Boarding bridge control method and device, electronic equipment and storage medium

Abstract

The invention provides a boarding bridge control method and device, electronic equipment and a storage medium, and relates to the technical field of boarding bridges. The method comprises the following steps: acquiring real-time data of a boarding bridge channel environment; analyzing the real-time data to obtain a target detection result; and obtaining a control instruction of the boarding bridge according to the target detection result, wherein the control instruction is used for controlling the motion state of the boarding bridge. According to the method, massive visual information does not need to be manually analyzed one by one, and the system directly processes the data to obtain the control instruction, so that the monitoring efficiency of the boarding bridge is improved, the manual processing requirement on massive visual information is reduced, and the misjudgment risk is reduced.

Description

Background Art

[0002] The safe operation of the boarding bridge mainly relies on manual inspections and camera monitoring. In the manual inspection mode, the boarding bridge operator needs to personally conduct inspections in the passage before operating the boarding bridge and ensure that there are no people in the passage before starting the operation. With the emergence of the remote operation mode, the operator's position has shifted to the remote operation room. In this mode, multiple cameras are usually installed in the boarding bridge passage, and the operator uses the monitoring screen to assist in confirming whether there are obstacles such as people in the passage, and then controls multiple boarding bridges through the remote operation console in the remote operation room.

[0003] However, in the actual application process, the remote operator needs to monitor multiple camera images simultaneously, which not only involves a large workload but also easily leads to distraction of attention and reduces the monitoring efficiency. And because the remote operator needs to process a large amount of visual information, it is easy to have defocusing, resulting in missing key details and increasing the risk of misjudgment.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The present disclosure provides a boarding bridge control method, device, electronic device and storage medium, which at least overcome the problems of low monitoring efficiency and high misjudgment risk in the related art to a certain extent.

[0006] Other features and advantages of the present disclosure will become apparent through the following detailed description, or will be learned in part through the practice of the present disclosure.

[0007] According to one aspect of the present disclosure, a boarding bridge control method is provided, including: obtaining real-time data of the boarding bridge passage environment; analyzing the real-time data to obtain a target detection result; and obtaining a control instruction for the boarding bridge according to the target detection result, where the control instruction is used to control the motion state of the boarding bridge.

[0008] In some embodiments, the real-time data is the real-time data collected by radar sensors and / or infrared sensors installed inside the boarding bridge passage and at each entrance and exit of the boarding bridge; the boarding bridge control method further includes: before the boarding bridge operates, obtaining first real-time data collected by sensors inside the boarding bridge passage and at each entrance and exit of the boarding bridge; obtaining a first sub-goal detection result based on the collected first real-time data; obtaining a first sub-control instruction for the boarding bridge according to the first sub-goal detection result, where the first sub-control instruction is used to control the motion state of the boarding bridge; and / or, the boarding bridge control method further includes: after the boarding bridge starts, shielding the sensors inside the boarding bridge passage, obtaining second real-time data collected by sensors at each entrance and exit of the boarding bridge; obtaining a second sub-goal detection result based on the collected second real-time data; obtaining a second sub-control instruction for the boarding bridge according to the second sub-goal detection result, where the second sub-control instruction is used to control the motion state of the boarding bridge.

[0009] In some embodiments, the real-time data is the image inside the boarding bridge passage collected by multiple image acquisition devices; the analyzing the real-time data to obtain a target detection result includes: inputting the image inside the boarding bridge passage collected by the multiple image acquisition devices into a target detection model to output a target detection result; where the target detection model is a model obtained through machine learning training for detecting whether a target object enters a target area inside the boarding bridge passage; obtaining a control instruction for the boarding bridge according to the target detection result, and the control instruction is used to control the motion state of the boarding bridge.

[0010] In some embodiments, the inputting the image inside the boarding bridge passage into the target detection model to output a target detection result includes: detecting whether there is a target object in the image of the boarding bridge passage collected; when there is the target object in the image of the boarding bridge passage collected, locating the position information of the target object; judging whether the target object enters the target area inside the boarding bridge passage according to the relationship between the target area inside the boarding bridge passage and the position information of the target object to obtain a target detection result.

[0011] In some embodiments, the judging whether the target object enters the target area inside the boarding bridge passage according to the relationship between the target area inside the boarding bridge passage and the position information of the target object includes: determining the behavior characteristics of the target object according to the relationship between the target area inside the boarding bridge passage and the position information of the target object; outputting an action category label and an abnormal confidence level corresponding to the behavior characteristics of the target object based on the behavior characteristics of the target object; if the abnormal confidence level is greater than a preset confidence level threshold, determining that the target object enters the target area inside the boarding bridge passage.

[0012] In some embodiments, outputting an action category label and an anomaly confidence corresponding to the behavioral characteristics of the target object includes: constructing an abnormal behavioral characteristics database for a target area within the boarding bridge passageway, where the abnormal behavioral characteristics database includes: abnormal behavioral characteristics of the target object entering the target area within the boarding bridge passageway; matching the behavioral characteristics of the target object with the abnormal behavioral characteristics in the abnormal behavioral characteristics database; if any abnormal behavioral characteristic in the abnormal behavioral characteristics database is matched, outputting an action category label and an anomaly confidence corresponding to the behavioral characteristics of the target object; and / or, outputting an action category label and an anomaly confidence corresponding to the behavioral characteristics of the target object includes: constructing a normal characteristics database for the boarding bridge passageway, where the normal characteristics database includes: normal characteristics of the target object not entering the target area within the boarding bridge passageway; calculating a similarity between the behavioral characteristics of the target object and the normal characteristics based on the behavioral characteristics of the target object and the normal characteristics database; and outputting an action category label and an anomaly confidence corresponding to the behavioral characteristics of the target object according to the similarity.

[0013] In some embodiments, outputting an action category label and an anomaly confidence corresponding to the behavioral characteristics of the target object according to the behavioral characteristics of the target object includes: constructing a hybrid intrusion detection model; the hybrid intrusion detection model includes a feature matching module and an anomaly detection module; inputting the behavioral characteristics of the target object into the feature matching module to obtain a feature matching detection result; inputting the behavioral characteristics of the target object into the anomaly detection module to obtain an anomaly detection result; and fusing the feature matching detection result and the anomaly detection result to output an action category label and an anomaly confidence corresponding to the behavioral characteristics of the target object.

[0014] In some embodiments, locating the position information of the target object includes: the target object includes a person and / or an object and can be freely configured; and / or, a size range of the target object that can be freely configured is set; and / or, the target area can be freely configured; and / or, a time threshold and / or a sensitivity threshold that can be freely configured are set.

[0015] In some embodiments, locating the position information of the target object includes: identifying the initial position information of the target object; when the change in the position information of the target object relative to the boarding bridge does not exceed a preset threshold, obtaining the static position information of the target object; when the change in the position information of the target object relative to the boarding bridge exceeds the preset threshold, tracking the target object to obtain the dynamic position information of the target object.

[0016] In some embodiments, the boarding bridge is a multi-section boarding bridge structure. The multi-section boarding bridge includes a first telescopic module, a second telescopic module, and a third telescopic module nested from outside to inside. The first end of the first telescopic module is connected to a fixing device. The second end of the first telescopic module is connected to the first end of the second telescopic module. The second end of the second telescopic module is connected to the first end of the third telescopic module. The second end of the third telescopic module is used to connect to an aircraft. When the boarding bridge is in a stationary state, the target area inside the boarding bridge includes at least a first stationary area and a second stationary area. When the boarding bridge is in a moving state, the target area inside the boarding bridge includes at least a first dynamic area and a second dynamic area. The first stationary area and the first dynamic area are located in the area where the second end of the first telescopic module is connected to the first end of the second telescopic module. The second stationary area and the second dynamic area are located in the area where the second end of the second telescopic module is connected to the first end of the third telescopic module.

