A Dual-Container Recognition Method, Device, System and Crane for Preventing the Hoisting of Container Trucks

Abstract

This application relates to the field of construction machinery, and particularly to a double-container recognition method, device, system and crane for preventing the lifting of container trucks. This double-container recognition method includes obtaining an initial scanned point cloud set of a scanner; obtaining an initial reference point according to the initial scanned point cloud set; obtaining the minimum recognized object size of the scanner according to the initial reference point; adaptively clustering all data points in the initial scanned point cloud set according to the minimum recognized object size and the initial reference point to generate a number of sub-point sets; and obtaining a container point set and an anti-lifting monitoring area according to the point clouds in the number of sub-point sets. The system identifies the point set formed by the containers according to the characteristics of different sub-point sets and divides the anti-lifting monitoring area, so as to ensure that two 20-foot containers can be accurately recognized, reduce the probability of the container truck being lifted, and ensure the operation safety of the crane and the container truck.

Description

Technical Field

[0001] The present application relates to the field of construction machinery, and particularly to a method, device, system and crane for double-container identification to prevent container lifting of a container truck. Background Art

[0002] The container lifting prevention system of a container truck is one of the necessary safety subsystems of an automated yard crane, and is used to prevent the vehicle body from being lifted when the container and the container truck lock head are not unlocked during the external container truck operation of the yard crane. The anti-lifting scheme based on horizontal laser scanning is to deploy a 2D laser at a fixed height of the crane saddle beam, and judge whether a container truck lifting accident occurs by monitoring whether there are still obstacles in the monitoring area when the lifting hook rises to a certain height.

[0003] However, in the related solutions, when a container truck loads two 20-foot containers and enters the yard for single-container unloading operation, since the distance between the front and rear containers is relatively close, how to separate the contour of the container to be operated, and then delimit the anti-lifting monitoring area, is one of the keys of the container truck lifting prevention system.

[0004] According to the measurement characteristics of the laser scanning device, the scanned point cloud of the container will show the characteristic of "sparse far and dense near". In order to aggregate the points belonging to the container in the distance together, the clustering scale needs to be set to a relatively large value. However, when a container truck with two 20-foot containers enters the operation area, this relatively large clustering scale cannot effectively distinguish the distance between the two containers that are relatively close, and the clustering scale needs to be modified, which greatly reduces the efficiency. Summary of the Invention

[0005] In view of this, the present application provides a method, device, system and crane for double-container identification to prevent container lifting of a container truck, which solves or improves the technical problem that it is difficult to accurately identify a double-container container truck to prevent a container truck lifting accident in the prior art.

[0006] According to one aspect of the present application, the present application provides a method for double-container identification to prevent container lifting of a container truck. The method for double-container identification to prevent container lifting of a container truck includes: obtaining an initial scanned point cloud set of a scanner; obtaining an initial reference point according to the initial scanned point cloud set; obtaining the minimum identifiable object size of the scanner according to the initial reference point; adaptively clustering all the point clouds in the initial scanned point cloud set according to the minimum identifiable object size and the initial reference point to generate a plurality of sub-point cloud sets; and obtaining a container point cloud set and an anti-lifting monitoring area according to the point clouds in the plurality of sub-point cloud sets.

[0007] In one embodiment, adaptive clustering is performed on the point clouds in the initial scanned point cloud set according to the minimum recognized object size and the initial reference point to generate a plurality of sub-point sets, including: obtaining a first adjacent point of the initial reference point according to the initial reference point; obtaining a first Euclidean distance between the initial reference point and the first adjacent point according to the initial reference point and the first adjacent point; and obtaining a plurality of sub-point sets according to the first Euclidean distance, the minimum recognized object size, and a preset margin coefficient.

[0008] In one embodiment, obtaining a plurality of sub-point sets according to the first Euclidean distance, the minimum recognized object size, and a preset margin coefficient includes: when the first Euclidean distance is less than or equal to the adaptive clustering scale, the initial reference point and the first adjacent point are the first sub-points in the first sub-point set; taking the first adjacent point as the current reference point and obtaining a second adjacent point of the current reference point; obtaining a second Euclidean distance between the current reference point and the second adjacent point according to the current reference point and the second adjacent point; and when the second Euclidean distance is less than or equal to the adaptive clustering scale, the second adjacent point is the first sub-point in the first sub-point set; wherein the plurality of sub-point sets includes the first sub-point set.

[0009] In one embodiment, obtaining a plurality of sub-point sets according to the first Euclidean distance, the minimum recognized object size, and a preset margin coefficient includes: when the first Euclidean distance is greater than the adaptive clustering scale, the first adjacent point is the second sub-point in the second sub-point set; wherein the plurality of sub-point sets includes the second sub-point set.

[0010] In one embodiment, obtaining the minimum recognized object size of the scanner according to the initial reference point includes: obtaining the distance between the initial reference point and the origin according to the initial reference point; obtaining the preset resolution angle of the scanner; and generating the minimum recognized object size of the scanner according to the distance between the initial reference point and the origin and the preset resolution angle.

