WO2022088389A1 - 机器人安检的方法、装置、设备及存储介质 - Google Patents

机器人安检的方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2022088389A1
WO2022088389A1 PCT/CN2020/133912 CN2020133912W WO2022088389A1 WO 2022088389 A1 WO2022088389 A1 WO 2022088389A1 CN 2020133912 W CN2020133912 W CN 2020133912W WO 2022088389 A1 WO2022088389 A1 WO 2022088389A1
Authority
WO
WIPO (PCT)
Prior art keywords
security inspection
target
detected
robot
candidate target
Prior art date
Application number
PCT/CN2020/133912
Other languages
English (en)
French (fr)
Inventor
李娜
刘启帆
赵玉梅
李竖三
郭峰
张涛
孙士超
蔡宝京
Original Assignee
博众精工科技股份有限公司
苏州博众机器人有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 博众精工科技股份有限公司, 苏州博众机器人有限公司 filed Critical 博众精工科技股份有限公司
Publication of WO2022088389A1 publication Critical patent/WO2022088389A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J11/00—Manipulators not otherwise provided for
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1679—Programme controls characterised by the tasks executed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697—Vision controlled systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V8/00—Prospecting or detecting by optical means
    • G01V8/10—Detecting, e.g. by using light barriers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Definitions

  • the embodiments of the present application relate to security inspection technology, for example, to a method, device, device, and storage medium for robot security inspection.
  • the human body security inspection method is that the staff holds the security inspection equipment to detect various types of contraband such as metal and non-metal carried by the human body, and the staff can only detect the scanned side of the inspected person at the same time. Or use fixed security inspection equipment, and only when pedestrians walk towards the security inspection equipment, the security inspection equipment will conduct security inspection.
  • the security inspection process wastes manpower and time, the efficiency and coverage of security inspections are low, and it is prone to missed inspections.
  • Embodiments of the present application provide a method, device, device, and storage medium for robot security inspection, so as to improve the efficiency and coverage of security inspection.
  • the embodiment of the present application provides a robot security inspection method, the method includes:
  • the starting position of the candidate target determine the starting distance between the candidate target and the security inspection robot
  • the security inspection equipment of the security inspection robot is controlled to rotate following the movement of the target to be detected, so that the security inspection robot can perform security inspection of the target to be detected.
  • the embodiment of the present application also provides a robot security inspection device, which includes:
  • a candidate target acquisition module configured to acquire the candidate target of the initial area of the detection channel and the initial position of the candidate target
  • an initial distance determination module configured to determine the initial distance between the candidate target and the security inspection robot according to the initial position of the candidate target
  • a target-to-be-detected determination module configured to determine that the candidate target is a target to be detected if the starting distance meets a preset requirement
  • the robot security inspection module is configured to control the security inspection equipment of the security inspection robot to rotate following the movement of the to-be-detected target according to the current position of the to-be-detected target, so that the security-inspection robot can perform real-time security inspection of the to-be-detected target.
  • Embodiments of the present application further provide a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor executes the program to achieve the performance as described in any embodiment of the present application
  • the robot security check method described above is a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, where the processor executes the program to achieve the performance as described in any embodiment of the present application.
  • the embodiments of the present application further provide a storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute the robot security inspection method according to any embodiment of the present application when executed by a computer processor.
  • FIG. 1 is a schematic flowchart of a robot security inspection method in Embodiment 1 of the present application.
  • FIG. 2 is a schematic diagram of an L-shaped channel in Embodiment 1 of the present application.
  • FIG. 3 is a schematic flowchart of a robot security inspection method in Embodiment 2 of the present application.
  • FIG. 4 is a structural block diagram of a robot security inspection device in Embodiment 3 of the present application.
  • FIG. 5 is a schematic structural diagram of a computer device in Embodiment 4 of the present application.
  • FIG. 1 is a schematic flowchart of a robot security inspection method provided in Embodiment 1 of the present application. This embodiment is applicable to the situation of performing security inspection on pedestrians, and the method can be executed by a robot security inspection device. As shown in Figure 1, the method includes the following steps:
  • Step 110 Obtain the candidate target of the initial area of the detection channel and the initial position of the candidate target.
  • the detection channel can be a straight channel, a broken line channel or a curved channel. Pedestrians enter the detection channel from the entrance of the detection channel and reach the exit of the detection channel.
  • the entrance of the detection channel is the starting point of the detection channel
  • the exit of the detection channel is the end point of the detection channel.
  • the security inspection robot can be placed in the middle of the detection channel or at the corner of the channel.
  • the detection channel is an "L"-shaped channel, and the security inspection robot is located at the corner of the L. Before the security inspection, the security inspection robot can face the starting area of the detection channel and obtain images or videos of the starting area of the detection channel in real time.
  • the security inspection robot can obtain the image or video within the range of the preset radius centered on the starting point of the detection channel through the camera and other equipment. This range is the starting area, and the target person or object in the starting area of the detection channel is the candidate target. That is, the security inspection robot can obtain multiple candidate targets in the starting area of the detection channel. For example, if there are two pedestrians waiting in the starting area for security inspection, the candidate targets obtained by the security inspection robot are two pedestrians.
  • the security inspection robot After obtaining the candidate target, determine the starting position of the candidate target. Since the security inspection robot can obtain the candidate target within the preset range of the starting area of the detection channel, the starting position of the candidate target and the starting position of the detection channel may be inconsistent. , for example, two pedestrians line up at the start of the detection channel, but the starting position of both pedestrians is not the exact location of the start of the detection channel.
  • obtaining the candidate target in the initial area of the detection channel and the initial position of the candidate target includes: determining the target type of the candidate target according to the image information of the candidate target obtained in the initial area of the detection channel; if the target type is If the detection type is preset, the starting position of the candidate target is obtained according to the depth information of the candidate target.
  • the candidate target After obtaining the candidate target of the initial region of the detection channel, the candidate target can be screened first.
  • a preset detection type is pre-stored, and the preset detection type is a type that allows the security inspection robot to perform tracking security inspection.
  • the preset detection type may be pedestrians or luggage.
  • the image information of the candidate target can be obtained first through the camera, and the pictures and videos of the candidate target can be obtained.
  • the target type of the candidate target can be determined.
  • the target type of the candidate target can be pedestrian, kitten, or dog. Compare the target type with the preset detection type.
  • the target type is consistent with the preset detection type, it is determined that the candidate target meets the requirements of the preset detection type, and the starting position of the candidate target can continue to be determined; if the target type is consistent with the preset detection type If the detection types are inconsistent, the detection of the candidate target is stopped, and the starting position of the candidate target does not need to be obtained. In this way, the candidate targets are first screened, and the candidate targets that do not meet the requirements of the detection type are eliminated, so as to avoid data confusion caused by too many targets tracked by the security inspection robot, and improve the efficiency and accuracy of the security inspection.
