Hoisting object detection method of intelligent tower crane and intelligent tower crane

Abstract

The invention discloses a lifting object detection method of an intelligent tower crane and the intelligent tower crane. The intelligent tower crane comprises an intelligent lifting hook and an image acquisition device. The intelligent lifting hook is used for being connected with a lifted object, obtaining state information of the lifted object and collecting point cloud data below the lifted object. The image acquisition device is used for acquiring a real-time image within a preset range of the lifting hook; the lifting object detection method comprises the steps that when it is determined that the lifting object is lifted according to the state information, the intelligent lifting hook is controlled to collect the point cloud data; according to the point cloud data and a preset contour algorithm, obtaining a suspended object contour of the suspended object; carrying out preset radius expansion on the profile of the hoisted object to obtain a hoisting dangerous area; detecting persons in the lifting dangerous area; and displaying the real-time image, and marking the hoisting dangerous area and the person on the real-time image to give an alarm. According to the invention, the computing power and the maintenance cost required for identifying the profile of the hanging object can be reduced, and the safety and the stability of the intelligent tower crane are improved.

Description

Technical Field

[0001] This application relates to the field of construction machinery and equipment technology, specifically to a method for detecting suspended objects on an intelligent tower crane and the intelligent tower crane itself. Background Technology

[0002] Currently, existing tower cranes primarily rely on machine vision to identify the outlines of objects being lifted using image processing technology. Machine vision-based methods depend on high-performance servers, resulting in high development and maintenance costs. Furthermore, in low-visibility environments, the performance of vision-based detection solutions degrades significantly, impacting the safety and stability of the tower crane. Summary of the Invention

[0003] In view of this, this application provides a method for detecting suspended objects using an intelligent tower crane and an intelligent tower crane itself, which reduces the computing power and maintenance costs required to identify the outline of suspended objects, and improves the safety and stability of the intelligent tower crane. The technical solution of this application is as follows: The first aspect of this application provides a method for detecting suspended objects using an intelligent tower crane. The intelligent tower crane includes an intelligent hook and an image acquisition device. The intelligent hook is used to connect to the suspended object, acquire the status information of the suspended object, and acquire point cloud data below it. The image acquisition device is used to acquire real-time images within a preset range of the hook. The method for detecting suspended objects includes: determining, based on the status information, when to lift the suspended object, controlling the intelligent hook to acquire the point cloud data; obtaining the suspended object contour based on the point cloud data and a preset contour algorithm; expanding the suspended object contour by a preset radius to obtain a lifting hazard area; detecting personnel within the lifting hazard area; displaying the real-time image, and marking the lifting hazard area and the personnel on the real-time image to issue an alarm.

[0004] In one embodiment of this application, the intelligent hook includes a position sensor, a mass sensor, and a lidar. The status information includes the hook position and the lifting mass. When determining to lift the object based on the status information, controlling the intelligent hook to collect the point cloud data includes: determining to lift the object when the lifting mass is greater than a preset value and the intelligent hook displacement is determined based on the hook position; controlling the lidar to collect the point cloud data; and determining that the intelligent hook is unloaded when the lifting mass is less than or equal to the preset value.

[0005] In one embodiment of this application, obtaining the outline of the suspended object based on the point cloud data and a preset outline algorithm includes: performing region filtering and downsampling processing on the point cloud data to obtain preprocessed point cloud data; performing elevation removal processing on the preprocessed point cloud data to obtain two-dimensional point cloud data; performing two-dimensional clustering processing on the two-dimensional point cloud data to obtain multiple point cloud clusters; selecting a target point cloud cluster from the multiple point cloud clusters based on the center position of the smart hook; and obtaining the outline of the suspended object based on the target point cloud cluster.

[0006] In one embodiment of this application, the step of selecting a target point cloud cluster from multiple point cloud clusters based on the center position of the smart hook includes: calculating the center point of each point cloud cluster; calculating the distance between each center point and the center position; and determining a preset number of point cloud clusters corresponding to smaller distances as the target point cloud clusters.

[0007] In one embodiment of this application, the suspended object detection method further includes: determining, based on the status information, when the intelligent hook is unloaded and off the ground, obtaining a danger zone with a preset radius centered on the intelligent hook; detecting the person within the danger zone; displaying the real-time image, and marking the danger zone and the person on the real-time image to issue an alarm.

