RTG automatic turn-around method and system based on visual analysis

Abstract

The application provides an RTG automatic transfer method and system based on visual analysis. The scheme of the application can realize real-time monitoring of pedestrian and vehicle conditions on a yard road, judges whether there is a safety hazard, and automatically issues an alarm when necessary to remind a tire crane driver to stop transfer operation, ensures operation safety, and does not affect the passing of the yard road.

Description

Technical Field

[0001] This invention relates to the field of intelligent security port technology, and more specifically, to an RTG automatic transition method and system based on visual analysis. Background Technology

[0002] In container yards, rubber-tired gantry cranes (LTGs) are the primary lifting equipment used for stacking and loading / unloading containers. However, during the process of LTGs switching operations from one yard to another, they often need to cross the yard's roads. Previously, to ensure operational safety, safety personnel were typically assigned to guide the cranes, requiring vehicles on the roads to temporarily stop to allow the LTGs to pass safely. While this method provides a certain level of safety, it has several problems. First, this manual guidance method is time-consuming and inefficient, as it requires additional manpower and necessitates temporarily halting vehicle traffic on the yard's roads during LTG transfers, easily causing traffic congestion and work delays. Second, due to human subjectivity and attention limitations, manual guidance may lead to misjudgments or oversights, resulting in safety hazards.

[0003] Therefore, there is an urgent need for an efficient and intelligent method to solve the safety problems of tire crane relocation operations in container yards. Summary of the Invention

[0004] In order to at least solve the technical problems existing in the background art, the present invention provides a visual analysis-based RTG automatic transition method, system, electronic device, storage medium and computer program product.

[0005] This invention provides a visual analysis-based automatic RTG transition method, comprising the following steps:

[0006] By using camera mapping technology, a mapping relationship is established between pixel coordinates in the camera and geographic information coordinates;

[0007] Identify the tire crane and each warning target in the camera image, and use the above mapping relationship to convert the pixel coordinates of the tire crane and each warning target into geographic information coordinates;

[0008] Based on the geographic information coordinates, predict the running direction and speed of each of the early warning targets;

[0009] Based on the geographic coordinates of the tire crane, the geographic coordinates of each warning target, the direction of travel, and the speed of travel, a collision risk analysis is performed on the transfer area of ​​the tire crane. Based on the collision risk analysis results, it is determined whether to issue a warning message to the tire crane cab.

[0010] Optionally, the step of establishing a mapping relationship between pixel coordinates in the camera and geographic information coordinates using camera mapping technology includes:

[0011] Using a specific calibration board or calibration point as a reference, and employing relevant calibration algorithms, the pixel coordinates in the images captured by the camera are converted into actual geographic coordinates, thereby establishing a mapping relationship between the pixel coordinates in the camera and geographic information coordinates.

[0012] Optionally, predicting the running direction and speed of each of the early warning targets based on the geographic information coordinates includes:

[0013] Based on the geographic coordinates of each warning target in consecutive frame images, the corresponding motion trajectory is obtained. Combining the principles of object kinematics, the running direction and running speed of the corresponding warning target are predicted.

[0014] Optionally, before identifying the tire crane and each warning target in the camera image, the method further includes:

[0015] The acquired video stream is preprocessed, including noise reduction, image enhancement, and size calibration.

[0016] Optionally, the YOLO algorithm based on deep learning is used to identify the tire crane and each of the warning targets in the camera image.

[0017] Optionally, the step of performing collision risk analysis on the relocation area of ​​the tire crane based on the geographical coordinates of the tire crane and the geographical coordinates of each of the warning targets, the direction of operation, and the speed of operation includes:

[0018] In the first period before the relocation begins, a warning area is determined based on the geographic information coordinates of the tire crane. Based on the geographic information coordinates of each warning target, the direction of operation, and the speed of operation, it is calculated whether each warning target will enter the warning area after the first period. If so, it is determined that there is a collision risk in the relocation area of ​​the tire crane; otherwise, it is determined that there is no collision risk in the relocation area of ​​the tire crane.

[0019] During the second period after the relocation begins, a warning area is determined based on the geographic information coordinates of the tire crane. Based on the geographic information coordinates of each warning target, the running direction, and the running speed, it is calculated whether each warning target will enter the warning area after the second period. If so, it is determined that there is a collision risk in the relocation area of ​​the tire crane; otherwise, it is determined that there is no collision risk in the relocation area of ​​the tire crane.

