WO2019052212A1 - 扫描质量检测方法、控制器和装置 - Google Patents

扫描质量检测方法、控制器和装置 Download PDF

Info

Publication number
WO2019052212A1
WO2019052212A1 PCT/CN2018/087702 CN2018087702W WO2019052212A1 WO 2019052212 A1 WO2019052212 A1 WO 2019052212A1 CN 2018087702 W CN2018087702 W CN 2018087702W WO 2019052212 A1 WO2019052212 A1 WO 2019052212A1
Authority
WO
WIPO (PCT)
Prior art keywords
person
security
quality
tested
joint point
Prior art date
Application number
PCT/CN2018/087702
Other languages
English (en)
French (fr)
Inventor
马艳芳
宁洪志
田龙
Original Assignee
同方威视技术股份有限公司
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 同方威视技术股份有限公司 filed Critical 同方威视技术股份有限公司
Publication of WO2019052212A1 publication Critical patent/WO2019052212A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06398—Performance of employee with respect to a job function
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • 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
    • 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
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30241—Trajectory

Definitions

  • the present disclosure relates to the field of security technology, and in particular to a scanning quality detecting method, controller and device.
  • security inspectors In the security inspection process of civil aviation, subway and other places, security inspectors (or commonly known as security personnel, security inspectors) use hand-held security devices (such as hand-held metal detectors) to conduct physical inspection of the passing personnel is an essential part of the inspection .
  • the personal inspection operation procedure is usually carried out in order from top to bottom, from inside to outside, from front to back, and the ten major inspection sites on the human body should be strictly investigated.
  • the top ten key examination sites include: head, shoulder, chest, hand, wrist, buttocks, armpits, ankles, waist, abdomen, feet.
  • a scanning quality detecting method including: acquiring a position of a detected part of a measured person according to an image of the measured person; and obtaining a video of the personal inspection by the safety inspector according to the safety inspector The scanning coverage area of the security instrument; the scanning quality is determined according to the matching degree of the location of the key inspection part and the scanning coverage area of the security inspection instrument.
  • obtaining the location of the detected part of the tested subject includes: obtaining a position of the joint point according to the dynamic image data of the measured person; determining a contour of the human body of the measured person according to the position of the plurality of joint points; determining a focus according to the contour of the human body The location of the site being inspected.
  • the key examination site includes one or more of a head, a shoulder, a chest, a hand, a wrist, a hip, an underarm, a crotch, a waist, an abdomen, and a foot.
  • the joint points include a head, a right shoulder, a left shoulder, a shoulder center, a right elbow, a left elbow, a right wrist, a left wrist, a right hip, a left hip, a right knee, a left knee, a right ankle, and a left ankle. one or more.
  • the obtaining the position of the joint point includes at least one of the following: performing joint point analysis on the plurality of different static images of the measured person to obtain the position of the joint point; or performing joint on the dynamic video image of the measured person. Point analysis to get the position of the joint point.
  • determining the human body contour of the measured person includes: determining a distance between each two joint points according to the position of the joint point; and selecting a joint point belonging to the same measured person according to the distance between the joint points; The joint points of the same person to be tested determine the contour of the human body of the person being tested.
  • the screening of the joint points belonging to the same person to be tested includes: if the distance between the two joint points meets at least one of a predetermined maximum threshold or less than a predetermined minimum threshold, the two joint points are considered not to belong to the same person.
  • the method for determining the scan quality comprises: determining the detection completion rate according to the ratio of the number of the detected parts covered by the scanned coverage area to the total number of the detected parts.
  • the manner of determining the scan quality comprises: determining the detection completion rate according to the proportion of each of the focused parts to be covered by the scanned coverage area and the weight of the key part to be inspected.
  • the scanning quality detecting method further includes: sending an alarm information if the detection completion rate is lower than a predetermined scanning quality threshold.
  • the position of the key part to be inspected can be determined according to the image of the person to be tested, and then the area covered by the security instrument is obtained according to the working image of the safety inspector, and it is determined whether the security inspection device scans the key part to be inspected, thereby realizing
  • the effective evaluation of the quality of the safety inspectors has been carried out to improve the quality of the safety inspectors, and the effectiveness of the security inspection and the safety of the security inspection site have been improved.
  • a scan quality detection controller including: a detected part position acquisition module configured to acquire a position of a key detected part of the measured person according to an image of the measured person;
  • the area obtaining module is configured to acquire a scanning coverage area of the security device according to the video of the security inspector performing personal inspection on the measured person;
  • the scanning quality determining module is configured to be according to the location of the key detected part and the scanning coverage area of the security inspection instrument The degree of matching determines the quality of the scan.
  • the detected part position obtaining module includes: a joint point position acquiring unit configured to acquire a position of the joint point according to the moving image data of the measured person; the human body contour determining unit is configured to be based on the positions of the plurality of joint points Determining a human body contour of the measured person; and a position determining unit configured to determine a position of the key examined portion according to the human body contour.
  • the joint point position obtaining unit is configured to perform at least one of the following operations: performing joint point analysis on the plurality of different static images of the measured person to obtain a position of the joint point; or, a dynamic video of the measured person The image is subjected to joint point analysis to obtain the position of the joint point.
  • the human body contour determining unit is configured to: determine a distance between each two joint points according to the position of the joint point; and select a joint point belonging to the same measured person according to the distance between the joint points; The joint point of a measured person determines the contour of the human body of the person being tested.
  • the scan quality determining module is configured to determine the detection completion rate according to a ratio of the number of the detected parts covered by the scanned coverage area to the total number of the detected parts.
  • the scan quality determining module is configured to: determine the detection completion rate according to the proportion of each of the focused detected parts covered by the scanned coverage area and the weight of the focused detected part.
  • the scan quality detection controller further includes: an alarm module configured to issue the alarm information when the detection completion rate is lower than a predetermined scan quality threshold.
  • Such a scanning quality detecting controller can determine the position of the key part to be inspected according to the image of the person to be tested, and then obtain the area covered by the security device according to the working image of the safety inspector, and determine whether the security inspection device scans the key part to be inspected. Thereby, the effective evaluation of the safety inspector's work quality is achieved, the purpose of improving the quality of the safety inspector is improved, and the effectiveness of the security inspection and the safety of the security inspection site are improved.
  • a scan quality detection controller comprising: a memory; and a processor coupled to the memory, the processor being configured to perform any of the above mentioned based on the instructions stored in the memory A scanning quality detection method.
  • Such a controller realizes an effective evaluation of the safety inspector's work quality, achieves the purpose of improving the quality of the safety inspector's work, and improves the effectiveness of the security inspection and the safety of the security inspection site.
  • a computer readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of any one of the scanning quality detection methods mentioned above.