[0008] In one embodiment of this application, the intelligent hook includes a position sensor and a mass sensor, and the status information includes the hook position and the lifting mass; the step of determining that the intelligent hook is off the ground unloaded based on the status information and obtaining the danger zone with the intelligent hook as the center point includes: determining that the lifting mass is less than or equal to the preset value, and determining that the intelligent hook is off the ground unloaded based on the hook position.

[0009] In one embodiment of this application, the step of expanding the outline of the suspended object by a preset radius to obtain a lifting danger zone includes: obtaining the circumcircle of the outline of the suspended object; and expanding the circumcircle by a preset radius to obtain a lifting danger zone.

[0010] A second aspect of this application provides an intelligent tower crane, including an intelligent hook, an image acquisition device, a display device, and a controller. The intelligent hook is used to connect to a suspended object, acquire the status information of the suspended object, and collect point cloud data below it. The image acquisition device is used to collect real-time images within a preset range of the hook. The controller is used to: determine when to lift the suspended object based on the status information, control the intelligent hook to collect the point cloud data; obtain the suspended object contour based on the point cloud data and a preset contour algorithm; expand the suspended object contour by a preset radius to obtain a lifting hazard area; detect personnel within the lifting hazard area; control the display device to display the real-time image, and mark the lifting hazard area and the personnel on the real-time image to issue an alarm.

[0011] In one embodiment of this application, the smart hook includes a position sensor, a mass sensor, and a lidar; the status information includes the hook position and the lifting mass; the position sensor is used to acquire the hook position; the mass sensor is used to acquire the lifting mass; and the lidar is used to acquire the point cloud data.

[0012] It is understood that this application, by acquiring the status information of the intelligent hook and determining the object to be lifted based on the status information, controls the intelligent hook to collect point cloud data below, and obtains the outline of the object to be lifted based on the point cloud data. Compared with machine vision methods, detecting the outline of the object requires less computing power, has lower development and maintenance costs, and is stable in low visibility conditions. After obtaining the outline of the object, the outline is expanded to obtain the lifting hazard area, and people in the lifting hazard area are detected and real-time alarms are displayed, which can improve the safety of the intelligent tower crane during operation. Attached Figure Description

[0013] Figure 1 This is a schematic block diagram of an intelligent tower crane provided in an embodiment of this application.

[0014] Figure 2 This is a flowchart illustrating a method for detecting suspended objects by an intelligent tower crane, as provided in an embodiment of this application.

[0015] Figure 3 This is a schematic block diagram of an intelligent hook provided in an embodiment of this application.

[0016] Figure 4 This is a flowchart illustrating a method for detecting the lifting of a suspended object, as provided in an embodiment of this application.

[0017] Figure 5 This is a flowchart illustrating a method for obtaining the outline of a suspended object according to an embodiment of this application.

[0018] Figure 6This is a schematic diagram of a process for filtering target point cloud clusters provided in an embodiment of this application.

[0019] Figure 7 This is a schematic diagram of a process for obtaining a lifting hazard area provided in an embodiment of this application.

[0020] Figure 8 This is a flowchart illustrating the second intelligent tower crane load detection method provided in this application embodiment.

[0021] Figure 9 This is a schematic block diagram of an intelligent tower crane provided in an embodiment of this application. Detailed Implementation

[0022] It should be noted that in the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0023] It should also be noted that the methods disclosed in the embodiments of this application or the methods shown in the flowcharts include one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged, and some steps can also be deleted.

[0024] Currently, existing tower cranes primarily rely on machine vision to identify the outlines of objects being lifted using image processing technology. Machine vision-based methods depend on high-performance servers, resulting in high development and maintenance costs. Furthermore, in low-visibility environments, the performance of vision-based detection solutions degrades significantly, impacting the safety and stability of the tower crane.

[0025] This application provides a method for detecting suspended objects using an intelligent tower crane and an intelligent tower crane, which reduces the computing power and maintenance costs required to identify the outline of suspended objects, and improves the safety and stability of the intelligent tower crane.

[0026] Please refer to Figure 1 , Figure 1 This is a schematic block diagram of an intelligent tower crane provided in an embodiment of this application, wherein the intelligent tower crane 100 includes an intelligent hook 110 and an image acquisition device 120.

[0027] In this embodiment, the intelligent hook 110 and the image acquisition device 120 are mounted on the boom 130 of the intelligent tower crane 100. The intelligent hook 110 is used to connect to the suspended load, acquire the status information of the suspended load, and collect point cloud data below. The image acquisition device 120 is used to collect real-time images within a preset range of the hook.

