Data processing method and system of half-height container management system

Abstract

The invention provides a data processing method and system for a half-height container management system, and the method comprises the steps: constructing a management model corresponding to a half-height container yard, and enabling the management model to comprise a plurality of monitoring points corresponding to container stacking; acquiring side images of the corresponding container stacks shot by the acquisition equipment at the monitoring points, and performing safety state analysis on the side images meeting angle identification conditions according to the angle analysis model to obtain angle analysis data; performing safety state analysis on the side image meeting the detail identification condition according to the multi-stage monitoring model to obtain detail analysis data; and generating safety monitoring data corresponding to the container stacking according to the angle analysis data or the detail analysis data, and updating the management model according to the safety monitoring data to obtain a safety monitoring model.

Description

Technical Field

[0001] The invention relates to data processing technology, and in particular to a data processing method and system for a semi-high container management system. Background Art

[0002] A half-high container is a special container that is half the height of a standard container. It is mainly used to transport heavy, large, bulk or oversized goods. In order to protect the safety of the goods, half-high containers are generally equipped with door locks to prevent the goods from being lost, damaged or stolen.

[0003] In the prior art, patrol personnel are generally dispatched to monitor the door lock status of each semi-high container. However, this method may not be able to provide timely warnings when the door lock status is abnormal, thereby reducing the safety of the goods in the container.

[0004] Therefore, how to monitor the door lock status of the container and improve the safety of the goods has become an urgent problem that needs to be solved. Summary of the invention

[0005] The present invention provides a data processing method and system for a half-high container management system, which can monitor the door lock status of the container and improve the safety of the goods.

[0006] A first aspect of the present invention provides a data processing method for a semi-high container management system, comprising: Constructing a management model corresponding to a semi-high container yard, the management model including monitoring points corresponding to a plurality of container stacks; Obtaining a side image of the corresponding container stack taken by the acquisition device at the monitoring point, performing a safety status analysis on the side image that meets the angle recognition condition according to the angle analysis model, and obtaining angle analysis data; Perform safety status analysis on the side image that meets the detail recognition conditions according to the multi-level monitoring model to obtain detail analysis data; The safety monitoring data corresponding to the container stack is generated according to the angle analysis data or the detail analysis data, and the management model is updated according to the safety monitoring data to obtain a safety monitoring model.

[0007] Optionally, in a possible implementation of the first aspect, obtaining a side image of the corresponding container stack photographed by a collection device at the monitoring point, performing a safety status analysis on the side image that meets the angle recognition condition according to an angle analysis model, and obtaining angle analysis data, includes: Acquire a real-time shooting interface of the acquisition device at the monitoring point based on a preset overhead shooting height, extract a stack overhead shooting contour in the real-time shooting interface, wherein the center point of the stack overhead shooting contour corresponds to the center point of the real-time shooting interface; Determine a contour line corresponding to an end face side of the container stack in the stack overhead profile as a reference line, wherein the end face side includes a front end with a container door and a rear end without a container door; Connect the center points of the two reference lines to obtain a guide line, and extend both ends of the guide line according to the overall shooting distance; Determine the direction from the center point of the guide line to the endpoint of the guide line as the guide direction, and control the acquisition device to move to the guide point corresponding to the corresponding endpoint based on the guide direction and the guide line; Acquire the end face side corresponding to the guide point as the target side, control the acquisition device to take images of the target side in the height direction according to the side shooting interval distance, and obtain multiple side images; Perform a door lock structure analysis on the side image, determine that the side image that meets the angle recognition condition is a first target image, and perform a safety status analysis on the first target image according to an angle analysis model to obtain angle analysis data.

[0008] Optionally, in a possible implementation manner of the first aspect, an end face side corresponding to the guide point is obtained as a target side, and the acquisition device is controlled to capture an image of the target side in a height direction according to a side shooting interval distance to obtain a plurality of side images, including: After the acquisition device reaches the guide point, the acquisition device is controlled to move to the side shooting position point in the height direction according to the side shooting interval distance, taking the guide point as a reference point; Acquire the side image captured by the acquisition device at the side shooting position, extract the end face contour in the side image, and acquire four edge points corresponding to the first end face contour in the acquisition direction; Generate an identification frame according to the edge points, and determine an image area in the side image located within the identification frame as an identification area; Performing door lock recognition on the recognition area, and when a door lock structure exists in the recognition area, determining that the side image meets the monitoring recognition condition; When the door lock structure does not exist in the recognition area, determining that the side image does not meet the monitoring and recognition condition, deleting the side image, and determining that the acquisition sequence number corresponding to the side image is the target sequence number; Acquire a current shooting height corresponding to the target ordinal number, and determine that the current shooting height is a target shooting height when the acquisition device acquires a side image of the other end face; Taking the side shooting position point as a reference, continue to control the acquisition device to move to the next side shooting position point in the height direction according to the side shooting interval distance; Repeat the above steps of identifying the door lock structure according to the side image until the acquisition sequence number is the preset acquisition sequence number corresponding to the container stack, and stop acquiring the side image of the target side.

[0009] Optionally, in a possible implementation manner of the first aspect, performing a door lock structure analysis on the side image, determining that the side image that meets the angle recognition condition is a first target image, and performing a safety status analysis on the first target image according to an angle analysis model to obtain angle analysis data, including: A side image satisfying the monitoring and identification condition is obtained as an identification image, and a hanging lock identification is performed on a door lock handle combination corresponding to the door lock structure in the identification image; Determine that the side image of the door lock handle combination without a hanging lock meets the angle recognition condition, and obtain the side image as the first target image; The closing angle corresponding to each door lock handle combination in the first target image is obtained according to the angle analysis model, and the safety status analysis of the closing angle is performed to obtain angle analysis data.

[0010] Optionally, in a possible implementation of the first aspect, obtaining a closing angle corresponding to each door lock handle combination in the first target image according to the angle analysis model, and performing a safety state analysis on the closing angle to obtain angle analysis data includes: Acquire the outline of the door handle support and the door handle in each of the door lock handle assemblies in the first target image, and the outline of the door lock rod connected to each of the door lock handle assemblies; Determine the connection point between the door lock rod contour and the door handle support contour, connect the center point of the door handle contour and the connection point to obtain a handle angle line, and connect the center point of the door handle support contour and the connection point to obtain a reference angle line; Determine a closing angle between the handle tilt line and the reference angle line, and when the closing angle is greater than or equal to a closing angle threshold, determine that the corresponding door lock handle combination is an abnormal door lock combination; When the closing angle is less than the closing angle threshold, the corresponding door lock handle combination is determined to be a normal door lock combination, and angle analysis data is obtained according to the abnormal door lock combination and / or the normal door lock combination.

[0011] Optionally, in a possible implementation of the first aspect, performing a safety status analysis on the side image that meets the detail recognition condition according to the multi-level monitoring model to obtain detail analysis data includes: Performing a door lock structure analysis on the side image, determining that the side image that meets the detail recognition condition is a second target image, and determining a detail collection set corresponding to the second target image according to the multi-level monitoring model; Generate an outer contour frame of the detail collection set, obtain a contour center point of the outer contour frame, and determine a direction from a center point of the second target image to the contour center point as an adjustment direction; Determine a phase difference distance between a center point of the second target image and a center point of the contour, and control the acquisition device to move to a first position point based on the adjustment direction and the phase difference distance; Control the acquisition device to move forward in the detail acquisition direction until the interface proportion of the overall combined contour corresponding to the detail acquisition set in the real-time shooting interface is within the optimal shooting proportion interval, and stop the movement of the acquisition device, and determine the corresponding position point as the detail acquisition point; The detail image captured by the acquisition device at the detail acquisition point is acquired, and the hanging lock in the detail image is securely identified to obtain detail analysis data.