[0011] In one embodiment, obtaining a container point set and an anti-lifting monitoring area according to the point clouds in the plurality of sub-point sets includes: obtaining the head-to-tail Euclidean distance between the head point and the tail point of each sub-point set, the sum of the abscissas of the head point and the tail point, and the number of points in the sub-point set according to the point clouds in the plurality of sub-point sets; and obtaining a container point set and an anti-lifting monitoring area according to the head-to-tail Euclidean distance between the head point and the tail point of each sub-point set, the sum of the abscissas of the head point and the tail point, and the number of points in the sub-point set.

[0012] In one embodiment, after obtaining the container point set and the anti-hanging monitoring area based on the point clouds in several of the sub-point sets, the method further includes: obtaining the opening dimension of the spreader when the spreader lands on the container; obtaining the initial identification point set of the container and the standard length of the container; obtaining a verified anti-hanging monitoring area based on the opening dimension of the spreader when the spreader lands on the container, the initial identification point set of the container, and the standard length; and generating a target anti-hanging monitoring area based on the verified anti-hanging monitoring area and the anti-hanging monitoring area.

[0013] In one embodiment, the generating the target anti-hanging monitoring area based on the verified anti-hanging monitoring area includes: when the verified anti-hanging monitoring area is consistent with the anti-hanging monitoring area, using the anti-hanging monitoring area as the target anti-hanging area; or when the verified anti-hanging monitoring area is inconsistent with the anti-hanging monitoring area, generating a reminder message and using the verified anti-hanging monitoring area as the target anti-hanging monitoring area.

[0014] According to a second aspect of the present application, the present application further provides a double-container identification device for anti-hanging of a truck tractor. This double-container identification device for anti-hanging of a truck tractor includes: a point cloud acquisition module for acquiring an initial scanned point cloud set of a scanner; a point cloud processing module for receiving the initial scanned point cloud set transmitted by the point cloud acquisition module, obtaining an initial reference point based on the initial scanned point cloud set, and obtaining the minimum identifiable object size of the scanner based on the initial reference point; a sub-point set generation module for receiving the minimum identifiable object size transmitted by the point cloud processing module, adaptively clustering all the point clouds in the initial scanned point cloud set according to the minimum identifiable object size and the initial reference point to generate several sub-point sets; and a monitoring area generation module for receiving the several sub-point sets transmitted by the sub-point set generation module and obtaining a container point set and an anti-hanging monitoring area based on the point clouds in the several sub-point sets.

[0015] According to a third aspect of the present application, the present application further provides a double-container identification system for anti-hanging of a truck tractor. This double-container identification system for anti-hanging of a truck tractor includes: a scanner, where the scanner is arranged on a crane; and the above-mentioned double-container identification device for anti-hanging of a truck tractor, where the double-container identification device for anti-hanging of a truck tractor is electrically connected to the scanner.

[0016] In one embodiment, the scanner includes: a two-dimensional laser scanner, and the two-dimensional laser scanner is arranged on the saddle beam of the crane.

[0017] According to a fourth aspect of the present application, the present application further provides a crane. This crane includes: the above-mentioned double-container identification system for anti-hanging of a truck tractor.

[0018] The present application provides a method, apparatus, system and crane for double - container identification with anti - hanging for container trucks. The method for double - container identification with anti - hanging for container trucks includes: obtaining an initial scanned point cloud set of a scanner; obtaining an initial reference point according to the initial scanned point cloud set; obtaining the minimum recognizable object size of the scanner according to the initial reference point; performing adaptive clustering on all data points in the initial scanned point cloud set according to the minimum recognizable object size and the initial reference point to generate a number of sub - point sets; and obtaining a container point set and an anti - hanging monitoring area according to the point clouds in the number of sub - point sets. By using the initial reference point and the minimum unit size recognizable by the scanner, clustering is performed on all point clouds in the initial scanned point cloud set, realizing adaptive clustering of all point clouds, and finally obtaining a number of different sub - point sets, and then distinguishing the double - container contour from the sub - point sets. In addition, the system further identifies the point set formed by the container according to the characteristics of different sub - point sets and divides the anti - hanging monitoring area, so as to ensure that two 20 - foot containers can be accurately identified, reduce the probability of the container truck being lifted, and ensure the operation safety of the crane and the container truck. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The figure shows a schematic flow chart of the method for double - container identification with anti - hanging for container trucks provided by an embodiment of the present application.

[0020] Figure 2 The figure shows a schematic flow chart of the method for generating sub - point sets in the method for double - container identification with anti - hanging for container trucks provided by another embodiment of the present application.

[0021] Figure 3 The figure shows a schematic flow chart of the method for double - container identification with anti - hanging for container trucks provided by another embodiment of the present application.

[0022] Figure 4 The figure shows a schematic flow chart of the method for verifying the anti - hanging monitoring area in the method for double - container identification with anti - hanging for container trucks provided by another embodiment of the present application.

[0023] Figure 5 The figure shows a schematic flow chart of the method for verifying the anti - hanging monitoring area in the method for double - container identification with anti - hanging for container trucks provided by another embodiment of the present application.

[0024] Figure 6 The figure shows a working principle diagram of the double - container system with anti - hanging for container trucks provided by an embodiment of the present application.