[0028] Next, combine Figure 1 This application introduces a method for detecting suspended objects on an intelligent tower crane, as described in an embodiment. Please refer to [link / reference]. Figure 2 Specifically, it includes the following steps: Step S21: When determining the object to be lifted based on the status information, control the intelligent hook to collect point cloud data.

[0029] In this embodiment, the intelligent tower crane also includes a controller, which is connected to the intelligent hook and the image acquisition device. The intelligent hook can acquire the aforementioned status information in real time and transmit it to the controller. The controller receives the status information transmitted by the intelligent hook, determines the lifting load based on the status information, and then controls the intelligent hook to acquire point cloud data below.

[0030] The status information includes the position, speed, and mass of the suspended load of the intelligent hook, among other things, without limitation. Sensors can be installed on the intelligent hook to acquire the aforementioned position, speed, and mass information and transmit it to the controller.

[0031] It is understandable that the orientation of the suspended object may change during the lifting process, thus altering its outline. Therefore, during the lifting process, the intelligent hook can collect point cloud data at preset time intervals, such as every 0.5 seconds, and transmit the data to the controller to update the point cloud related to the suspended object in real time and refresh its outline promptly. Alternatively, the controller can be configured with multiple time intervals corresponding to different lifting speeds, and the controller can match the current lifting speed to the corresponding time interval to control the intelligent hook to collect point cloud data.

[0032] Step S22: Obtain the outline of the suspended object based on the point cloud data and the preset contour algorithm.

[0033] In this embodiment, after obtaining the point cloud data for the current period, the controller can obtain the outline of the suspended object for the current period based on the point cloud data and a preset contour algorithm. For example, the controller can perform point cloud clustering processing to divide the point cloud data into multiple point cloud clusters, then filter out each target point cloud cluster corresponding to the suspended object, and finally obtain the outline of the suspended object based on the target point cloud clusters.

[0034] Step S23: Expand the outline of the suspended object by a preset radius to obtain the lifting danger zone.

[0035] In this embodiment, after obtaining the outline of the suspended object through point cloud data, the controller can expand the outline of the suspended object by a preset radius to form a lifting hazard zone. It is understood that after being lifted, the suspended object is off the ground, and a certain area below the suspended object at a high altitude is dangerous. Therefore, by expanding the outline of the suspended object to form a lifting hazard zone, and marking and displaying this zone, early warnings can be provided to workers within the lifting hazard zone, improving worker safety. For example, the preset radius can be 3 meters, meaning the outline of the suspended object is expanded by 3 meters to form the lifting hazard zone.

[0036] Step S24: Detect people in the hoisting danger zone.

[0037] In this embodiment, the controller can also be connected to an image acquisition device to acquire real-time images of the hook within a preset range. After acquiring the real-time images and the aforementioned lifting hazard area, the controller can detect whether any person is present in the lifting hazard area of ​​the real-time image. If a person is detected in the lifting hazard area, the controller can mark the person in the real-time image.

[0038] Step S25: Display the real-time image and mark the dangerous areas and personnel involved in the hoisting on the real-time image to issue an alarm.

[0039] In this embodiment, the intelligent tower crane system may also include an image display device connected to the controller. The image display device can receive and display real-time images. During the lifting process, after identifying the hazardous area, the controller can control the image display device to mark it on the displayed real-time image, for example, by encircling the hazardous area with a red line. Furthermore, during the lifting process, the controller can also control the image display device to mark people within the hazardous area on the displayed real-time image, for example, by marking them with a red frame.

[0040] It is understood that this application, by acquiring the status information of the intelligent hook and determining the object to be lifted based on the status information, controls the intelligent hook to collect point cloud data below, and obtains the outline of the object to be lifted based on the point cloud data. Compared with machine vision methods, detecting the outline of the object requires less computing power, has lower development and maintenance costs, and is stable in low visibility conditions. After obtaining the outline of the object, the outline is expanded to obtain the lifting hazard area, and people in the lifting hazard area are detected and real-time alarms are displayed, which can improve the safety of the intelligent tower crane during operation.

[0041] In some embodiments, such as Figure 3As shown, the intelligent hook 110 includes a position sensor 111, a mass sensor 112, and a lidar 113. The status information includes the hook position and the lifting mass.