  • Such a computer readable storage medium realizes an effective evaluation of the quality of the safety inspector by executing the program instructions thereon, and achieves the purpose of improving the quality of the safety inspector, and improves the effectiveness of the security inspection and the security of the security inspection site.
  • a scan quality detecting apparatus including: a first image capturing device for acquiring an image including a measured person; and a second image capturing device for acquiring a security inspector pair A video of a person performing a personal inspection; and, any of the above scanning quality detection controllers.
  • Such a scanning quality detecting device can acquire the working video of the image of the person to be tested and the safety inspector, and then determine the position of the key part to be inspected according to the image of the person to be tested, and then acquire the area covered by the security device according to the working image of the safety inspector. Determine whether the security inspection device scans the key inspection sites in place, thus achieving an effective assessment of the safety inspector's work quality, improving the quality of the safety inspectors' work, and improving the effectiveness of the security inspection and the security of the security inspection site.
  • FIG. 1 is a schematic diagram of some embodiments of a scan quality detection controller of the present disclosure.
  • FIG. 2 is a schematic diagram of still other embodiments of a scan quality detection controller of the present disclosure.
  • FIG. 3 is a flow chart of some embodiments of a scan quality detection method of the present disclosure.
  • FIG. 4 is a flow chart of still another embodiment of a scan quality detection method of the present disclosure.
  • FIG. 5 is a schematic diagram of key position in the scanning quality detecting method of the present disclosure.
  • FIG. 6 is a schematic diagram showing some embodiments of displaying a human body being covered in the scanning quality detecting method of the present disclosure.
  • FIG. 7 is a schematic diagram of still further embodiments of a scan quality detection controller of the present disclosure.
  • FIG. 8 is a schematic diagram of some embodiments of a detected location location acquisition module in a scan quality detection controller of the present disclosure.
  • FIG. 9 is a schematic diagram of some embodiments of a scan quality detecting device of the present disclosure.
  • FIG. 10 is a schematic diagram of some embodiments of a deployment of a scan quality detection device of the present disclosure.
  • the scan quality detection controller includes a memory 110 and a processor 120.
  • the memory 110 can be a magnetic disk, flash memory or any other non-volatile storage medium.
  • the memory is used to store instructions in a corresponding embodiment of the scanning quality detecting method below.
  • the processor 120 is coupled to the memory 110 and can be implemented as one or more integrated circuits, such as a microprocessor or a microcontroller.
  • the processor 120 is configured to execute instructions stored in the memory, enabling an effective evaluation of the quality of the security inspector's work.
  • the scan quality detection controller may also be as shown in FIG. 2, and the scan quality detection controller 200 includes a memory 210 and a processor 220. Processor 220 is coupled to memory 210 via BUS bus 230.
  • the scan quality detection controller 200 can also be connected to the external storage device 250 via the storage interface 240 to invoke external data, and can also be connected to the network or another computer system (not shown) via the network interface 260. The transmission and execution flow of signaling is not described in detail here.
  • the present disclosure also provides a computer readable storage medium having stored thereon computer program instructions that, when executed by a processor, implement the steps of the method in a corresponding embodiment of the scan quality detection method.
  • a processor implements the steps of the method in a corresponding embodiment of the scan quality detection method.
  • embodiments of the present disclosure can be provided as a method, apparatus, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware aspects. Moreover, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code. .
  • FIG. 1 A flow chart of some embodiments of the scan quality detection method of the present disclosure is shown in FIG.
  • the position of the detected part of the subject is obtained based on the image of the person to be tested.
  • the determined position may be based on a predetermined standing position of the person to be tested when performing the security check, and the spatial position and spatial coordinates of the highlighted part when the measured person stands in the standing position may also be The position and coordinates of the person to be measured are moved in accordance with the movement of the person being measured.
  • the contour of the measured person may be obtained according to the acquired image of the measured person, and then the key detected part is positioned on the contour to obtain the focused part of the measured person in the contour of the measured person. position.
  • the focused examination site may include one or more of a head, a shoulder, a chest, a hand, a wrist, a hip, an underarm, a crotch, a waist, an abdomen, or a foot, which may be specific to a security situation. Choose and adjust as needed.
  • the scan coverage area of the security device is obtained based on the video of the security inspector performing a personal inspection on the person being tested.
  • the security inspector may first identify the security instrument in the video of the personal inspection of the test subject, obtain the scan track of the security tester, and determine the security tester according to the width or scan width of the preset security tester. Scan the coverage area.
  • the scan quality is determined based on the degree of matching of the position of the focused portion to the scan coverage area of the security device. If the scanning coverage area of the security device completely covers all the key parts to be inspected, it is determined that the scanning quality is high; if the scanning coverage area of the security inspection instrument fails to completely cover all the key inspection parts, the number of parts to be inspected may be covered according to the number or The ratio measures the quality of the scan. In some embodiments, if the scan quality is unsatisfactory, an alert message may be sent to alert the security inspector to rescan. In some embodiments, the acquired scan quality can also be used as an important indicator for the safety inspector's assessment.
  • the position of the key part to be inspected can be determined according to the image of the person to be tested, and then the area covered by the security instrument is obtained according to the working image of the safety inspector, and it is determined whether the security inspection device scans the key part to be inspected. Therefore, the effective evaluation of the quality of the safety inspectors is achieved, the purpose of improving the quality of the safety inspectors is improved, and the effectiveness of the security inspection and the safety of the security inspection site are improved.
  • the position of the joint site may be determined by first acquiring the position of the joint point and then constructing the contour of the human body based on the position of the joint point.
  • the method can reduce the inaccurate contour analysis caused by the occlusion, and can also avoid the positioning error of the key detected part caused by the difference in the body proportion, and improve the positioning of the key detected part. accuracy.
  • the acquired image or video may be coordinate-adjusted according to the position of the set image capturing device, and the error caused by the difference in the angle between the acquired image of the detected part and the personal inspection video may be corrected.
  • the acquired image may be a static image of a plurality of frames, such as capturing a multi-frame image when the measured person passes through the security channel, and determining the position of the joint point of the measured person by comparing and analyzing the multi-frame image; the acquired image It can also be a video image, such as a video that moves when the person being tested passes through the security check channel, and determines the position of the joint point of the measured person by analyzing the motion of the measured person.
  • the image data of the measured person can be obtained by using the image capturing device in the entrance of the security check channel or the channel, thereby reducing the hardware modification cost and facilitating the popularization and application.
  • a predetermined distance may be set that is the maximum height, width, or other threshold determined by experimental data, practical experience, etc., that helps to increase the point of attachment of the joint. The distance between each joint point is obtained, and the distance between the joint points is compared with a predetermined distance. If the distance between the joint points is greater than the predetermined distance, the joint point is considered to belong to a different person.