[0012] Optionally, in a possible implementation manner of the first aspect, performing a door lock structure analysis on the side image, determining that the side image that meets the detail recognition condition is a second target image, and determining a detail collection set corresponding to the second target image according to the multi-level monitoring model, includes: A side image satisfying the monitoring and identification condition is obtained as an identification image, and a hanging lock identification is performed on a door lock handle combination corresponding to the door lock structure in the identification image; Determine that the side image of the door lock handle combination with the hanging lock meets the detail recognition condition, and obtain the side image as the second target image; Acquire the combined contours corresponding to each door lock handle combination in the second target image according to the multi-level monitoring model, number each of the combined contours, and obtain the position number corresponding to each of the combined contours; Based on the center point of each of the combined contours, the combined distance between each of the combined contours is determined, the door lock handle combinations whose combined distance is less than the door lock distance threshold are determined to be the same group of the detail collection set, and a corresponding collection number is added to the detail collection set according to the position number.

[0013] Optionally, in a possible implementation manner of the first aspect, acquiring a detail image captured by the acquisition device at the detail acquisition point, performing security identification on a hanging lock in the detail image, and obtaining detail analysis data includes: Extracting the hanging lock outline corresponding to the hanging lock in each door lock handle combination in the detail image, and when the hanging lock outline is in an open state, determining that the corresponding door lock handle combination is an abnormal door lock combination; When the hanging lock profile is in a closed state, calling a standard hanging lock profile, comparing the hanging lock profile with the standard hanging lock profile to obtain a comparison value, wherein the standard hanging lock profile includes a front standard profile and a back standard profile; The locket contour having the comparison value greater than the similarity threshold is obtained as the secondary determination contour, and the orientation of the secondary determination contour compared with the front standard contour is determined as the positive orientation, and the orientation of the secondary determination contour compared with the rear standard contour is determined as the rear orientation; Retrieving a plurality of reference door images corresponding to the container stack, each of the reference door images being provided with a corresponding preset end face side and a preset acquisition sequence number; Determine, according to the end face side and the acquisition sequence number of the side image corresponding to the detail image, a reference door image corresponding to the detail image as a comparison door image; Determine a reference orientation corresponding to a reference hanging lock contour having the same position number as the second determination contour in the comparison door image, and if the orientation of the second determination contour is consistent with the reference orientation, determine that the corresponding door lock handle combination is a normal door lock combination; If the orientation of the secondary determination profile is inconsistent with the reference orientation, the corresponding door lock handle combination is determined to be an abnormal door lock combination, and detailed analysis data is obtained according to the abnormal door lock combination and / or the normal door lock combination.

[0014] Optionally, in a possible implementation manner of the first aspect, generating safety monitoring data corresponding to the container stack according to the angle analysis data or the detail analysis data, and updating the management model according to the safety monitoring data to obtain a safety monitoring model, includes: Acquire multiple sub-containers corresponding to the container stack, and construct monitoring nodes corresponding to each of the sub-containers; According to the number of stacking layers corresponding to each of the sub-containers, the monitoring nodes are arranged from large to small and then connected to obtain a monitoring structure; Obtaining a collection sequence number corresponding to each of the angle analysis data or the detail analysis data, and binding the monitoring nodes and the angle analysis data or the detail analysis data having the same collection sequence number and arrangement order according to the collection sequence number and the arrangement order of each of the monitoring nodes; Determine the monitoring node where the abnormal door lock combination exists as an abnormal node, and determine the warning level of the abnormal node according to the number of abnormalities corresponding to the abnormal door lock combination; The pixel value corresponding to the corresponding warning level is retrieved to update the abnormal node, and the safety monitoring data corresponding to the container stack is obtained. The safety monitoring data is bound to the corresponding monitoring point in the management model to obtain a safety monitoring model.

[0015] A second aspect of the present invention provides a data processing system for a semi-high container management system, comprising: A management module, used to construct a management model corresponding to a semi-high container yard, wherein the management model includes monitoring points corresponding to a plurality of container stacks; An angle module, used to obtain the side image of the corresponding container stack taken by the acquisition device at the monitoring point, and perform safety status analysis on the side image that meets the angle recognition condition according to the angle analysis model to obtain angle analysis data; A detail module is used to perform safety status analysis on the side image that meets the detail recognition conditions according to the multi-level monitoring model to obtain detail analysis data; A monitoring module is used to generate safety monitoring data corresponding to the container stacking according to the angle analysis data or the detail analysis data, and to update the management model according to the safety monitoring data to obtain a safety monitoring model.

[0016] The beneficial effects of the present invention are as follows: The present invention can monitor the door lock status of the container and improve the safety of the goods. The present invention will dispatch a collection device to monitor the door lock status of each container in a plurality of container stacks in a semi-high container yard, so that when the door lock status of the container is abnormal, the management personnel can be reminded in time to reduce the safety hazards of the goods.

[0017] When monitoring the door lock status of multiple container stacks in a semi-high container yard, the present invention will perform different state detections on the container door locks according to the type of door locks. For door locks without hanging locks, this solution will determine whether they are in a closed state by the closed angle between the door handle and the door handle, so that the management personnel can be reminded in time when the closed angle between the door handle and the door handle is in an abnormal state, such as an open state. For door locks with hanging locks, this solution will control the drone to perform secondary amplification image acquisition on the door locks with hanging locks, so that the door lock handle combination in the image can be clearer, improving the accuracy of recognition, and when performing abnormal analysis, this solution will perform multi-level detection on the closed state and orientation of the hanging lock, so as to further improve the accuracy of recognition.

[0018] The present invention will also determine the corresponding warning level based on the number of abnormal door locks on each container, so that containers with low safety factors can be warned. The present invention will also use different pixel values ​​for different warning levels to display warnings to management personnel, so that management personnel can observe the safety level of the corresponding container through the pixel value and make targeted processing strategies for containers with low safety factors in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flow chart of a data processing method of a semi-high container management system provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a side image captured by a collection device provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a side image provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of a data processing system of a half-high container management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] See also Figure 1 , is a flow chart of a data processing method of a semi-high container management system provided by an embodiment of the present invention, Figure 1 The execution subject of the method shown may be a software and / or hardware device. The execution subject of the present application may include but is not limited to at least one of the following: user equipment, network equipment, etc. Among them, user equipment may include but is not limited to computers, smart phones, personal digital assistants (PDA) and the electronic devices mentioned above. Network equipment may include but is not limited to a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers, wherein cloud computing is a type of distributed computing, a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. It includes steps S1 to S4, as follows: S1, constructing a management model corresponding to a semi-high container yard, wherein the management model includes monitoring points corresponding to a plurality of container stacks.

[0022] In actual applications, in order to ensure the safety of goods in semi-high containers, door locks are generally installed on the containers. If the door locks are damaged, the safety of the goods in the containers may be affected. Based on this, this solution will dispatch collection equipment to monitor the door lock status of each container in multiple container stacks in the semi-high container yard, so that when the door lock status of the container is abnormal, the management personnel can be reminded in time to reduce the safety risks of the goods.

[0023] Among them, the half-high container yard refers to the site where half-high containers are stacked, the container stack refers to the stack formed by multiple stacked half-high containers, and the management model refers to the twin model corresponding to the half-high container yard. The management personnel can construct the management model accordingly based on the actual situation. The model can include monitoring points corresponding to multiple container stacks. Subsequently, the acquisition equipment can be dispatched to the corresponding monitoring points to collect images of the door locks of the container stacks, and the door lock status can be detected for the collected image data, so that the management personnel can be promptly prompted when the door lock status is abnormal. The monitoring point refers to the point for monitoring the door lock status corresponding to the container stack.

[0024] S2, obtaining the side image of the corresponding container stack taken by the acquisition device at the monitoring point, performing safety status analysis on the side image that meets the angle recognition condition according to the angle analysis model, and obtaining angle analysis data.