  • Step 120 Determine the starting distance between the candidate target and the security inspection robot according to the starting position of the candidate target.
  • the starting distance between the candidate target and the security inspection robot is determined according to the position of the security inspection robot.
  • the starting distance is the distance between the position of the candidate target in the starting area of the detection channel and the security inspection robot.
  • the starting distance can be calculated according to the position coordinates of the candidate target and the position coordinates of the security inspection robot.
  • Step 130 If the starting distance meets the preset requirement, determine the candidate target as the target to be detected.
  • the preset requirement can be a preset distance, for example, the preset distance is the maximum distance that allows the security inspection robot to use the candidate target as the target to be detected.
  • the starting distance between the candidate target and the security inspection robot is compared with the preset distance. If the starting distance is less than or equal to the preset distance, the candidate target is determined to be the target to be detected, and the security inspection robot can track the candidate target for security inspection.
  • the preset requirement can also be to use the candidate target corresponding to the minimum starting distance as the target to be detected. If the starting distances between multiple candidate targets and the security inspection robot are determined, the starting distances are compared and the minimum starting distance is selected. The candidate target is the target to be detected.
  • the method further includes: if the initial distance between the candidate target and the security inspection robot does not meet the preset requirements, controlling The security robot removes the lock on the candidate target.
  • the security inspection robot removes the lock on the candidate target, and moves towards the starting area of the detection channel to obtain The target to be detected that meets the requirements. If there is no candidate target that meets the preset requirements in the starting area, the security inspection robot can move toward the starting point of the detection channel and continue to acquire candidate targets in the starting area of the detection channel. It can also be that the security inspection equipment on the security inspection robot faces the starting point of the detection channel, for example, the security inspection equipment can be a binocular stereo camera.
  • candidate targets that do not meet the preset distance requirements can be found in time, to avoid tracking and security inspection of candidate targets that do not meet the preset distance requirements, to realize the screening of the targets to be detected, to reduce the task load of the security inspection robot, and to avoid data confusion and cause security inspection. error, improve the efficiency and accuracy of security inspection.
  • Step 140 According to the current position of the target to be detected, the security inspection equipment of the security inspection robot is controlled to follow the movement of the target to be detected to rotate, so that the security inspection robot can perform security inspection of the target to be detected.
  • the target to be detected is locked.
  • the face or the whole pedestrian can be recognized by the camera, so as to lock the target frame of the pedestrian.
  • the security inspection robot determines the current position of the target to be detected in real time, and rotates according to the movement of the target to be detected. Only the security inspection equipment can be rotated, so that the target to be detected is always in the visual center of the security inspection equipment on the security inspection robot. .
  • the pedestrian detection and target tracking algorithm is used to realize the automatic following function in the detection channel.
  • the chassis of the security inspection robot can be fixed on the ground, and only the security inspection equipment on the security inspection robot can be rotated.
  • the security inspection robot can perform security inspection on the target to be detected during the rotation process. For example, it can detect the temperature of the target to be detected.
  • the head of the security inspection robot can be equipped with a temperature measurement camera, which can perform face recognition and detect human body temperature. If the body temperature is too high , it will alert the staff.
  • the shoulder of the security inspection robot can be equipped with an ID card identification function, which can identify pedestrians and enter the identified ID card into the background system.
  • real-time temperature measurement, video monitoring and face recognition can be performed on the inspected personnel within the field of view, and the temperature measurement video data of the whole process can be recorded and stored for later traceability.
  • Security inspection robots can also detect contraband to be detected, and security inspection equipment can use terahertz detection technology.
  • security inspection equipment can use optical cameras and terahertz detection modules, and use passive terahertz real-time imaging technology. Detection of various types of contraband such as metal or non-metal.
  • the non-contact detection method can quickly obtain security information through real-time imaging, thereby shortening the response time to potential threats.
  • FIG. 2 is a schematic diagram of an L-shaped channel.
  • the detection channel can be an "L"-shaped channel, and the security inspection robot 201 is placed at the corner of the L.
  • the security inspection robot 201 can ensure comprehensive security inspection of the front and back of the target to be detected.
  • the target to be detected only needs to pass through the detection channel at a normal speed to complete the front and back detection, which greatly improves the security inspection efficiency and the security inspection coverage of the target to be detected.
  • the target to be detected is tracked in real time, and the whole process of security inspection is carried out in the detection channel. It solves the problem in the related art that only local security inspections can be performed on the target to be detected or cannot be tracked, and automatic security inspection is performed on the front and back of the target to be detected during the movement of the target to be detected, which saves manpower and time and improves the security inspection. efficiency and coverage.
  • FIG. 3 is a schematic flowchart of a robot security inspection method provided in Embodiment 2 of the present application. This embodiment is described based on the foregoing embodiment, and the method can be executed by a robot security inspection device. As shown in Figure 3, it includes the following steps:
  • Step 310 Obtain the candidate target of the initial area of the detection channel and the initial position of the candidate target.
  • Step 320 Determine the initial distance between the candidate target and the security inspection robot according to the initial position of the candidate target.
  • Step 330 If the starting distance meets the preset requirement, determine the candidate target as the target to be detected.
  • Step 340 Acquire the current position of the target to be detected in real time, and determine whether the current position of the target to be detected meets the security inspection requirements of the security inspection equipment.
  • the target tracking algorithm can be used to obtain the current position of the target to be detected in real time, and according to the current position of the target to be detected, it is determined whether the security inspection robot needs to continue to track the target to be detected.
  • the security inspection robot performs security inspection through the security inspection equipment, and the security inspection requirements of the security inspection equipment can be preset. For example, the security inspection requirements can be set to a certain preset distance. If the distance between the target to be detected and the security inspection robot exceeds the preset distance, it indicates that If the distance between the target to be detected and the security inspection robot is too far, it is not necessary to perform security inspection on the target to be detected.
  • the security inspection will continue to be tracked; if the current position of the target to be detected does not meet the security inspection requirements of the security inspection device, the tracking security inspection of the target to be detected will end.
  • determining whether the current position of the target to be detected meets the security inspection requirements of the security inspection equipment includes: determining the current distance between the target to be detected and the security inspection robot according to the current position of the target to be detected; comparing the current distance with a preset security inspection distance , to determine whether the current distance exceeds the preset security inspection distance; if the current distance exceeds the preset security inspection distance, it is determined that the current position of the target to be detected does not meet the security inspection requirements of the security inspection equipment.