[0017] According to another aspect of the present disclosure, there is also provided a boarding bridge control device, including: a first acquisition module, configured to acquire real-time data of the boarding bridge passage environment; a target detection module, configured to analyze the real-time data to obtain a target detection result; a second acquisition module, configured to obtain a control instruction for the boarding bridge according to the target detection result, and the control instruction is used to control the motion state of the boarding bridge.

[0018] According to another aspect of the present disclosure, there is also provided an electronic device, which includes: a processor; and a memory, configured to store executable instructions of the processor. Wherein, the processor is configured to execute the boarding bridge control method described in any one of the above by executing the executable instructions.

[0019] According to another aspect of the present disclosure, there is also provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the boarding bridge control method described in any one of the above.

[0020] According to another aspect of the present disclosure, there is also provided a computer program product, including: a computer program or instruction, and when the computer program or instruction is executed by a processor, it implements the boarding bridge control method described in any one of the above.

[0021] The boarding bridge control method, device, electronic device, and storage medium provided in the embodiments of the present disclosure obtain real-time data of the boarding bridge passage environment; analyze the real-time data to obtain a target detection result; and obtain a control instruction for the boarding bridge according to the target detection result, where the control instruction is used to control the motion state of the boarding bridge. Since the above method does not require manual analysis of a large amount of visual information one by one, the system directly processes the data to obtain the control instruction, thereby improving the monitoring efficiency of the boarding bridge, reducing the manual processing requirement for a large amount of visual information, and reducing the risk of misjudgment.

[0022] Furthermore, since this embodiment improves the monitoring efficiency and reduces the risk of misjudgment, obtaining the control instruction for the boarding bridge according to the target detection result and controlling the motion state of the boarding bridge can ensure the safety of personnel and equipment during the movement of the boarding bridge.

[0023] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0025] Figure 1 Exemplary system architecture diagram showing a boarding bridge control method in an embodiment of the present disclosure;

[0026] Figure 2A Exemplary layout diagram of multiple cameras of a boarding bridge in an embodiment of the present disclosure;

[0027] Figure 2B Exemplary layout diagram of multiple sensors of a boarding bridge in an embodiment of the present disclosure;

[0028] Figure 3A Exemplary flowchart of a boarding bridge control method in an embodiment of the present disclosure;

[0029] Figure 3B Exemplary flowchart of another boarding bridge control method in an embodiment of the present disclosure;

[0030] Figure 3C Exemplary flowchart of another boarding bridge control method in an embodiment of the present disclosure;

[0031] Figure 4 Exemplary flowchart of a method for obtaining a target detection result in an embodiment of the present disclosure;

[0032] Figure 5A flowchart of a method for obtaining the position information of a target object in an embodiment of the present disclosure is shown;

[0033] Figure 6 A flowchart of a method for determining whether a target object enters a target area in an embodiment of the present disclosure is shown;

[0034] Figure 7 A flowchart of a method for outputting an action category label in an embodiment of the present disclosure is shown;

[0035] Figure 8 A flowchart of a method for outputting an action category label in an embodiment of the present disclosure is shown;

[0036] Figure 9 A flowchart of a method for outputting an action category label in an embodiment of the present disclosure is shown;

[0037] Figure 10 A schematic diagram of a boarding bridge structure in an embodiment of the present disclosure is shown;

[0038] Figure 11 A schematic diagram of a target area in an embodiment of the present disclosure is shown;

[0039] Figure 12 Another schematic diagram of a target area in an embodiment of the present disclosure is shown;

[0040] Figure 13 A schematic diagram of a boarding bridge control device in an embodiment of the present disclosure is shown;

[0041] Figure 14 A structural block diagram of a boarding bridge control electronic device in an embodiment of the present disclosure is shown. Detailed implementation manners

[0042] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0043] In addition, the drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0044] The following will, with reference to the accompanying drawings, elaborate in detail on the specific implementation manners of the embodiments of the present disclosure.

[0045] Figure 1 Fig. shows a schematic diagram of an exemplary application system architecture to which the boarding bridge control method in the embodiments of the present disclosure can be applied. As Figure 1 shown, the system architecture may include an environmental data acquisition device 101, a network 102, and a server 103.

[0046] The network 102 is used to provide a medium for the communication link between the environmental data acquisition device 101 and the server 103, and can be a wired network or a wireless network.

[0047] Optionally, the above-mentioned wireless network or wired network uses standard communication technologies and / or protocols. The network is usually the Internet, but can also be any network, including but not limited to any combination of a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a private network, or a virtual private network). In some embodiments, technologies and / or formats including hypertext markup language (HTML), extensible markup language (XML), etc. are used to represent the data exchanged through the network. In addition, conventional encryption technologies such as secure socket layer (SSL), transport layer security (TLS), virtual private network (VPN), and Internet protocol security (IPSec) can be used to encrypt all or some of the links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0048] The environmental data acquisition device 101 can be various types of cameras or sensors, including but not limited to high-definition network cameras, thermal imaging cameras, panoramic cameras, intelligent analysis cameras, and depth cameras, etc.

[0049] Optionally, in order to achieve full coverage monitoring of the internal passage of the boarding bridge, based on the number of telescopic sections of the boarding bridge, the length, height, and environmental information of the passage, different numbers of environmental data acquisition devices 101 are configured to achieve blind spot-free detection of people or other objects in the passage.

[0050] In some embodiments, when the environmental data acquisition device is an image acquisition device, the number of environmental data acquisition devices 101 is the number of telescopic sections of the boarding bridge plus 1. For example, at least three image acquisition devices are set for two-section boarding bridges, and at least four image acquisition devices are set for three-section boarding bridges. Figure 2A A schematic diagram of the layout of multiple cameras on a boarding bridge provided by an embodiment of the present disclosure. Figure 2A As shown, taking a three-section boarding bridge as an example, the three-section boarding bridge includes an outer channel 1, a middle channel 2, an inner channel 3, a receiving circular platform 4 and a turntable 5 which are nested from outside to inside.

[0051] Among them, the front middle section camera 1011 is installed at one end of the receiving platform 4 close to the outer channel 1, and is used to collect images from the outer channel 1 to the inner channel 3. The rear middle section camera 1012 is installed at the middle channel 2 close to the connection between the outer channel 1 and the middle channel 2, and is used to collect images from the middle channel 2 to the receiving platform 4. The rear middle section camera 1013 is installed at the inner channel 3 close to the connection between the inner channel 3 and the middle channel 2, and is used to collect images from the inner channel 3 to the outer channel 1. The front end camera 1014 is installed at one end close to the aircraft cabin door, and is used for the docking of the boarding bridge and the aircraft cabin door.

[0052] In some embodiments, when the environmental data collection device is a sensor, the number of environmental data collection devices 101 is the number of telescopic sections of the boarding bridge plus 2. For example, a two-section boarding bridge is provided with at least four sensor devices, and a three-section boarding bridge is provided with at least five sensor devices. Figure 2B A schematic diagram of the layout of multiple sensors on a boarding bridge provided by an embodiment of the present disclosure. Figure 2B As shown, taking a three-section boarding bridge as an example, the three-section boarding bridge includes an outer channel 1, a middle channel 2, an inner channel 3, a receiving circular platform 4 and a turntable 5 which are nested from outside to inside.