[0025] The above-mentioned collection equipment can be a drone. Specifically, the drone can go to the monitoring point corresponding to the corresponding container stack to collect images of the end face side of the container stack with the box door, and then analyze the door lock status of the collected image, so as to timely detect containers with abnormal door lock status and remind management personnel.

[0026] The side image refers to the image data taken by the drone on the side of the container stack. It can be understood that when analyzing the door lock status, this solution will perform different state analyses on door locks with hanging locks and door locks without hanging locks. For door locks without hanging locks, this solution will determine whether it is in a closed state based on the closed angle between the door handle and the door handle, that is, use the angle analysis model to perform a safety state analysis on the door lock status. This solution will elaborate on the state analysis method of door locks with hanging locks below, so it will not be repeated here.

[0027] Among them, the angle analysis model refers to a model for performing state analysis on door lock components, such as the closing angle between a door handle and a door handle. When the door lock component in the side image has a hanging lock, it can be determined that the side image meets the angle recognition conditions, that is, it meets the conditions for performing state analysis on the closing angle between the door lock components. The angle analysis data refers to the data obtained after analyzing the closed state of the door lock.

[0028] Based on the above embodiment, the specific implementation of step S2 may be: S21, obtaining a real-time shooting interface of the acquisition device at the monitoring point based on a preset overhead shooting height, extracting a stack overhead shooting contour in the real-time shooting interface, wherein the center point of the stack overhead shooting contour corresponds to the center point of the real-time shooting interface.

[0029] See also Figure 2 , which is a schematic diagram of a side image captured by a collection device provided in an embodiment of the present invention. It can be understood that since a container stack is formed by stacking multiple containers, the drone can first fly above the container stack when collecting data to determine the end face side for image collection, and then go to the corresponding end face side to collect images of the container door on the side of the container. In actual applications, the height at which the drone takes a bird's-eye view of the corresponding container stack can be pre-configured, and at this height the drone can capture the overall outline of the topmost container.

[0030] It is understandable that since the container doors are generally on the side, when the drone is taking a bird's-eye view of the container stack, it can determine the side where the door end face is located, and then move to the front of the corresponding side and then move down to take pictures of the side of each layer of containers. For example, the drone can follow Figure 2 The moving track shown in the figure is moved accordingly, so that the side of the container at the corresponding level can be photographed.

[0031] The preset aerial photography height refers to the pre-set altitude of the drone when taking aerial photography, and the stack aerial photography contour refers to the top contour corresponding to the topmost container when the drone takes aerial photography. It is understandable that in order to enable the drone to be located at the center of the container stack during shooting, the center point of the stack aerial photography contour can be aligned with the center point of the real-time shooting interface.

[0032] S22, determining a contour line corresponding to an end face side of the container stack in the stack overhead profile as a reference line, wherein the end face side includes a front end with a container door and a rear end without a container door.

[0033] It can be understood that the side of the container includes a front face with a door and a rear face without a door, as well as side walls on both sides. When viewed from a top-down angle, its outline is generally rectangular. The lengths of the outlines of the front face and the rear face are generally the same, and the lengths of the outlines of the side walls on both sides are generally the same. The outlines corresponding to the front and rear ends are generally shorter than the outlines corresponding to the side walls. Therefore, it can be determined that the line segment with the shortest length of the stack outline in the top-down shot is the outline corresponding to the end face of the container stack.

[0034] S23, connecting the center points of the two reference lines to obtain a guide line, and extending both ends of the guide line according to the overall shooting distance.

[0035] It can be understood that in order to enable the drone to move to the front of the corresponding end face side and then move down to capture images of the corresponding end face side, a guide line can be generated to guide the movement of the drone, so that the drone can move accordingly in the horizontal direction through the guide line.

[0036] The guide line is a line segment that guides the drone to move horizontally. In order to enable the drone to move to the front of the end face, the two ends of the guide line can be extended so that the drone can move to the front of the container stack. The overall shooting distance can be the shooting distance between the drone and the container when shooting the side of the container. The shooting distance can be set in advance, and at this distance, the drone can capture the image corresponding to the side of the entire container.

[0037] S24, determining the direction from the center point of the guide line to the endpoint of the guide line as the guide direction, and controlling the acquisition device to move to the guide point corresponding to the corresponding endpoint based on the guide direction and the guide line.

[0038] It is understandable that since it is impossible to determine which contour line corresponds to the front end of the container door and which contour line corresponds to the rear end without the container door from a bird's-eye view, and when analyzing the door lock status, the door lock is generally configured on the end face where the container door is located, so it is necessary to analyze the captured image corresponding to the side where the container door is located. Therefore, this solution will first control the drone to go to one side for shooting, and then perform door lock status analysis on the side image corresponding to the container with the container door on this side, and record the container that is not a container door, so that when shooting on the other side, the recorded container corresponding to the container door image can be quickly collected.

[0039] Therefore, the above-mentioned guiding direction includes two directions, namely, the directions pointing from the center point to the two ends of the guiding line. When the UAV is collecting data, it can first go to one side through the guiding line and the guiding direction to collect images, then fly back to the original position, and then go to the other side through the guiding line and another guiding direction to collect images.

[0040] The guidance point refers to the location of the UAV after it moves horizontally according to the guidance line and guidance direction.

[0041] S25, acquiring the end face side corresponding to the guide point as the target side, controlling the acquisition device to take images of the target side in the height direction according to the side shooting interval distance, and obtaining a plurality of side images.

[0042] The target side is the side on which the drone is currently collecting images. When the drone moves downward, it can move according to the side shooting interval distance. The side shooting interval distance is the interval downward movement distance when the drone takes pictures of the container in the height direction. The interval distance can be set accordingly according to the length of the container in the height direction, so that the drone can collect images of each container in the height direction separately when shooting.

[0043] It is worth mentioning that when the drone is collecting images of the side of the topmost container, if it cannot capture a complete image of the side of the container after moving down to the side shooting interval distance, the drone can continue to be controlled to move downward until the drone's real-time shooting interface is able to capture a complete image of the side of the first container, then the drone can be stopped from moving. The drone can continue to move downward according to the side shooting interval distance for subsequent shooting.

[0044] In some embodiments, step S25 may be implemented through steps S251 to S258, as follows: S251, after the acquisition device reaches the guide point, the acquisition device is controlled to move downward to the side shooting position point in the height direction according to the side shooting interval distance, taking the guide point as a reference point.

[0045] The side shooting position point refers to the position point where the drone shoots the side of the container at the corresponding level, for example Figure 2 As shown in , there are 4 layers of containers in total, and the above-mentioned side shooting position point can be the position point when the drone takes a side shot of the top layer, i.e., the 4th layer of containers.

[0046] S252, obtaining the side image captured by the acquisition device at the side capture position, extracting the end face contour in the side image, and obtaining four edge points corresponding to the first end face contour in the acquisition direction.

[0047] like Figure 2 As shown, since containers of adjacent levels are close together, when photographing the containers of the upper level, a portion of the upper part of the containers of the lower level may also be photographed in the image. Therefore, in order to eliminate other interference in the image, this solution will extract the end face of the currently photographed container for subsequent corresponding analysis.

[0048] See also Figure 3, is a schematic diagram of a side image provided by an embodiment of the present invention. It is understandable that the end face profile of a container generally has corresponding edge points. Therefore, in order to determine the end face portion of the container, the end face profile in the side image can be extracted, that is, the overall profile corresponding to the front end or rear end of the container, and then the edge points located at the four corners of the end face profile can be determined, so that the end face area corresponding to the corresponding container can be determined later through the edge points. The edge points can be the four vertices of the end face profile.

[0049] S253: Generate an identification frame according to the edge points, and determine an image area in the side image within the identification frame as a identification area.