  • a predetermined minimum distance may also be set, and if the distance between the joint points is less than the predetermined minimum distance, the joint point is considered to belong to a different person.
  • a predetermined horizontal distance, a predetermined vertical distance, and the like may also be set as a threshold for determining whether the joint point belongs to the same person.
  • the predetermined horizontal distance is related to the vertical distance between the joint points under normal conditions, and the predetermined horizontal distance is related to the horizontal distance between the joint points under normal conditions, thereby performing the distance between the joint points from the horizontal and vertical directions. Compare and improve the accuracy of joint point screening.
  • the joint points belonging to the same person can be selected from the acquired joint points, and the contour of the human body can be determined according to the determined joint points belonging to the same person, thereby improving the accuracy of the determined position of the key examined portion.
  • the joint point position may be used in combination with the contour of the human body in the image to determine the person to which the joint point belongs. For example, if the joint points of the two joint points do not intersect, it is considered to belong to different people, thereby improving the joint. The accuracy of point attribution analysis.
  • FIG. 4 is a flow chart of still another embodiment of a scan quality detection method of the present disclosure.
  • step 401 the position of the joint point in the map is obtained from a dynamic video image containing the measured person or a plurality of different still images.
  • step 402 the distance between the joint points is determined based on the position of the joint point.
  • the joint points belonging to the same person to be tested are selected according to the distance between the joint points.
  • the joint points can be screened using any of the methods mentioned above.
  • the human contour of the subject is determined based on the joint points belonging to the same person to be tested.
  • the joint points can be classified according to their location.
  • the joint points can be as shown in Figure 5, including the head, right shoulder, left shoulder, shoulder center, right elbow, left elbow, right wrist, left wrist, right hip, left hip, right knee, left One or more of the knee, right ankle, and left ankle.
  • step 405 the position of the focused portion to be inspected is determined based on the determined contour of the human body.
  • the key parts to be examined may include the head, shoulders, chest, hands, wrists, buttocks, underarms, ankles, waist, abdomen, feet, and the like. In some embodiments, adjustments can be made depending on the application and actual needs.
  • step 406 a video of the personal inspection of the person being inspected by the security inspector is obtained, and the position of the security instrument in the video is determined based on the deep learning, and then the motion track of the security device is analyzed to determine the scanning coverage area of the security device.
  • the scan quality is determined based on the degree of matching of the position of the focused portion to the scan coverage area of the security device.
  • the left and right are respectively two display effects, and the circle identifies the key part to be inspected (the key part to be inspected can be repeated with each joint point), and the circled circle indicates that the position is covered by the scanning coverage area of the security inspection instrument.
  • the circle with ⁇ indicates that the position is not covered by the scanning coverage area of the security instrument.
  • the number of the selected parts to be covered may be determined according to the key detected part covered by the scanned coverage area, thereby determining the number of the covered parts to be covered and the total number of parts to be inspected.
  • the ratio is determined to determine the completion rate of the test; the weight of each key spot to be inspected can also be set, and the sum of the weights of the covered parts to be inspected can be determined as the detection completion rate; it can also be determined that each key spot is scanned and covered.
  • the ratio of the area coverage is calculated by multiplying the coverage ratio by the weight of the corresponding key detected part, and the weighted value of each key detected part covered by the scanned coverage area is obtained, and all the weighted values are added to determine the detection completion rate.
  • each of the key inspection sites may be an area, and each key inspection site may be covered by the scanning coverage area of the security inspection device according to the location of the key inspection site and the scanning coverage area of the security inspection device. proportion.
  • the detection completion rate is determined according to the proportion covered by the scanned coverage area of each key inspection site, or the detection completion rate can be determined according to the weight of each key inspection site, thereby achieving a more detailed work quality of the safety inspector. evaluation of.
  • the non-contact joint position acquisition method can be used to model the key parts of the personal safety inspection, and the safety inspector work for the personal inspection can be completed without adding additional assessment procedures and assessing human input. The quality is assessed without affecting the efficiency of the security channel.
  • the security inspector's work quality can be detected in real time.
  • the alarm information is sent in time to remind the security inspector to re-scan, thereby improving the security quality and avoiding potential security risks.
  • the detected part position acquisition module 701 can acquire the position of the focused subject to be tested based on the image of the person to be tested.
  • the determined position may be based on a predetermined standing position of the person to be tested when performing the security check, and the spatial position and spatial coordinates of the highlighted part when the measured person stands in the standing position may also be The position and coordinates of the person to be measured are moved in accordance with the movement of the person being measured.
  • the contour of the measured person may be obtained according to the acquired image of the measured person, and then the focused detected part is positioned on the contour to obtain the position of the tested part of the tested subject.
  • the scan coverage area acquisition module 702 can acquire the scan coverage area of the security device according to the video that the security inspector performs a personal inspection on the test subject.
  • the security inspector may first identify the security instrument in the video of the personal inspection of the test subject, obtain the scan track of the security tester, and determine the security tester according to the width or scan width of the preset security tester. Scan the coverage area.
  • the scan quality determination module 703 can determine the scan quality based on the degree of matching of the position of the focused portion to the scan coverage area of the security device.
  • Such a scanning quality detecting controller can determine the position of the key part to be inspected according to the image of the person to be tested, and then obtain the area covered by the security device according to the working image of the safety inspector, and determine whether the security inspection device scans the key part to be inspected. Thereby, the effective evaluation of the safety inspector's work quality is achieved, the purpose of improving the quality of the safety inspector is improved, and the effectiveness of the security inspection and the safety of the security inspection site are improved.
  • the detected part position obtaining module 701 can determine the position of the joint point of the tested person according to the acquired multi-frame static image (such as capturing a multi-frame image when the measured person passes through the security inspection channel);
  • the location location acquisition module 701 can also determine the location of the joint point of the measured person by analyzing the motion of the measured person according to the acquired video image (such as the video that is moved when the measured person passes through the security inspection channel).
  • Such a scanning quality detecting controller can acquire the image data of the measured person by using the image capturing device in the entrance of the security check channel or the channel, thereby reducing the hardware transformation cost and facilitating the popularization and application.
  • FIG. 8 is a schematic diagram of some embodiments of a detected location location acquisition module in a scan quality detection controller of the present disclosure.
  • the off-node position acquisition unit 801 can acquire the position of the joint point in the map based on the dynamic video image containing the measured person or a plurality of different still images.
  • the human body contour determining unit 802 is capable of determining the human body contour of the measured person based on the joint point.