[0053] Among them, detection sensors are installed at all entrances and exits of the boarding bridge, including sensor S1 at the turntable entrance, sensor S5 at the front door of the arrival gate, and sensor S6 at the service door. At the same time, sensors S2, S3, and S4 are installed inside the boarding bridge channel.

[0054] The server 103 may be a server that provides various services, such as a background management server that provides support for the device operated by the user using the environmental data acquisition device 101. The background management server may analyze and process the received request data, and feed back the processing results to the image acquisition device.

[0055] Optionally, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0056] Those skilled in the art can know that Figure 1 the number of environmental data collection devices, networks, and servers in

[0057] is only illustrative. According to actual needs, there can be any number of image collection devices, networks, and servers. The embodiments of the present disclosure do not limit this.

[0058] In some embodiments, the boarding bridge control method provided in the embodiments of the present disclosure can be executed by the server in the above system architecture; in other embodiments, the boarding bridge control method provided in the embodiments of the present disclosure can be implemented by the environmental data collection device and the server in the above system architecture through interaction.

[0059] Figure 3A shows a flowchart of a boarding bridge control method in the embodiments of the present disclosure. As Figure 3C shown, the boarding bridge control method provided in the embodiments of the present disclosure includes the following steps:

[0060] S302A, obtain real-time data of the boarding bridge passage environment.

[0061] In this embodiment, the current environmental information in the boarding bridge passage is collected through various sensors (such as cameras, radar sensors, and / or infrared sensors, etc.), including real-time data on the positions of people, the placement of objects, light, and other situations.

[0062] S304A, analyze the real-time data to obtain a target detection result.

[0063] In this embodiment, the data obtained in S302A is processed and analyzed. For example, image recognition technology is used to analyze information such as the outlines and movement trajectories of people or objects in the images captured by the camera, so as to determine whether there are targets that may affect the operation of the boarding bridge and their states. Similarly, for the data of other sensors such as radar and infrared, analysis will also be carried out according to their respective principles and corresponding algorithms. For example, the radar sensor determines the relevant information of an object by the difference between the transmitted signal and the received reflected signal, so as to determine whether there are targets that may affect the operation of the boarding bridge in the boarding bridge passage and their states.

[0064] S306A, obtain the control instruction of the boarding bridge according to the target detection result, and the control instruction is used to control the movement state of the boarding bridge.

[0065] In this embodiment, during the operation of the boarding bridge, in order to ensure the safety of people or other objects in the boarding bridge passage, before the boarding bridge starts to operate, an instruction will be sent to the boarding bridge control system, requiring it to start detecting the situation in the boarding bridge passage. Through the monitoring of the target object in S302A - S304A, the detection result is fed back to the PLC (Programmable Logic Controller) control system of the boarding bridge. The PLC control system then decides whether the boarding bridge can start operating or needs to stop according to these detection results, combined with the preset safety rules and logic.

[0066] In one embodiment, in some cases, the PLC control system may display the target detection result to the operator, and the operator determines whether to issue a control instruction according to the on - site situation and safety rules. For example, if the detection result shows that there are people in the target area of the boarding bridge passage, the operator will choose not to issue a start instruction or issue a stop instruction to ensure the safety of people.

[0067] In one embodiment, the PLC control system can be built - in with a complete set of logical judgment mechanisms. When the target detection result meets certain preset conditions (such as someone breaks into the target area), the system will automatically issue corresponding control instructions, such as stopping immediately, and reminding the intruder to leave the target area as soon as possible through the voice system. This method can greatly reduce human misjudgment and response time, and improve the safety and reliability of the system.

[0068] In this embodiment, there is no need for manual analysis of a large amount of visual information one by one. The system directly processes the data to obtain control instructions, thereby improving the monitoring efficiency of the boarding bridge, reducing the manual processing requirements for a large amount of visual information, and reducing the risk of misjudgment.

[0069] In some embodiments, the real-time data may be the real-time data collected by radar sensors or infrared sensors installed inside the boarding bridge passage and / or at the entrances and exits of the boarding bridge. Considering that the boarding bridge passage is an enclosed area, during the operation of the boarding bridge, as long as no personnel are detected entering through all the entrance and exit sensors of the boarding bridge, it can be effectively ensured that there are still no personnel in the passage. Figure 3B The flowchart of yet another boarding bridge control method in the embodiments of the present disclosure is shown, as Figure 3B shown, the boarding bridge control method provided in the embodiments of the present disclosure includes the following steps:

[0070] S302B, before the boarding bridge operates, obtain the first real-time data collected by sensors at the positions inside the boarding bridge passage and at the entrances and exits of the boarding bridge.

[0071] In this embodiment, the sensors at the positions inside the boarding bridge passage and at the entrances and exits of the boarding bridge may include radar sensors and / or infrared sensors. Among them, the radar sensor uses electromagnetic waves to detect targets. In the boarding bridge scenario, it can detect information such as the distance and speed of objects within a certain range. The infrared sensor senses the presence and position of objects by detecting the infrared rays emitted by the objects. It is sensitive to objects with different temperatures and can play a role in darker light. In this embodiment, the two can be used alone or in combination to collect real-time data.

[0072] S304B, obtain the first sub-target detection result according to the collected first real-time data.

[0073] In this embodiment, the first sub-target detection result is used to indicate whether there are target objects inside the boarding bridge passage (including the passage entrances and exits). The target object refers to an entity that needs to be detected and recognized. For the detection scenario inside the boarding bridge passage, the target object is usually a person. The target object can be a single individual or a group composed of multiple individuals. It can be understood that the target object can also be other objects such as animals and suitcases.

[0074] S306B, obtain the first sub-control instruction of the boarding bridge according to the first sub-target detection result, where the first sub-control instruction is used to control the motion state of the boarding bridge.

[0075] In this embodiment, the first sub-goal detection result indicates whether there is a target object in the boarding bridge passage (including the passage entrances and exits). When there is a target object in the boarding bridge passage (including the passage entrances and exits), the boarding bridge will not be able to start or continue running, preventing the boarding bridge from starting when there are obstacles and avoiding harm to personnel or damage to equipment. At the same time, an alarm prompt can also be triggered until the target objects in the passage and at the boarding bridge entrances and exits are removed to ensure unobstructed passage. When there is no target object in the boarding bridge passage (including the passage entrances and exits), the first sub-control instruction controls the boarding bridge to start running.

[0076] S308B. After the first sub-control instruction controls the boarding bridge to start, the sensors inside the boarding bridge passage are shielded, and the second real-time data collected by the sensors at the positions of the boarding bridge entrances and exits is obtained.

[0077] In this embodiment, in order to avoid misjudging normal state changes (such as the self-movement of equipment, etc.) inside the passage as abnormal situations after the boarding bridge starts, the sensors inside the boarding bridge passage are shielded. Then, real-time data is collected from the sensors at the positions of the boarding bridge entrances and exits to reflect the situation of the boarding bridge passage entrances and exits during movement, ensuring the safe operation of the boarding bridge.

[0078] S310B. Obtain the second sub-goal detection result based on the collected second real-time data, and obtain the second sub-control instruction of the boarding bridge according to the second sub-goal detection result, where the second sub-control instruction is used to control the movement state of the boarding bridge.

[0079] In this embodiment, the second sub-goal detection result is used to indicate whether there is a target object entering the passage entrance and exit. If it is detected that a target object such as a person enters the passage entrance and exit, the second sub-control instruction of the boarding bridge is obtained to make the boarding bridge stop running and avoid potential dangers.

[0080] In some embodiments, the intruding personnel can also be reminded by a voice system to leave the dangerous area as soon as possible. The voice system plays a warning role to ensure the safe operation of the boarding bridge and the safety of personnel.