[0050] When generating the recognition frame, the four edge points may be connected to obtain a rectangular recognition frame, and then the image area in the side image within the recognition frame is used as the recognition area for subsequent analysis and recognition.

[0051] S254, performing door lock recognition on the recognition area, and when a door lock structure exists in the recognition area, determining that the side image meets a monitoring recognition condition.

[0052] It can be understood that since the collected side image may be an image corresponding to the front face with a container door, or an image corresponding to the rear face without a container door, and the image corresponding to the rear face generally does not have a door lock structure, the door lock recognition can be performed on the recognition area. If there is a door lock structure in the recognition area, it may correspond to the front face, and the door lock status can be monitored. Therefore, it can be determined that the corresponding side image meets the monitoring and recognition conditions, that is, it meets the conditions for door lock status monitoring. Subsequently, the door lock status of the corresponding container can be analyzed for abnormalities based on the image, and the door lock structure, that is, Figure 3 The door lock handle combination shown in .

[0053] S255, when the door lock structure does not exist in the identification area, determine that the side image does not meet the monitoring and identification conditions, delete the side image, and determine that the acquisition sequence number corresponding to the side image is the target sequence number.

[0054] When the door lock structure does not exist in the identification area, it means that the collected side image may not have the image corresponding to the rear end face of the box door, and its front end face may be on the other side. Therefore, it can be determined that the side image does not meet the monitoring and identification conditions, and the side image is deleted.

[0055] The collection sequence number refers to the number of times the drone performs side collection. The collection sequence number is related to the number of container layers collected by the drone. For example Figure 2As shown in , when the drone is collecting side images of the 4th layer container, the corresponding target ordinal number is 1, that is, the 4th layer container is the first container to be collected in the height direction. Since the front end and the rear end correspond to each other, using the collection ordinal number as the target ordinal number can quickly determine the position point of the drone when collecting images on the other side, so that the end face with the box door on the other side can be quickly collected.

[0056] S256, obtaining a current shooting height corresponding to the target sequence number, and determining the current shooting height as a target shooting height when the acquisition device acquires a side image of the other end face.

[0057] Specifically, after obtaining the target ordinal number, the collection height corresponding to the target ordinal number, that is, the above-mentioned current shooting height, can be recorded, and the height can be bound to the other end face side. That is, the drone can be controlled to quickly move down to the corresponding position point to collect data on the door end face of the corresponding container when collecting data on the other side, without having to collect the side faces of the containers at the corresponding levels in turn and then determine whether they are images corresponding to the door end face.

[0058] S257, taking the side shooting position point as a reference, continue to control the acquisition device to move downward to the next side shooting position point in the height direction according to the side shooting interval distance.

[0059] It is worth mentioning that before the drone moves down to the next side-shooting position point for image acquisition, it will complete the analysis of the container door lock status corresponding to the previous position point and then perform the corresponding downward image acquisition. That is, when analyzing the status of the door lock with a hanging lock, this solution will also control the drone to collect detail images of the corresponding container. After the detail image of the previous container is collected, the drone can be controlled to move to the side-shooting position point, and then move down accordingly according to the side-shooting interval distance. After arriving at the next side-shooting position point, the image of the next level of container is collected and the corresponding door lock status analysis is performed.

[0060] Specifically, when moving to the next side shooting position point, the current position point of the drone can be used as a reference, and the side shooting interval distance can be moved downward to reach the next side shooting position point.

[0061] S258, repeating the above step of identifying the door lock structure according to the side image until the acquisition sequence number is a preset acquisition sequence number corresponding to the container stack, and then stopping the acquisition of the side image of the target side.

[0062] Repeat the above steps of identifying the door lock structure based on the side image, that is, repeat the steps of shooting the side image at the side shooting position and analyzing the door lock on the side image. When the door lock structure exists in the side image, the door lock status can be further identified, so that the management personnel can be reminded in time when there is an abnormality in the door lock status. The preset acquisition sequence number can correspond to the number of stacking layers of the container stack. When the container stack has 4 layers, the preset acquisition sequence number can be 4, so that the drone can be controlled to collect side images of each layer of containers in turn.

[0063] It is worth mentioning that when the drone collects images of the other side of the end face, it can arrange multiple target shooting heights from large to small after moving to the corresponding guidance point to obtain a collection sequence, and then move down to the position points corresponding to the corresponding target shooting heights according to the collection sequence to collect images of the corresponding containers. The collected images can directly determine whether they meet the monitoring and identification conditions for subsequent door lock status identification, thereby improving the efficiency of detecting the door lock status on the other side.

[0064] S26, performing a door lock structure analysis on the side image, determining that the side image that meets the angle recognition condition is a first target image, performing a safety status analysis on the first target image according to an angle analysis model, and obtaining angle analysis data.

[0065] It is understandable that, in actual applications, the door lock structure of a container may include a rotating door lock combination and a door lock combination with a hanging lock. The former door lock combination generally includes a door handle and a door handle support, and the container door is locked by rotating the door handle to the corresponding position of the door handle support, while the latter door lock combination generally locks the container door with a hanging lock.

[0066] Therefore, when detecting the door lock status of the former door lock combination, it is possible to determine whether the door lock structure is in a closed state by the angle difference between the door handle and the door handle support. However, when detecting the door lock status of the latter door lock combination, it is necessary to determine whether the door lock status is abnormal by judging the status of the hanging lock.

[0067] Specifically, the side image that meets the angle recognition condition is a side image corresponding to a door lock structure that is a rotary door lock combination. When the state of this door lock structure is identified, the closed angle between the door lock structures can be analyzed through an angle analysis model.

[0068] The angle analysis model is a model for performing closed angle analysis on a door lock combination without a hanging lock, and the angle analysis data is data corresponding to an abnormal door lock or a normal door lock obtained after performing angle analysis on the door lock state.

[0069] Step S26 specifically includes steps S261 to S263, which are as follows: S261, acquiring a side image that meets the monitoring and identification conditions as an identification image, and performing hanging lock identification on a door lock handle combination corresponding to the door lock structure in the identification image.

[0070] It is understandable that only when the side image meets the monitoring and recognition conditions, this solution will perform door lock status recognition on the corresponding side image.

[0071] In practical applications, the contour corresponding to the door lock handle combination can be extracted, and then the sub-contours corresponding to the door handle, door handle and hanging lock in the extracted contour can be determined through the standard image corresponding to the door lock handle combination taken in advance. If there is no hanging lock in the door lock handle combination, that is, when it corresponds to a rotary door lock combination, the sub-contour corresponding to the hanging lock cannot be obtained. Based on this, the door lock handle combination can be identified as a hanging lock to determine its corresponding door lock combination type.

[0072] S262, determining that the side image of the door lock handle combination without a hanging lock meets the angle recognition condition, and acquiring the side image as the first target image.

[0073] The side image of the door lock handle combination without a hanging lock is the side image corresponding to the rotary door lock combination, so it can be determined as the first target image, that is, the image for detecting the door lock state of the rotary door lock combination.

[0074] S263: Acquire the closing angle corresponding to each door lock handle combination in the first target image according to the angle analysis model, and perform safety status analysis on the closing angle to obtain angle analysis data.

[0075] The closing angle is the angle between the door handle and the door handle in the door lock handle combination. Figure 3 As shown, when the rotary door lock combination is closed, the door handle and the door handle support are tightly combined. Therefore, when determining the door lock state corresponding to this type of door lock handle combination, the corresponding abnormality analysis can be performed through the closing angle corresponding to the door lock handle combination.

[0076] In some embodiments, the above angle analysis data can be obtained by the following steps: S2631, acquiring the door handle outline and the door handle outline in each of the door lock handle combinations in the first target image, and the door lock rod outline connected to each of the door lock handle combinations.

[0077] See also Figure 3The door lock handle combination is generally connected with the door lock rod. Therefore, when determining the closing angle corresponding to the door lock handle combination, it can be determined accordingly according to the outline of the door handle support, the outline of the door handle, and the outline of the door lock rod.

