perform enhancement processing on the obtained image inside the belly of the aircraft to obtain an enhanced image for recognizing the ArUco code; Based on the enhanced image with the recognized ArUco code, perform pose detection of the assembly hook and the mounting bracket to obtain pose data; Based on the obtained pose data, perform trajectory planning for bomb hanging inside the belly of the aircraft and output trajectory data; Based on the output trajectory data, control the platform to drive the assembly hook to hang the bomb body on the mounting bracket.

2. The intelligent assembly method applicable to low-light environments according to claim 1, characterized in that, Perform enhancement processing on the obtained image inside the belly of the aircraft to obtain an enhanced image, specifically including: The obtained image inside the belly of the aircraft is an RGB image. Convert the RGB image to the HSV space, extract the V component, which is the main target for subsequent enhancement, and keep the H and S components unchanged; Process the extracted luminance V component to enhance the image brightness; process the extracted luminance V component through the Retinex algorithm improved based on guided filtering; For the enhanced luminance V component, increase the contrast and improve the visibility of image details; Optimize the overall luminance distribution and adjust the overall luminance; Synthesize the enhanced V component with the original H and S components, and then convert it to the enhanced RGB image.

3. The intelligent assembly method applicable to low-light environments according to claim 1, characterized in that, Obtain an image inside the belly of the aircraft, where the image inside the belly of the aircraft contains ArUco codes, and the ArUco codes are respectively pasted on the assembly hook and the mounting bracket; Recognize the ArUco code to obtain its corner pixel coordinates and depth information, and calculate its world coordinate system coordinates through coordinate system conversion to obtain the relative pose relationship between the assembly hook and the mounting bracket.

4. The intelligent assembly method applicable to low-light environments according to claim 1, characterized in that, Recognize the ArUco code to obtain its corner pixel coordinates, specifically including: Perform grayscale processing, image filtering on the image, then perform threshold segmentation, and then perform edge detection; Screen the ArUco code contour, perform perspective transformation on the ArUco code, and perform ArUco code encoding recognition, and finally obtain the ArUco code corner pixel coordinates.

5. The intelligent assembly method applicable to low-illumination environments according to claim 1, characterized in that, Based on the obtained pose data, perform trajectory planning for bomb hanging inside the belly of the aircraft and output trajectory data, specifically including: Based on the obtained relative pose relationship between the assembly hook and the mounting bracket, adopt the piecewise polynomial interpolation method in the joint space, input the joint positions of the starting point, waypoints, and ending point, and calculate and output the speed and acceleration of the joint movement through piecewise polynomials.

6. The intelligent assembly method applicable to low-illumination environments according to claim 1, characterized in that It also includes a trajectory optimization step: The goal of time optimization for the six-degree-of-freedom platform trajectory is to minimize the movement time under the premise of meeting the speed and acceleration limits: the trajectory after piecewise polynomial interpolation planning is divided into three segments, and the time used for each segment of the trajectory is T1, T2, T3. Use the improved particle swarm optimization algorithm to optimize the trajectory and find the shortest time for each segment of the trajectory, and thus obtain the optimal time for the trajectory movement. Its objective function is expressed as: f(t) = min(T1 + T2 + T3) This function is also the fitness value function, which is used to measure the quality of particles. The smaller the fitness value of the particle, that is, the smaller the objective function, the better the particle.

7. An intelligent assembly system applicable to low-light environments, characterized in that, including: The image processing module is configured to: obtain an image inside the belly of the aircraft, and if the image inside the belly of the aircraft is obtained under low illumination and the ArUco code cannot be recognized, perform enhancement processing on the obtained image inside the belly of the aircraft to obtain an enhanced image so as to recognize the ArUco code; The pose data detection module is configured to: perform pose detection of the assembly hook and the assembly rack based on the enhanced image with the recognized ArUco code to obtain pose data; The trajectory planning module is configured to: perform trajectory planning for the ammunition hanging inside the belly of the aircraft based on the obtained pose data and output trajectory data; The assembly module is configured to: control the platform to drive the assembly hook to hang the projectile on the assembly rack based on the output trajectory data.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1 to 6.

9. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of the above claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it executes the steps of the method according to any one of the above claims 1-6.

Images