  • the position determining unit 803 is capable of determining the position of the focused portion to be inspected based on the determined contour of the human body.
  • the scanning quality detecting controller adopts the method of first acquiring the position of the joint point and reconstructing the contour to perform the positioning of the key detected part, and can reduce the inaccurate contour analysis caused by the occlusion, and can also reduce the inaccurate contour analysis caused by the occlusion. Avoid the positioning error of the key parts to be detected caused by the difference in the body's body proportion, and improve the accuracy of the location of the key parts to be inspected.
  • the human body contour determining unit 802 needs to distinguish the acquired joint points to determine the person to which the joint point belongs.
  • a predetermined distance may be set that is the maximum height, width, or other value determined from experimental data, practical experience, and the like. The distance between each joint point is obtained, and the distance between the joint points is compared with a predetermined distance. If the distance between the joint points is greater than the predetermined distance, the joint point is considered to belong to a different person.
  • a predetermined minimum distance may also be set, and if the distance between the joint points is less than the predetermined minimum distance, the joint points are considered to belong to different people.
  • a predetermined horizontal distance, a predetermined vertical distance, and the like may also be set as a threshold for determining whether the joint point belongs to the same person.
  • the predetermined horizontal distance is related to the vertical distance between the joint points under normal conditions, and the predetermined horizontal distance is related to the horizontal distance between the joint points under normal conditions, thereby comparing the joint point distances from the horizontal and vertical directions, and improving the joint The accuracy of the point screening.
  • the scanning quality detecting controller can select the joint points belonging to the same person from the acquired joint points, and then determine the contour of the human body according to the determined joint points belonging to the same person, thereby improving the accuracy of determining the position of the key detected parts. .
  • the human body contour determining unit 802 can be configured to determine the person to which the joint point belongs by using the joint point to analyze the human body contour in the image, for example, if the two joint points belong to the human body without intersection point, the attribution is considered Improve the accuracy of joint point attribution analysis for different people.
  • the scan quality determining module 703 may determine the number of the highlighted parts to be covered according to the key detected part covered by the scanned coverage area, thereby determining the number of the covered parts to be covered.
  • the proportion of the total number of inspection parts is determined to determine the detection completion rate; the weight of each key inspection site may be set, and the ratio of the sum of the weights of the covered key inspection parts to the total weight is determined, and the detection completion rate is used; It is also possible to determine the proportion of each focused part to be covered by the scanned coverage area, calculate the product of the coverage ratio and the weight of the corresponding key inspection part, and obtain the weighted value of each key inspection part covered by the scanning coverage area, and The sum of all the weight values determines the detection completion rate.
  • each of the key inspection sites may be an area
  • the scan quality determination module 703 may determine, according to the location of the key inspection site and the scanning coverage area of the security device, that each of the key inspection sites is scanned by the security inspection device.
  • the ratio covered by the coverage area is determined according to the proportion covered by the scanned coverage area of each key inspection part, or the detection completion rate can be determined according to the weight of each key inspection part, thereby realizing the safety inspector A more detailed assessment of the quality of work.
  • Such a scanning quality detecting controller can model the key parts of the personal safety inspection by using the non-contact joint point position capturing method, and realize the safety of the personal inspection without increasing the additional examination process and the input of the manpower.
  • the assessment of the quality of the inspector's work does not affect the efficiency of the security inspection passage.
  • the scan quality detection controller can also include an alert module.
  • the scanning quality detection controller can detect the quality of the safety inspector in real time. When the quality of the security inspection fails, the alarm module sends out an alarm message in time to remind the security inspector to re-scan, thereby improving the quality of the security inspection and avoiding potential safety hazards.
  • the first image capturing device 901 can acquire an image including a measured person, and the image can be a plurality of different static pictures or a video image.
  • the image capture device can be a camera or a video camera. In some embodiments, the image capture device can be deployed at the entrance, interior, or exit of the security channel.
  • the second image capture device 902 can acquire a video of a personal inspection by the security inspector on the person being tested.
  • the second image capture device 902 can be a camera that can be located near a security inspector to capture the location of the security instrument's movement trajectory, such as the rear side of the security inspector.
  • the first image acquisition device and the second image acquisition device can be the same device.
  • the scan quality detection controller 903 may be any one of the scan quality detection controllers mentioned above, configured to monitor the quality of the safety inspector based on the image and video data acquired from the first and second image acquisition devices. .
  • Such a scanning quality detecting device can acquire the working video of the image of the person to be tested and the safety inspector, and then determine the position of the key part to be inspected according to the image of the person to be tested, and then acquire the area covered by the security device according to the working image of the safety inspector. Determine whether the security inspection device scans the key inspection sites in place, thus achieving an effective assessment of the safety inspector's work quality, improving the quality of the safety inspectors' work, and improving the effectiveness of the security inspection and the security of the security inspection site.
  • the measured person 1001 passes through the security check channel in the direction 1000, and the image including the measured person 1001 is acquired by the camera 1004 and sent to the server 1006 for analysis.
  • the server 1006 is capable of executing any of the scanning quality detecting methods mentioned above.
  • the security inspector 1002 carries the personal inspection of the person to be tested 1001, and the camera 1004 acquires the inspection video and sends it to the server 1006 for analysis.
  • the acquired images may be stored in storage device 1005 for archival and invocation analysis.
  • Such a scanning quality detecting device realizes the evaluation of the work quality of the personal inspection safety inspector without increasing the additional examination process and the manpower, and does not affect the efficiency of the security inspection passage, and improves the reliability of the security inspection;
  • a background device for comparative analysis reduces the performance bottleneck of data transmission and helps improve execution efficiency.
  • the scan quality detecting device may further include an alarm device capable of receiving the alarm information from the scan quality detection controller, and determining that the security check is not in place, thereby prompting the security inspector to perform the scan again, thereby improving the quality of the security check and avoiding Causes a safety hazard.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.
  • the methods and apparatus of the present disclosure may be implemented in a number of ways.
  • the methods and apparatus of the present disclosure may be implemented in software, hardware, firmware or any combination of software, hardware, firmware.
  • the above-described sequence of steps for the method is for illustrative purposes only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless otherwise specifically stated.
  • the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine readable instructions for implementing a method in accordance with the present disclosure.
  • the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Multimedia (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Human Computer Interaction (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Security & Cryptography (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Alarm Systems (AREA)
  • Image Analysis (AREA)