[0078] S2632, determine the connection point between the door lock rod contour and the door handle support contour, connect the center point of the door handle contour and the connection point to obtain the handle angle line, connect the center point of the door handle support contour and the connection point to obtain the reference angle line.

[0079] When determining the connection point between the door lock rod contour and the door handle contour, multiple contour points in the door handle contour that intersect with the door lock rod contour can be determined, and then the X-coordinate extreme values ​​and Y-coordinate extreme values ​​of these contour points are obtained, and the center point corresponding to the multiple contour points is determined according to the middle value of the extreme coordinate values, and the center point is determined as the connection point.

[0080] The oblique direction of the door handle can be obtained by connecting the center point and the connection point of the door handle contour, and the inclination direction of the door handle support can be obtained by connecting the center point and the connection point of the door handle support contour. Therefore, the closed angle between the door handle and the door handle support can be determined by the angle between the obtained handle angle line and the reference angle line.

[0081] S2633, determining the closing angle between the handle inclination line and the reference angle line, and when the closing angle is greater than or equal to a closing angle threshold, determining that the corresponding door lock handle combination is an abnormal door lock combination.

[0082] When the closing angle is greater than or equal to the closing angle threshold, it indicates that the door lock handle combination may be in the open state, so it can be determined that it is an abnormal door lock combination with an abnormal door lock state. The closing angle threshold is the angle threshold between the door handle and the door handle in the closed state.

[0083] S2634, when the closing angle is less than the closing angle threshold, determine that the corresponding door lock handle combination is a normal door lock combination, and obtain angle analysis data according to the abnormal door lock combination and / or the normal door lock combination.

[0084] When the closing angle is less than the closing angle threshold, it indicates that the door lock handle combination may be in a closed state, which is normal, and therefore it can be determined that the door lock handle combination is a normal door lock combination.

[0085] Through the above method, the door lock status can be accurately analyzed, so that the management personnel can be reminded in time when the door lock is abnormal, thereby improving the safety of the goods.

[0086] S3, performing safety status analysis on the side image that meets the detail recognition conditions according to the multi-level monitoring model to obtain detail analysis data.

[0087] Among them, the multi-level monitoring model is a model for detecting state abnormalities of door lock handle combinations with hanging locks, the detail recognition condition is that the door lock structure in the side image is a door lock handle combination with hanging locks, and the detail analysis data is the data obtained after detecting state abnormalities of door lock handle combinations with hanging locks.

[0088] When performing abnormal analysis on this type of door lock handle combination, since the side image obtained is an overall image of the side of the container, and the hanging lock may occupy a relatively small proportion in the image, it may not be possible to accurately identify the details of the hanging lock. Therefore, in order to more accurately identify and detect the hanging lock, this solution will control the drone to perform secondary magnification image acquisition on the door lock handle combination, so that the door lock handle combination in the image can be clearer, thereby improving the accuracy of recognition.

[0089] Based on the above embodiment, the specific implementation of step S3 may be: S31, performing a door lock structure analysis on the side image, determining that the side image that meets the detail recognition condition is a second target image, and determining a detail collection set corresponding to the second target image according to the multi-level monitoring model.

[0090] The detail recognition condition is that the door lock structure is a door lock combination corresponding to a hanging lock, and the second target image is an image for detecting the door lock state of the door lock combination with the hanging lock.

[0091] It is understandable that there may be more than one door lock combination in the door, and the door lock combinations on the same side are generally close to each other. For example, the door lock combinations corresponding to the hanging locks may also be arranged in accordance with Figure 3 The door lock combinations are arranged in a way of left and right sides, so when zooming in on the details of the door lock combination, the door lock combinations that are close to each other can be collected together, for example, the two door lock combinations on the left can be collected together, and the two door lock combinations on the right can be collected together, thereby improving the efficiency of image collection. The detail collection set is a set of door lock combinations that can be collected together.

[0092] Specifically, step S31 can be implemented by the following steps: S311, acquiring a side image that meets the monitoring and identification conditions as an identification image, and performing hanging lock identification on a door lock handle combination corresponding to a door lock structure in the identification image.

[0093] Similarly, only when the side image meets the monitoring and recognition conditions, this solution will perform door lock status recognition on the corresponding side image.

[0094] S312, determining that the side image of the door lock handle combination of the hanging lock meets the detail recognition condition, and acquiring the side image as the second target image.

[0095] The side image of the door lock handle combination of the hanging lock is the image corresponding to the door lock combination of the hanging lock, so it can be used as the second target image.

[0096] S313: Acquire the combination contours corresponding to the door lock handle combinations in the second target image according to the multi-level monitoring model, number the combination contours, and obtain the position numbers corresponding to the combination contours.

[0097] The combined outline is the overall outline corresponding to the door handle outline, the door handle outline and the hanging lock outline.

[0098] In some embodiments, when numbering the combined contours, the second target image can be subjected to coordinate processing, and then the center point of each combined contour is determined as the coordinate origin, and its position is determined according to the quadrant corresponding to the center point of each combined contour in the coordinate system, and the positions are numbered according to their positions to determine their corresponding position numbers.

[0099] Specifically, it can be determined that the corresponding position of the first quadrant can be the upper left position, the corresponding position of the second quadrant can be the upper right position, the corresponding position of the third quadrant can be the lower left position, and the fourth quadrant position can be the lower right position, and then each combination contour is numbered according to the position, that is, the combination contour at the upper left position is numbered as upper left 1, the combination contour at the lower left position is numbered as lower left 1, the combination contour at the upper right position is numbered as upper right 1, and the combination contour at the lower right position is numbered as lower right 1, so that the relative positions corresponding to each door lock combination can be quickly determined by numbering, so that the management personnel can quickly determine the specific positions corresponding to the abnormal door locks.

[0100] S314, based on the center point of each of the combined contours, determine the combined distance between each of the combined contours, determine that the door lock handle combinations whose combined distance is less than the door lock distance threshold are the same group of the detail collection set, and add a corresponding collection number to the detail collection set according to the position number.

[0101] The above combination distance is the interval distance between the combined contours. The door lock distance threshold refers to the threshold corresponding to the interval distance when the door lock combination is uniformly collected. The combined contours smaller than the threshold may be contours with a closer interval and can be collected together. For example Figure 3 The two door lock combinations located at the upper and lower parts on the left side and the two door lock combinations located at the upper and lower parts on the right side can be respectively used as a set of detail collection sets.

[0102] It can be understood that in order to determine the specific position of the door lock combination corresponding to the detail collection set, the corresponding collection number can be added to the detail collection set through the position number of the corresponding combination contour. For example, when the detail collection set corresponds to the upper and lower combination contours on the left side, the corresponding collection number can be 1 for the upper left and 1 for the lower left.

[0103] S32, generating an outer contour frame of the detail collection set, obtaining a contour center point of the outer contour frame, and determining a direction from a center point of the second target image to the contour center point as an adjustment direction.

[0104] When obtaining the outer contour frame of the detail collection set, you can first obtain the X-axis extreme values ​​and Y-axis extreme values ​​of the coordinate points of all combined contours in the detail collection set, generate four vertical line segments based on the X-axis extreme values ​​and the Y-axis extreme values, and generate an outer contour frame through these four line segments. The outer contour frame is an outer rectangular frame covering all combined contours in the detail collection set, and the contour center point can be obtained through the center point of the contour frame.

[0105] It is understandable that since there may be multiple detail collection sets, the drone can first go to the corresponding location point to collect details from one of the detail collection sets and then fly back to the original position to collect details from another detail collection set, so as to obtain a detailed enlarged image of each door lock combination.