[0042] In this embodiment, position sensor 111 is used to acquire the position of the hook. Mass sensor 112 is used to acquire the lifting mass. LiDAR 113 is used to acquire point cloud data. Position sensor 111 can be installed inside the smart hook 110, mass sensor 112 can be installed on the hook of the smart hook 110, and LiDAR 113 can be installed on the outside of the smart hook 110 and vertically downwards.

[0043] Please refer to Figure 4 , Figure 4 This application provides a flowchart illustrating a method for detecting the lifting of an object, which specifically includes the following steps: Step S41: When it is determined that the lifting mass is greater than the preset value and the displacement of the intelligent hook is determined according to the position of the hook, the object to be lifted is determined.

[0044] In this embodiment, the controller is connected to the position sensor and mass sensor of the smart hook to receive the hook position transmitted by the position sensor and the lifting mass transmitted by the mass sensor in real time. When the controller determines that the lifting mass is greater than a preset value and determines the displacement of the smart hook based on the hook position, it determines that the smart hook is lifting the object. The preset value can be 0 and is not limited here.

[0045] Step S42: Control the lidar to collect point cloud data.

[0046] In this embodiment, after the smart hook determines the object to be lifted, the controller then controls the lidar to collect point cloud data, so as to avoid the lidar running for a long time and improve the lidar's service life.

[0047] Step S43: When the lifting mass is less than or equal to the preset value, determine that the intelligent hook is unloaded.

[0048] It is understandable that when the lifting mass is less than or equal to the preset value, the displacement of the intelligent hook can be determined based on the hook position, thus indicating that the intelligent hook is moving under no-load. Conversely, when the lifting mass is less than or equal to the preset value, the intelligent hook can be determined to be stationary under no-load based on the hook position.

[0049] Please refer to Figure 5 , Figure 5 This application provides a flowchart illustrating a method for obtaining the outline of a suspended object, which specifically includes the following steps: Step S51: Perform regional filtering and downsampling on the point cloud data to obtain preprocessed point cloud data.

[0050] In this embodiment, a region is defined centered on the smart hook, and point cloud data outside this region is filtered out; this is the aforementioned region filtering process. Uniform downsampling can also be performed based on the horizontal distribution of the point cloud data. It can be understood that after obtaining the point cloud data, the controller first performs region filtering and downsampling on the point cloud data, which can reduce the amount of point cloud data, thereby reducing the subsequent computational load on the controller and improving detection efficiency.

[0051] Step S52: Perform elevation removal processing on the preprocessed point cloud data to obtain two-dimensional point cloud data.

[0052] In this embodiment of the application, the elevation removal process removes the height information from the point cloud data, thereby reducing the elevation dimension information of the point cloud data and increasing the horizontal plane density of the point cloud data, thus reducing the efficiency and accuracy of subsequent suspended object contour detection.

[0053] Step S53: Perform two-dimensional clustering on the two-dimensional point cloud data to obtain multiple point cloud clusters.

[0054] In this embodiment of the application, after obtaining two-dimensional point cloud data, the controller can traverse each point cloud data and perform two-dimensional clustering processing to obtain multiple point cloud clusters. For example, when traversing to point A, if the controller detects that point cloud data P exists in the vicinity of point A, it can consider point cloud data A and point cloud data P to be of the same class, and finally obtain multiple point cloud clusters.

[0055] Step S54: Select the target point cloud cluster from multiple point cloud clusters based on the center position of the smart hook.

[0056] In this embodiment, the controller can select point cloud clusters that are closer to the center of the smart hook as the target point cloud clusters. For example, in some embodiments, the distance between the center of each point cloud cluster and the center position can be obtained first, and point cloud clusters with a distance greater than a preset distance can be filtered out to finally obtain the target point cloud clusters.

[0057] Step S55: Obtain the outline of the suspended object based on the target point cloud cluster.

[0058] In this embodiment of the application, after obtaining the target point cloud cluster, the controller can obtain the outline of the suspended object based on the target point cloud cluster. For example, after determining the target point cloud cluster, the controller can obtain the edge outline of the target point cloud cluster as the outline of the suspended object.

[0059] In some embodiments, such as Figure 6 As shown, the steps for filtering out target point cloud clusters may further include the following steps: Step S61: Calculate the center point of each point cloud cluster.

[0060] Step S62: Calculate the distance between each center point and the center position.

[0061] Step S63: Determine the target point cloud cluster as the point cloud cluster corresponding to a preset number of smaller distances.