Abstract

本公开提出一种扫描质量检测方法、控制器和装置，涉及安检领域。本公开的一种扫描质量检测方法包括：根据被测人的图像获取被测人的重点被检部位的位置；根据安全检查员对被测人进行人身检查的视频获取安检仪的扫描覆盖区域；根据重点被检部位的位置与安检仪的扫描覆盖区域的匹配程度确定扫描质量。通过这样的方法，能够根据被测人的图像确定其重点被检部位的位置，再根据安全检查员的工作图像获取安检仪覆盖的区域，确定安检仪对重点被检部位是否扫描到位，从而实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。

Description

扫描质量检测方法、控制器和装置
相关申请的交叉引用
本公开是以CN申请号为201710840241.0,申请日为2017年9月18日的申请为基础，并主张其优先权，该CN申请的公开内容在此作为整体引入本公开中。
技术领域
本公开涉及安检技术领域，特别是一种扫描质量检测方法、控制器和装置。
背景技术
在民航、地铁等场所的安检流程中，安全检查员(或俗称为安检人员、安检员)使用手持安检仪(例如手持式金属探测仪)对通过的人员进行人身检查是必不可少的重要环节。人身检查操作程序通常是以由上到下、由里到外、由前到后的顺序进行检查，对人身体上的十大重点检查部位要进行严查。通常情况下，十大重点检查部位包括：头部、肩胛、胸部、手部、手腕、臀部、腋下、裆部、腰部、腹部、脚。
由于人的个性特征、生理疲劳因素、心理疲劳因素、生理节律以及其它事件因素等的影响，安全检查员作业的可靠性会受到影响，因此现在安全检查员的工作多采用倒班制，例如一个班组内部同样岗位的工作人员每一到两个小时相互替换，以尽可能保障安全检查员的精力。但是，这样的方式起到的作用有限，不能够对安全检查员的工作质量进行有效的监控和评估。
发明内容
本公开的一个目的在于监控安全检查员进行人身检查时的扫描质量，以提高安全检查员的工作质量。
根据本公开的一些实施例，提出一种扫描质量检测方法，包括：根据被测人的图像获取被测人的重点被检部位的位置；根据安全检查员对被测人进行人身检查的视频获取安检仪的扫描覆盖区域；根据重点被检部位的位置与安检仪的扫描覆盖区域的匹配程度确定扫描质量。
可选地，获取被测人重点被检部位的位置包括：根据被测人的动态图像数据获取关节点的位置；根据多个关节点的位置确定被测人的人体轮廓；根据人体轮廓确定重 点被检部位的位置。
可选地，重点被检部位包括头部、肩胛、胸部、手部、手腕、臀部、腋下、裆部、腰部、腹部、脚中的一个或多个。
可选地，关节点包括头部、右肩膀、左肩膀、肩中心、右手肘、左手肘、右手腕、左手腕、右髋、左髋、右膝、左膝、右脚踝、左脚踝中的一个或多个。
可选地，获取关节点的位置包括以下至少一种方式：对被测人的多张不同的静态图像进行关节点分析，获取关节点的位置；或，对被测人的动态视频图像进行关节点分析，获取关节点的位置。
可选地，确定被测人的人体轮廓包括：根据关节点的位置确定每两个关节点之间的距离；根据关节点之间的距离筛选出属于同一个被测人的关节点；根据属于同一个被测人的关节点确定被测人的人体轮廓。
可选地，筛选出属于同一个被测人的关节点包括：若两个关节点之间的距离符合大于预定最大阈值或小于预定最小阈值中的至少一种，则认为两个关节点不属于同一个人。
可选地，确定扫描质量的方式包括：根据被扫描覆盖区域覆盖的重点被检部位的个数占全部重点被检部位数量的比例确定检测完成率。
可选地，确定扫描质量的方式包括：根据各个重点被检部位被扫描覆盖区域覆盖的比例和重点被检部位的权重确定检测完成率。
可选地，扫描质量检测方法还包括：若检测完成率低于预定扫描质量阈值，则发出告警信息。
通过这样的方法，能够根据被测人的图像确定其重点被检部位的位置，再根据安全检查员的工作图像获取安检仪覆盖的区域，确定安检仪对重点被检部位是否扫描到位，从而实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。
根据本公开的另一些实施例，提出一种扫描质量检测控制器，包括：被检部位位置获取模块，被配置为根据被测人的图像获取被测人的重点被检部位的位置；扫描覆盖区域获取模块，被配置为根据安全检查员对被测人进行人身检查的视频获取安检仪的扫描覆盖区域；扫描质量确定模块，被配置为根据重点被检部位的位置与安检仪的扫描覆盖区域的匹配程度确定扫描质量。
可选地，被检部位位置获取模块包括：关节点位置获取单元，被配置为根据被测 人的动态图像数据获取关节点的位置；人体轮廓确定单元，被配置为根据多个关节点的位置确定被测人的人体轮廓；和位置确定单元，被配置为根据人体轮廓确定重点被检部位的位置。
可选地，关节点位置获取单元被配置为执行以下至少一种操作：对被测人的多张不同的静态图像进行关节点分析，获取关节点的位置；或，对被测人的动态视频图像进行关节点分析，获取关节点的位置。
可选地，人体轮廓确定单元被配置为：根据关节点的位置确定每两个关节点之间的距离；根据关节点之间的距离筛选出属于同一个被测人的关节点；根据属于同一个被测人的关节点确定被测人的人体轮廓。
可选地，扫描质量确定模块被配置为：根据被扫描覆盖区域覆盖的重点被检部位的个数占全部重点被检部位数量的比例确定检测完成率。
可选地，扫描质量确定模块被配置为：根据各个重点被检部位被扫描覆盖区域覆盖的比例和重点被检部位的权重确定检测完成率。
可选地，扫描质量检测控制器还包括：告警模块，被配置为当检测完成率低于预定扫描质量阈值时，发出告警信息。
这样的扫描质量检测控制器能够根据被测人的图像确定其重点被检部位的位置，再根据安全检查员的工作图像获取安检仪覆盖的区域，确定安检仪对重点被检部位是否扫描到位，从而实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。
根据本公开的又一些实施例，提出一种扫描质量检测控制器，包括：存储器；以及耦接至存储器的处理器，处理器被配置为基于存储在存储器的指令执行上文中提到的任意一种扫描质量检测方法。
这样的控制器实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。
根据本公开的再一些实施例，提出一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现上文中提到的任意一种扫描质量检测方法的步骤。
这样的计算机可读存储介质通过执行其上的程序指令，实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。
另外，根据本公开的一些实施例，提出一种扫描质量检测装置，包括：第一图像采集设备，用于获取包括被测人的图像；第二图像采集设备，用于获取安全检查员对被测人进行人身检查的视频；和，上文中任意一种扫描质量检测控制器。
这样的扫描质量检测装置能够获取被测人图像和安全检查员的工作视频，进而根据被测人的图像确定其重点被检部位的位置，再根据安全检查员的工作图像获取安检仪覆盖的区域，确定安检仪对重点被检部位是否扫描到位，从而实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。
附图说明
此处所说明的附图用来提供对本公开的进一步理解，构成本公开的一部分，本公开的示意性实施例及其说明用于解释本公开，并不构成对本公开的不当限定。在附图中：
图1为本公开的扫描质量检测控制器的一些实施例的示意图。
图2为本公开的扫描质量检测控制器的另一些实施例的示意图。
图3为本公开的扫描质量检测方法的一些实施例的流程图。
图4为本公开的扫描质量检测方法的另一些实施例的流程图。
图5为本公开的扫描质量检测方法中关键点位置的示意图。
图6为本公开的扫描质量检测方法中显示人体被覆盖情况的一些实施例的示意图。
图7为本公开的扫描质量检测控制器的又一些实施例的示意图。
图8为本公开的扫描质量检测控制器中被检部位位置获取模块的一些实施例的示意图。
图9为本公开的扫描质量检测装置的一些实施例的示意图。
图10为本公开的扫描质量检测装置部署情况的一些实施例的示意图。
具体实施方式
下面通过附图和实施例，对本公开的技术方案做进一步的详细描述。
本公开扫描质量检测控制器的一些实施例的结构示意图如图1所示。扫描质量检测控制器包括存储器110和处理器120。其中：存储器110可以是磁盘、闪存或其它 任何非易失性存储介质。存储器用于存储下文中扫描质量检测方法的对应实施例中的指令。处理器120耦接至存储器110，可以作为一个或多个集成电路来实施，例如微处理器或微控制器。该处理器120用于执行存储器中存储的指令，能够实现对安全检查员工作质量的有效评估。