[0106] Specifically, when zooming in on the corresponding detail collection set, you can first move to the front of the door lock combination corresponding to the detail collection set, and then move forward to find the best collection position for collection. When moving to the front of the door lock combination corresponding to the detail collection set, you can determine the moving direction of the drone by adjusting the direction.

[0107] S33, determining the phase difference distance from the center point of the second target image to the center point of the contour, and controlling the acquisition device to move to the first position point based on the adjustment direction and the phase difference distance.

[0108] Among them, the difference distance is the corresponding moving distance when the drone moves to the front of the door lock combination corresponding to the detail collection set, and the first position point is the position point in front of the door lock combination corresponding to the detail collection set.

[0109] S34, controlling the acquisition device to move forward in the detail acquisition direction until the interface ratio of the overall combined contour corresponding to the detail acquisition set in the real-time shooting interface is within the optimal shooting ratio interval, stopping the movement of the acquisition device, and determining the corresponding position point as the detail acquisition point.

[0110] In practical applications, the detail collection direction may be the direction in which the drone is moving forward, that is, the direction in which the drone is approaching the container.

[0111] It is worth mentioning that the shooting angles of the drone's shooting lens can be different when it is taking a bird's-eye view and a side view. The angle when taking a bird's-eye view of the container can be the shooting angle corresponding to the overhead view, and when shooting the side of the container, it can be the shooting angle corresponding to the front view. Therefore, the drone's real-time shooting interface will always be shooting in the direction of the container. When the drone moves forward in the direction of detail collection, the center point of the real-time shooting interface can always be aligned with the center point of the overall combined outline.

[0112] Among them, the overall combined contour refers to all combined contours corresponding to the detail collection set. When determining the interface proportion, an outer rectangular frame corresponding to the overall combined contour can be generated. Specifically, four mutually perpendicular line segments can be generated through the X-axis extreme values ​​and Y-axis extreme values ​​corresponding to the overall combined contour to form the outer rectangular frame, and then the above-mentioned interface proportion is determined by the area proportion of the outer rectangular frame in the real-time shooting interface.

[0113] The optimal shooting ratio range refers to the optimal shooting ratio of the door lock combination in the real-time shooting interface. When the interface ratio of the overall combination outline corresponding to the detail collection set is in the optimal shooting ratio range, it means that the image ratio of the door lock combination corresponding to the detail collection set taken at the current position point will be the best. Therefore, the movement of the drone can be stopped and the corresponding position point can be determined as the detail collection point. The detail collection point is the optimal position point for collecting detail magnified images of the door lock combination.

[0114] S35, obtaining a detail image taken by the acquisition device at the detail acquisition point, performing security identification on the hanging lock in the detail image, and obtaining detail analysis data.

[0115] The detail image is an image obtained by magnifying and capturing the door lock combination. In some embodiments, the following steps can be performed to securely identify the hanging lock in the detail image to obtain detail analysis data: S35, extracting the hanging lock outline corresponding to the hanging lock in each door lock handle combination in the detail image, and when the hanging lock outline is in an open state, determining that the corresponding door lock handle combination is an abnormal door lock combination.

[0116] It is understandable that the detail image may include more than one door lock handle combination. Therefore, when analyzing the door lock status, the hanging lock contour corresponding to the hanging lock in each door lock handle combination can be extracted, and the door lock status can be identified accordingly through the hanging lock contour.

[0117] It can be understood that when the hanging lock is closed, the locking rod will generally be connected with the lock shell. For example, when the locking rod is U-shaped, it will be connected with both ends of the lock shell below when closed. Therefore, when determining the door lock state of the hanging lock, it can be judged by whether both ends of the locking rod are connected with the lock shell. When one end of the locking rod is not connected with the lock shell, it can be determined that it is in the open state, and the door lock combination of the corresponding container may be opened. Therefore, the corresponding door lock handle combination can be determined as an abnormal door lock combination.

[0118] It is worth mentioning that if the door lock structure of the corresponding container is a door lock structure with a hanging lock, but the outline of the hanging lock is not identified during identification, then the corresponding door lock handle combination can also be determined as an abnormal door lock combination.

[0119] S351, when the hanging lock profile is in a closed state, retrieve a standard hanging lock profile, compare the hanging lock profile with the standard hanging lock profile to obtain a comparison value, the standard hanging lock profile includes a front standard profile and a back standard profile.

[0120] When both ends of the lock rod are connected to the lock shell, it can be determined that it is in a closed state. It is understandable that in actual applications, the container may be opened halfway and then locked by personnel. In this case, if the container is not opened without authorization, it may also affect the safety of the goods in the container.

[0121] The orientation of the lock face when the container is locked generally does not change. For example, when the container is locked for the first time, the front side of the lock faces outward. In the absence of external force, its orientation will generally not change the next time. If the orientation of the lock changes, it is possible that someone has opened the container and then locked it. Therefore, after determining the opening and closing state of the container, this solution will also perform a second detection of the orientation of the container.

[0122] It is understandable that the front and back images of a lock are generally different. Therefore, when determining the orientation of the lock, the orientation corresponding to the current hanging lock can be determined by comparing the standard hanging lock outline with the hanging lock outline.

[0123] The front standard contour refers to the contour image corresponding to the front side of the lock, and the back standard contour refers to the contour image corresponding to the back side of the lock.

[0124] S352, obtaining the contour of the hanging lock with the comparison value greater than the similarity threshold as the secondary determination contour, determining the orientation of the secondary determination contour compared with the front standard contour as the positive orientation, and determining the orientation of the secondary determination contour compared with the rear standard contour as the rear orientation.

[0125] The similarity threshold refers to the similarity value when comparing contours. If it is greater than the threshold, it means that the similarity of the two contours is very high and they are likely to be consistent. Therefore, it can be determined that the orientation of the secondary determined contour compared with the front standard contour is the positive orientation, and the orientation of the secondary determined contour compared with the reverse standard contour is the reverse orientation.

[0126] S353, retrieving a plurality of reference door images corresponding to the container stack, each of the reference door images being provided with a corresponding preset end face side and a preset acquisition sequence number.

[0127] Among them, the reference door image refers to the image corresponding to the door of each container in the container stack, and the image can be taken after the container stack is locked. It can be understood that since the end face side and acquisition sequence number corresponding to the door of each container may be different, in order to determine the initial orientation of the hanging lock in the door of each container, a corresponding preset end face side and preset acquisition sequence number can be configured for each reference door image, so that the orientation of the corresponding hanging lock in the door of the corresponding container can be compared through the preset end face side and the preset acquisition sequence number.

[0128] S354, determining a reference door image corresponding to the detail image as a comparison door image according to the end face side and the acquisition sequence number of the side image corresponding to the detail image.

[0129] It is worth mentioning that the comparison door image contains all door lock combinations, while the detail image only contains the enlarged door lock combination. Therefore, when making a comparison, you can first determine the position number of each door lock structure in the comparison door image and the position number of each door lock structure in the detail image, and then compare the orientation of the hanging locks in the corresponding door lock structures through the position numbers.

[0130] When determining the position number of the door lock structure in the detail image, its acquisition side can be determined first, and then its corresponding upper and lower positions can be determined, and numbered according to the acquisition side and the upper and lower positions. For example, when the drone acquires the two door lock structures on the left, it can be determined that the position number of the door lock structure at the upper position is upper left 1, and the position number of the door lock structure at the lower position is lower left 1.

[0131] S355, determining the reference orientation corresponding to the reference hanging lock contour with the same position number as the secondary determination contour in the comparison door image, and if the orientation of the secondary determination contour is consistent with the reference orientation, determining that the corresponding door lock handle combination is a normal door lock combination.

[0132] In practical applications, the reference orientations corresponding to the reference hanging lock outlines in the door image can be configured in advance. When the orientation of the secondary determined outline is consistent with the reference orientation, it means that the orientation of the hanging lock has not changed, which may be normal, so the corresponding door lock handle combination can be determined to be a normal door lock combination.