  • the security inspection requirement can be set as a preset security inspection distance, the current position of the target to be detected can be obtained, and the current distance between the target to be detected and the security inspection robot can be determined according to the current position of the target to be detected and the position of the security inspection robot. Compare the current distance with the preset security inspection distance to determine whether the current distance exceeds the preset security inspection distance. If the security inspection robot determines that the current distance between the target to be detected and the security inspection robot exceeds the preset security inspection distance during the security inspection process, it means that the target to be detected is far away from the security inspection robot and has exceeded the range that the security inspection robot can detect.
  • the security inspection robot can stop the tracking security inspection of the target to be detected.
  • the target to be detected can be screened at any time during the tracking process of the target to be detected, so as to avoid detecting the target to be detected even after the target to be detected has moved away, to realize the determination of the target that really needs to be detected, and to save the time of security inspection. , improve the efficiency and accuracy of security inspection.
  • determining whether the current position of the target to be detected meets the security inspection requirements of the security inspection equipment further includes: according to the current position of the target to be detected, determining whether the target to be detected is at the end point of the detection channel; if the target to be detected is at the end point of the detection channel , it is determined that the current position of the target to be detected does not meet the security inspection requirements of the security inspection equipment.
  • the security inspection requirement may also be a preset location for ending the security inspection.
  • the location for ending the security inspection may be set as the end point of the detection channel.
  • the security inspection robot determines the current position of the target to be detected in real time, compares the current position with the end position of the detection channel, and determines whether the target to be detected is at the end of the detection channel. If the target to be detected is located at the end of the detection channel, it means that the target to be detected has passed the detection channel, the current position of the target to be detected does not meet the security inspection requirements of the security inspection equipment, and the security inspection device does not need to detect the target to be detected.
  • the target to be detected is not at the end of the detection channel, it means that the target to be detected is still in the detection channel, and the security inspection equipment also needs to track and inspect the target to be detected.
  • the target to be detected can be screened at any time during the tracking process of the target to be detected, so as to avoid the target to be detected after the target to be detected has moved away, and to realize the determination of the target that needs to be detected, save the time of security inspection and improve the Efficiency and precision of security checks.
  • Step 350 If the current position of the target to be detected meets the security inspection requirements of the security inspection equipment, then determine the current angle between the visual center point of the security inspection device and the target to be detected; The visual center point is consistent with the current position of the target to be detected. If the current position of the target to be detected does not meet the security inspection requirements of the security inspection equipment, the tracking security inspection of the target to be detected is stopped, and the security inspection equipment of the security inspection robot is controlled to rotate until the detection range of the security inspection robot covers the starting area of the detection channel.
  • the target to be detected continues to be tracked and inspected.
  • the process of tracking the target to be detected it is necessary to ensure that the target to be detected is located in the center of the visual range of the security inspection equipment.
  • Determine the current position of the target to be detected and the position of the visual center point of the security inspection equipment and determine the angle between the target to be detected and the visual center point of the security inspection equipment according to the current position and the position of the visual center point, which is the current angle.
  • the current angle is the rotation angle of the security inspection equipment, and the rotation of the security inspection equipment is controlled according to the rotation angle.
  • the security inspection robot automatically rotates the security inspection equipment to the direction of the starting point of the detection channel, re-identifies the candidate target, and conducts a new round of security inspection.
  • the present application by acquiring candidate targets in the initial area of the detection channel, and determining the initial distance between the candidate target and the robot according to the initial position of the candidate target, it is convenient to select the targets to be detected that meet the requirements from the candidate targets. Detect the position of the target, track the target to be detected in real time, and conduct the whole process of security inspection in the detection channel. According to the preset security inspection requirements, it is determined whether the security inspection of the target to be detected is over, so as to realize the sequential identification and detection of the target to be detected, and avoid useless security inspection.
  • FIG. 4 is a structural block diagram of a robot security inspection device provided in Embodiment 3 of the present application.
  • the robot security inspection device can execute a robot security inspection method provided by any embodiment of the present application, and has functional modules corresponding to the execution method. As shown in FIG.
  • the device includes: a candidate target acquisition module 401, which is set to acquire the candidate target of the starting area of the detection channel and the starting position of the candidate target; the starting distance determination module 402 is set to obtain the starting position of the candidate target according to the position, determine the initial distance between the candidate target and the security inspection robot; the target determination module 403 to be detected is set to determine the candidate target as the target to be detected if the initial distance meets the preset requirements; the robot security inspection module 404 is set to The current position of the target to be detected, the security inspection equipment that controls the security inspection robot rotates following the movement of the target to be detected, for the security inspection robot to perform real-time security inspection of the target to be detected.
  • a candidate target acquisition module 401 which is set to acquire the candidate target of the starting area of the detection channel and the starting position of the candidate target
  • the starting distance determination module 402 is set to obtain the starting position of the candidate target according to the position, determine the initial distance between the candidate target and the security inspection robot
  • the target determination module 403 to be detected is set
  • the candidate target acquisition module 401 includes: a type determination unit, set to determine the target type of the candidate target according to the image information of the candidate target obtained in the initial area of the detection channel; a position acquisition unit, set to if the target type If the detection type is the preset detection type, the starting position of the candidate target is obtained according to the depth information of the candidate target.
  • the device further includes: a candidate target continuation detection module, which is set to, after determining the initial distance between the candidate target and the security inspection robot according to the initial position of the candidate target, if the initial distance between the candidate target and the security inspection robot is If the initial distance does not meet the preset requirements, control the security inspection robot to remove the lock on the candidate target.
  • a candidate target continuation detection module which is set to, after determining the initial distance between the candidate target and the security inspection robot according to the initial position of the candidate target, if the initial distance between the candidate target and the security inspection robot is If the initial distance does not meet the preset requirements, control the security inspection robot to remove the lock on the candidate target.