[0062] In this embodiment of the application, after the controller obtains the distance between each center point and the center position, it can sort each distance, for example, sort them from smallest to largest. After sorting, it obtains a preset number of target distances from smallest to largest, and finally obtains the point cloud clusters corresponding to the preset number of smaller distances as the target point cloud clusters.

[0063] Please refer to Figure 7 , Figure 7 A flowchart illustrating the process of obtaining a lifting hazard area, provided in this application embodiment, specifically includes the following steps: Step S71: Obtain the circumcircle of the suspended object's outline.

[0064] Step S72: Expand the circumcircle by a preset radius to obtain the lifting danger zone.

[0065] In this embodiment of the application, after the controller obtains multiple target point cloud clusters, it can first obtain the outline of the suspended object based on the target point cloud clusters at the edge, and then obtain the circumcircle of the outline of the suspended object.

[0066] Please refer to Figure 8 , Figure 8 A flowchart illustrating the second intelligent tower crane load detection method provided in this application embodiment specifically includes the following steps: Step S81: Based on the status information, determine the danger zone with a preset radius centered on the smart hook when it is unloaded and off the ground.

[0067] It is understandable that when the intelligent hook moves to the location of the suspended object, it is unloaded and off the ground. There is also a danger in a certain direction below the intelligent hook at a high altitude. Therefore, a danger zone can be obtained with the intelligent hook as the center point, and the danger zone can be marked and displayed to provide early warning to workers in the danger zone, thereby improving the safety of workers in the workplace.

[0068] In some embodiments, the smart hook includes a position sensor and a mass sensor, and the status information includes the hook position and the lifted mass. That is, when it is determined that the lifted mass is less than or equal to a preset value, and the displacement of the smart hook is determined based on the hook position, it is determined that the hook is off the ground unloaded.

[0069] Step S82: Detect people in the danger zone.

[0070] In this embodiment, when the controller detects that the smart hook is unloaded and off the ground, it can also control the image acquisition device to acquire real-time images within a preset range and detect whether there are any people in the danger zone of the real-time images. If a person is detected in the danger zone, the controller can mark the person in the real-time images.

[0071] Step S83: Display the real-time image and mark dangerous areas and people on the real-time image to issue an alarm.

[0072] In this embodiment, the image display device can also receive and display real-time images when the intelligent hook is unloaded and off the ground. After identifying the danger zone, the controller can control the image display device to mark it on the displayed real-time image, for example, by encircling the danger zone with a red line. Furthermore, during the process of the intelligent hook being unloaded and off the ground, the controller can also control the image display device to mark people within the displayed danger zone, for example, by marking people with a red frame within the danger zone.

[0073] Please refer to Figure 9 , Figure 9 This is a schematic block diagram of an intelligent tower crane provided in an embodiment of this application. The intelligent tower crane 900 includes an intelligent hook 910, an image acquisition device 920, a display device 930, and a controller 940. The intelligent hook 910 is used to connect to the suspended object, acquire the status information of the suspended object, and collect point cloud data below it; the image acquisition device 920 is used to collect real-time images within a preset range of the hook.

[0074] The controller 940 is used to: control the intelligent hook 910 to collect point cloud data when the lifting object is determined according to the status information; obtain the lifting object contour according to the point cloud data and the preset contour algorithm; expand the lifting object contour by a preset radius to obtain the lifting danger zone; detect people in the lifting danger zone; control the display device 930 to display the real-time image; and mark the lifting danger zone and people on the real-time image to issue an alarm.

[0075] In this embodiment, the smart hook 910 includes a position sensor 911, a mass sensor 912, and a lidar 913. The status information includes the hook position and the lifted mass. The position sensor 911 is used to acquire the hook position. The mass sensor 912 is used to acquire the lifted mass. The lidar 913 is used to acquire point cloud data. In some embodiments, the position sensor 911 includes an RTK sensor.

[0076] This application also provides a computer storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the above-described suspended object detection method.

[0077] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer storage medium or transmitted through the computer storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0078] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks. Unless otherwise specified, the technical features of this embodiment and its implementation can be combined arbitrarily.

[0079] The embodiments described above are merely preferred embodiments of this application and are not intended to limit the scope of this application. Any modifications and improvements made by those skilled in the art to the technical solutions of this application without departing from the spirit of this application should fall within the protection scope defined by the claims of this application.