[0081] In this embodiment, since the boarding bridge passage is an enclosed area, the situation inside the boarding bridge is detected once before the boarding bridge runs, and then the boarding bridge is started when there is no target object in the boarding bridge passage. At the same time, during the operation of the boarding bridge, the sensors inside the boarding bridge passage are shielded, and all the boarding bridge entrance and exit sensors are used to detect whether there is a target object entering, improving the safety of the boarding bridge operation while effectively avoiding misjudgment.

[0082] In some embodiments, the real-time data can be images inside the boarding bridge passage collected by multiple image acquisition devices. Figure 3C Show another flowchart of the boarding bridge control method in the embodiments of the present disclosure, asFigure 3C As shown in the figure, the boarding bridge control method provided in the embodiments of the present disclosure includes the following steps:

[0083] S302C, obtain images in the boarding bridge passage collected by multiple image acquisition devices.

[0084] A boarding bridge is a movable passage connecting an aircraft and a terminal building. The boarding bridge passage refers to the space inside this passage, and the boarding bridge passage can be extended through the telescopic movement of the boarding bridge. When the boarding bridge passage retracts, its length is shorter, and when the boarding bridge passage extends, it can reach dozens of meters.

[0085] An image acquisition device refers to a camera or sensor device installed in the boarding bridge passage for capturing real-time video streams or static images. Images are digital image information generated by the image acquisition device, including but not limited to real-time video, RGB color images, grayscale images, depth images, etc. It should be noted that in actual application processes, the above images in the boarding bridge passage are generally collected in real time for the purpose of analyzing the images in the boarding bridge passage in real time to identify whether people enter the target area before or during the movement of the boarding bridge, so as to issue an alarm or notify relevant responsible persons in a timely manner.

[0086] Specifically, install multiple image acquisition devices at different key positions of the boarding bridge (such as both ends and the middle connection), ensuring that the image acquisition area covers the entire interior of the boarding bridge passage. When it is necessary to control the movement of the boarding bridge, start the image acquisition device to record or capture the real-time situation in the passage. Then, transmit the collected images to the server through a wired or wireless network for subsequent analysis.

[0087] S304C, input the images in the boarding bridge passage collected by multiple image acquisition devices into the target detection model, and output the target detection result.

[0088] The target detection model is a model obtained through machine learning training for detecting whether a target object enters the target area in the boarding bridge passage.

[0089] The target object refers to an entity that needs to be detected and recognized. For the detection scenario in the boarding bridge passage, the target object is usually a person. The target object can be a single individual or a group composed of multiple individuals. It can be understood that the target object can also be other objects such as animals and suitcases. In addition, in the actual detection process, the size range of the target object can also be freely configured according to requirements.

[0090] In some embodiments, the target object includes people and / or objects and can be freely configured; and / or, a freely configurable size range of the target object is set.

[0091] The target area refers to the area that needs to be monitored and detected. Here, it refers to the area within the boarding bridge passage where people or objects are prohibited from entering. The area within the boarding bridge passage where people or objects are prohibited from entering is generally the area where there may be risks of extrusion and shearing, such as the connection of two passages. The target area is usually defined by the setter of the monitoring system according to actual needs, and the embodiments of the present disclosure do not limit this. In this embodiment, setting the target area can also avoid false detection of target objects located outside the boarding bridge. That is to say, in some embodiments, the target area can be freely configured.

[0092] In this embodiment, the target detection model is a model trained based on machine learning and is used to identify and locate target objects in images. The target detection result is whether the target object enters the target area within the boarding bridge passage, and specifically may include the detected target object category, the position of the target object, and the confidence score.

[0093] The target detection model can choose frameworks such as YOLO (You Only Look Once), Faster R-CNN (Regions with Convolutional Neural Networks), SSD (Single Shot MultiBox Detector), etc. for training.

[0094] Specifically, a large number of historical images of the boarding bridge passage collected by multiple image acquisition devices with annotations are used for training to learn to identify and locate whether the target object in the image enters the target area within the boarding bridge passage. It can be understood that the historical images include images of the boarding bridge passage under various scenarios (such as the stationary state and moving state of the boarding bridge), various lighting conditions, and background interferences to ensure the stable performance of the target detection model in various complex environments.

[0095] Through this embodiment, it is possible to detect target objects in multiple boarding bridge passages and ensure the accuracy and stability of the detection.

[0096] S306C, obtain the control instruction of the boarding bridge according to the target detection result, and the control instruction is used to control the motion state of the boarding bridge.

[0097] In summary, by obtaining the images of the boarding bridge passage collected by multiple image acquisition devices and using the target detection model trained by machine learning to process these images, the target detection result is output. This method can automatically and accurately detect whether there are people or other obstacles in the boarding bridge passage, and thus generate the control instruction of the boarding bridge according to the target detection result to control the motion state of the boarding bridge.

[0098] In one embodiment,Figure 4 This is a flowchart of a method for obtaining target detection results provided by an embodiment of the present disclosure. Combining Figure 4 As shown, input the image in the boarding bridge passage into the target detection model, and the output target detection results may include:

[0099] S402, detect whether there is a target object in the collected image of the boarding bridge passage.

[0100] In this embodiment, target detection technology can be used to quickly and accurately locate and identify the target of interest in the image. The position of the target object can be marked in the image.

[0101] Specifically, preprocess the collected image of the boarding bridge passage, such as denoising, enhancing contrast, etc., to improve the detection effect of subsequent algorithms. Use deep learning algorithms (such as convolutional neural networks) to extract feature information in the image, and these feature information are used to distinguish different target objects. Based on the extracted feature information, use the target detection algorithm to mark the detection area containing the target object in the image. Post-process the detected target area, such as removing redundant bounding boxes, adjusting the size and position of the bounding boxes, etc., to improve the accuracy and robustness of the detection.

[0102] In one embodiment, the type of the target object can be preset, such as one or more of a person, an animal, a luggage case, etc. To further improve the detection accuracy and reliability, the size parameters of the target object, such as the maximum size and the minimum size, can also be preset. The embodiment of the present disclosure does not limit the specific parameter values.

[0103] Through this embodiment, it can be determined whether there is a target object in the boarding bridge passage according to the image in the boarding bridge passage.

[0104] S404, when there is the target object in the collected image of the boarding bridge passage, locate the position information of the target object.

[0105] In this embodiment, the position information refers to the specific coordinates or relative position of the target object in the image or image frame, usually represented by pixel values or distances relative to a certain reference point.

[0106] On the basis that S402 detects that the collected image of the boarding bridge passage contains a target object, in consecutive image frames, a tracking algorithm can be used to continuously track the target object. There are various possible implementation manners for the tracking algorithm. The following are example possible implementation manners of the tracking algorithm:

[0107] Feature-based tracking: Realize tracking by extracting the features (such as edges, corners, textures, etc.) of the target object and matching the extracted features of the target object in subsequent image frames.

[0108] Region-based tracking: Based on the position of the target object in the initial image frame, a rectangular box (i.e., the detection region) containing the target is defined, and the position and size of this rectangular box are continuously updated in subsequent image frames to track the target object. This method is applicable to the situation where the target object remains relatively stable in the image sequence.

[0109] Model-based tracking: First, a three-dimensional model is established for the target object, and then tracking is achieved by matching the model with the features in the subsequent image frames. This method has good processing capabilities for the pose changes and occlusion situations of the target object.

[0110] Deep learning-based tracking: Utilize deep learning algorithms (such as convolutional neural networks) to extract the features of the target object, and train a model to predict the position and shape of the target object in subsequent image frames.