[0133] S356, if the orientation of the secondary determination contour is inconsistent with the reference orientation, the corresponding door lock handle combination is determined to be an abnormal door lock combination, and detailed analysis data is obtained according to the abnormal door lock combination and / or the normal door lock combination.

[0134] If the orientation of the secondary determination contour is inconsistent with the reference orientation, it means that the orientation of the hanging lock has changed, and it may have been opened halfway, which is abnormal. Therefore, the corresponding door lock handle combination can be determined as an abnormal door lock combination.

[0135] Through the above method, the state of the door lock structure can be analyzed at multiple levels, thereby improving the accuracy of detecting the door lock state.

[0136] S4, generating safety monitoring data corresponding to the container stack according to the angle analysis data or the detail analysis data, and updating the management model according to the safety monitoring data to obtain a safety monitoring model.

[0137] After obtaining the angle analysis data or the detailed analysis data, the solution will also generate the corresponding safety monitoring data of the container stack according to the analyzed data to update the management model, so that the management personnel can view the monitoring status of each container stack through the safety monitoring model. The safety monitoring data is the door lock monitoring data corresponding to the container stack.

[0138] Based on the above embodiment, the specific implementation of step S4 may be: S41, obtaining a plurality of sub-containers corresponding to the container stack, and constructing a monitoring node corresponding to each of the sub-containers.

[0139] Among them, the sub-container is a plurality of containers stacked corresponding to the container stack. It is understandable that the door lock monitoring data corresponding to each container may be different. In order to enable the management personnel to view the monitoring status of each container, a monitoring node corresponding to each sub-container can be constructed, and the data collected corresponding to each sub-container can be bound through the monitoring node in the future, so that the management personnel can click the corresponding node to retrieve the collected data corresponding to the corresponding container and send it to the management personnel for viewing.

[0140] S42, according to the number of stacking layers corresponding to each of the sub-containers, the monitoring nodes are arranged from large to small and connected to obtain a monitoring structure.

[0141] It can be understood that the arrangement order in the monitoring structure corresponds to the order in which the drone collects data.

[0142] S43, obtaining the collection sequence number corresponding to each of the angle analysis data or the detail analysis data, and binding the monitoring nodes and the angle analysis data or the detail analysis data having the same collection sequence number and arrangement order according to the collection sequence number and the arrangement order of each of the monitoring nodes.

[0143] It can be understood that the monitoring structures corresponding to different end face sides are different. When binding the monitoring nodes and the angle analysis data or the detail analysis data with the same collection sequence and arrangement order, the monitoring nodes and the corresponding angle analysis data or the detail analysis data on the same side are bound. In order to distinguish the end face side corresponding to the monitoring structure, a label corresponding to the corresponding end face side can be added to the monitoring structure.

[0144] For example, the first monitoring node corresponds to the topmost container, and when binding, the angle analysis data or detail analysis data collected for the topmost container is also bound to the first monitoring node.

[0145] S44, determining that the monitoring node having the abnormal door lock combination is an abnormal node, and determining the warning level of the abnormal node according to the number of abnormalities corresponding to the abnormal door lock combination.

[0146] It is understandable that the more abnormal door lock structures there are, the lower the safety factor of the container may be, and therefore the corresponding warning level can be higher, so that management personnel can check the corresponding containers in time to reduce the safety risks of the goods in the containers.

[0147] When determining the warning level, multiple warning levels can be set in advance, and a corresponding abnormal quantity interval can be set for each warning level, and then the corresponding warning level can be determined according to the abnormal quantity interval in which the abnormal quantity is located.

[0148] S45, retrieving the pixel value corresponding to the corresponding warning level to update the abnormal node, obtaining the safety monitoring data corresponding to the container stack, and binding the safety monitoring data with the corresponding monitoring point in the management model to obtain a safety monitoring model.

[0149] In practical applications, the higher the warning level, the more eye-catching the corresponding pixel value can be, so that managers can observe the safety level of the corresponding container through the pixel value. For example, the pixel value corresponding to the highest warning level can be dark red, and the lower the level, the lighter the red pixel value can be.

[0150] Through the above method, containers with low safety factors can be warned, so that managers can make targeted handling strategies in time.

[0151] See also Figure 4 , is a structural diagram of a data processing system of a half-high container management system provided by an embodiment of the present invention, the data processing system of the half-high container management system comprises: A management module, used to construct a management model corresponding to a semi-high container yard, wherein the management model includes monitoring points corresponding to a plurality of container stacks; An angle module, used to obtain the side image of the corresponding container stack taken by the acquisition device at the monitoring point, and perform safety status analysis on the side image that meets the angle recognition condition according to the angle analysis model to obtain angle analysis data; A detail module is used to perform safety status analysis on the side image that meets the detail recognition conditions according to the multi-level monitoring model to obtain detail analysis data; A monitoring module is used to generate safety monitoring data corresponding to the container stacking according to the angle analysis data or the detail analysis data, and to update the management model according to the safety monitoring data to obtain a safety monitoring model.

[0152] Figure 4 The apparatus of the embodiment shown can be used to perform Figure 1 The implementation principles and technical effects of the steps in the method embodiment shown are similar and will not be repeated here.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A data processing method for a semi-high container management system, characterized in that: include: Constructing a management model corresponding to a semi-high container yard, the management model including monitoring points corresponding to a plurality of container stacks; Obtaining a side image of the corresponding container stack taken by the acquisition device at the monitoring point, performing a safety status analysis on the side image that meets the angle recognition condition according to the angle analysis model, and obtaining angle analysis data; Perform safety status analysis on the side image that meets the detail recognition conditions according to the multi-level monitoring model to obtain detail analysis data; The safety monitoring data corresponding to the container stack is generated according to the angle analysis data or the detail analysis data, and the management model is updated according to the safety monitoring data to obtain a safety monitoring model.

2. The method according to claim 1, characterized in that: Obtain the side image of the corresponding container stack taken by the acquisition device at the monitoring point, perform safety status analysis on the side image that meets the angle recognition condition according to the angle analysis model, and obtain angle analysis data, including: Acquire a real-time shooting interface of the acquisition device at the monitoring point based on a preset overhead shooting height, extract a stack overhead shooting contour in the real-time shooting interface, wherein the center point of the stack overhead shooting contour corresponds to the center point of the real-time shooting interface; Determine a contour line corresponding to an end face side of the container stack in the stack overhead profile as a reference line, wherein the end face side includes a front end with a container door and a rear end without a container door; Connect the center points of the two reference lines to obtain a guide line, and extend both ends of the guide line according to the overall shooting distance; Determine the direction from the center point of the guide line to the endpoint of the guide line as the guide direction, and control the acquisition device to move to the guide point corresponding to the corresponding endpoint based on the guide direction and the guide line; Acquire the end face side corresponding to the guide point as the target side, control the acquisition device to take images of the target side in the height direction according to the side shooting interval distance, and obtain multiple side images; Perform a door lock structure analysis on the side image, determine that the side image that meets the angle recognition condition is a first target image, and perform a safety status analysis on the first target image according to an angle analysis model to obtain angle analysis data.