[0025] Figure 7 The figure shows a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In the description of this application, the meaning of "a plurality of" is at least two, such as two, three, etc., unless otherwise specifically defined. In the embodiments of this application, all directional indications (such as up, down, left, right, front, back, top, bottom...) are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0027] In addition, the mention of "embodiment" in this article means that the specific features, structures or characteristics described in connection with the embodiment can be included in at least one embodiment of this application. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0028] Overview of the Application

[0029] When the container carrier enters the operation area with a 40-foot container, for the anti-lifting system to effectively identify the long side of the 40-foot container, it is necessary to cluster the obtained laser point cloud, that is, to identify and extract the point set belonging to the long side of the container from all the point cloud data. When performing point cloud clustering, the general method based on Euclidean distance is to set a clustering scale Δs, calculate the distances between all adjacent points, and those with a distance less than Δs are aggregated together as the contour points of the same object, otherwise they do not belong to the contour of the same object.

[0030] According to the measurement characteristics of the laser scanner, the scanned point cloud of the container will show the characteristic of "sparse far and dense near". To aggregate the points belonging to the container in the distance together, the clustering scale Δs here needs to be set to a larger value. However, when the container carrier enters the operation area with two 20-foot containers, this larger Δs cannot effectively distinguish the distance between the two containers that are relatively close, resulting in misidentifying the two containers as a 40-foot container. At this time, Δs needs to be gradually reduced until the container spacing can be identified. Such a method has significant disadvantages. First, the clustering scale needs to be modified during the point cloud recognition process, which reduces the efficiency. In addition, when the distance between the container and the scanner changes, the originally set clustering scale will no longer be applicable.

[0031] In this application, by introducing an adaptive point cloud scale clustering method to identify the double - container spacing, both the identification efficiency and applicability are improved. This double - container identification method for preventing the lifting of container trucks includes: obtaining the initial scanned point cloud set of the scanner; obtaining the initial reference point according to the initial scanned point cloud set; obtaining the minimum identifiable object size of the scanner according to the initial reference point; performing adaptive clustering on all data points in the initial scanned point cloud set according to the minimum identifiable object size and the initial reference point to generate several sub - point sets; and obtaining the container point set and the anti - lifting monitoring area according to the point clouds in the several sub - point sets. Using the initial reference point and the minimum unit size that the scanner can identify, clustering is performed on all the point clouds in the initial scanned point cloud set, realizing adaptive clustering for all the point clouds, and finally obtaining several different sub - point sets, and then distinguishing the double - container contour from the sub - point sets. In addition, the system further identifies the point set formed by the containers according to the characteristics of different sub - point sets and divides the anti - lifting monitoring area, so as to ensure that two 20 - foot containers can be accurately identified, reduce the probability of the container truck being lifted, and ensure the operation safety of the crane and the container truck.

[0032] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0033] Figure 1 The following shows a schematic flow chart of the double - container identification method for preventing the lifting of container trucks provided by an embodiment of the present application. As Figure 1 shown, this double - container identification method for preventing the lifting of container trucks specifically includes the following steps:

[0034] Step 100: Obtain the initial scanned point cloud set of the scanner.

[0035] The scanner refers to a laser scanner, which is an instrument that measures the dimensions and shapes of workpieces by means of scanning technology. The initial scanned point cloud set is the point cloud set obtained by the scanner through horizontal scanning after the container truck loaded with containers enters the operation area and stops. This point cloud set has not been screened and clustered and is an initial parent point set.

[0036] Step 200: Obtain the initial reference point according to the initial scanned point cloud set.

[0037] The initial reference point is the point cloud selected and defined by the system as the first reference point after the initial point cloud set is obtained completely. Using this reference point, clustering is performed on other initial point clouds, making the identification and screening of point clouds more feasible.

[0038] Step 300: Obtain the minimum recognizable object size of the scanner according to the initial reference point.

[0039] The minimum recognizable object size of the scanner is the minimum unit size that the scanner can recognize during use.

[0040] Step 400: Perform adaptive clustering on all the point clouds in the initial scanned point cloud set according to the minimum recognizable object size and the initial reference point to generate several subsets of points.

[0041] A subset of points is a subset of point clouds clustered and recognized from the initial scanned point cloud set, and each subset of point clouds can be initially judged as an independent object. By using the initial reference point and the minimum unit size that the scanner can recognize, clustering is performed on all the point clouds in the initial scanned point cloud set, and the relationship between any point cloud in the mother point cloud set, the initial reference point, and the minimum recognizable object size can be judged. Then, adaptive clustering of all the point clouds is realized, and finally several different subsets of points are obtained. The double-box contour can be distinguished from the subsets of points.

[0042] Step 500: Obtain the container point set and the anti-lifting monitoring area according to the point clouds in several subsets of points.

[0043] After the division of the subsets of points is completed in the above steps, the system can further identify the point set formed by the container and the point set formed by non-container objects according to the characteristics of different subsets of points, and then divide the anti-lifting monitoring area to ensure that two 20-foot containers can be accurately identified, reduce the probability of the truck being lifted, and ensure the operation safety of the crane and the truck.