[0111] In this embodiment, on the basis of determining the existence of the target, by further analyzing the motion trajectory of the target object, it is possible to accurately judge whether a person has entered the target region.

[0112] S406. According to the relationship between the position information of the target region and the target object, determine whether the target object has entered the target region within the boarding bridge passage to obtain the target detection result.

[0113] In this embodiment, within the boarding bridge passage, according to safety regulations or actual requirements, the target region is clearly defined in a software manner (such as setting virtual boundaries in the monitoring system). Compare the position information of the target object with the position information of the target region to determine whether the target object has entered the boundary of the target region, that is, whether it has entered the restricted area, and generate the target detection result.

[0114] In this embodiment, in order to avoid false alarms and missed detections, further configurable time thresholds and / or sensitivity thresholds and target confidence levels and other parameters can be set to improve the accuracy and reliability of the detection.

[0115] In one embodiment, if the target object enters the target region, an alarm mechanism can also be triggered, such as emitting a sound warning, displaying a warning message, or sending a notification to relevant personnel. The sound warning is, for example, "You have entered a restricted area. Please leave immediately!". It can be understood that the above warnings and / or notifications are triggered in the scenario of controlling the movement of the boarding bridge. In this embodiment, by detecting the presence of a target object in the target region of the boarding bridge passage, an alarm is issued and relevant personnel are notified so as to take timely measures to deal with potential safety risks.

[0116] In one embodiment, Figure 5 It is a flowchart of a method for obtaining the position information of a target object provided by an embodiment of the present disclosure.

[0117] Combined with Figure 5 As shown, the position information of the target object can be located, including:

[0118] S502, identify the initial position information of the target object.

[0119] The initial position information refers to the position information of the target object relative to a fixed reference point in the boarding bridge passage when the target object is first detected. The initial position information can include the coordinates of the target object (such as pixel coordinates), the distance and direction relative to a certain point, etc.

[0120] In this embodiment, by identifying the initial position information of the target object, the specific state of the target object in the boarding bridge passage can be determined.

[0121] S504, when the change in the position information of the target object relative to the boarding bridge does not exceed the preset threshold, obtain the static position information of the target object.

[0122] In this embodiment, the preset threshold is a position change range threshold set according to actual application requirements, which is used to determine whether the target object is in a static state or a moving state in the boarding bridge passage. The static position information is when the change in the position information of the target object relative to a fixed reference point in the boarding bridge does not exceed the preset threshold within a period of time, it is considered that the target object is in a static state, and the position information recorded at this time is the static position information.

[0123] S506, when the change in the position information of the target object relative to the boarding bridge exceeds the preset threshold, track the target object to obtain the dynamic position information of the target object.

[0124] In this embodiment, the dynamic position information refers to when the change in the position information of the target object relative to a fixed reference point in the boarding bridge passage exceeds the preset threshold, it is considered that the target object is in a dynamic state, and the position information of the target object obtained and recorded in real time through the tracking algorithm at this time is the dynamic position information.

[0125] In this embodiment, when it is detected that the position change of the target object exceeds the preset threshold, the tracking algorithm is used to detect and update the position information of the target object in real time in consecutive image frames. Record and output the dynamic position information of the target object.

[0126] In this embodiment, compared with the related art where conventional motion sensors are installed throughout the entire length of the boarding bridge passage, by using object recognition and object tracking, it is only necessary to install cameras at key positions in the passage to achieve the tracking and positioning of the target object. Moreover, in the related art, conventional motion sensors may generate false alarms due to the movement of the passage itself (such as the telescoping and rotation of the boarding bridge), misinterpreting the movement of the boarding bridge itself as the movement of personnel, thus interfering with the normal movement of the boarding bridge. This embodiment can accurately distinguish the movement of the target object from the movement of the passage itself, effectively avoiding the occurrence of false alarms and improving the accuracy of detection.

[0127] In one embodiment, Figure 6 is a flowchart of a method for determining whether a target object enters a target area according to an embodiment of the present disclosure. As shown in Figure 6 , determining whether the target object enters the target area in the boarding bridge passage according to the relationship between the position information of the target area and the target object may include:

[0128] S602, determine the behavior characteristics of the target object according to the relationship between the position information of the target area and the target object.

[0129] Behavior characteristics refer to several possible behaviors that may occur based on the preliminary judgment of the current position information of the target object and its relationship with the target area. For example, approaching, moving away, wandering, entering, etc.

[0130] In this embodiment, first, obtain the position information of the target object in the boarding bridge passage, and compare the position information of the target object in the boarding bridge passage with the position information of the target area. According to the comparison result, judge several possible behaviors that the target object may be performing, and these behaviors are called behavior characteristics. The determination of behavior characteristics is obtained through the analysis of factors such as the current position, moving direction, and speed of the target object.

[0131] S604, output an action category label and an abnormal confidence level corresponding to the behavior characteristics of the target object based on the behavior characteristics of the target object.

[0132] In this embodiment, the action category label refers to the classification result of the behavior characteristics of the target object, such as normal walking, abnormal stay, entering a restricted area, etc. The abnormal confidence level refers to the confidence level that the behavior characteristics of the target object are determined to be abnormal behaviors, usually expressed as a probability or a score.

[0133] In this embodiment, machine learning or deep learning algorithms can be used to analyze and classify the behavior characteristics of the target object to obtain the action category label of the behavior characteristics of the target object, that is, the classification result of the behavior characteristics of the target object. At the same time, the system also outputs the abnormal confidence level corresponding to the behavior characteristics of the target object to indicate the confidence level of the system in the classification result.

[0134] S606. If the anomaly confidence level is greater than a preset confidence threshold, it is determined that the target object has entered the target area within the boarding bridge passage.

[0135] In this embodiment, the confidence threshold refers to the minimum confidence level for determining whether the behavioral characteristics of the target object are abnormal, and is used to distinguish whether the target object has entered the target area within the boarding bridge passage.

[0136] Specifically, compare the anomaly confidence level corresponding to the behavioral characteristics of the target object with the preset confidence threshold. If the anomaly confidence level is greater than the confidence threshold, it is considered that the behavior of the target object is abnormal, that is, the target object has entered the target area within the boarding bridge passage. At this time, the system can trigger an alarm mechanism to notify relevant personnel to take necessary measures.

[0137] In one embodiment, Figure 7 is a flowchart of a method for outputting action category labels provided by an embodiment of the present disclosure. As shown in combination with Figure 7 Based on the behavioral characteristics of the target object, outputting an action category label and the anomaly confidence level corresponding to the behavioral characteristics of the target object may include:

[0138] S702. Construct an abnormal behavior characteristic database for the target area within the boarding bridge passage.

[0139] This embodiment provides a detection method based on abnormal characteristics. In the detection method based on abnormal characteristics, an abnormal behavior characteristic database is pre-constructed, which contains various known abnormal behavior characteristics of the target object in the target area, that is, the abnormal behavior characteristics of the target object entering the target area within the boarding bridge passage. When the behavior of the target object is detected, the behavioral characteristics of the target object are extracted and matched with the abnormal behavior characteristics in the abnormal behavior characteristic database to determine whether the target object has entered the target area within the boarding bridge passage. The known abnormal behavior characteristics of the target object in the target area can be defined based on parameters such as the movement trajectory, speed, direction, and residence time of the target object.

[0140] S704. Match the behavioral characteristics of the target object with the abnormal behavior characteristics in the abnormal behavior characteristic database.

[0141] In this embodiment, the behavioral characteristics of the target object are extracted. These characteristics are compared one by one with the abnormal behavior characteristics in the abnormal behavior characteristic database, and the similarity between the behavioral characteristics and the abnormal behavior characteristics is calculated to determine whether there is a match.