在一些实施例中，扫描质量检测控制器还可以如图2所示，扫描质量检测控制器200包括存储器210和处理器220。处理器220通过BUS总线230耦合至存储器210。该扫描质量检测控制器200还可以通过存储接口240连接至外部存储装置250以便调用外部数据，还可以通过网络接口260连接至网络或者另外一台计算机系统(未标出)。信令的传输和执行流程此处不再进行详细介绍。
在该实施例中，通过存储器存储数据指令，再通过处理器处理上述指令，能够实现对安全检查员工作质量的有效评估和监督。
在另一些实施例中，本公开还提出一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现扫描质量检测方法对应实施例中的方法的步骤。本领域内的技术人员应明白，本公开的实施例可提供为方法、装置或计算机程序产品。因此，本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用非瞬时性存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本公开的扫描质量检测方法的一些实施例的流程图如图3所示。
在步骤301中，根据被测人的图像获取被测人的重点被检部位的位置。在一些实施例中，确定的位置可以是以预定的进行安检时被测人的站立位置为基准，当被测人站在该站立位置时重点被检部位的空间位置、空间坐标，还可以是以被测人为基准的位置、坐标，其空间位置随被测人的移动而移动。在一些实施例中，可以根据获取的被测人的图像获取被测人的轮廓，再在轮廓上进行重点被检部位定位，得到被测人的重点被检部位的在被测人轮廓中的位置。在一些实施例中，重点被检部位可以包括头部、肩胛、胸部、手部、手腕、臀部、腋下、裆部、腰部、腹部或脚中的一个或多个，可以根据安检场合的具体需要而选择和调整。
在步骤302中，根据安全检查员对被测人进行人身检查的视频获取安检仪的扫描覆盖区域。在一些实施例中，可以先在安全检查员对被测人进行人身检查的视频中识别安检仪，获取安检仪的扫描轨迹，再结合预先设定的安检仪的宽度或扫描宽度确定 安检仪的扫描覆盖区域。
在步骤303中，根据重点被检部位的位置与安检仪的扫描覆盖区域的匹配程度确定扫描质量。若安检仪的扫描覆盖区域完全覆盖所有重点被检部位，则确定扫描质量高；若安检仪的扫描覆盖区域未能完全覆盖所有重点被检部位，则可以根据重点被检部位被覆盖的数量或比例衡量扫描质量。在一些实施例中，若扫描质量不合格，还可以发出告警信息提醒安全检查员重新扫描。在一些实施例中，还可以将获取的扫描质量作为对安全检查员考核的重要指标。
由于每个人的体型不同，即使站在相同的被扫描区域进行人身检查，其重点被检部位在空间中的位置也并不相同。通过上文实施例中的，能够根据被测人的图像确定其重点被检部位的位置，再根据安全检查员的工作图像获取安检仪覆盖的区域，确定安检仪对重点被检部位是否扫描到位，从而实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。
在一些实施例中，可以采取先获取关节点位置，再在关节点位置的基础上构建人体轮廓的方式来确定重点被检部位的位置。这样的方式与直接根据图像获取人体轮廓的方式相比，能够减少遮挡造成的轮廓解析不准确的情况，也能够避免人体身材比例不同造成的重点被检部位定位错误，提高重点被检部位定位的准确性。
在一些实施例中，可以根据设置的图像采集设备的位置对获取的图像或视频进行坐标调整，纠正由于获取的被检部位图像与人身检查视频的角度差异造成的误差。
在一些实施例中，获取的图像可以为多帧的静态图像，如被测人经过安检通道时捕捉多帧图像，通过对多帧图像的比较分析确定被测人关节点的位置；获取的图像还可以是视频图像，如被测人经过安检通道时走动的视频，通过对被测人动作的分析确定被测人关节点的位置。
通过这样的方法，能够利用安检通道入口或通道内的图像采集设备获取被测人的图像数据，降低硬件改造成本，有利于推广应用。
在一些实施例中，当获取的图像中包括多个人时，如安检通道中有多个人，需要对获取的关节点进行区分，确定关节点归属的人。在一些实施例中，可以设定预定距离，该预定距离为人体最大高度、宽度或其他的根据实验数据、实践经验等确定的有助于提高关节点归属人的阈值。获取每两个关节点之间的距离，将关节点之间的距离与预定距离进行比较，若关节点之间的距离大于预定距离，则认为关节点归属于不同的人。在一些实施例中，还可以设置预定最小距离，若关节点之间的距离小于预定最 小距离，则认为关节点归属于不同的人。在一些实施例中，还可以设置预定水平距离、预定垂直距离等来作为判断关节点是否属于同一个人的阈值。预定水平距离与正常情况下关节点之间的垂直距离相关，预定水平距离与正常情况下关节点之间的水平距离相关，从而从水平、竖直两个方向上对关节点之间的距离进行比较，提高关节点筛选的准确度。
通过这样的方法，能够从获取的关节点中筛选出归属于同一个人的关节点，进而根据确定的归属于同一个人的关节点确定人体轮廓，从而提高确定的重点被检部位位置的准确性。
在另一些实施例中，可以采用关节点位置结合图像中的人体轮廓进行分析的方式确定关节点归属的人，如两个关节点归属的人体没有相交点则认为归属于不同人，从而提高关节点归属分析的准确性。
图4为本公开的扫描质量检测方法的另一些实施例的流程图。
在步骤401中，根据包含被测人的动态视频图像或多张不同的静态图像获取图中关节点的位置。
在步骤402中，根据关节点的位置确定各个关节点之间的距离。
在步骤403中，根据关节点之间的距离筛选出属于同一个被测人的关节点。在一些实施例中，可以采用上文中提到的任意一种方法筛选关节点。
在步骤404中，根据属于同一个被测人的关节点确定被测人的人体轮廓。在一些实施例中，可以根据关节点的位置将其归类。在一些实施例中，关节点可以如图5所示，包括头部、右肩膀、左肩膀、肩中心、右手肘、左手肘、右手腕、左手腕、右髋、左髋、右膝、左膝、右脚踝、左脚踝中的一个或多个。在完成关节点分类后，将人体上相邻类别的关节点连接，确定被测人的人体轮廓。
在步骤405中，根据确定的人体轮廓确定重点被检部位的位置。重点被检部位可以包括头部、肩胛、胸部、手部、手腕、臀部、腋下、裆部、腰部、腹部、脚等。在一些实施例中，可以根据应用场合和实际需求进行调整。
在步骤406中，获取安全检查员对被测人进行人身检查的视频，基于深度学习确定视频中安检仪的位置，进而解析安检仪的运动轨迹，确定安检仪的扫描覆盖区域。
在步骤407中，根据重点被检部位的位置与安检仪的扫描覆盖区域的匹配程度确定扫描质量。如图6所示，左、右分别为两种显示效果，圆圈标识重点被检部位(重点被检部位可以与各个关节点重复)，圈中带√表明该位置被安检仪的扫描覆盖区域 覆盖，圈中带×表明该位置未被安检仪的扫描覆盖区域覆盖。
在一些实施例中，可以根据被扫描覆盖区域覆盖的重点被检部位确定被覆盖的重点被检部位的个数，进而确定被覆盖的重点被检部位的个数占重点被检部位总个数的比例，从而确定检测完成率；也可以设定各个重点被检部位的权重，确定被覆盖的重点被检部位的权重之和作为检测完成率；还可以确定每个重点被检部位被扫描覆盖区域覆盖的比例，计算该覆盖比例与对应的重点被检部位的权重的乘积，得到每个重点被检部位被扫描覆盖区域覆盖的加权值，将全部加权值相加确定检测完成率。
在另一些实施例中，每个重点被检部位可以是一个区域，可以根据重点被检部位的位置和安检仪的扫描覆盖区域确定每个重点被检部位被安检仪的扫描覆盖区域所覆盖的比例。接下来，根据每个重点被检部位被扫描覆盖区域所覆盖的比例确定检测完成率，或者可以配合每个重点被检部位的权重确定检测完成率，从而实现对安全检查员工作质量的更加细致的评估。
通过这样的方法，能够采用非接触式关节点位置捕获方法对人身安全检查的重点部位进行建模，实现了在不增加额外考核过程和考核人力投入的情况下，完成对人身检查安全检查员工作质量的评估，且不影响安检通道通过效率。
在一些实施例中，可以采用实时对安全检查员工作质量进行检测的方式，当安检质量不达标时及时发出告警信息，提醒安全检查员重新进行扫描，从而提高了安检质量，避免造成安全隐患。
