Container aerial position correction method and system
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GUANGZHOU ZHONGLIAN TALLY CO LTD
- Filing Date
- 2026-04-13
- Publication Date
- 2026-08-07
AI Technical Summary
[0004]本发明提供一种集装箱空中位置校正方法和系统，以解决现有技术中对于集装箱控制能力不足，安全性不足和留痕能力不足的问题
[0034]The present invention provides the following beneficial effects: it enables real-time attitude correction, predicts and stably iterates attitude and trajectory through algorithms, supports a wide range of scenarios, and can accurately and safely correct and control the aerial position of containers. In some embodiments, it can achieve automatic interruption in case of anomalies and supports continuous optimization of the data learning module.
Smart Images
Figure CN122530293A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to image processing, and more particularly to a method and system for correcting the aerial position of a container. Background Technology
[0002] When port quay cranes or yard cranes are lifting containers, the attitude deviation between the spreader and the container or hatch is difficult to quantify in real time due to the influence of wind load, spreader swing angle, structural obstruction and visual blind spots. Traditionally, relying on manual visual judgment has the following problems: (1) there is no unified coordinate reference, making it difficult to carry out closed-loop control; (2) there is a lack of real-time calculation of swing angle and prediction error; (3) it cannot be linked with unlocking / locking and safety threshold; (4) there is a lack of data traceability and model self-learning mechanism.
[0003] The above problems urgently need to be addressed. Summary of the Invention
[0004] This invention provides a method and system for correcting the aerial position of a container, in order to solve the problems of insufficient control, safety and traceability of containers in the prior art.
[0005] This invention provides a method for correcting the aerial position of a container, comprising:
[0006] Receive lifting or positioning signals, initiate a calibration session, and synchronize the clock;
[0007] Data is collected by multiple sensors, including multi-angle cameras, and multi-source data packets are output.
[0008] Process the images in the multi-source data packets and output synchronization frames;
[0009] Identify container feature points from the synchronization frame and output the feature point coordinate set;
[0010] Based on the feature point coordinate set, solve for the pose T and output the pose result;
[0011] Generate target pose Output standard alignment reference;
[0012] Calculation error It also predicts short-time biases and outputs the prediction results;
[0013] Based on the available execution axes, allocate control quantities and generate a target allocation table and constraints;
[0014] Calculate the trajectory, add anti-slip compensation, and output the control sequence;
[0015] PLC execution control, with real-time error updates;
[0016] Once the error reaches the tolerance level, unlocking or lowering is performed and recorded.
[0017] In some embodiments, the following are included:
[0018] Capture five-view images, error curves, and logs, and incorporate them into the retraining dataset.
[0019] In some embodiments, the data acquisition via multiple sensors, including a multi-angle camera, includes:
[0020] Data is acquired from top-view / side-view cameras, laser rangefinders, IMUs, and PLCs.
[0021] In some embodiments, the process of processing images in multi-source data packets and outputting synchronization frames specifically includes:
[0022] Perform distortion correction, HDR enhancement, dehazing, image stabilization, and ROI cropping on images from multi-source data packets. Output a synchronization frame.
[0023] In some embodiments, the step of identifying container feature points from the synchronization frame and outputting a set of feature point coordinates specifically includes:
[0024] Identify the corner castings, edges, and guide grooves of the container from the synchronization frame, and output the set of feature point coordinates.
[0025] In some embodiments, the step of solving the pose T based on the feature point coordinate set and outputting the pose result specifically involves:
[0026] The 6DoF pose T is solved using PnP or multi-view geometry combined with laser height calculation, and the pose results are output.
[0027] In some embodiments, EKF is used to predict short-term biases.
[0028] In some embodiments, the calculated trajectory, incorporating anti-swing compensation, outputs a control sequence, specifically including:
[0029] The trajectory is calculated using LQR / MPC, anti-swing compensation is added, and the control sequence u(t) is output.
[0030] In some embodiments, the system also includes monitoring gaps, wind speed, and intrusion, and triggering warnings and pauses when an anomaly is detected.