[0044] In a possible implementation manner, Figure 2 The figure shows a schematic flowchart of the method for generating subsets of points in the double-box identification method for preventing the lifting of a truck provided by another embodiment of the present application. As Figure 2 shown, step 400 may further include the following steps:

[0045] Step 410: Obtain the first adjacent point of the initial reference point according to the initial reference point.

[0046] The first adjacent point is the adjacent point closest to the initial reference point. Taking the initial reference point as a reference, it is more feasible and reliable to judge the clustering of the point cloud closest to it.

[0047] Step 420: Obtain the first Euclidean distance between the initial reference point and the first adjacent point according to the initial reference point and the first adjacent point.

[0048] The Euclidean distance (also known as the Euclidean metric) is a commonly used distance definition, referring to the actual distance between two points in an m-dimensional space, or the natural length of a vector (i.e., the distance from this point to the origin). The Euclidean distance in two-dimensional and three-dimensional spaces is the actual distance between two points. The first Euclidean distance refers to the Euclidean distance Δs between the initial reference point and the first adjacent point, which can be calculated according to the coordinates of the initial reference point and the first adjacent point and Formula 1. Formula 1 is as follows:

[0049]

[0050] where the coordinates of the initial reference point are (x1, y1), and the coordinates of the first adjacent point are (x2, y2).

[0051] Step 430: Obtain a number of sub-point sets according to the first Euclidean distance, the minimum recognized object size, and the preset margin coefficient.

[0052] The margin coefficient refers to the degree value with a certain margin, or the coefficient value allowing a certain error. The preset margin coefficient k is a margin coefficient value obtained after multiple recognition tests on the spacing of 20-foot containers under actual conditions. This margin coefficient value can be pre-input into the system for use. However, to improve the recognition accuracy, the current preset margin coefficient can also be verified before each double-container recognition. According to Verification Formula 1, calculate the first Euclidean distance Δs, the minimum recognized object size Δl, and the preset margin coefficient k to judge the relationship between the first Euclidean distance and the clustering scale. The minimum recognized object size Δl is the minimum recognized size of the ideal object surface. Therefore, through Verification Formula 1, it can be determined whether the first adjacent point can be clustered into the current sub-point set. Among them, Verification Formula 1 is as follows:

[0053] Δs ≤ k * Δl (Verification Formula 1)

[0054] Further, Step 430 may include the following steps:

[0055] Step 4301: When the first Euclidean distance is less than or equal to the adaptive clustering scale, the initial reference point and the first adjacent point are the first sub-points in the first sub-point set.

[0056] The first sub-point set is one of the above-mentioned several sub-point sets; the first sub-point refers to the point in the first sub-point set. When the first Euclidean distance is less than or equal to the adaptive clustering scale, it indicates that the Euclidean distance between the initial reference point and the first adjacent point meets the condition of belonging to the same object. Therefore, it is feasible and relatively accurate to divide the initial reference point and the first adjacent point into the same sub-point set.

[0057] Step 4302: Take the first adjacent point as the current reference point and obtain the second adjacent point of the current reference point.

[0058] The current reference point is the currently selected reference point. To distinguish it from the initial reference point, it is named the current reference point; the second adjacent point is the adjacent point closest to the current reference point, and it is also the point cloud to be clustered next. As the reference point is updated and replaced, the minimum recognized object size Δl also changes accordingly, so as to achieve the purpose of adaptively clustering all point clouds in the initial scanned point cloud set one by one, and avoid the problem of difficult recognition of the distance between 20-foot containers caused by uniformly setting the clustering scale.

[0059] Step 4303: Obtain the second Euclidean distance between the current reference point and the second adjacent point according to the current reference point and the second adjacent point.

[0060] The second Euclidean distance refers to the Euclidean distance between the current reference point and the second adjacent point. Similarly, it can be calculated using the coordinates of the current reference point and the second adjacent point. The second Euclidean distance is used to judge the clustering division of the second adjacent point in the subsequent process.

[0061] Step 4304: When the second Euclidean distance is less than or equal to the adaptive clustering scale, the second adjacent point is the first sub-point in the first subset.

[0062] Similarly to Step 430, use verification formula 1 and the current second Euclidean distance, preset margin coefficient, and the current minimum recognized object size to judge the relationship between the second Euclidean distance and the adaptive clustering scale, so as to judge whether the second adjacent point belongs to the first subset. Thus, it is easy to obtain that when the second Euclidean distance is less than or equal to the adaptive clustering scale, the second adjacent point is the first sub-point in the first subset.

[0063] In another possible implementation, as Figure 2 shown, several subsets may also include a second subset and a third subset, etc. After Step 430, Step 400 may further include Step 4305:

[0064] Step 4305: When the first Euclidean distance is greater than the adaptive clustering scale, the first adjacent point is the second sub-point in the second subset.

[0065] The second sub-point refers to the point in the second subset. When the first Euclidean distance is greater than the adaptive clustering scale, it means that the Euclidean distance between the second adjacent point and the current reference point is relatively large, and the possibility of not belonging to the same object point set is relatively high. Therefore, it is more accurate to divide the second adjacent point into other subsets, or to remove the first subset from the initial scanned point cloud set as an independent subset.