  • the robot security inspection module 404 includes: a current position determination unit, configured to obtain the current position of the target to be detected in real time, and determine whether the current position of the target to be detected meets the security inspection requirements of the security inspection equipment; the current angle determination unit, set to if The current position of the target to be detected meets the security inspection requirements of the security inspection equipment, then the current angle between the visual center point of the security inspection equipment and the target to be detected is determined; the rotation angle determination unit is set to determine the rotation angle of the security inspection equipment according to the current angle, so that The visual center point of the security inspection equipment is consistent with the current position of the target to be detected; the security inspection stop unit is set to stop the tracking security inspection of the target to be detected and control the security inspection of the security inspection robot if the current position of the target to be detected does not meet the security inspection requirements of the security inspection equipment The equipment rotates so that the detection range of the security inspection robot covers the starting area of the detection channel.
  • the current position determination unit is set to: determine the current distance between the target to be detected and the security inspection robot according to the current position of the target to be detected; compare the current distance with the preset security inspection distance to determine whether the current distance exceeds the preset security inspection distance Distance; if the current distance exceeds the preset security inspection distance, it is determined that the current location of the target to be detected does not meet the security inspection requirements of the security inspection equipment.
  • the current position determination unit is further configured to: determine whether the target to be detected is at the end point of the detection channel according to the current position of the target to be detected; if the target to be detected is at the end point of the detection channel, then determine the current position of the target to be detected Does not meet the security inspection requirements of the security inspection equipment.
  • the detection channel is an L-shaped channel.
  • the security inspection equipment adopts terahertz detection technology.
  • the present application by acquiring candidate targets in the initial area of the detection channel, and determining the initial distance between the candidate target and the robot according to the initial position of the candidate target, it is convenient to select the targets to be detected that meet the requirements from the candidate targets. Detect the position of the target, track the target to be detected in real time, and carry out the full tracking security inspection in the detection channel. It solves the problem in the related art that only local security inspections can be performed on the target to be detected or cannot be tracked, and automatic security inspection is performed on the front and back of the target to be detected during the movement of the target to be detected, which saves manpower and time and improves the security inspection. efficiency and coverage.
  • FIG. 5 is a schematic structural diagram of a computer device according to Embodiment 4 of the present application.
  • Figure 5 shows a block diagram of an exemplary computer device 500 suitable for use in implementing embodiments of the present application.
  • the computer device 500 shown in FIG. 5 is only an example, and does not impose any limitation on the function and scope of use of the embodiments of the present application.
  • computer device 500 takes the form of a general-purpose computing device.
  • Components of computer device 500 may include, but are not limited to, one or more processors or processing units 501, system memory 502, and a bus 503 connecting various system components including system memory 502 and processing unit 501.
  • Bus 503 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, MicroChannel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (Video Electronics Standards Association) , VESA) local bus and Peripheral Component Interconnect (PCI) bus.
  • Computer device 500 includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 500, including both volatile and nonvolatile media, removable and non-removable media.
  • System memory 502 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 504 and/or cache memory 505 .
  • Computer device 500 may also include other removable/non-removable, volatile/non-volatile computer system storage media.
  • storage system 506 may be configured to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard disk drive").
  • disk drives configured to read and write to removable non-volatile magnetic disks (eg, "floppy disks") and removable non-volatile optical disks (eg, portable compact disk read-only memories) may be provided.
  • Memory 502 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of various embodiments of the present application.
  • Program modules 507 generally perform the functions and/or methods of the embodiments described herein.
  • Computer device 500 may also communicate with one or more external devices 509 (eg, keyboards, pointing devices, display 510, etc.), with one or more devices that enable a user to interact with the computer device 500, and/or with Any device (eg, network card, modem, etc.) that enables the computer device 500 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 511 . Also, computer device 500 may communicate with one or more networks (eg, Local Area Network (LAN), Wide Area Network (WAN), and/or public networks such as the Internet) through network adapter 512. As shown in FIG. 5 , network adapter 512 communicates with other modules of computer device 500 via bus 503 . It should be understood that, although not shown in FIG.
  • computer device 500 may be used in conjunction with computer device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays of Independent Disks, RAID) systems, tape drives, and data backup storage systems, etc.
  • the processing unit 501 executes a variety of functional applications and data processing by running a program stored in the system memory 502, for example, to implement a robot security inspection method provided by the embodiment of the present application, including: obtaining a candidate target of the starting area of the detection channel and the starting position of the candidate target; according to the starting position of the candidate target, determine the starting distance between the candidate target and the security inspection robot; if the starting distance meets the preset requirements, the candidate target is determined as the target to be detected; The current position of the target, the security inspection equipment that controls the security inspection robot rotates following the movement of the target to be detected, for the security inspection robot to perform security inspection of the target to be detected.
  • the fifth embodiment of the present application also provides a storage medium containing computer-executable instructions, on which a computer program is stored, and when the program is executed by a processor, implements the robot security inspection method provided by the embodiment of the present application, including: obtaining Detect the candidate target in the starting area of the channel and the starting position of the candidate target; according to the starting position of the candidate target, determine the starting distance between the candidate target and the security inspection robot; if the starting distance meets the preset requirements, then determine the candidate target It is the target to be detected; according to the current position of the target to be detected, the security inspection equipment that controls the security inspection robot rotates following the movement of the target to be detected, for the security inspection robot to perform security inspection of the target to be detected.
  • the computer storage medium of the embodiments of the present application may adopt any combination of one or more computer-readable media.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above.
  • An example (non-exhaustive list) of a computer readable storage medium includes: an electrical connection having one or more wires, a portable computer disk, a hard disk, RAM, Read-Only Memory (ROM), erasable Programmable read-only memory (Electrically Programmable Read-Only-Memory, EPROM) or flash memory, optical fiber, CD-ROM, optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber cable, radio frequency (RF), etc., or any suitable combination of the foregoing.
  • suitable medium including but not limited to wireless, wire, optical fiber cable, radio frequency (RF), etc., or any suitable combination of the foregoing.
  • Computer program code for performing the operations of the present application may be written in one or more programming languages, including object-oriented programming languages—such as Java, Smalltalk, C++, but also conventional Procedural programming language - such as the "C" language or similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a LAN or WAN, or may be connected to an external computer (eg, using an Internet service provider to connect through the Internet).