[0020] Wherein, the first duration is longer than the second duration.

[0021] This invention also provides a visual analysis-based RTG automated transfer system, comprising a plurality of cameras, a processing module, and a storage module deployed within a container yard, wherein the processing module is connected to each of the cameras and the storage module respectively; wherein,

[0022] The storage module is used to store executable computer program code;

[0023] The camera is used to capture real-time video streams of the container yard road area and transmit them to the processing module.

[0024] The processing module is configured to execute the method described in the preceding one by invoking the executable computer program code in the storage module.

[0025] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to perform the method as described in any of the preceding claims.

[0026] The present invention also provides a computer storage medium storing a computer program that, when executed by a processor, performs the method described in any of the preceding claims.

[0027] The present invention also provides a computer program product, comprising a computer program stored on a non-transitory computer-readable medium, characterized in that: when the computer program is executed by a processor, it implements the method described in any of the preceding claims.

[0028] The proposed solution can automatically monitor and provide early warnings about pedestrians and vehicles on container yard roads to ensure the safety and efficiency of rubber-tired gantry crane (LTG) relocation operations. By receiving the LTG relocation operation signal, the system automatically activates surrounding cameras to perform real-time analysis of the road areas the relocation will traverse, detecting the presence and movement of pedestrians and vehicles, and making intelligent judgments and early warnings based on the detection results, thereby improving operational safety and efficiency. Attached Figure Description

[0029] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of an RTG automatic transition method based on visual analysis disclosed in an embodiment of the present invention.

[0031] Figure 2 This is a flowchart illustrating an RTG automatic transition method based on visual analysis disclosed in an embodiment of the present invention.

[0032] Figure 3 This is a schematic diagram of the structure of an RTG automatic transition system based on visual analysis disclosed in an embodiment of the present invention. Detailed Implementation

[0033] The technical solutions of the embodiments of the present 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 the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0035] In the description of this invention, it should be noted that if terms such as "upper," "lower," "inner," or "outer" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of this invention is usually placed, they are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the system or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this invention.

[0036] The terms "first," "second," "third," and "fourth," etc., used in the specification and claims of this invention are used to distinguish different objects, not to describe a specific order of objects. For example, first input, second input, third input, and fourth input, etc., are used to distinguish different inputs, not to describe a specific order of inputs.

[0037] In embodiments of the present invention, the terms "exemplarily" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplarily" or "for example" in embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the terms "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0038] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more, for example, multiple processing units means two or more processing units; multiple elements means two or more elements, etc.

[0039] It should be noted that, where there is no conflict, the features in the embodiments of the present invention can be combined with each other.

[0040] like Figure 1 As shown in the figure, an RTG automatic transition method based on visual analysis according to an embodiment of the present invention includes the following steps:

[0041] S1. Establish a mapping relationship between pixel coordinates in the camera and geographic information coordinates through the camera's map calibration technology;

[0042] Camera calibration refers to the process of determining the camera's internal parameters (such as focal length and principal point offset) and external parameters (such as the camera's position and orientation), as well as mapping the camera's pixel coordinates to the real-world coordinate system. Its main principles are as follows:

[0043] Internal parameter calibration: Using a calibration board or a specific calibration object, a series of images are captured at different positions and angles. By mapping the pixel coordinates of specific points in these images (such as the corner points of the calibration board) to real-world coordinates, the camera's internal parameters, such as focal length, principal point offset, and lens distortion, are determined using the camera model and calibration algorithms.

[0044] External parameter calibration: For each calibration image, the camera's position and orientation need to be recorded. Calculations are performed using known reference points and scene structure.

[0045] Coordinate mapping: After calibration, the pixel coordinates in the image captured by the camera can be mapped to the real-world coordinate system using the calibration results. This allows the target position in the image to be converted into coordinates in the actual scene, achieving an accurate correspondence between the image and the real world.