3. The method according to claim 2, characterized in that The end face side corresponding to the guide point is obtained as the target side, and the acquisition device is controlled to take images of the target side in the height direction according to the side shooting interval distance to obtain multiple side images, including: After the acquisition device reaches the guide point, the acquisition device is controlled to move to the side shooting position point in the height direction according to the side shooting interval distance, taking the guide point as a reference point; Acquire the side image captured by the acquisition device at the side shooting position, extract the end face contour in the side image, and acquire four edge points corresponding to the first end face contour in the acquisition direction; Generate an identification frame according to the edge points, and determine an image area in the side image located within the identification frame as an identification area; Performing door lock recognition on the recognition area, and when a door lock structure exists in the recognition area, determining that the side image meets the monitoring recognition condition; When the door lock structure does not exist in the recognition area, determining that the side image does not meet the monitoring and recognition condition, deleting the side image, and determining that the acquisition sequence number corresponding to the side image is the target sequence number; Acquire a current shooting height corresponding to the target sequence number, and determine that the current shooting height is a target shooting height when the acquisition device acquires a side image of the other end face; Taking the side shooting position point as a reference, continue to control the acquisition device to move to the next side shooting position point in the height direction according to the side shooting interval distance; Repeat the above steps of identifying the door lock structure according to the side image until the acquisition sequence number is the preset acquisition sequence number corresponding to the container stack, and stop acquiring the side image of the target side.

4. The method according to claim 3, characterized in that: Performing a door lock structure analysis on the side image, determining that the side image that meets the angle recognition condition is a first target image, and performing a safety status analysis on the first target image according to an angle analysis model to obtain angle analysis data, including: Acquire a side image that meets the monitoring and identification conditions as an identification image, and perform hanging lock identification on a door lock handle combination corresponding to the door lock structure in the identification image; Determine that the side image of the door lock handle combination without a hanging lock meets the angle recognition condition, and obtain the side image as the first target image; The closing angle corresponding to each door lock handle combination in the first target image is obtained according to the angle analysis model, and the safety status analysis of the closing angle is performed to obtain angle analysis data.

5. The method according to claim 4, characterized in that Acquiring the closing angle corresponding to each door lock handle combination in the first target image according to the angle analysis model, and performing safety status analysis on the closing angle to obtain angle analysis data, including: Acquire the outline of the door handle support and the door handle in each of the door lock handle assemblies in the first target image, and the outline of the door lock rod connected to each of the door lock handle assemblies; Determine the connection point between the door lock rod contour and the door handle support contour, connect the center point of the door handle contour and the connection point to obtain a handle angle line, and connect the center point of the door handle support contour and the connection point to obtain a reference angle line; Determine a closing angle between the handle tilt line and the reference angle line, and when the closing angle is greater than or equal to a closing angle threshold, determine that the corresponding door lock handle combination is an abnormal door lock combination; When the closing angle is less than the closing angle threshold, the corresponding door lock handle combination is determined to be a normal door lock combination, and angle analysis data is obtained according to the abnormal door lock combination and / or the normal door lock combination.

6. The method according to claim 3, characterized in that According to the multi-level monitoring model, the safety status of the side image that meets the detail recognition conditions is analyzed to obtain the detail analysis data, including: Performing a door lock structure analysis on the side image, determining that the side image that meets the detail recognition condition is a second target image, and determining a detail collection set corresponding to the second target image according to the multi-level monitoring model; Generate an outer contour frame of the detail collection set, obtain a contour center point of the outer contour frame, and determine a direction from a center point of the second target image to the contour center point as an adjustment direction; Determine a phase difference distance between a center point of the second target image and a center point of the contour, and control the acquisition device to move to a first position point based on the adjustment direction and the phase difference distance; Control the acquisition device to move forward in the detail acquisition direction until the interface proportion of the overall combined contour corresponding to the detail acquisition set in the real-time shooting interface is within the optimal shooting proportion interval, and stop the movement of the acquisition device, and determine the corresponding position point as the detail acquisition point; The detail image captured by the acquisition device at the detail acquisition point is acquired, and the hanging lock in the detail image is securely identified to obtain detail analysis data.

7. The method according to claim 6, characterized in that Performing a door lock structure analysis on the side image, determining that the side image that meets the detail recognition condition is a second target image, and determining a detail collection set corresponding to the second target image according to the multi-level monitoring model, including: Acquire a side image that meets the monitoring and identification conditions as an identification image, and perform hanging lock identification on a door lock handle combination corresponding to the door lock structure in the identification image; Determine that the side image of the door lock handle combination with the hanging lock meets the detail recognition condition, and obtain the side image as the second target image; Acquire the combined contours corresponding to each door lock handle combination in the second target image according to the multi-level monitoring model, number each of the combined contours, and obtain the position number corresponding to each of the combined contours; Based on the center point of each of the combined contours, the combined distance between each of the combined contours is determined, the door lock handle combinations whose combined distance is less than the door lock distance threshold are determined to be the same group of the detail collection set, and a corresponding collection number is added to the detail collection set according to the position number.

8. The method according to claim 7, characterized in that Acquiring a detail image captured by the acquisition device at the detail acquisition point, performing security identification on the hanging lock in the detail image, and obtaining detail analysis data, including: Extracting the hanging lock outline corresponding to the hanging lock in each door lock handle combination in the detail image, and when the hanging lock outline is in an open state, determining that the corresponding door lock handle combination is an abnormal door lock combination; When the hanging lock profile is in a closed state, calling a standard hanging lock profile, comparing the hanging lock profile with the standard hanging lock profile to obtain a comparison value, wherein the standard hanging lock profile includes a front standard profile and a back standard profile; The locket contour having the comparison value greater than the similarity threshold is obtained as the secondary determination contour, and the orientation of the secondary determination contour compared with the front standard contour is determined as the positive orientation, and the orientation of the secondary determination contour compared with the rear standard contour is determined as the rear orientation; Retrieving a plurality of reference door images corresponding to the container stack, each of the reference door images being provided with a corresponding preset end face side and a preset acquisition sequence number; Determine, according to the end face side and the acquisition sequence number of the side image corresponding to the detail image, a reference door image corresponding to the detail image as a comparison door image; Determine a reference orientation corresponding to a reference hanging lock contour having the same position number as the second determination contour in the comparison door image, and if the orientation of the second determination contour is consistent with the reference orientation, determine that the corresponding door lock handle combination is a normal door lock combination; If the orientation of the secondary determination profile is inconsistent with the reference orientation, the corresponding door lock handle combination is determined to be an abnormal door lock combination, and detailed analysis data is obtained according to the abnormal door lock combination and / or the normal door lock combination.

9. The method according to claim 5 or 8, characterized in that: Generating safety monitoring data corresponding to the container stacking according to the angle analysis data or the detail analysis data, and updating the management model according to the safety monitoring data to obtain a safety monitoring model, including: Acquire multiple sub-containers corresponding to the container stack, and construct monitoring nodes corresponding to each of the sub-containers; According to the number of stacking layers corresponding to each of the sub-containers, the monitoring nodes are arranged from large to small and then connected to obtain a monitoring structure; Obtaining a collection sequence number corresponding to each of the angle analysis data or the detail analysis data, and binding the monitoring nodes and the angle analysis data or the detail analysis data having the same collection sequence number and arrangement order according to the collection sequence number and the arrangement order of each of the monitoring nodes; Determine the monitoring node where the abnormal door lock combination exists as an abnormal node, and determine the warning level of the abnormal node according to the number of abnormalities corresponding to the abnormal door lock combination; The pixel value corresponding to the corresponding warning level is retrieved to update the abnormal node, and the safety monitoring data corresponding to the container stack is obtained. The safety monitoring data is bound to the corresponding monitoring point in the management model to obtain a safety monitoring model.

10. A data processing system for a semi-high container management system, characterized in that: include: A management module, used to construct a management model corresponding to a semi-high container yard, wherein the management model includes monitoring points corresponding to a plurality of container stacks; An angle module, used to obtain the side image of the corresponding container stack taken by the acquisition device at the monitoring point, and perform safety status analysis on the side image that meets the angle recognition condition according to the angle analysis model to obtain angle analysis data; A detail module is used to perform safety status analysis on the side image that meets the detail recognition conditions according to the multi-level monitoring model to obtain detail analysis data; A monitoring module is used to generate safety monitoring data corresponding to the container stacking according to the angle analysis data or the detail analysis data, and to update the management model according to the safety monitoring data to obtain a safety monitoring model.

Images