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Robotics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geophysics (AREA)
  • Manipulator (AREA)

Abstract

一种机器人安检的方法、装置、设备及存储介质。其中，该方法包括：获取检测通道起始区域的候选目标和所述候选目标的起始位置（110）；根据所述候选目标的起始位置，确定所述候选目标与安检机器人之间的起始距离（120）；若所述起始距离满足预设要求，则确定所述候选目标为待检测目标（130）；根据所述待检测目标的当前位置，控制所述安检机器人的安检设备跟随所述待检测目标的运动进行旋转，供所述安检机器人对所述待检测目标进行安检（140）。

Description

机器人安检的方法、装置、设备及存储介质
本申请要求在2020年10月29日提交中国专利局、申请号为202011182933.9的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及安检技术，例如涉及一种机器人安检的方法、装置、设备及存储介质。
背景技术
人们在进入地铁站或火车站等地时，通常要进行安检，以保证没有随身携带危险物品，若安检力度不够大，则可能会导致交通事故，影响生命安全。
人体安检方法是由工作人员手持安检设备，检测人体随身携带的金属和非金属等多类违禁品，且同一时刻工作人员只能检测被检人员被扫描的一侧。或者采用固定的安检设备，只有当行人走向安检设备时，安检设备才进行安检。安检过程浪费人力和时间，安检的效率与覆盖率较低，容易发生漏检等情况。
发明内容
本申请实施例提供一种机器人安检的方法、装置、设备及存储介质，以提高安检的效率和覆盖率。
本申请实施例提供了一种机器人安检方法，该方法包括：
获取检测通道起始区域的候选目标和所述候选目标的起始位置；
根据所述候选目标的起始位置，确定所述候选目标与安检机器人之间的起始距离；
若所述起始距离满足预设要求，则确定所述候选目标为待检测目标；
根据所述待检测目标的当前位置，控制所述安检机器人的安检设备跟随所述待检测目标的运动进行旋转，供所述安检机器人对所述待检测目标进行安检。
本申请实施例还提供了一种机器人安检装置，该装置包括：
候选目标获取模块，设置为获取检测通道起始区域的候选目标和所述候选目标的起始位置；
起始距离确定模块，设置为根据所述候选目标的起始位置，确定所述候选目标与安检机器人之间的起始距离；
待检测目标确定模块，设置为若所述起始距离满足预设要求，则确定所述候选目标为待检测目标；
机器人安检模块，设置为根据所述待检测目标的当前位置，控制所述安检机器人的安检设备跟随所述待检测目标的运动进行旋转，供所述安检机器人对所述待检测目标进行实时安检。
本申请实施例还提供了一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如本申请任意实施例所述的机器人安检方法。
本申请实施例还提供了一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行如本申请任意实施例所述的机器人安检方法。
附图说明
图1是本申请实施例一中的一种机器人安检方法的流程示意图；
图2是本申请实施例一中的L型通道示意图；
图3是本申请实施例二中的一种机器人安检方法的流程示意图；
图4是本申请实施例三中的一种机器人安检装置的结构框图；
图5是本申请实施例四中的一种计算机设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请进行说明。此处所描述的实施例仅仅用于解释本申请，而非对本申请的限定。为了便于描述，附图中仅示出了与本申请相关的部分而非全部结构。
实施例一
图1为本申请实施例一提供的一种机器人安检方法的流程示意图，本实施例可适用于对行人进行安检的情况，该方法可以由一种机器人安检装置来执行。如图1所示，该方法包括如下步骤：
步骤110、获取检测通道起始区域的候选目标和候选目标的起始位置。
检测通道可以是直线通道、折线通道或曲线通道，行人从检测通道的入口进入检测通道，到达检测通道的出口，检测通道的入口为检测通道起点，检测通道的出口为检测通道终点。安检机器人可以放在检测通道的中间位置或通道拐角处，例如，检测通道为“L”型通道，安检机器人位于L的拐角处。在进行 安检之前，安检机器人可以朝向检测通道起始区域，实时获取检测通道起始区域的图像或视频。安检机器人可以通过摄像头等设备获取到以检测通道起点处为中心，预设半径的范围内的图像或视频，该范围即为起始区域，处于检测通道起始区域内的目标人或目标物即为候选目标。即安检机器人可以获取到检测通道起始区域的多个候选目标，例如，存在两个行人，在起始区域排队等候安检，则安检机器人获取到的候选目标为两个行人。
在获取到候选目标后，确定候选目标的起始位置，由于安检机器人可以获取到检测通道起始区域预设范围内的候选目标，因此，候选目标的起始位置与检测通道起点的位置可以不一致，例如，两个行人在检测通道起点排队，但两个行人的起始位置均不是检测通道起点的准确位置。
可选的，获取检测通道起始区域的候选目标和候选目标的起始位置，包括：根据在检测通道起始区域获取到的候选目标的图像信息，确定候选目标的目标类型；若目标类型为预设检测类型，则根据候选目标的深度信息，获取候选目标的起始位置。
在得到检测通道起始区域的候选目标后，可以先对候选目标进行一次筛选。预先存储预设检测类型，预设检测类型是允许安检机器人进行跟踪安检的类型，例如，预设检测类型可以是行人或行李箱等。可以先通过摄像头获取候选目标的图像信息，可以获取候选目标的图片和视频。根据获取到的图像信息，可以确定候选目标的目标类型，例如，候选目标的目标类型可以是行人、小猫或小狗等。将目标类型与预设检测类型进行对比，若目标类型与预设检测类型一致，则确定候选目标符合预设检测类型的要求，可以继续确定该候选目标的起始位置；若目标类型与预设检测类型不一致，则对候选目标进行停止检测，不需要获取该候选目标的起始位置。这样设置，先对候选目标进行一次筛选，淘汰不符合检测类型要求的候选目标，避免安检机器人跟踪的目标过多导致数据混乱，提高安检的效率和精度。
步骤120、根据候选目标的起始位置，确定候选目标与安检机器人之间的起始距离。
在确定候选目标的起始位置之后，根据安检机器人所在的位置，确定候选目标与安检机器人之间的起始距离。起始距离为候选目标在检测通道起始区域中的位置与安检机器人之间的距离，可以根据候选目标的位置坐标和安检机器人的位置坐标计算起始距离。
步骤130、若起始距离满足预设要求，则确定候选目标为待检测目标。
预设要求可以是一个预设距离，例如，预设距离为允许安检机器人将候选 目标作为待检测目标的最大距离。在得到起始距离后，将候选目标与安检机器人之间的起始距离与预设距离进行比较。若起始距离小于或等于预设距离，则确定该候选目标为待检测目标，安检机器人可以对该候选目标进行跟踪安检。预设要求也可以是将最小起始距离所对应的候选目标作为待检测目标，若确定多个候选目标与安检机器人之间的起始距离，则对起始距离进行比较，选取起始距离最小的候选目标为待检测目标。
可选的，在根据候选目标的起始位置，确定候选目标与安检机器人之间的起始距离之后，还包括：若候选目标与安检机器人之间的起始距离不满足预设要求，则控制安检机器人移除对候选目标的锁定。
若起始距离不满足预设要求，例如在比较起始距离后，存在起始距离较远的候选目标，则安检机器人移除对该候选目标的锁定，并朝向检测通道的起始区域，获取符合要求的待检测目标。若起始区域均没有满足预设要求的候选目标，则安检机器人可以朝向检测通道的起点，继续获取检测通道起始区域的候选目标。也可以是安检机器人上的安检设备朝向检测通道起点，例如，安检设备可以是双目立体相机。这样设置，及时发现不符合预设距离要求的候选目标，避免对不符合预设距离要求的候选目标进行跟踪安检，实现对待检测目标的筛选，减少安检机器人的任务量，避免数据混乱，造成安检误差，提高安检效率和精度。
步骤140、根据待检测目标的当前位置，控制安检机器人的安检设备跟随待检测目标的运动进行旋转，供安检机器人对待检测目标进行安检。