[0046] S2. Identify the tire crane and each warning target in the camera image, and use the above mapping relationship to convert the pixel coordinates of the tire crane and each warning target into geographic information coordinates;

[0047] S3. Based on the geographic information coordinates, predict the running direction and running speed of each of the early warning targets;

[0048] S4. Based on the geographic information coordinates of the tire crane and the geographic information coordinates of each of the warning targets, the running direction, and the running speed, perform a collision risk analysis on the transfer area of ​​the tire crane, and determine whether to issue a warning message to the tire crane cab based on the collision risk analysis results.

[0049] When a collision risk is detected and the warning target has not stopped, the system automatically issues a warning signal to remind the tire crane operator to stop the relocation operation. The warning signal is delivered through sound, lights, and digital displays so that the operator can take timely measures to avoid potential safety risks.

[0050] In this embodiment of the invention, the invention makes full use of cameras deployed in the relocation area of ​​the tire crane. The cameras are used to automatically analyze the position of the tire crane, the position of each warning target, the running direction, and the running speed in the relocation area to conduct collision risk analysis. When there is a collision risk, the invention sends a warning message to the tire crane cab for the driver's reference, so as to ensure the safe conduct of the relocation operation.

[0051] The aforementioned warning targets include pedestrians and various vehicles. Computer vision technology, including target detection and tracking algorithms, is used to analyze and process images captured by the camera in real time, thereby accurately identifying various targets in the scene. The pixel coordinates of the identified targets within the camera are then converted into actual geographic coordinates. Through the previously performed camera mapping, the pixel coordinates in the camera image can be mapped to actual geographic coordinates, thus obtaining the target's location information in the actual scene.

[0052] Furthermore, the above steps can be integrated into a real-time monitoring system to continuously monitor and analyze pedestrian and vehicle conditions in the container yard road area. Additionally, the intelligent detection system can be integrated with the relocation operation signal interface of the rubber-tired gantry cranes to achieve real-time communication and collaborative operation between the system and the gantry cranes, ensuring the safe conduct of relocation operations.

[0053] The solution of the present invention can achieve at least the following effects:

[0054] 1) Mapping is used to map the pixel coordinates in the camera image to the actual geographic coordinates, improving the accuracy and reliability of location information; 2) Computer vision technology is used to identify and track targets in the image, enabling real-time monitoring of the scene; 3) Combining the principles of object kinematics, the system can accurately predict the direction and speed of pedestrians and vehicles, and detect potential safety hazards in advance; 4) The automatic warning system can issue timely alarms to remind the tire crane operator to pay attention to safety and reduce the risk of accidents.

[0055] Optionally, the step of establishing a mapping relationship between pixel coordinates in the camera and geographic information coordinates using camera mapping technology includes:

[0056] Using a specific calibration board or calibration point as a reference, and employing relevant calibration algorithms, the pixel coordinates in the images captured by the camera are converted into actual geographic coordinates, thereby establishing a mapping relationship between the pixel coordinates in the camera and geographic information coordinates.

[0057] In this embodiment of the invention, a calibration plate or calibration point is set up in the container yard, the geographic information coordinates of the calibration plate or calibration point are determined in advance, calibration images are collected and camera maps are calibrated, and then the internal and external parameters of the camera are established using relevant calibration algorithms, and a mapping relationship is established between pixel coordinates and geographic information coordinates.

[0058] Optionally, predicting the running direction and speed of each of the early warning targets based on the geographic information coordinates includes:

[0059] Based on the geographic coordinates of each warning target in consecutive frame images, the corresponding motion trajectory is obtained. Combining the principles of object kinematics, the running direction and running speed of the corresponding warning target are predicted.

[0060] In this embodiment of the invention, by fitting the geographic information coordinates of the warning target identified in each image frame, the motion trajectory of the warning target can be obtained. In addition to the geographic information coordinates, the motion trajectory also includes the motion direction and motion speed calculated in the second calculation. By combining the kinematics principle of the object, the running direction and running speed of the warning target in the next period of time can be deduced.

[0061] This step is preferably implemented using a filter method (such as a Kalman filter).

[0062] Optionally, before identifying the tire crane and each warning target in the camera image, the method further includes:

[0063] The acquired video stream is preprocessed, including noise reduction, image enhancement, and size calibration.

[0064] In this embodiment of the invention, a real-time video stream of the container yard road area can be acquired using a camera or other image acquisition device. However, before performing target recognition and feature extraction on the real-time video stream, preprocessing of the acquired video stream is required, including noise reduction, image enhancement, and size calibration, to improve the accuracy of subsequent target detection and tracking.