图7为本公开的扫描质量检测控制器的一些实施例的示意图。被检部位位置获取模块701能够根据被测人的图像获取被测人的重点被检部位的位置。在一些实施例中，确定的位置可以是以预定的进行安检时被测人的站立位置为基准，当被测人站在该站立位置时重点被检部位的空间位置、空间坐标，还可以是以被测人为基准的位置、坐标，其空间位置随被测人的移动而移动。在一些实施例中，可以根据获取的被测人的图像获取被测人的轮廓，再在轮廓上进行重点被检部位定位，得到被测人的重点被检部位的位置。扫描覆盖区域获取模块702能够根据安全检查员对被测人进行人身检查的视频获取安检仪的扫描覆盖区域。在一些实施例中，可以先在安全检查员对被测人进行人身检查的视频中识别安检仪，获取安检仪的扫描轨迹，再结合预先设定的安检仪的宽度或扫描宽度确定安检仪的扫描覆盖区域。扫描质量确定模块703能够根据重点被检部位的位置与安检仪的扫描覆盖区域的匹配程度确定扫描质量。
这样的扫描质量检测控制器能够根据被测人的图像确定其重点被检部位的位置， 再根据安全检查员的工作图像获取安检仪覆盖的区域，确定安检仪对重点被检部位是否扫描到位，从而实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。
在一些实施例中，被检部位位置获取模块701能够根据获取的多帧静态图像(如被测人经过安检通道时捕捉多帧图像)，通过比较分析确定被测人关节点的位置；被检部位位置获取模块701也可以根据获取的视频图像(如被测人经过安检通道时走动的视频)，通过对被测人动作的分析确定被测人关节点的位置。
这样的扫描质量检测控制器能够利用安检通道入口或通道内的图像采集设备获取被测人的图像数据，降低硬件改造成本，有利于推广应用。
图8为本公开的扫描质量检测控制器中被检部位位置获取模块的一些实施例的示意图。关节点位置获取单元801能够根据包含被测人的动态视频图像或多张不同的静态图像获取图中关节点的位置。人体轮廓确定单元802能够根据关节点确定被测人的人体轮廓。位置确定单元803能够根据确定的人体轮廓确定重点被检部位的位置。
这样扫描质量检测控制器采用先获取关节点位置再构建轮廓的方式进行重点被检部位定位，与直接根据图像获取人体轮廓的方式相比，能够减少遮挡造成的轮廓解析不准确的情况，也能够避免人体身材比例不同造成的重点被检部位定位错误，提高重点被检部位定位的准确性。
在一些实施例中，当获取的图像中包括多个人时，如安检通道中有多个人，人体轮廓确定单元802需要对获取的关节点进行区分，确定关节点归属的人。在一些实施例中，可以设定预定距离，该预定距离为人体最大高度、宽度或其他的根据实验数据、实践经验等确定的值。获取每两个关节点之间的距离，将关节点之间的距离与预定距离进行比较，若关节点之间的距离大于预定距离，则认为关节点归属于不同的人。在一个实施例中，还可以设置预定最小距离，若关节点之间的距离小于预定最小距离，则认为关节点归属于不同的人。在一些实施例中，还可以设置预定水平距离、预定垂直距离等来作为判断关节点是否属于同一个人的阈值。预定水平距离与正常情况下关节点之间的垂直距离相关，预定水平距离与正常情况下关节点之间的水平距离相关，从而从水平和竖直两个方向上进行关节点距离比较，提高关节点筛选的准确度。
这样扫描质量检测控制器能够从获取的关节点中筛选出归属于同一个人的关节点，进而根据确定的归属于同一个人的关节点确定人体轮廓，从而提高确定的重点被检部位位置的准确性。
在另一些实施例中，人体轮廓确定单元802可以被配置为采用关节点结合图像中的人体轮廓进行分析的方式确定关节点归属的人，如两个关节点归属的人体没有相交点则认为归属于不同人，提高关节点归属分析的准确性。
在一些实施例中，扫描质量确定模块703可以根据被扫描覆盖区域覆盖的重点被检部位确定被覆盖的重点被检部位的个数，进而确定被覆盖的重点被检部位的个数占重点被检部位总个数的比例，从而确定检测完成率；也可以设定各个重点被检部位的权重，确定被覆盖的重点被检部位的权重之和占总权重的比例，并作为检测完成率；还可以确定每个重点被检部位被扫描覆盖区域覆盖的比例，计算该覆盖比例与对应的重点被检部位的权重的乘积，得到每个重点被检部位被扫描覆盖区域覆盖的加权值，将全部加权值相加确定检测完成率。
在另一些实施例中，每个重点被检部位可以是一个区域，扫描质量确定模块703可以根据重点被检部位的位置和安检仪的扫描覆盖区域确定每个重点被检部位被安检仪的扫描覆盖区域所覆盖的比例，进而根据每个重点被检部位被扫描覆盖区域所覆盖的比例确定检测完成率，或者可以配合每个重点被检部位的权重确定检测完成率，从而实现对安全检查员工作质量的更加细致的评估。
这样的扫描质量检测控制器能够采用非接触式关节点位置捕获方法对人身安全检查的重点部位进行建模，实现了在不增加额外考核过程和考核人力的投入的情况下，完成对人身检查安全检查员工作质量的评估，且不影响安检通道通过效率。
在一些实施例中，扫描质量检测控制器还可以包括告警模块。扫描质量检测控制器可以实时对安全检查员工作质量进行检测，当安检质量不通过时，告警模块及时发出告警信息，提醒安全检查员重新进行扫描，从而提高了安检质量，避免造成安全隐患。
图9为本公开的扫描质量检测装置的一些实施例的示意图。第一图像采集设备901能够获取包括被测人的图像，该图像可以是多帧不同的静态图片，也可以是视频图像。图像采集设备可以是照相机或者摄像机。在一些实施例中，图像采集设备可以部署在安检通道的入口、内部或出口。第二图像采集设备902能够获取安全检查员对被测人进行人身检查的视频。第二图像采集设备902可以是摄像机，可以位于安全检查员附近能够拍摄到安检仪移动轨迹的位置，如安全检查员的后侧方。在一些实施例中，第一图像采集设备和第二图像采集设备可以为同一个设备。扫描质量检测控制器903可以为上文中提到的任意一种扫描质量检测控制器，被配置为根据从第一、第二 图像采集设备获取的图像、视频数据对安全检查员的工作质量进行监控。
这样的扫描质量检测装置能够获取被测人图像和安全检查员的工作视频，进而根据被测人的图像确定其重点被检部位的位置，再根据安全检查员的工作图像获取安检仪覆盖的区域，确定安检仪对重点被检部位是否扫描到位，从而实现了对安全检查员工作质量的有效评估，达到提高安全检查员工作质量的目的，提高了安检的有效性和安检场所的安全性。
在一些实施例中，如图10所示，被测人1001按照方向1000经过安检通道，由摄像机1004获取包括被测人1001的图像，发送到服务器1006进行分析。服务器1006能够执行上文中提到的任意一种扫描质量检测方法。安全检查员1002手持安检仪1003对被测人1001进行人身检查，摄像机1004获取检查视频，并发送给服务器1006进行分析。在一些实施例中，获取的图像可以存储在存储设备1005中以便留档和调用分析。
这样的扫描质量检测装置实现了在不增加额外考核过程和考核人力的情况下，完成对人身检查安全检查员工作质量的评估，且不影响安检通道通过效率，提高了安检的可靠性；采用同一个后台设备进行对比分析，降低了数据传输的性能瓶颈，有利于提高执行效率。
在一些实施例中，扫描质量检测装置还可以包括告警器，能够接收来自扫描质量检测控制器的告警信息，及时确定安全检查未到位，从而提醒安全检查员重新进行扫描，提高了安检质量，避免造成安全隐患。
本公开是参照根据本公开实施例的方法、设备(系统)和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
至此，已经详细描述了本公开。为了避免遮蔽本公开的构思，没有描述本领域所公知的一些细节。本领域技术人员根据上面的描述，完全可以明白如何实施这里公开的技术方案。
可能以许多方式来实现本公开的方法以及装置。例如，可通过软件、硬件、固件或者软件、硬件、固件的任何组合来实现本公开的方法以及装置。用于所述方法的步骤的上述顺序仅是为了进行说明，本公开的方法的步骤不限于以上具体描述的顺序，除非以其它方式特别说明。此外，在一些实施例中，还可将本公开实施为记录在记录介质中的程序，这些程序包括用于实现根据本公开的方法的机器可读指令。因而，本公开还覆盖存储用于执行根据本公开的方法的程序的记录介质。
最后应当说明的是：以上实施例仅用以说明本公开的技术方案而非对其限制；尽管参照较佳实施例对本公开进行了详细的说明，所属领域的普通技术人员应当理解：依然可以对本公开的具体实施方式进行修改或者对部分技术特征进行等同替换；而不脱离本公开技术方案的精神，其均应涵盖在本公开请求保护的技术方案范围当中。