[0066] It should be understood that step 430 is only an example of the judgment process for some point clouds in the initial scanned point cloud set. After step 4305, the clustering calculation should continue to be performed on the adjacent points closest to the reference point in the way of such reference point iteration until the clustering calculation of the last point in the initial scanned point cloud set is completed. In this way, the adaptive clustering of all point clouds in the initial scanned point cloud set can be realized, and a reliable and accurate subset of points can be obtained.

[0067] Specifically, Figure 3 The figure shows a schematic flow chart of a double-container recognition method for preventing the lifting of a container truck provided by another embodiment of the present application. As Figure 3 shown, step 300 may further include the following steps:

[0068] Step 310: Obtain the distance between the initial reference point and the origin according to the initial reference point.

[0069] The origin is the preset origin of the coordinate system where the point cloud is located, and the distance between the reference point and the origin can be represented by d.

[0070] Step 320: Obtain the preset resolution angle of the scanner.

[0071] The preset resolution angle θ is the resolution ability of the scanner. That is, the ability of the scanner imaging system or the scanner system components to distinguish the minimum distance between two adjacent objects differently.

[0072] Step 330: Generate the minimum recognition object size of the scanner according to the distance between the initial reference point and the origin and the preset resolution angle.

[0073] According to formula two, the distance d between the reference point and the origin and the preset resolution angle θ are calculated to generate the minimum recognition object size Δl for the subsequent calculation of the adaptive clustering scale. Among them, formula two is:

[0074] Δl = θ * d Formula (two)

[0075] In a possible implementation manner, as Figure 3 shown, step 500 may further include the following steps:

[0076] Step 510: Obtain the head-to-tail Euclidean distance, the sum of the abscissas of the head point and the tail point, and the number of points in the subset of points for each subset of points according to the point clouds in several subsets of points.

[0077] The head point and the tail point are the first point and the last point in the subset of points. When several subsets of points are divided, each subset of points can be considered as an object. Obtaining the head-to-tail Euclidean distance, the sum of the abscissas of the head point and the tail point, and the number of points in the subset of points for each subset of points is the premise for accurately dividing the container.

[0078] Step 520: Obtain the container point set and the anti-lifting monitoring area according to the head-to-tail Euclidean distance between the starting point and the ending point of each sub-point set, the sum of the abscissas of the starting point and the ending point, and the number of points in the sub-point set.

[0079] Using the head-to-tail Euclidean distance between the starting point and the ending point of each sub-point set, the sum of the abscissas of the starting point and the ending point, and the number of points in the sub-point set obtained in the above steps, complete the extraction of the target point set of the container and the identification of the double-container working condition, and then calculate and delimit the anti-lifting monitoring area according to the target container point set.

[0080] In another possible implementation, Figure 4 The following shows a schematic flowchart of the method for verifying the anti-lifting monitoring area in the double-container identification method for truck anti-lifting provided by another embodiment of the present application. As Figure 1 and Figure 4 shown, after step 500, this double-container identification method for truck anti-lifting may further include the following steps:

[0081] Step 610: Obtain the spreader opening size when the spreader lands on the container.

[0082] The spreader opening size refers to the preset opening size when the spreader lifts the container. According to this spreader opening size, it can assist in judging the size range of the container on the current truck.

[0083] Step 620: Obtain the initial identification point set of the container and the standard length of the container.

[0084] The initial identification point set of the container is the container point set identified by using the conventional clustering scale method. The standard lengths of the containers are as follows: 20-foot: 605.8 cm, 40-foot: 1219.2 cm.

[0085] Step 630: Obtain the verified anti-lifting monitoring area according to the spreader opening size when the spreader lands on the container, the initial identification point set of the container, and the standard length of the container.

[0086] Combining the currently set spreader opening size, the container point set identified by the conventional method, and the standard length of the container, during the use period or the early stage of the method in the present application, after the staff identifies the target container point set, they can manually delimit the anti-lifting monitoring area as the verified anti-lifting monitoring area. This verified anti-lifting monitoring area is used for comparison and verification with the anti-lifting monitoring area to further improve the reliability of the delimitation result.

[0087] Step 640: Generate the target anti-lifting monitoring area according to the verified anti-lifting monitoring area and the anti-lifting monitoring area.

[0088] Furthermore, Figure 5 as shown, as Figure 5As shown, step 640 may include the following steps:

[0089] Step 6401: Verify the anti-lifting monitoring area. When it is verified that the anti-lifting monitoring area is consistent with the anti-lifting monitoring area, use the anti-lifting monitoring area as the target anti-lifting area.

[0090] The target anti-lifting area is the final anti-lifting area. Compare the verified anti-lifting monitoring area obtained by the auxiliary method with the anti-lifting monitoring area obtained by the adaptive clustering process. If the distance between the corresponding vertices of the two rectangular monitoring areas is less than or equal to the preset determination threshold σ, it means that the verified anti-lifting monitoring area is consistent with the anti-lifting monitoring area, indicating that the recognition and delimitation result is relatively accurate, and applying this result is safer and more effective.

[0091] Or:

[0092] Step 6402: Verify the anti-lifting monitoring area according to the verified anti-lifting monitoring area. When the verified anti-lifting monitoring area is inconsistent with the anti-lifting monitoring area, generate a reminder message and use the verified anti-lifting monitoring area as the target anti-lifting monitoring area.