[0065] Optionally, the YOLO algorithm based on deep learning is used to identify the tire crane and each of the warning targets in the camera image.

[0066] In this embodiment of the invention, a target detection algorithm is used to analyze the preprocessed video frames to identify targets such as tire cranes, pedestrians, and vehicles. The invention preferably uses the YOLO algorithm based on deep learning. For each detected target, target recognition is then performed to determine its category and location. The invention preferably uses a pre-trained neural network model to achieve target recognition.

[0067] Optionally, the step of performing collision risk analysis on the relocation area of ​​the tire crane based on the geographical coordinates of the tire crane and the geographical coordinates of each of the warning targets, the direction of operation, and the speed of operation includes:

[0068] In the first period before the relocation begins, a warning area is determined based on the geographic information coordinates of the tire crane. Based on the geographic information coordinates of each warning target, the direction of operation, and the speed of operation, it is calculated whether each warning target will enter the warning area after the first period. If so, it is determined that there is a collision risk in the relocation area of ​​the tire crane; otherwise, it is determined that there is no collision risk in the relocation area of ​​the tire crane.

[0069] During the second period after the relocation begins, a warning area is determined based on the geographic information coordinates of the tire crane. Based on the geographic information coordinates of each warning target, the running direction, and the running speed, it is calculated whether each warning target will enter the warning area after the second period. If so, it is determined that there is a collision risk in the relocation area of ​​the tire crane; otherwise, it is determined that there is no collision risk in the relocation area of ​​the tire crane.

[0070] Wherein, the first duration is longer than the second duration.

[0071] In this embodiment of the invention, the invention analyzes whether there is a collision risk in the transfer area of ​​the tire crane in two time periods: before the transfer begins and after the transfer begins. Specifically:

[0072] In the first period before the relocation begins (from receiving the relocation start signal from the cab until the tire crane starts), a first warning zone is determined based on the tire crane's position coordinates and its own dimensions and structure. The first warning zone includes the area where the tire crane itself is located, plus a small section of its relocation route corresponding to the current moment. In the second period after the relocation begins (from before the tire crane starts until the relocation ends), a second warning zone is determined in the same manner. Based on the aforementioned motion information of each warning target, it can be calculated whether it will enter the first or second warning zone after the first or second time period. If so, it is determined that the warning target poses a risk of collision with the tire crane, and a warning message needs to be sent to the cab for the driver's reference to take actions such as braking, deceleration, or issuing a warning.

[0073] Specifically, the first and second time periods before the start of the transfer are different, with the second time period being shorter than the first. This is because before the rubber-tired gantry crane starts moving, it has not yet entered the road within the container yard and is stationary. Pedestrians or vehicles intending to enter the transfer area on this road are more likely to perceive the crane as not started and not requiring transfer. Therefore, they are more likely not to slow down, leading to a higher risk of collision. Thus, this invention sets a longer first time period within the first time period, meaning that a warning is issued when the remaining time for pedestrians or vehicles to enter the warning area of ​​the rubber-tired gantry crane is predicted to be longer. Once the rubber-tired gantry crane is started, it enters the road within the container yard in motion. Due to its large size and easy identification, pedestrians or vehicles intending to enter the transfer area on this road are more likely to determine that the gantry crane is started and needs to be transferred. Therefore, pedestrians or vehicles are less likely to drive without slowing down, resulting in a lower risk of collision. Thus, this invention sets the second time period to be shorter, meaning that the warning is only issued when the remaining time for pedestrians or vehicles to enter the warning area of ​​the gantry crane is short.

[0074] It should be noted that when the tire crane starts its relocation operation, the operator communicates with the intelligent detection system through the relocation operation signal interface to send a relocation start signal to it.

[0075] like Figure 2 As shown, this invention also discloses a visual analysis-based RTG automated transfer system, comprising several cameras, a processing module, and a storage module deployed within the container yard, wherein the processing module is connected to each of the cameras and the storage module respectively; wherein,

[0076] The storage module is used to store executable computer program code;

[0077] The camera is used to capture real-time video streams of the container yard road area and transmit them to the processing module.