[0142] S706. If any abnormal behavior characteristic in the abnormal behavior characteristic database is matched, output the action category label and the anomaly confidence level corresponding to the behavioral characteristics of the target object.

[0143] In this embodiment, if an abnormal behavior feature matching the behavior feature of the target object is found in the abnormal behavior feature database, an action category label and a corresponding abnormal confidence level are output. The action category label represents the detected type of abnormal behavior, and the abnormal confidence level represents the confidence level of the system in this judgment.

[0144] In one embodiment, Figure 8 is a flowchart of a method for outputting an action category label provided by an embodiment of the present disclosure. As shown in combination with Figure 8 Based on the behavior feature of the target object, outputting an action category label and an abnormal confidence level corresponding to the behavior feature of the target object may include:

[0145] S802, establish a normal feature database in the boarding bridge passage.

[0146] This embodiment provides a detection method based on abnormality. In the detection method based on abnormality, by comparing the difference between the behavior feature of the target object and the normal feature, it is determined whether the target object enters the target area in the boarding bridge passage.

[0147] In this embodiment, collect the normal feature data in the boarding bridge passage and establish a normal feature database. Among them, the normal feature database includes the normal features when the target object does not enter the target area in the boarding bridge passage. Specifically, the normal features when the target object does not enter the target area in the boarding bridge passage may be the feature data where there is no target object in the target area, or the movement trajectory, speed, residence time, behavior pattern, etc. corresponding to the normal behavior feature of the target object.

[0148] When the behavior feature of the target object is obtained, compare the behavior feature of the target object with the normal features in the normal feature database to identify the behavior feature that does not match the normal feature of the target object.

[0149] S804, based on the behavior feature of the target object and the normal feature database, calculate the similarity between the behavior feature of the target object and the normal feature.

[0150] In this embodiment, obtain the behavior feature of the target object, use a similarity measurement method (such as cosine similarity, Euclidean distance, etc.) to compare the behavior feature of the target object with the normal features in the normal feature database, calculate and output a similarity value, which reflects the degree of closeness between the behavior feature and the normal behavior.

[0151] S806, output an action category label and an abnormal confidence level corresponding to the behavior feature of the target object according to the similarity.

[0152] In this embodiment, the action category label and abnormal confidence are output according to the similarity between the behavior feature of the target object and the normal feature. If the similarity is lower than a certain threshold, the behavior feature is considered abnormal, and the corresponding action category label and abnormal confidence are output.

[0153] In this embodiment, since the data of normal features is easier to obtain, the normal feature database can contain a wider range of feature data, which helps to reduce missed detections due to insufficient exhaustiveness of abnormal behavior features. And since the normal feature database can be updated and adjusted as the environment changes, the accuracy and robustness of detection can be improved.

[0154] In one embodiment, Figure 9 A flow chart of a method for outputting action category labels provided by an embodiment of the present disclosure. Figure 9 As shown, outputting the action category label and the abnormality confidence corresponding to the behavior feature of the target object based on the behavior feature of the target object may include:

[0155] S902, constructing a hybrid intrusion detection model; the hybrid intrusion detection model includes a feature matching module and an anomaly detection module.

[0156] In this embodiment, the feature matching module is used to match the behavior features of the target object with known abnormal behavior features, and the abnormality detection module is used to compare the differences between the behavior features of the target object and normal features.

[0157] The construction process of the feature matching module can refer to the previous construction of the abnormal behavior feature database of the target area in the boarding bridge channel, and the construction process of the anomaly detection module can refer to the previous construction of the normal feature database in the boarding bridge channel, which will not be repeated in this embodiment.

[0158] S904, inputting the behavior features of the target object into a feature matching module to obtain a feature matching detection result.

[0159] In this embodiment, the behavior characteristics of the target object are input into the feature matching module, and the implementation structure of obtaining the feature matching detection result can refer to the previous text, and the behavior characteristics of the target object are matched with the abnormal behavior characteristics in the abnormal behavior feature database. If any abnormal behavior feature in the abnormal behavior feature database is matched, the action category label and the abnormal confidence corresponding to the behavior characteristics of the target object are output. The specific implementation process is not repeated here.

[0160] S906, inputting the behavior characteristics of the target object into an anomaly detection module to obtain an anomaly detection result.

[0161] In this embodiment, the process of inputting the behavioral characteristics of the target object into the feature matching module to obtain the feature matching detection result can refer to the previous text. Based on the behavioral characteristics of the target object and the normal feature database, the similarity between the behavioral characteristics of the target object and the normal features is calculated, and the action category label and the anomaly confidence corresponding to the behavioral characteristics of the target object are output according to the similarity. The specific implementation process will not be elaborated here.

[0162] S908, fuse the feature matching detection result and the anomaly detection result, and output the action category label and the anomaly confidence corresponding to the behavioral characteristics of the target object.

[0163] In this embodiment, according to the fusion algorithm, the two results are comprehensively evaluated, and according to the evaluation result, the action category label and the anomaly confidence are determined and output.

[0164] In this embodiment, the hybrid intrusion detection model can make full use of the advantages of both feature-based detection and anomaly-based detection methods to improve the detection accuracy and coverage.

[0165] In one embodiment, the boarding bridge can adopt a multi-section boarding bridge structure. Figure 10 A schematic diagram of a multi-section boarding bridge structure is shown, as Figure 10 shown, the multi-section boarding bridge includes a first telescopic module 110, a second telescopic module 120, and a third telescopic module 130 nested from the outside to the inside; the first end of the first telescopic module 110 is connected to the fixing device, the second end of the first telescopic module 110 is connected to the first end of the second telescopic module 120, the second end of the second telescopic module 120 is connected to the first end of the third telescopic module 130, and the second end of the third telescopic module 130 is used to connect to the aircraft.

[0166] Figure 11 This is a schematic diagram of a target area provided by an embodiment of the present disclosure. Figure 12 This is another schematic diagram of a target area provided by an embodiment of the present disclosure.

[0167] When the boarding bridge is in a stationary state, the target area inside the boarding bridge at least includes a first stationary area 111 and a second stationary area 112.

[0168] When the boarding bridge is in a moving state, the target area inside the boarding bridge at least includes a first dynamic area 121 and a second dynamic area 122.

[0169] Combined with Figure 11 and Figure 12As shown, the first static region and the first dynamic region are located in the region where the second end of the first telescopic module is connected to the first end of the second telescopic module, and the second static region and the second dynamic region are located in the region where the second end of the second telescopic module is connected to the first end of the third telescopic module.

[0170] By Figure 11 and Figure 12 comparison, it can be clearly seen that as the boarding bridge expands and contracts, the target area changes. In this embodiment, the target detection model can detect the target area inside the boarding bridge in real time and dynamically adjust the monitoring range and detection parameters according to the movement state of the boarding bridge.

[0171] It should be noted that the acquisition, storage, use, processing, etc. of images in the technical solution of the present disclosure all comply with the relevant provisions of national laws and regulations. In the embodiments of the present disclosure, various types of data such as personal identity data, operation data, and behavior data related to individuals, customers, and crowds have been authorized.

[0172] Based on the same inventive concept, an embodiment of the present disclosure also provides a boarding bridge control device, as described in the following embodiments. Since the principle of solving problems in this device embodiment is similar to that of the above method embodiment, the implementation of this device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be described again.