[0031] On the other hand, the present embodiment provides a container air position correction system, including:
[0032] Memory, used to store programs;
[0033] A processor is used to load a program to execute the container air position correction method described above.
[0034] The present invention provides the following beneficial effects: it enables real-time attitude correction, predicts and stably iterates attitude and trajectory through algorithms, supports a wide range of scenarios, and can accurately and safely correct and control the aerial position of containers. In some embodiments, it can achieve automatic interruption in case of anomalies and supports continuous optimization of the data learning module. Attached Figure Description
[0035] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0036] Figure 1 This is a flowchart provided in an embodiment of this application;
[0037] Figure 2 This is another flowchart provided in the embodiment itself. Detailed Implementation
[0038] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0039] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The terms "upper," "lower," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Unless otherwise expressly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly, for example, as a fixed connection, a detachable connection, or an integral connection; a mechanical connection or an electrical connection; a direct connection or an indirect connection through an intermediate medium; or a connection within two elements. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.
[0040] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class, without limiting the number of objects; for example, a first object can be one or more. Furthermore, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects have an "or" relationship.
[0041] Definitions:
[0042] PnP (Perspective-n-Points) refers to the problem of object motion localization from 3D to 2D point pairs. That is, given the coordinates of the object in the world coordinate system and the pixel coordinates of the object in the image plane of the camera, the problem is to solve for the pose of the camera (six degrees of freedom, position coordinates and three orientation angles).
[0043] IMU stands for Inertial Measurement Unit.
[0044] Programmable Logic Controller (PLC).
[0045] LQR algorithm: Based on a linear system model, it solves for the optimal control input by optimizing a quadratic cost function (such as path deviation, control input, etc.), and is suitable for linear systems or locally linearized nonlinear systems.
[0046] MPC algorithm: By predicting the state and control input for the next N steps, it finds the optimal control sequence that minimizes the cost function, performs rolling optimization at each step, and dynamically adjusts the control strategy.
[0047] HDR enhancement is a technique that optimizes visual effects by improving the dynamic range of contrast and brightness in an image. It is commonly used in display devices, photography, and video processing.
[0048] Region of Interest (ROI) cropping is a technique in image processing that extracts a subset of an image by defining specific regions (such as rectangles, circles, or polygons). Its aim is to focus on key content, reduce computational load, and improve processing efficiency.
[0049] Reference Figure 1 and Figure 2 This application provides a method for correcting the aerial position of a container, which specifically includes:
[0050] S0 Trigger and Initialization: Receives a lift or position signal, initiates a calibration session, and synchronizes the clock. Outputs the session context.
[0051] S1 Multi-source Acquisition: Acquires data from top / side view cameras, laser rangefinders, IMUs, and PLCs, and outputs multi-source data packets.
[0052] S2 Image and Sensing Preprocessing: Performs distortion correction, HDR enhancement, dehazing, image stabilization, and ROI cropping. Outputs synchronized frames.
[0053] S3 Feature Detection and Target Recognition: Identifies corner castings, edges, and guide grooves; different algorithms are used for different objects. Outputs a set of feature point coordinates.
[0054] S4 Pose Calculation (Fusion Positioning): Uses PnP or multi-view geometry combined with laser height to solve for 6DoF pose T and outputs the pose result.
[0055] S5 Desired Pose Establishment: Generating the target pose from the CTS / ship diagram Output standard alignment reference.
[0056] S6 Errors and Dynamic Prediction: Calculation Errors Use EKF to predict short-time bias and output the prediction results.
[0057] S7 Correction Planning: Assign control quantities based on available execution axes, and generate target assignment tables and constraints.
[0058] S8 Trajectory Generation: The trajectory is calculated using LQR / MPC, anti-swing compensation is added, and the control sequence u(t) is output.
[0059] S9 Safety Threshold and Dynamic Assessment: Monitors gaps, wind speed, intrusion, and triggers warnings and pauses for abnormal events.
[0060] S10 Closed-loop execution and feedback: PLC executes control, updates errors in real time, and forms a closed loop.