[0078] The processing module is configured to execute the method described in the preceding one by invoking the executable computer program code in the storage module.

[0079] The present invention also discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory to execute the method as described in any of the preceding claims.

[0080] The present invention also discloses a computer storage medium storing a computer program, which is executed by a processor as described in any of the preceding methods.

[0081] The present invention also discloses a computer program product comprising a computer program stored on a non-transitory computer-readable medium, wherein the computer program, when executed by a processor, implements the method described in any of the preceding claims.

[0082] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0083] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0084] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0085] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0086] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0087] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0088] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0089] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A visual analysis-based automatic RTG transition method, characterized in that, Includes the following steps: By using camera mapping technology, a mapping relationship is established between pixel coordinates in the camera and geographic information coordinates; Identify the tire crane and each warning target in the camera image, and use the above mapping relationship to convert the pixel coordinates of the tire crane and each warning target into geographic information coordinates; Based on the geographic information coordinates, predict the running direction and speed of each of the early warning targets; Based on the geographic coordinates of the tire crane and the geographic coordinates of each warning target, the direction of operation, and the speed of operation, a collision risk analysis is performed on the transfer area of ​​the tire crane. Based on the collision risk analysis results, it is determined whether to issue a warning message to the tire crane cab. The YOLO algorithm based on deep learning identifies the tire crane and each of the warning targets in the camera image; The step of performing collision risk analysis on the relocation area of ​​the tire crane based on the geographical coordinates of the tire crane and the geographical coordinates of each of the early warning targets, the direction of operation, and the speed of operation includes: In the first period before the relocation begins, a warning area is determined based on the geographic information coordinates of the tire crane. Based on the geographic information coordinates of each warning target, the direction of operation, and the speed of operation, it is calculated whether each warning target will enter the warning area after the first period. If so, it is determined that there is a collision risk in the relocation area of ​​the tire crane; otherwise, it is determined that there is no collision risk in the relocation area of ​​the tire crane. During the second period after the relocation begins, a warning area is determined based on the geographic information coordinates of the tire crane. Based on the geographic information coordinates of each warning target, the running direction, and the running speed, it is calculated whether each warning target will enter the warning area after the second period. If so, it is determined that there is a collision risk in the relocation area of ​​the tire crane; otherwise, it is determined that there is no collision risk in the relocation area of ​​the tire crane. Wherein, the first duration is longer than the second duration.

2. The RTG automatic transition method based on visual analysis according to claim 1, characterized in that: The establishment of a mapping relationship between pixel coordinates in the camera and geographic information coordinates using camera mapping technology includes: Using a specific calibration board or calibration point as a reference, and employing relevant calibration algorithms, the pixel coordinates in the images captured by the camera are converted into actual geographic coordinates, thereby establishing a mapping relationship between the pixel coordinates in the camera and geographic information coordinates.

3. The RTG automatic transition method based on visual analysis according to claim 1, characterized in that: The prediction of the running direction and speed of each of the early warning targets based on the geographic information coordinates includes: Based on the geographic coordinates of each warning target in consecutive frame images, the corresponding motion trajectory is obtained. Combining the principles of object kinematics, the running direction and running speed of the corresponding warning target are predicted.

4. The RTG automatic transition method based on visual analysis according to claim 1, characterized in that: Before identifying the tire crane and various warning targets in the camera view, the following is also included: The acquired video stream is preprocessed, including noise reduction, image enhancement, and size calibration.

5. A visual analysis-based RTG automated transfer system, comprising a plurality of cameras, a processing module, and a storage module deployed within a container yard, wherein the processing module is connected to each of the cameras and the storage module respectively; wherein, The storage module is used to store executable computer program code; The camera is used to capture real-time video streams of the container yard road area and transmit them to the processing module. The characteristic is that the processing module is configured to execute the method as described in any one of claims 1-4 by calling the executable computer program code in the storage module.

6. An electronic device, comprising: Memory containing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to perform the method as described in any one of claims 1-4.

7. A computer storage medium storing a computer program, characterized in that: The computer program is executed by the processor to perform the method as described in any one of claims 1-4.

8. A computer program product comprising a computer program stored on a non-transitory computer-readable medium, characterized in that: When the computer program is executed by a processor, it implements the method as described in any one of claims 1-4.

Images