[0173] Figure 13 shows a schematic diagram of a boarding bridge control device in an embodiment of the present disclosure, as Figure 13 shown, the device includes: a first acquisition module 131, a target detection module 132, and a second acquisition module 133;

[0174] The first acquisition module 131 is configured to acquire real-time data of the boarding bridge passage environment; the target detection module 132 is configured to analyze the real-time data to obtain a target detection result; the second acquisition module 133 is configured to obtain a control instruction for the boarding bridge according to the target detection result, and the control instruction is used to control the movement state of the boarding bridge.

[0175] In some embodiments, the real-time data is the real-time data collected by radar sensors and / or infrared sensors installed inside the boarding bridge passage and at each entrance and exit of the boarding bridge; the first acquisition module 131 is further configured to, before the boarding bridge operates, acquire first real-time data collected by sensors inside the boarding bridge passage and at each entrance and exit of the boarding bridge; the target detection module 132 is further configured to obtain a first sub-target detection result according to the collected first real-time data; the second acquisition module 133 is further configured to obtain a first sub-control instruction for the boarding bridge according to the first sub-target detection result, wherein the first sub-control instruction is used to control the motion state of the boarding bridge; and / or, the first acquisition module 131 is further configured to, after the boarding bridge starts, block the sensors inside the boarding bridge passage and acquire second real-time data collected by sensors at each entrance and exit of the boarding bridge; the target detection module 132 is further configured to obtain a second sub-target detection result according to the collected second real-time data; the second acquisition module 133 is further configured to obtain a second sub-control instruction for the boarding bridge according to the second sub-target detection result, wherein the second sub-control instruction is used to control the motion state of the boarding bridge.

[0176] In some embodiments, the real-time data is an image inside the boarding bridge passage collected by a plurality of image acquisition devices; the target detection module 132 is configured to input the image inside the boarding bridge passage into a target detection model and output a target detection result; wherein, the target detection model is a model obtained by machine learning training for detecting whether a target object enters a target area inside the boarding bridge passage; the second acquisition module 133 is configured to obtain a control instruction for the boarding bridge according to the target detection result, and the control instruction is used to control the motion state of the boarding bridge.

[0177] In one embodiment, the target detection module 132 is specifically configured to: mark a detection area containing the target object in the image inside the boarding bridge passage; track the target object to obtain position information of the target object; and determine whether the target object enters the target area inside the boarding bridge passage according to the relationship between the target area inside the boarding bridge passage and the position information of the target object, so as to obtain a target detection result.

[0178] In one embodiment, the target detection module 132 is specifically configured to: determine the behavior characteristics of the target object according to the relationship between the target area inside the boarding bridge passage and the position information of the target object; output an action category label and an abnormal confidence level corresponding to the behavior characteristics of the target object based on the behavior characteristics of the target object; and if the abnormal confidence level is greater than a preset confidence level threshold, determine that the target object enters the target area inside the boarding bridge passage.

[0179] In one embodiment, the target detection module 132 is specifically configured to: construct an abnormal behavior feature database for the target area, where the abnormal behavior feature database includes: abnormal behavior features of the target object entering the target area within the boarding bridge passage; match the behavior features of the target object with the abnormal behavior features in the abnormal behavior feature database; if any abnormal behavior feature in the abnormal behavior feature database is matched, output an action category label and an abnormal confidence level corresponding to the behavior features of the target object; and / or, the target detection module 132 is specifically configured to: establish a normal feature database for the target area within the boarding bridge passage; compare the behavior features of the target object with the normal feature database of the target area to obtain the similarity between the behavior features of the target object and the normal features of the target area; and output an action category label and an abnormal confidence level corresponding to the behavior features of the target object according to the similarity.

[0180] In one embodiment, the target detection module 132 is specifically configured to: construct a hybrid intrusion detection model; the hybrid intrusion detection model includes a feature matching module and an anomaly detection module; input the behavior features of the target object into the feature matching module to obtain a feature matching detection result; input the behavior features of the target object into the anomaly detection module to obtain an anomaly detection result; fuse the feature matching detection result and the anomaly detection result, and output an action category label and an abnormal confidence level corresponding to the behavior features of the target object.

[0181] In some embodiments, the target object includes a person and / or an object and can be freely configured; and / or, a size range of the target object that can be freely configured is set; and / or, the target area can be freely configured; and / or, a time threshold and / or a sensitivity threshold that can be freely configured are set.

[0182] In one embodiment, the target detection module 132 is specifically configured to: identify the initial position information of the target object; when the change in the position information of the target object relative to the boarding bridge does not exceed a preset threshold, obtain the static position information of the target object; when the change in the position information of the target object relative to the boarding bridge exceeds the preset threshold, track the target object to obtain the dynamic position information of the target object.

[0183] In one embodiment, the boarding bridge is a multi-section boarding bridge structure. The multi-section boarding bridge includes a first telescopic module, a second telescopic module, and a third telescopic module that are nested from the outside to the inside. The first end of the first telescopic module is connected to a fixing device, the second end of the first telescopic module is connected to the first end of the second telescopic module, the second end of the second telescopic module is connected to the first end of the third telescopic module, and the second end of the third telescopic module is used to connect to an aircraft. When the boarding bridge is in a stationary state, the target area inside the boarding bridge at least includes a first stationary area and a second stationary area. When the boarding bridge is in a moving state, the target area inside the boarding bridge at least includes a first dynamic area and a second dynamic area. The first stationary area and the first dynamic area are located in the area where the second end of the first telescopic module is connected to the first end of the second telescopic module, and the second stationary area and the second dynamic area are located in the area where the second end of the second telescopic module is connected to the first end of the third telescopic module.

[0184] It should be noted here that the examples and application scenarios realized by each module in the above device embodiments are the same as the corresponding steps in the method embodiments, but are not limited to the content disclosed in the above method embodiments. It should be noted that the above modules, as part of a device, can be executed in a computer system such as a set of computer-executable instructions.

[0185] Those skilled in the art can understand that various aspects of the present disclosure can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuit", "module" or "system" here.

[0186] Based on the same inventive concept, an electronic device is also provided in the embodiments of the present disclosure. The electronic device includes: a processor; and a memory for storing executable instructions of the processor. Wherein, the processor is configured to execute the boarding bridge control method of any one of the above via executing the executable instructions. Since the principle of solving problems in this electronic device embodiment is similar to that of the above method embodiment, the implementation of this electronic device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be described again.

[0187] Next, refer to Figure 14 to describe the electronic device 1400 according to this embodiment of the present disclosure. Figure 14 The electronic device 1400 shown is only an example and should not bring any limitation to the functions and usage scope of the embodiments of the present disclosure.

[0188] As Figure 14As shown, the electronic device 1400 is presented in the form of a general computing device. The components of the electronic device 1400 may include, but are not limited to: at least one of the above-mentioned processing units 1410, at least one of the above-mentioned storage units 1420, and a bus 1430 that connects different system components (including the storage unit 1420 and the processing unit 1410).

[0189] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 1410, so that the processing unit 1410 executes the steps according to various exemplary embodiments of the present disclosure described in the "Exemplary Method" section of the present specification. For example, the processing unit 1410 may execute the following steps of the above method embodiment: obtaining images in the boarding bridge passage collected by a plurality of image acquisition devices; inputting the images in the boarding bridge passage collected by the plurality of image acquisition devices into a target detection model to output a target detection result; wherein, the target detection model is a model obtained by machine learning training for detecting whether a target object enters a target area in the boarding bridge passage; obtaining a control instruction for the boarding bridge according to the target detection result, and the control instruction is used to control the motion state of the boarding bridge.

[0190] The storage unit 1420 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 14201 and / or a cache storage unit 14202, and may further include a read-only storage unit (ROM) 14203.