[0061] S11 Alignment Confirmation and Linkage Control: After the error reaches the tolerance, the locking or lowering is executed and recorded.
[0062] S12 Data Recording and Self-Learning: Capture five-view images, error curves, and logs, and incorporate them into the retraining dataset.
[0063] In the system implementing this embodiment, the main functional divisions are as follows:
[0064] Module enter Output use Feature detection Image Frame Feature points Pose calculation Pose calculation Feature point + laser height T Error prediction Error prediction T, e, Δe prediction Trajectory Planning Trajectory Planning e, Δe u(t) Control Execution Control Execution u(t) Feedback data Update error Data learning Event Data Model parameters Improve prediction accuracy
[0065] Beneficial effects of this embodiment
[0066] 1. Establish a full-process 6DoF closed loop to achieve real-time attitude correction; 2. Combine EKF and MPC algorithms to enable stable iteration between prediction and execution; 3. Safety assessment is embedded in the main loop, and abnormalities will automatically interrupt the process; 4. The data learning module continuously optimizes the model; 5. Supports deployment in multiple scenarios (inside the cabin, at the ship's side, and in the yard).
[0067] It is understood that in the actual scenarios described in this embodiment, including in-flight alignment within the cabin, automatic correction is performed using the guide beam as a reference, and automatic unlocking occurs once the tolerance is met. Before landing, correction is performed using the chassis lock position as... It performs yaw and lateral shift corrections, and links speed limits with driver confirmation.
[0068] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0069] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical coding feature maps; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for correcting the aerial position of a container, characterized in that, include: Receive lifting or positioning signals, initiate a calibration session, and synchronize the clock; Data is collected by multiple sensors, including multi-angle cameras, and multi-source data packets are output. Process the images in the multi-source data packets and output synchronization frames; Identify container feature points from the synchronization frame and output the feature point coordinate set; Based on the feature point coordinate set, solve for the pose T and output the pose result; Generate target pose Output standard alignment reference; Calculation error It also predicts short-time biases and outputs the prediction results; Based on the available execution axes, allocate control quantities and generate a target allocation table and constraints; Calculate the trajectory, add anti-slip compensation, and output the control sequence; PLC execution control, with real-time error updates; Once the error reaches the tolerance level, unlocking or lowering is performed and recorded.
2. The container aerial position correction method according to claim 1, characterized in that, include: Capture five-view images, error curves, and logs, and incorporate them into the retraining dataset.
3. The container aerial position correction method according to claim 1, characterized in that, The data acquisition via multiple sensors, including multi-angle cameras, includes: Data is acquired from top-view / side-view cameras, laser rangefinders, IMUs, and PLCs.
4. The container aerial position correction method according to claim 1, characterized in that, The process of processing images from multi-source data packets and outputting synchronization frames specifically includes: Perform distortion correction, HDR enhancement, dehazing, image stabilization, and ROI cropping on images from multi-source data packets, and output synchronized frames.
5. The container aerial position correction method according to claim 1, characterized in that, The step of identifying container feature points from the synchronization frame and outputting a set of feature point coordinates specifically includes: Identify the corner castings, edges, and guide grooves of the container from the synchronization frame, and output the set of feature point coordinates.
6. The container aerial position correction method according to claim 3, characterized in that, The process of solving the pose T based on the feature point coordinate set and outputting the pose result is as follows: The 6DoF pose T is solved using PnP or multi-view geometry combined with laser height calculation, and the pose results are output.
7. The container aerial position correction method according to claim 1, characterized in that, Use EKF to predict short-term biases.
8. The container aerial position correction method according to claim 1, characterized in that, The calculated trajectory, with anti-swing compensation added, outputs a control sequence, specifically including: The trajectory is calculated using LQR / MPC, anti-swing compensation is added, and the control sequence u(t) is output.
9. The container aerial position correction method according to claim 1, characterized in that, Also includes: Monitor gaps, wind speed, and intrusions, and trigger warnings and pauses when anomalies are detected.
10. A container aerial position correction system, characterized in that, include: Memory, used to store programs; A processor for loading a program to execute the container air position correction method as described in any one of claims 1-9.