Claims

1. A method for detecting suspended objects on an intelligent tower crane, characterized in that, The intelligent tower crane includes an intelligent hook and an image acquisition device; the intelligent hook is used to connect to the suspended object, obtain the status information of the suspended object, and collect point cloud data below it; The image acquisition device is used to acquire real-time images within a preset range of the hook; The method for detecting suspended objects includes: When determining to lift the load based on the status information, control the smart hook to collect the point cloud data; The outline of the suspended object is obtained based on the point cloud data and the preset contour algorithm; The outline of the suspended object is expanded by a preset radius to obtain the lifting danger zone; Detect people within the lifting hazard area; The real-time image is displayed, and the dangerous lifting area and the person are marked on the real-time image to issue an alarm.

2. The method for detecting suspended objects as described in claim 1, characterized in that, The intelligent hook includes a position sensor, a mass sensor, and a lidar, and the status information includes the hook position and the lifting mass. When determining to lift the load based on the status information, controlling the smart hook to collect the point cloud data includes: When it is determined that the lifting mass is greater than a preset value, and the displacement of the smart hook is determined according to the position of the hook, the object to be lifted is lifted. Control the lidar to acquire the point cloud data; When the lifting mass is determined to be less than or equal to the preset value, the smart hook is determined to be unloaded.

3. The method for detecting suspended objects as described in claim 1, characterized in that, The step of obtaining the outline of the suspended object based on the point cloud data and a preset contour algorithm includes: The point cloud data is subjected to regional filtering and downsampling to obtain preprocessed point cloud data; The preprocessed point cloud data is subjected to elevation removal processing to obtain two-dimensional point cloud data; The two-dimensional point cloud data is subjected to two-dimensional clustering to obtain multiple point cloud clusters; The target point cloud cluster is selected from multiple point cloud clusters based on the center position of the intelligent hook. The outline of the suspended object is obtained based on the target point cloud cluster.

4. The method for detecting suspended objects as described in claim 3, characterized in that, The step of selecting the target point cloud cluster from multiple point cloud clusters based on the center position of the smart hook includes: Calculate the center point of each of the point cloud clusters; Calculate the distance between each of the center points and the center location; The point cloud clusters corresponding to the smaller distances are determined as the target point cloud clusters.

5. The method for detecting suspended objects as described in claim 1, characterized in that, The method for detecting suspended objects also includes: Based on the status information, when the intelligent hook is unloaded and off the ground, a danger zone with a preset radius is obtained with the intelligent hook as the center point. Detect the person within the danger zone; The system displays the real-time image and marks the danger zone and the person on the real-time image to issue an alert.

6. The method for detecting suspended objects as described in claim 5, characterized in that, The intelligent hook includes a position sensor and a mass sensor, and the status information includes the hook position and the lifting mass. The step of determining, based on the status information, when the intelligent hook is unloaded and off the ground, to obtain the danger zone with the intelligent hook as the center point, includes: When the lifting mass is determined to be less than or equal to the preset value, and the displacement of the intelligent hook is determined based on the hook position, the unloaded lifting off the ground is determined.

7. The method for detecting suspended objects as described in claim 1, characterized in that, The step of expanding the outline of the suspended object by a preset radius to obtain the lifting danger zone includes: Obtain the circumcircle of the suspended object's outline; The circumcircle is expanded by a preset radius to obtain the lifting danger zone.

8. An intelligent tower crane, characterized in that, It includes an intelligent hook, an image acquisition device, a display device, and a controller; the intelligent hook is used to connect to the suspended object, acquire the status information of the suspended object, and collect point cloud data below it; the image acquisition device is used to collect real-time images within a preset range of the hook; The controller is used for: When determining to lift the load based on the status information, control the smart hook to collect the point cloud data; The outline of the suspended object is obtained based on the point cloud data and the preset contour algorithm; The outline of the suspended object is expanded by a preset radius to obtain the lifting danger zone; Detect people within the lifting hazard area; The display device is controlled to display the real-time image, and the dangerous area of ​​the hoisting and the person are marked on the real-time image to issue an alarm.

9. The intelligent tower crane as described in claim 8, characterized in that, The intelligent hook includes a position sensor, a mass sensor, and a lidar, and the status information includes the hook position and the lifting mass. The position sensor is used to obtain the position of the hook; The mass sensor is used to obtain the lifting mass; The lidar is used to acquire the point cloud data.

10. The intelligent tower crane as described in claim 8, characterized in that, The position sensor includes an RTK sensor.

Images