Claims (17)

  1. 一种扫描质量检测方法，包括：
    根据被测人的图像获取被测人的重点被检部位的位置；
    根据安全检查员对所述被测人进行人身检查的视频获取安检仪的扫描覆盖区域；
    根据所述重点被检部位的位置与所述安检仪的扫描覆盖区域的匹配程度确定扫描质量。
  2. 根据权利要求1所述的方法，其中，
    所述获取被测人重点被检部位的位置包括：
    根据被测人的动态图像数据获取关节点的位置；
    根据多个所述关节点的位置确定被测人的人体轮廓；
    根据所述人体轮廓确定所述重点被检部位的位置。
  3. 根据权利要求2所述的方法，其中，
    所述重点被检部位包括头部、肩胛、胸部、手部、手腕、臀部、腋下、裆部、腰部、腹部、脚中的一个或多个；
    和/或，
    所述关节点包括头部、右肩膀、左肩膀、肩中心、右手肘、左手肘、右手腕、左手腕、右髋、左髋、右膝、左膝、右脚踝、左脚踝中的一个或多个。
  4. 根据权利要求2所述的方法，其中，所述获取关节点的位置包括以下至少一种方式：
    对所述被测人的多张不同的静态图像进行关节点分析，获取关节点的位置；
    或，
    对所述被测人的动态视频图像进行关节点分析，获取关节点的位置。
  5. 根据权利要求4所述的方法，其中，所述确定被测人的人体轮廓包括：
    根据关节点的位置确定每两个关节点之间的距离；
    根据所述关节点之间的距离筛选出属于同一个被测人的关节点；
    根据属于同一个被测人的所述关节点确定所述被测人的人体轮廓。
  6. 根据权利要求5所述的方法，其中，所述筛选出属于同一个被测人的关节点包括：
    若两个关节点之间的距离符合大于预定最大阈值或小于预定最小阈值中的至少一种，则认为两个关节点不属于同一个人。
  7. 根据权利要求1所述的方法，其中，所述确定扫描质量的方式包括：
    根据被所述扫描覆盖区域覆盖的所述重点被检部位的个数占全部所述重点被检部位数量的比例确定检测完成率；
    或，
    根据各个所述重点被检部位被所述扫描覆盖区域覆盖的比例和所述重点被检部位的权重确定检测完成率。
  8. 根据权利要求7所述的方法，还包括：若所述检测完成率低于预定扫描质量阈值，则发出告警信息。
  9. 一种扫描质量检测控制器，包括：
    被检部位位置获取模块，被配置为根据被测人的图像获取被测人的重点被检部位的位置；
    扫描覆盖区域获取模块，被配置为根据安全检查员对所述被测人进行人身检查的视频获取安检仪的扫描覆盖区域；
    扫描质量确定模块，被配置为根据所述重点被检部位的位置与所述安检仪的扫描覆盖区域的匹配程度确定扫描质量。
  10. 根据权利要求9所述的控制器，其中，所述被检部位位置获取模块包括：
    关节点位置获取单元，被配置为根据被测人的动态图像数据获取关节点的位置；
    人体轮廓确定单元，被配置为根据多个所述关节点的位置确定被测人的人体轮廓；和，
    位置确定单元，被配置为根据所述人体轮廓确定所述重点被检部位的位置。
  11. 根据权利要求10所述的控制器，其中，所述关节点位置获取单元被配置为执行以下至少一种操作：
    对所述被测人的多张不同的静态图像进行关节点分析，获取关节点的位置；
    或，
    对所述被测人的动态视频图像进行关节点分析，获取关节点的位置。
  12. 根据权利要求11所述的控制器，其中，所述人体轮廓确定单元被配置为：
    根据所述关节点的位置确定每两个关节点之间的距离；
    根据所述关节点之间的距离筛选出属于同一个被测人的关节点；
    根据属于同一个被测人的关节点确定所述被测人的人体轮廓。
  13. 根据权利要求9所述的控制器，其中，所述扫描质量确定模块被配置为：
    根据被所述扫描覆盖区域覆盖的所述重点被检部位的个数占全部所述重点被检部位数量的比例确定检测完成率；
    或，
    根据各个所述重点被检部位被所述扫描覆盖区域覆盖的比例和所述重点被检部位的权重确定检测完成率。
  14. 根据权利要求13所述的控制器，还包括：告警模块，被配置为当所述检测完成率低于预定扫描质量阈值时，发出告警信息。
  15. 一种扫描质量检测控制器，包括：
    存储器；以及
    耦接至所述存储器的处理器，所述处理器被配置为基于存储在所述存储器的指令执行如权利要求1至8任一项所述的方法。
  16. 一种计算机可读存储介质，其上存储有计算机程序指令，该指令被处理器执行时实现权利要求1至8任意一项所述的方法的步骤。
  17. 一种扫描质量检测装置，包括：
    第一图像采集设备，被配置为获取包括被测人的图像；
    第二图像采集设备，被配置为获取安全检查员对所述被测人进行人身检查的视频；和，
    权利要求9～15任意一项所述的扫描质量检测控制器。
PCT/CN2018/087702 2017-09-18 2018-05-21 扫描质量检测方法、控制器和装置 WO2019052212A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710840241.0 2017-09-18
CN201710840241.0A CN109522912B (zh) 2017-09-18 2017-09-18 扫描质量检测方法、控制器和装置

Publications (1)

Publication Number Publication Date
WO2019052212A1 true WO2019052212A1 (zh) 2019-03-21

Family

ID=65723475

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/087702 WO2019052212A1 (zh) 2017-09-18 2018-05-21 扫描质量检测方法、控制器和装置

Country Status (2)

Country Link
CN (1) CN109522912B (zh)
WO (1) WO2019052212A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110006928A (zh) * 2019-05-07 2019-07-12 安徽启路达光电科技有限公司 多技术人包安检系统

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111126771B (zh) * 2019-11-26 2023-06-20 公安部第一研究所 基于区域关注度预测安检员识图质量监督保障系统及方法
CN111209793A (zh) * 2019-12-05 2020-05-29 重庆特斯联智慧科技股份有限公司 一种基于人工智能的区域屏蔽人体安检方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040098237A1 (en) * 2002-11-14 2004-05-20 Accenture Global Services Gmbh Security checkpoint simulation
CN202257964U (zh) * 2011-01-06 2012-05-30 北京铁道工程机电技术研究所 动车组检修作业监控评价管理系统
CN104965235A (zh) * 2015-06-12 2015-10-07 同方威视技术股份有限公司 一种安检系统及方法

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102651148A (zh) * 2011-02-24 2012-08-29 刘中库 安检值机监控系统的监控方法
CN204359356U (zh) * 2015-01-14 2015-05-27 中国人民解放军海军工程大学 基于多传感器融合的船用手持式安全检查仪
JP2016157357A (ja) * 2015-02-26 2016-09-01 株式会社日立製作所 作業者品質管理方法及び作業者品質管理装置
CN106707362B (zh) * 2016-12-02 2018-12-25 北京航星机器制造有限公司 一种人体安检监督系统

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040098237A1 (en) * 2002-11-14 2004-05-20 Accenture Global Services Gmbh Security checkpoint simulation
CN202257964U (zh) * 2011-01-06 2012-05-30 北京铁道工程机电技术研究所 动车组检修作业监控评价管理系统
CN104965235A (zh) * 2015-06-12 2015-10-07 同方威视技术股份有限公司 一种安检系统及方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110006928A (zh) * 2019-05-07 2019-07-12 安徽启路达光电科技有限公司 多技术人包安检系统

Also Published As

Publication number Publication date
CN109522912B (zh) 2021-04-02
CN109522912A (zh) 2019-03-26

Similar Documents

Publication Publication Date Title
KR102307356B1 (ko) 컴퓨터 보조 진단 장치 및 방법
JP6467041B2 (ja) 超音波診断装置、及び画像処理方法
CN105249922B (zh) 断层图像拍摄设备和断层图像拍摄方法
US11134886B2 (en) Quantified injury diagnostics
US8840557B2 (en) Ultrasonic apparatus for measuring a labor progress parameter
US20150002538A1 (en) Ultrasound image display method and apparatus
US9436871B2 (en) Posture detection method and system
WO2019052212A1 (zh) 扫描质量检测方法、控制器和装置
CN110031909A (zh) 安检系统及安检方法
WO2015010531A1 (zh) 人体安全检查方法和人体安全检查系统
KR20160016460A (ko) 관심영역의 시각화 장치 및 방법
CN106419938B (zh) 一种基于运动能量释放估算的注意缺陷多动障碍(adhd)检测系统
WO2014101538A1 (zh) 人体安检设备和人体安检方法
CN113139962B (zh) 用于脊柱侧凸概率评估的系统和方法
Soleimani et al. Carotid artery wall motion estimation from consecutive ultrasonic images: Comparison between block-matching and maximum-gradient algorithms
CN110717461A (zh) 一种疲劳状态识别方法、装置和设备
US20190274620A1 (en) Method for diagnosing scoliosis using spatial coordinates of body shape and computer program therefor
US8444461B2 (en) Systems and methods for the detection of anatomical structures and positions thereof
JP2015160049A (ja) 超音波診断装置及び超音波診断装置の利用者姿勢の評価報知方法
Chu et al. 3D human body reconstruction for worker ergonomic posture analysis with monocular video camera
CN115578789A (zh) 脊柱侧弯检测装置、系统及计算机可读存储介质
Hannah et al. Collecting shoulder kinematics with electromagnetic tracking systems and digital inclinometers: A review
US20190298227A1 (en) Tremor detector, stress assessment system including the same, and method of assessing stress
JP6379899B2 (ja) 情報処理装置、脈波計測プログラムおよび脈波計測方法
KR20230093470A (ko) 밀리미터파 인체 보안검사 시스템 및 방법

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: 18856325

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: 18856325

Country of ref document: EP

Kind code of ref document: A1