在确定待检测目标后，对待检测目标进行锁定，例如，可以通过摄像头识别人脸或行人整体，从而对行人的目标框进行锁定。在待检测目标移动的过程中，安检机器人实时确定待检测目标的当前位置，根据待检测目标的移动进行旋转，可以只旋转安检设备，使待检测目标始终处于安检机器人上的安检设备的视觉中心。例如，采用行人检测与目标跟踪算法实现检测通道内的自动跟随功能。可以将安检机器人的底盘固定在地面上，只旋转安检机器人上的安检设备。安检机器人在旋转过程中可以对待检测目标进行安检，例如，可以检测待检测目标的温度，安检机器人的头部可以设置有测温摄像头，可以进行人脸识别并检测人的体温，若体温超高，则会报警提示工作人员。安检机器人的肩部可以配有身份证识别功能，对行人进行身份识别，将识别的身份证录入后台系统。在安检过程中，可以对视场范围内的被检测人员进行实时测温、视频监控以及人脸识别，并将全过程的测温和视频数据进行记录和储存，便于后期追溯。安检机器人也可以对待检测目标的违禁品进行检测，安检设备可以利用太赫兹检测技术，例如，安检设备可以采用光学摄像头和太赫兹检测模块，采用被动 式太赫兹实时成像技术，实现对人体随身携带的金属或非金属等多类违禁品在内的探测。非接触式的探测方式通过实时成像能快速获取安检信息，从而缩短对潜在威胁的反应时间。
图2为L型通道示意图。检测通道可以是“L”型通道，安检机器人201放置在L的拐角处，通过安检机器人201跟随待检测目标的旋转，可以保证安检机器人201对待检测目标正面和背面的全面安检。待检测目标只需以正常速度穿过检测通道，便可完成正面检测与背面检测，大大提升安检效率和对待检测目标的安检覆盖率。
本实施例的技术方案，通过获取检测通道起始区域的候选目标，根据候选目标的起始位置，确定候选目标与机器人之间的起始距离，便于从候选目标中筛选满足要求的待检测目标，根据待检测目标的位置，实时跟踪待检测目标，在检测通道中进行全程追踪安检。解决了相关技术中，只能对待检测目标进行局部安检或无法追踪安检的问题，实现了在待检测目标运动过程中，对待检测目标的正面和背面进行自动安检，节约了人力和时间，提高安检的效率和覆盖率。
实施例二
图3为本申请实施例二提供的一种机器人安检方法的流程示意图，本实施例以上述实施例为基础进行说明，该方法可以由机器人安检装置来执行。如图3所示，包括如下步骤：
步骤310、获取检测通道起始区域的候选目标和候选目标的起始位置。
步骤320、根据候选目标的起始位置，确定候选目标与安检机器人之间的起始距离。
步骤330、若起始距离满足预设要求，则确定候选目标为待检测目标。
步骤340、实时获取待检测目标的当前位置，确定待检测目标的当前位置是否满足安检设备的安检要求。
在确定待检测目标后，需要对待检测目标进行实时跟踪。因此，可以采用目标跟踪算法实时获取待检测目标的当前位置，根据待检测目标的当前位置，确定安检机器人是否需要对该待检测目标继续进行跟踪安检。安检机器人通过安检设备进行安检，可以预设安检设备的安检要求，例如，可以将安检要求设置为一定的预设距离，若待检测目标与安检机器人之间的距离超过预设的距离，则说明待检测目标与安检机器人距离过远，可以不对该待检测目标进行安检。若待检测目标的当前位置满足安检设备的安检要求，则继续跟踪安检；若待检测目标的当前位置不满足安检设备的安检要求，则对该待检测目标的跟踪安检 结束。
可选的，确定待检测目标的当前位置是否满足安检设备的安检要求，包括：根据待检测目标的当前位置，确定待检测目标与安检机器人的当前距离；将当前距离与预设安检距离进行比较，确定当前距离是否超过预设安检距离；若当前距离超过预设安检距离，则确定待检测目标的当前位置不满足安检设备的安检要求。
可以将安检要求设置为一个预设安检距离，获取待检测目标的当前位置，根据待检测目标的当前位置和安检机器人的位置，可以确定待检测目标与安检机器人之间的当前距离。将当前距离与预设安检距离进行比较，确定当前距离是否超过预设安检距离。若安检机器人在安检过程中，确定待检测目标与安检机器人之间的当前距离超过预设安检距离，则说明待检测目标距离安检机器人较远，已经超过了安检机器人可以检测到的范围，待检测目标的当前位置不满足安检设备的安检要求，安检机器人可以停止对该待检测目标的跟踪安检。这样设置，可以在对待检测目标的跟踪过程中，随时对待检测目标进行筛选，避免待检测目标已经远离后仍然对该待检测目标进行检测，实现对真正需要进行检测的目标进行确定，节约安检时间，提高安检的效率和精度。
可选的，确定待检测目标的当前位置是否满足安检设备的安检要求，还包括：根据待检测目标的当前位置，确定待检测目标是否在检测通道终点处；若待检测目标在检测通道终点处，则确定待检测目标的当前位置不满足安检设备的安检要求。
安检要求还可以是预设一个结束安检的地点，例如，可以将结束安检的地点设置为检测通道的终点。安检机器人实时确定待检测目标的当前位置，将当前位置与检测通道的终点位置进行比较，确定待检测目标是否处于检测通道的终点处。若待检测目标位于检测通道终点，则说明待检测目标已经通过了检测通道，待检测目标的当前位置不满足安检设备的安检要求，安检设备不需要再对待检测目标进行检测。若待检测目标不在检测通道终点，则说明待检测目标仍然处于检测通道内，安检设备还需要对待检测目标进行跟踪和安检。这样设置，可以在对待检测目标的跟踪过程中，随时对待检测目标进行筛选，避免待检测目标已经远离后仍然对待检测目标进行检测，实现对真正需要进行检测的目标进行确定，节约安检时间，提高安检的效率和精度。
步骤350、若待检测目标的当前位置满足安检设备的安检要求，则确定安检设备的视觉中心点与待检测目标之间的当前角度；根据当前角度，确定安检设备的旋转角度，使安检设备的视觉中心点与待检测目标的当前位置一致。若待检测目标的当前位置不满足安检设备的安检要求，则停止对待检测目标的跟踪 安检，控制安检机器人的安检设备旋转，至安检机器人的检测范围覆盖检测通道的起始区域。
若确定待检测目标满足安检设备的安检要求，则继续对待检测目标进行跟踪和安检。在对待检测目标跟踪的过程中，需要保证待检测目标位于安检设备视觉范围中的中心位置。确定待检测目标的当前位置和安检设备视觉中心点的位置，根据当前位置和视觉中心点位置，确定待检测目标与安检设备视觉中心点之间的角度，该角度为当前角度。当前角度为安检设备的旋转角度，根据旋转角度，控制安检设备旋转。例如，待检测目标在视觉中心点左侧30度的位置处，则将安检设备朝向左旋转30度，使安检设备的视觉中心点与待检测目标的当前位置一致。若确定待检测目标不满足安检设备的安检要求，则说明安检机器人可以停止对待检测目标的跟踪和安检，安检机器人需要确定新的待检测目标。安检机器人自动将安检设备旋转至检测通道起点的方向，重新识别候选目标，进行新一轮的安检。
本申请实施例通过获取检测通道起始区域的候选目标，根据候选目标的起始位置，确定候选目标与机器人之间的起始距离，便于从候选目标中筛选满足要求的待检测目标，根据待检测目标的位置，实时跟踪待检测目标，在检测通道中进行全程追踪安检，根据预设的安检要求，确定对待检测目标的安检是否结束，实现对待检测目标的依次识别和检测，避免无用安检。解决了相关技术中，只能对待检测目标进行局部安检或无法追踪安检的问题，实现了在待检测目标运动过程中，对待检测目标的正面和背面进行自动安检，节约了人力和时间，提高安检的效率和覆盖率。
实施例三
图4为本申请实施例三所提供的一种机器人安检装置的结构框图。机器人安检装置可执行本申请任意实施例所提供的一种机器人安检方法，且具备执行方法相应的功能模块。如图4所示，该装置包括：候选目标获取模块401，设置为获取检测通道起始区域的候选目标和候选目标的起始位置；起始距离确定模块402，设置为根据候选目标的起始位置，确定候选目标与安检机器人之间的起始距离；待检测目标确定模块403，设置为若起始距离满足预设要求，则确定候选目标为待检测目标；机器人安检模块404，设置为根据待检测目标的当前位置，控制安检机器人的安检设备跟随待检测目标的运动进行旋转，供安检机器人对待检测目标进行实时安检。
可选的，候选目标获取模块401，包括：类型确定单元，设置为根据在检测通道起始区域获取到的候选目标的图像信息，确定候选目标的目标类型；位置获取单元，设置为若目标类型为预设检测类型，则根据候选目标的深度信息， 获取候选目标的起始位置。