[0093] Compare the verified anti-lifting monitoring area obtained by the auxiliary method with the anti-lifting monitoring area obtained by the adaptive clustering process. If the distance between the corresponding vertices of the two rectangular monitoring areas is greater than the preset determination threshold σ, it means that the recognition and division result obtained by the adaptive clustering process is inaccurate. Then, generate a reminder or warning message for the operator and use the verified anti-lifting monitoring area obtained by the auxiliary method as the target anti-lifting monitoring area.

[0094] According to the second aspect of the present application, the present application also provides a double-container recognition device for anti-lifting of a container truck, Figure 6 The following shows the working principle diagram of the double-container system for anti-lifting of a container truck provided by an embodiment of the present application. Next, Figure 6 this device will be further described.

[0095] As Figure 6As shown in the figure, the double-container recognition device for preventing the lifting of the container truck specifically includes a point cloud acquisition module 100, a point cloud processing module 200, a sub-point set generation module 300, and a monitoring area generation module 400. Among them, the point cloud acquisition module 100 is used to acquire the initial scanned point cloud set scanned by the scanner 500; the point cloud processing module 200 is used to receive the initial scanned point cloud set transmitted by the point cloud acquisition module 100, and based on the initial scanned point cloud set, obtain the initial reference point, and based on the initial reference point, obtain the minimum recognizable object size of the scanner 500; the sub-point set generation module 300 is used to receive the minimum recognizable object size transmitted by the point cloud processing module 200, and based on the minimum recognizable object size and the initial reference point, perform adaptive clustering on all the point clouds in the initial scanned point cloud set to generate a number of sub-point sets; the monitoring area generation module 400 is used to receive the number of sub-point sets transmitted by the sub-point set generation module 300, and based on the points in the number of sub-point sets, obtain the container point set and the anti-lifting monitoring area.

[0096] The double-container recognition device for preventing the lifting of the container truck provided in this application includes a point cloud acquisition module 100, a point cloud processing module 200, a sub-point set generation module 300, and a monitoring area generation module 400. This device can acquire the initial scanned point cloud set of the scanner 500; based on the initial scanned point cloud set, obtain the initial reference point; based on the initial reference point, obtain the minimum recognizable object size of the scanner 500; based on the minimum recognizable object size and the initial reference point, perform adaptive clustering on all the data points in the initial scanned point cloud set to generate a number of sub-point sets; and based on the point clouds in the number of sub-point sets, obtain the container point set and the anti-lifting monitoring area. By using the initial reference point and the minimum unit size recognizable by the scanner 500, perform clustering on all the point clouds in the initial scanned point cloud set, achieve adaptive clustering for all the point clouds, and finally obtain a number of different sub-point sets, and then distinguish the double-container contour from the sub-point sets. In addition, the system further identifies the point set formed by the container according to the characteristics of different sub-point sets and divides the anti-lifting monitoring area, so as to ensure that two 20-foot containers can be accurately identified, reduce the probability of the container truck being lifted, and ensure the operation safety of the crane and the container truck.

[0097] According to the third aspect of this application, this application also provides a double-container recognition system for preventing the lifting of the container truck. The following will be combined with Figure 6 Describe this double-container recognition system for preventing the lifting of the container truck.

[0098] As Figure 6As shown in the figure, the double-container recognition system for preventing the lifting of the container truck specifically includes a scanner 500 and the above-mentioned double-container recognition device for preventing the lifting of the container truck. The double-container recognition device for preventing the lifting of the container truck is electrically connected to the scanner 500. After the scanner 500 scans to obtain point clouds, it transmits the point cloud data to the double-container recognition device, enabling the double-container recognition device to identify the target container and divide the anti-lifting monitoring area.

[0099] The double-container recognition system for preventing the lifting of the container truck provided in this application includes a scanner 500 and the above-mentioned double-container recognition device for preventing the lifting of the container truck. After the scanner 500 scans the container truck entering the operation area and the containers on the container truck, it transmits the scanned point cloud data to the double-container recognition device, enabling the double-container recognition device to obtain the initial scanned point cloud set of the scanner 500; obtain the initial reference point according to the initial scanned point cloud set; obtain the minimum recognizable object size of the scanner 500 according to the initial reference point; perform adaptive clustering on all data points in the initial scanned point cloud set according to the minimum recognizable object size and the initial reference point to generate several sub-point cloud sets; and obtain the container point cloud set and the anti-lifting monitoring area according to the points in the several sub-point cloud sets. By using the initial reference point and the minimum unit size that the scanner 500 can recognize, cluster all the point clouds in the initial scanned point cloud set, perform adaptive clustering on all the point clouds, and finally obtain several different sub-point cloud sets, and then distinguish the double-container contour from the sub-point cloud sets. In addition, the system further identifies the point cloud set formed by the container according to the characteristics of different sub-point cloud sets and divides the anti-lifting monitoring area, so as to ensure that two 20-foot containers can be accurately identified, reduce the probability of the container truck being lifted, and ensure the operation safety of the crane and the container truck.