[0191] The storage unit 1420 may further include a program / utilities 14204 having a set (at least one) of program modules 14205. Such program modules 14205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0192] The bus 1430 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0193] The electronic device 1400 may also communicate with one or more external devices 1440 (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1400, and / or may communicate with any device (such as a router, a modem, etc.) that enables the electronic device 1400 to communicate with one or more other computing devices. Such communication may be carried out through the input / output (I / O) interface 1450. Moreover, the electronic device 1400 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 1460. As shown in the figure, the network adapter 1460 communicates with other modules of the electronic device 1400 through the bus 1430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in combination with the electronic device 1400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0194] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or can be implemented by the way of software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, and the software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0195] Based on the same inventive concept, an embodiment of the present disclosure also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the boarding bridge control method in any one of the above. Since the principle of solving problems in the embodiment of the computer-readable storage medium is similar to that in the above method embodiment, the implementation of the embodiment of the computer-readable storage medium can refer to the implementation of the above method embodiment, and the repeated parts will not be described again.

[0196] More specific examples of the computer-readable storage medium in the present disclosure may include but are not limited to: an electrical connection having one or more wires, a portable computer 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.

[0197] In the present disclosure, a computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0198] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0199] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including 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 a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0200] Based on the same inventive concept, embodiments of the present disclosure also provide a computer program product, including: a computer program or instruction, which when executed by a processor implements the boarding bridge control method of any one of the foregoing method embodiments. Since the principle of solving problems in this computer program product embodiment is similar to that of the foregoing method embodiments, the implementation of this computer program product embodiment may refer to the implementation of the foregoing method embodiments, and the repeated parts will not be described again.

[0201] It should be noted that although several modules or units of a device for action execution are mentioned in the foregoing detailed description, such a division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more of the foregoing modules or units may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided and embodied by multiple modules or units.

[0202] In addition, although the various steps of the methods in this disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in that specific order, or that all of the steps shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0203] From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0204] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of this disclosure. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in this disclosure. The specification and examples are only considered exemplary, and the true scope and spirit of this disclosure are pointed out by the appended claims.

Claims

1. A boarding bridge control method, characterized in that: include: Obtain real-time data of the boarding bridge channel environment; Analyzing the real-time data to obtain target detection results; A control instruction of the boarding bridge is obtained according to the target detection result, and the control instruction is used to control the movement state of the boarding bridge.

2. The boarding bridge control method according to claim 1, characterized in that: The real-time data is real-time data collected by radar sensors and / or infrared sensors installed inside the boarding bridge passage and at each entrance and exit of the boarding bridge; The boarding bridge control method further comprises: Before the boarding bridge is in operation, first real-time data collected by sensors inside the boarding bridge passage and at each entrance and exit of the boarding bridge is obtained; Acquire a first sub-target detection result according to the collected first real-time data; Acquire a first sub-control instruction of the boarding bridge according to the first sub-target detection result, wherein the first sub-control instruction is used to control the motion state of the boarding bridge; And / or, the boarding bridge control method further includes: When the boarding bridge is started, the sensors inside the boarding bridge channel are shielded to obtain the second real-time data collected by the sensors at the entrances and exits of the boarding bridge; Acquire a second sub-target detection result according to the collected second real-time data; A second sub-control instruction for the boarding bridge is obtained according to the second sub-target detection result, wherein the second sub-control instruction is used to control the motion state of the boarding bridge.

3. The boarding bridge control method according to claim 1, characterized in that: The real-time data is images in the boarding bridge channel collected by multiple image acquisition devices; The analyzing the real-time data to obtain the target detection result includes: The images within the boarding bridge channel captured by the multiple image acquisition devices are input into a target detection model, and a target detection result is output; wherein the target detection model is a model obtained through machine learning training and used to detect whether a target object enters a target area within the boarding bridge channel.

4. The boarding bridge control method according to claim 3, characterized in that: The step of inputting the image in the boarding bridge channel into the target detection model and outputting the target detection result comprises: Detect whether there is a target object in the acquired image of the boarding bridge channel; When the target object exists in the acquired image in the boarding bridge channel, locating the position information of the target object; According to the relationship between the target area in the boarding bridge passage and the position information of the target object, it is determined whether the target object enters the target area in the boarding bridge passage to obtain a target detection result.

5. The boarding bridge control method according to claim 4, characterized in that: The determining, based on the relationship between the target area in the boarding bridge passage and the position information of the target object, whether the target object enters the target area in the boarding bridge passage comprises: Determining the behavior characteristics of the target object according to the relationship between the target area in the boarding bridge channel and the position information of the target object; Outputting an action category label and an abnormality confidence corresponding to the behavior feature of the target object based on the behavior feature of the target object; If the abnormality confidence is greater than a preset confidence threshold, it is determined that the target object enters the target area within the boarding bridge passage.

6. The boarding bridge control method according to claim 5, characterized in that: The outputting the action category label and the abnormality confidence corresponding to the behavior feature of the target object based on the behavior feature of the target object includes: Constructing an abnormal behavior feature database of the target area in the boarding bridge passage, wherein the abnormal behavior feature database includes: abnormal behavior features of the target object entering the target area in the boarding bridge passage; Matching the behavior characteristics of the target object with the abnormal behavior characteristics in the abnormal behavior characteristic database; If any abnormal behavior feature in the abnormal behavior feature database is matched, output the action category label and the abnormal confidence corresponding to the behavior feature of the target object; And / or, outputting the action category label and the abnormality confidence corresponding to the behavior feature of the target object based on the behavior feature of the target object includes: Constructing a normal feature database in the boarding bridge passage, wherein the normal feature database includes: normal features of the target object not entering the target area in the boarding bridge passage; Based on the behavior characteristics of the target object and the normal characteristics database, calculating the similarity between the behavior characteristics of the target object and the normal characteristics; Output the action category label and the abnormality confidence corresponding to the behavior feature of the target object according to the similarity.

7. The boarding bridge control method according to claim 5, characterized in that: The step of outputting the action category label and the abnormality confidence corresponding to the behavior feature of the target object based on the behavior feature of the target object includes: Constructing a hybrid intrusion detection model; the hybrid intrusion detection model includes a feature matching module and an anomaly detection module; Inputting the behavior characteristics of the target object into a feature matching module to obtain a feature matching detection result; Inputting the behavior characteristics of the target object into an anomaly detection module to obtain an anomaly detection result; The feature matching detection result and the anomaly detection result are fused to output the action category label and the anomaly confidence corresponding to the behavior feature of the target object.

8. The boarding bridge control method according to claim 3, characterized in that: The target object includes a person or object and can be freely configured; and / or, setting a size range of the target object that is freely configurable; and / or, the target area is freely configurable; And / or, a freely configurable time threshold and / or sensitivity threshold is set.

9. The boarding bridge control method according to claim 4, characterized in that: The positioning of the position information of the target object includes: Identifying initial location information of the target object; When the change in the position information of the target object relative to the boarding bridge does not exceed a preset threshold, obtaining the static position information of the target object; When the change in the position information of the target object relative to the boarding bridge exceeds a preset threshold, the target object is tracked to obtain the dynamic position information of the target object.

10. A boarding bridge control device, characterized in that: include: The first acquisition module is used to acquire real-time data of the boarding bridge channel environment; A target detection module, used for analyzing the real-time data to obtain a target detection result; The second acquisition module is used to acquire the control instruction of the boarding bridge according to the target detection result, and the control instruction is used to control the movement state of the boarding bridge.

11. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; Wherein, the processor is configured to execute the boarding bridge control method described in any one of claims 1 to 9 by executing the executable instructions.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the boarding bridge control method according to any one of claims 1 to 9 is implemented.

Images