可选的，该装置还包括：候选目标继续检测模块，设置为在根据候选目标的起始位置，确定候选目标与安检机器人之间的起始距离之后，若候选目标与安检机器人之间的起始距离不满足预设要求，则控制安检机器人移除对候选目标的锁定。
可选的，机器人安检模块404，包括：当前位置确定单元，设置为实时获取待检测目标的当前位置，确定待检测目标的当前位置是否满足安检设备的安检要求；当前角度确定单元，设置为若待检测目标的当前位置满足安检设备的安检要求，则确定安检设备的视觉中心点与待检测目标之间的当前角度；旋转角度确定单元，设置为根据当前角度，确定安检设备的旋转角度，使安检设备的视觉中心点与待检测目标的当前位置一致；安检停止单元，设置为若待检测目标的当前位置不满足安检设备的安检要求，则停止对待检测目标的跟踪安检，控制安检机器人的安检设备旋转，至安检机器人的检测范围覆盖检测通道的起始区域。
可选的，当前位置确定单元，设置为：根据待检测目标的当前位置，确定待检测目标与安检机器人的当前距离；将当前距离与预设安检距离进行比较，确定当前距离是否超过预设安检距离；若当前距离超过预设安检距离，则确定待检测目标的当前位置不满足安检设备的安检要求。
可选的，当前位置确定单元，还设置为：根据待检测目标的当前位置，确定待检测目标是否在检测通道终点处；若待检测目标在检测通道终点处，则确定待检测目标的当前位置不满足安检设备的安检要求。
可选的，检测通道为L型通道。
可选的，安检设备采用太赫兹检测技术。
本申请实施例通过获取检测通道起始区域的候选目标，根据候选目标的起始位置，确定候选目标与机器人之间的起始距离，便于从候选目标中筛选满足要求的待检测目标，根据待检测目标的位置，实时跟踪待检测目标，在检测通道中进行全程追踪安检。解决了相关技术中，只能对待检测目标进行局部安检或无法追踪安检的问题，实现了在待检测目标运动过程中，对待检测目标的正面和背面进行自动安检，节约了人力和时间，提高安检的效率和覆盖率。
实施例四
图5是本申请实施例四提供的一种计算机设备的结构示意图。图5示出了适于用来实现本申请实施方式的示例性计算机设备500的框图。图5显示的计算机设备500仅仅是一个示例，不对本申请实施例的功能和使用范围带来任何 限制。
如图5所示，计算机设备500以通用计算设备的形式表现。计算机设备500的组件可以包括但不限于：一个或者多个处理器或者处理单元501，系统存储器502，连接不同系统组件(包括系统存储器502和处理单元501)的总线503。
总线503表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(Industry Standard Architecture，ISA)总线，微通道体系结构(MicroChannel Architecture，MAC)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association，VESA)局域总线以及外围组件互连(Peripheral Component Interconnect，PCI)总线。
计算机设备500包括多种计算机系统可读介质。这些介质可以是任何能够被计算机设备500访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
系统存储器502可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory，RAM)504和/或高速缓存存储器505。计算机设备500还可以包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统506可以设置为读写不可移动的、非易失性磁介质(图5未显示，通常称为“硬盘驱动器”)。尽管图5中未示出，可以提供设置为对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如便携式紧凑磁盘只读存储器(Compact Disc Read-Only Memory，CD-ROM),高密度数字视频只读存储器(Digital Video Disc Read-Only Memory，DVD-ROM)或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线503相连。存储器502可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本申请多个实施例的功能。
具有一组(至少一个)程序模块507的程序/实用工具508，可以存储在例如存储器502中，这样的程序模块507包括但不限于操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或某种组合中可能包括网络环境的实现。程序模块507通常执行本申请所描述的实施例中的功能和/或方法。
计算机设备500也可以与一个或多个外部设备509(例如键盘、指向设备、显示器510等)通信，还可与一个或者多个使得用户能与该计算机设备500交互的设备通信，和/或与使得该计算机设备500能与一个或多个其它计算设备进 行通信的任何设备(例如网卡，调制解调器等)通信。这种通信可以通过输入/输出(Input/Output，I/O)接口511进行。并且，计算机设备500还可以通过网络适配器512与一个或者多个网络(例如局域网(Local Area Network，LAN)，广域网(Wide Area Network，WAN)和/或公共网络，例如因特网)通信。如图5所示，网络适配器512通过总线503与计算机设备500的其它模块通信。应当明白，尽管图5中未示出，可以结合计算机设备500使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、磁盘阵列(Redundant Arrays of Independent Disks，RAID)系统、磁带驱动器以及数据备份存储系统等。
处理单元501通过运行存储在系统存储器502中的程序，从而执行多种功能应用以及数据处理，例如实现本申请实施例所提供的一种机器人安检方法，包括：获取检测通道起始区域的候选目标和候选目标的起始位置；根据候选目标的起始位置，确定候选目标与安检机器人之间的起始距离；若起始距离满足预设要求，则确定候选目标为待检测目标；根据待检测目标的当前位置，控制安检机器人的安检设备跟随待检测目标的运动进行旋转，供安检机器人对待检测目标进行安检。
实施例五
本申请实施例五还提供一种包含计算机可执行指令的存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请实施例所提供的一种机器人安检方法，包括：获取检测通道起始区域的候选目标和候选目标的起始位置；根据候选目标的起始位置，确定候选目标与安检机器人之间的起始距离；若起始距离满足预设要求，则确定候选目标为待检测目标；根据待检测目标的当前位置，控制安检机器人的安检设备跟随待检测目标的运动进行旋转，供安检机器人对待检测目标进行安检。
本申请实施例的计算机存储介质，可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的一个例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、RAM、只读存储器(Read-Only Memory，ROM)、可擦式可编程只读存储器(Electrically Programmable Read-Only-Memory，EPROM)或闪存、光纤、CD-ROM、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、电线、光缆、射频(radio frequency，RF)等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络，包括LAN或WAN，连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。