[0100] In a possible implementation manner, the scanner 500 in the above system can be a two-dimensional laser scanner, that is, a 2D laser scanner, and this 2D laser scanner is arranged on the saddle beam of the crane. When the container truck with containers enters the operation area and stops, the 2D laser scanner can obtain a two-dimensional point cloud set, that is, the initial scanned point cloud set, by horizontal scanning.

[0101] In addition, the present application also provides a crane, which includes the above-mentioned double-container identification system for preventing the lifting of the truck. This crane can obtain the initial scanned point cloud set of the scanner 500; obtain the initial reference point according to the initial scanned point cloud set; obtain the minimum identifiable object size of the scanner 500 according to the initial reference point; perform adaptive clustering on all data points in the initial scanned point cloud set according to the minimum identifiable object size and the initial reference point to generate a number of sub-point cloud sets; and obtain the container point cloud set and the anti-lifting monitoring area according to the point clouds in the number of sub-point cloud sets. By using the initial reference point and the minimum unit size that the scanner 500 can identify, clustering is performed on all the point clouds in the initial scanned point cloud set, and adaptive clustering is achieved for all the point clouds, and finally a number of different sub-point cloud sets are obtained, and the double-container contour is distinguished from the sub-point cloud sets. In addition, the system further identifies the point cloud set formed by the container according to the characteristics of different sub-point cloud sets and divides the anti-lifting monitoring area, so as to ensure that two 20-foot containers can be accurately identified, reduce the probability of the truck being lifted, and ensure the operation safety of the crane and the truck.

[0102] Next, refer to Figure 7 to describe the electronic device according to the embodiment of the present application. Figure 7 The following shows a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0103] As Figure 7 shown, the electronic device 600 includes one or more processors 601 and a memory 602.

[0104] The processor 601 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or information execution capabilities, and may control other components in the electronic device 600 to perform desired functions.

[0105] The memory 601 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more pieces of computer program information may be stored on the computer-readable storage media, and the processor 601 may run the program information to implement the double-container identification method for preventing the lifting of the truck in the various embodiments of the present application described above or other desired functions.

[0106] In one example, the electronic device 600 may further include: an input device 603 and an output device 604, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0107] The input device 603 may include, for example, a keyboard, a mouse, and the like.

[0108] The output device 604 may output various information to the outside. The output device 604 may include, for example, a display, a communication network, and remote output devices connected thereto, and the like.

[0109] Of course, for the sake of simplicity, Figure 7 only some of the components related to the present application in the electronic device 600 are shown in [the figure], and components such as a bus, an input / output interface, and the like are omitted. In addition, according to specific application scenarios, the electronic device 600 may further include any other appropriate components.

[0110] In addition to the above methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program information, and when the computer program information is run by a processor, the processor is caused to execute the steps in the double-container identification method for preventing container lifting according to various embodiments of the present application described in this specification.

[0111] The computer program product may be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0112] In addition, an embodiment of the present application may also be a computer-readable storage medium, on which computer program information is stored, and when the computer program information is run by a processor, the processor is caused to execute the steps in the double-container identification method for preventing container lifting according to various embodiments of the present application described in this specification.

[0113] The computer-readable storage medium may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0114] The basic principles of the present application have been described above in connection with specific embodiments. However, it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are only examples and not limitations. It cannot be considered that these advantages, benefits, effects, etc. are essential for each embodiment of the present application. Additionally, the specific details disclosed above are only for illustrative and facilitating understanding purposes, rather than limitations. These details do not limit the present application to necessarily adopting the above specific details for implementation.

[0115] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms meaning "including but not limited to" and can be used interchangeably with each other. The word "or" and "and" used herein refer to the word "and / or" and can be used interchangeably with it, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to" and can be used interchangeably with it.

[0116] It should also be noted that in the devices, equipment, and methods of the present application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present application.

[0117] The above description of the disclosed aspects enables any person skilled in the art to make or use the present application. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

[0118] The above are only the preferred embodiments of the creation of the present application and are not used to limit the creation of the present application. Any modifications, equivalent replacements, etc. made within the spirit and principles of the creation of the present application shall be included within the protection scope of the creation of the present application.

Claims

1. A double - box recognition method for preventing the lifting of container trucks, characterized in that, Including: Obtain the initial scanned point cloud set of the scanner; Obtain an initial reference point according to the initial scanned point cloud set; Obtain the minimum recognizable object size of the scanner according to the initial reference point; Perform adaptive clustering on all the point clouds in the initial scanned point cloud set according to the minimum recognizable object size and the initial reference point to generate a number of sub-point cloud sets; And Obtain a container point cloud set and an anti-lifting monitoring area according to the point clouds in a number of the sub-point cloud sets; The performing adaptive clustering on all the point clouds in the initial scanned point cloud set according to the minimum recognizable object size and the initial reference point to generate a number of sub-point cloud sets includes: Obtain a first adjacent point of the initial reference point according to the initial reference point; Obtain a first Euclidean distance between the initial reference point and the first adjacent point according to the initial reference point and the first adjacent point; Obtain a number of the sub-point cloud sets according to the first Euclidean distance, the minimum recognizable object size and a preset margin coefficient.

2. The double-container recognition method for preventing the container crane from lifting the truck according to claim 1, characterized in that, The obtaining a number of the sub-point cloud sets according to the first Euclidean distance, the minimum recognizable object size and a preset margin coefficient includes: When the first Euclidean distance is less than or equal to the adaptive clustering scale, the initial reference point and the first adjacent point are the first sub-points in the first sub-point cloud set; Take the first adjacent point as the current reference point and obtain a second adjacent point of the current reference point; Obtain a second Euclidean distance between the current reference point and the second adjacent point according to the current reference point and the second adjacent point; and When the second Euclidean distance is less than or equal to the adaptive clustering scale, the second adjacent point is the first sub-point in the first sub-point cloud set; Wherein, a number of the sub-point cloud sets include the first sub-point cloud set.

3. The double-container recognition method for preventing the container crane from lifting the truck as claimed in claim 1, wherein The obtaining a number of the sub-point cloud sets according to the first Euclidean distance, the minimum recognizable object size and a preset margin coefficient includes: When the first Euclidean distance is greater than the adaptive clustering scale, the first adjacent point is the second sub-point in the second sub-point cloud set; Wherein, a number of the sub-point cloud sets include the second sub-point cloud set.

4. The double-container recognition method for preventing the container crane from lifting the container truck according to claim 1, wherein The obtaining the minimum recognizable object size of the scanner according to the initial reference point includes: Obtain the distance between the initial reference point and the origin according to the initial reference point; Obtain the preset resolution angle of the scanner; and Generate the minimum recognizable object size of the scanner according to the distance between the initial reference point and the origin and the preset resolution angle.

5. The double-container recognition method for preventing lifting of container trucks according to claim 1, wherein The obtaining a container point cloud set and an anti-lifting monitoring area according to the point clouds in a number of the sub-point cloud sets includes: Obtain the head-to-tail Euclidean distance between the head point and the tail point of each sub-point cloud set, the sum of the abscissas of the head point and the tail point and the number of points in the sub-point cloud set according to the point clouds in a number of the sub-point cloud sets; Obtain a container point cloud set and an anti-lifting monitoring area according to the head-to-tail Euclidean distance between the head point and the tail point of each sub-point cloud set, the sum of the abscissas of the head point and the tail point and the number of points in the sub-point cloud set.

6. The double-container recognition method for preventing lifting of container trucks according to claim 1, characterized in that, After obtaining the container point set and the anti-lifting monitoring area based on the point clouds in several of the sub-point sets, the following steps are further included: Obtain the spreader opening dimension when the spreader lands on the container; Obtain the initial identification point set of the container and the standard length of the container; Based on the spreader opening dimension when the spreader lands on the container, the initial identification point set of the container, and the standard length, obtain the verified anti-lifting monitoring area; Generate a target anti-lifting monitoring area based on the verified anti-lifting monitoring area.

7. The double-container recognition method for preventing the container crane from lifting the truck as claimed in claim 6, wherein, The generating a target anti-lifting monitoring area based on the verified anti-lifting monitoring area includes: When the verified anti-lifting monitoring area is consistent with the anti-lifting monitoring area, use the anti-lifting monitoring area as the target anti-lifting monitoring area; or When the verified anti-lifting monitoring area is inconsistent with the anti-lifting monitoring area, generate a reminder message and use the verified anti-lifting monitoring area as the target anti-lifting monitoring area.

8. A double-container recognition device for preventing the lifting of container trucks, characterized in that, It includes: A point cloud acquisition module for acquiring the initial scanned point cloud set of the scanner; A point cloud processing module for receiving the initial scanned point cloud set transmitted by the point cloud acquisition module, obtaining an initial reference point based on the initial scanned point cloud set, and obtaining the minimum recognizable object size of the scanner based on the initial reference point; A sub-point set generation module for receiving the minimum recognizable object size transmitted by the point cloud processing module, adaptively clustering all the point clouds in the initial scanned point cloud set based on the minimum recognizable object size and the initial reference point to generate several sub-point sets; the adaptively clustering all the point clouds in the initial scanned point cloud set based on the minimum recognizable object size and the initial reference point to generate several sub-point sets includes: obtaining the first adjacent point of the initial reference point based on the initial reference point; obtaining the first Euclidean distance between the initial reference point and the first adjacent point based on the initial reference point and the first adjacent point; obtaining several of the sub-point sets based on the first Euclidean distance, the minimum recognizable object size, and a preset margin coefficient; and A monitoring area generation module for receiving the several sub-point sets transmitted by the sub-point set generation module and obtaining the container point set and the anti-lifting monitoring area based on the point clouds in the several sub-point sets.

9. A double-container recognition system for preventing the lifting of container trucks, characterized in that, It includes: A scanner, and the scanner is arranged on the crane; The double-container identification device for anti-lifting of the container carrier as claimed in claim 8, and the double-container identification device for anti-lifting of the container carrier is electrically connected to the scanner.

10. The double-container identification system for preventing lifting of container trucks according to claim 9, characterized in that, The scanner includes: A two-dimensional laser scanner, and the two-dimensional laser scanner is arranged on the saddle beam of the crane.

11. A crane, characterized in that, It includes: The double-container identification system for anti-lifting of the container carrier as claimed in claim 9 or 10.

Images