Claims (11)

  1. 一种机器人安检方法，包括：
    获取检测通道起始区域的候选目标和所述候选目标的起始位置；
    根据所述候选目标的起始位置，确定所述候选目标与安检机器人之间的起始距离；
    在所述起始距离满足预设要求的情况下，确定所述候选目标为待检测目标；
    根据所述待检测目标的当前位置，控制所述安检机器人的安检设备跟随所述待检测目标的运动进行旋转，供所述安检机器人对所述待检测目标进行安检。
  2. 根据权利要求1所述的方法，其中，获取检测通道起始区域的候选目标和所述候选目标的起始位置，包括：
    根据在检测通道起始区域获取到的候选目标的图像信息，确定所述候选目标的目标类型；
    在所述目标类型为预设检测类型的情况下，根据所述候选目标的深度信息，获取所述候选目标的起始位置。
  3. 根据权利要求1所述的方法，，在根据所述候选目标的起始位置，确定所述候选目标与安检机器人之间的起始距离之后，还包括：
    在所述候选目标与安检机器人之间的起始距离不满足预设要求的情况下，控制所述安检机器人移除对所述候选目标的锁定。
  4. 根据权利要求1所述的方法，其中，根据所述待检测目标的当前位置，控制所述安检机器人的安检设备跟随所述待检测目标的运动进行旋转，包括：
    实时获取所述待检测目标的当前位置，确定所述待检测目标的当前位置是否满足安检设备的安检要求；
    响应于所述待检测目标的当前位置满足所述安检设备的安检要求的确定结果，确定所述安检设备的视觉中心点与待检测目标之间的当前角度；
    根据所述当前角度，确定所述安检设备的旋转角度，使所述安检设备的视觉中心点与所述待检测目标的当前位置一致；
    响应于所述待检测目标的当前位置不满足所述安检设备的安检要求的确定结果，停止对所述待检测目标的跟踪安检，控制所述安检机器人的安检设备旋转，至所述安检机器人的检测范围覆盖检测通道的起始区域。
  5. 根据权利要求4所述的方法，其中，确定所述待检测目标的当前位置是否满足安检设备的安检要求，包括：
    根据所述待检测目标的当前位置，确定所述待检测目标与安检机器人的当 前距离；
    将当前距离与预设安检距离进行比较，确定所述当前距离是否超过预设安检距离；
    响应于所述当前距离超过所述预设安检距离的确定结果，确定所述待检测目标的当前位置不满足安检设备的安检要求。
  6. 根据权利要求4所述的方法，其中，确定所述待检测目标的当前位置是否满足安检设备的安检要求，还包括：
    根据所述待检测目标的当前位置，确定所述待检测目标是否在检测通道终点处；
    响应于所述待检测目标在所述检测通道终点处的确定结果，确定所述待检测目标的当前位置不满足安检设备的安检要求。
  7. 根据权利要求1所述的方法，其中，所述检测通道为L型通道。
  8. 根据权利要求1所述的方法，其中，所述安检设备采用太赫兹检测技术。
  9. 一种机器人安检装置，包括：
    候选目标获取模块，设置为获取检测通道起始区域的候选目标和所述候选目标的起始位置；
    起始距离确定模块，设置为根据所述候选目标的起始位置，确定所述候选目标与安检机器人之间的起始距离；
    待检测目标确定模块，设置为在所述起始距离满足预设要求的情况下，确定所述候选目标为待检测目标；
    机器人安检模块，设置为根据所述待检测目标的当前位置，控制所述安检机器人的安检设备跟随所述待检测目标的运动进行旋转，供所述安检机器人对所述待检测目标进行实时安检。
  10. 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现如权利要求1-8中任一所述的机器人安检方法。
  11. 一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行如权利要求1-8中任一所述的机器人安检方法。
PCT/CN2020/133912 2020-10-29 2020-12-04 机器人安检的方法、装置、设备及存储介质 WO2022088389A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011182933.9 2020-10-29
CN202011182933.9A CN112307952A (zh) 2020-10-29 2020-10-29 一种机器人安检的方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2022088389A1 true WO2022088389A1 (zh) 2022-05-05

Family

ID=74331774

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/133912 WO2022088389A1 (zh) 2020-10-29 2020-12-04 机器人安检的方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN112307952A (zh)
WO (1) WO2022088389A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115620358A (zh) * 2022-09-21 2023-01-17 联通数字科技有限公司 一种快递检测方法、装置及计算机可读存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2532080A (en) * 2014-11-10 2016-05-11 Epicuro Ltd Security inspection device image processing
CN106093937A (zh) * 2016-05-18 2016-11-09 中国电子科技集团公司第四十研究所 一种微波毫米波人体安检系统及安检方法
CN106645224A (zh) * 2016-12-26 2017-05-10 同方威视技术股份有限公司 安检设备及方法
CN111046810A (zh) * 2019-12-17 2020-04-21 联想(北京)有限公司 一种数据处理方法及处理装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2532080A (en) * 2014-11-10 2016-05-11 Epicuro Ltd Security inspection device image processing
CN106093937A (zh) * 2016-05-18 2016-11-09 中国电子科技集团公司第四十研究所 一种微波毫米波人体安检系统及安检方法
CN106645224A (zh) * 2016-12-26 2017-05-10 同方威视技术股份有限公司 安检设备及方法
CN111046810A (zh) * 2019-12-17 2020-04-21 联想(北京)有限公司 一种数据处理方法及处理装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115620358A (zh) * 2022-09-21 2023-01-17 联通数字科技有限公司 一种快递检测方法、装置及计算机可读存储介质
CN115620358B (zh) * 2022-09-21 2024-02-09 联通数字科技有限公司 一种快递检测方法、装置及计算机可读存储介质

Also Published As

Publication number Publication date
CN112307952A (zh) 2021-02-02

Similar Documents

Publication Publication Date Title
US11367330B2 (en) Information processing system, method and computer readable medium for determining whether moving bodies appearing in first and second videos are the same or not using histogram
CN111738240A (zh) 区域监测方法、装置、设备及存储介质
US12046044B2 (en) Information processing apparatus, control method, and program
US20190248390A1 (en) Track intrusion detection system
US11688078B2 (en) Video object detection
KR20190046351A (ko) 침입 탐지방법 및 그 장치
CN106023372A (zh) 基于人脸识别的图书馆出入管理系统
CN110139037A (zh) 对象监测方法及装置、存储介质和电子设备
WO2022088389A1 (zh) 机器人安检的方法、装置、设备及存储介质
CN109740526B (zh) 信号灯识别方法、装置、设备及介质
CN109636832A (zh) 停靠检测方法、装置、电子设备和存储介质
CN113570622A (zh) 一种障碍物确定方法、装置、电子设备以及存储介质
CN109188419B (zh) 障碍物速度的检测方法、装置、计算机设备及存储介质
CN113353072A (zh) 一种行车控制方法、装置、服务器及介质
CN112153270A (zh) 云台零点检测方法、装置、摄像机及存储介质
KR102448710B1 (ko) 딥러닝 기반 출차관리 방법 및 시스템
CN118675374B (zh) 基于实际位置的保障节点采集方法、装置、介质及设备
CN115285150A (zh) 一种轨道交通站台门智能防夹方法、装置、设备及介质
CN117315581A (zh) 机场站坪安全管理方法、装置、设备以及计算机存储介质
CN114120437A (zh) 机车乘务员的规范行为分析方法、装置、设备及存储介质
KR20240109225A (ko) 구조물 점검을 위한 제어 장치 및 그 동작 방법
CN116675084A (zh) 一种电梯异常上报方法、装置、电子设备和存储介质
CN114973113A (zh) 目标检测和追踪的方法及系统
CN118675374A (zh) 基于实际位置的保障节点采集方法、装置、介质及设备
CN118609182A (zh) 机场机坪人脸识别方法、装置、介质和设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20959548

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20959548

Country of ref document: EP

Kind code of ref document: A1