WO2016180324A1 - Procédé, système et serveur de traitement pour déterminer des informations de suivi d'une personne cible - Google Patents

Procédé, système et serveur de traitement pour déterminer des informations de suivi d'une personne cible Download PDF

Info

Publication number
WO2016180324A1
WO2016180324A1 PCT/CN2016/081596 CN2016081596W WO2016180324A1 WO 2016180324 A1 WO2016180324 A1 WO 2016180324A1 CN 2016081596 W CN2016081596 W CN 2016081596W WO 2016180324 A1 WO2016180324 A1 WO 2016180324A1
Authority
WO
WIPO (PCT)
Prior art keywords
identification information
unique identification
intersection
wifi
target person
Prior art date
Application number
PCT/CN2016/081596
Other languages
English (en)
Chinese (zh)
Inventor
刁一平
虞丽峰
Original Assignee
杭州海康威视数字技术股份有限公司
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
Priority claimed from CN201510308669.1A external-priority patent/CN106296724B/zh
Application filed by 杭州海康威视数字技术股份有限公司 filed Critical 杭州海康威视数字技术股份有限公司
Priority to US15/573,519 priority Critical patent/US10185023B2/en
Priority to EP16792174.1A priority patent/EP3297276B1/fr
Publication of WO2016180324A1 publication Critical patent/WO2016180324A1/fr

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a method, a system, and a processing server for determining trajectory information of a target person.
  • the trajectory tracking of the target person that is, the trajectory information of the target person.
  • the trajectory information of the target person it is necessary to obtain all video recordings including the target person. Based on the position of the image capturing device that collects the video recordings, the trajectory information of the target person can be determined, and the trajectory tracking of the target person can be realized.
  • the above method requires analysis of a large number of video recordings, and analyzes whether a large number of video recordings contain target characters, and the analysis process is time consuming and laborious, and the process is very complicated.
  • the embodiment of the present application discloses a method, a system, and a processing server for determining the trajectory information of a target person, so as to avoid analyzing a large amount of video recording.
  • the embodiment of the present application discloses a method for determining trajectory information of a target person, which is applied to a processing server, where the processing server is connected to multiple image collection devices including a wireless fidelity WiFi detector;
  • the method includes:
  • a preset intersection manner for at least two first image collection devices of the plurality of first image acquisition devices: respectively obtaining an appearance time of the target person in the specified video recording, respectively determining to include the occurrence time a detection time interval, and respectively obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval; Performing intersection processing on the obtained set of unique identification information of the WiFi terminal to obtain an intersection of the unique identification information;
  • the embodiment of the present application discloses a processing server, where the processing server is connected to multiple image collection devices including a WiFi detector, and the processing server specifically includes:
  • An interface module configured to obtain a plurality of specified video recordings including a target person
  • a data processor configured to determine a plurality of first image capturing devices that capture the specified video recording
  • a preset intersection manner for at least two first image collection devices of the plurality of first image acquisition devices: respectively obtaining an appearance time of the target person in the specified video recording, respectively determining to include the occurrence time a detection time interval, and respectively obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval; and performing intersection processing of the obtained unique identification information of the WiFi terminal, Obtain a unique identification information intersection;
  • the embodiment of the present application discloses a method for determining trajectory information of a target person, which is applied to a system including a processing server and a plurality of image collection devices connected to the processing server, and the image collection device includes wireless fidelity WiFi detection.
  • the method includes:
  • the image capture device captures a video recording and outputs the video recording
  • the WiFi detector detects the unique identification information of the WiFi terminal in its own detection area, and outputs a correspondence between the detected unique identification information and the detection time of the unique identification information;
  • the processing server obtains a plurality of specified video recordings including the target person based on the video recording; determining a plurality of first image capturing devices that capture the specified video recording; according to a preset intersection And a set mode, for at least two first image capturing devices of the plurality of first image capturing devices: respectively obtaining an occurrence time of the target person in the specified video recording, and determining a detection time interval including the occurrence time respectively Obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval according to the correspondence between the unique identification information and the detection time of the unique identification information, respectively Obtaining the intersection of the unique identification information of the obtained WiFi terminal to obtain the intersection of the unique identification information; determining the unique identification information of the WiFi terminal in which the unique identification information is centralized as the unique identification information of the target person; The image capturing device of all the WiFi detectors of the target person's unique identification information; determining the trajectory information of the target person according to the location of the image capturing device where all the
  • the embodiment of the present application discloses a system for determining trajectory information of a target person, where the system specifically includes a processing server and a plurality of image capturing devices connected to the processing server, and the image capturing device includes a wireless fidelity WiFi detector. ;among them,
  • An image capture device for capturing a video recording and outputting the video recording
  • a WiFi detector configured to detect unique identification information of the WiFi terminal in the detection area of the detection unit, and output a correspondence between the detected unique identification information and the detection time of the unique identification information
  • the embodiment of the present application discloses an application program for executing a method for determining the trajectory information of the target person at runtime.
  • the embodiment of the present application discloses a storage medium, where the storage medium is used to store an application.
  • the application is configured to perform a method of determining trajectory information of the target person.
  • the embodiment of the present application has at least the following advantages: in the embodiment of the present application, multiple video recordings including the target person may be specified (ie, all video recordings including the target person) Part of the video recording, which can be specified by the user) to determine the unique identification information of the target person, and obtain the image acquisition device of all WiFi (WirelessFIdelit) detectors that detect the unique identification information of the target person. And determining the trajectory information of the target person according to the location of the image acquisition device where all the WiFi detectors are located. In the above manner, only a small amount of the video recording containing the target person can obtain the trajectory information of the target person, and does not need a large amount of video. The video is analyzed to reduce the process of analyzing a large number of video recordings.
  • WiFi WirelessFIdelit
  • FIG. 3 is a schematic flowchart of a method for determining trajectory information of a target person according to Embodiment 2 of the present application;
  • FIG. 4 is a schematic flowchart of a method for determining trajectory information of a target person according to Embodiment 3 of the present application;
  • a first embodiment of the present application provides a system for determining trajectory information of a target person.
  • the system may specifically include a processing server and a plurality of image capturing devices connected to the processing server.
  • the processing server and the plurality of image collection devices are connected by wire or wirelessly.
  • the image capturing device includes a WiFi detector and an image capturing module (such as an intelligent camera with an image capturing function), and the image capturing device captures a video recording through an image capturing module, and the WiFi detector can be built in the image capturing.
  • the WiFi detector in the device may also be a WiFi detector deployed separately from the image collection device. For the convenience of description, the WiFi detector is built in the image collection device as an example.
  • An image acquisition device for capturing video recordings and outputting video recordings.
  • the WiFi detector is configured to detect unique identification information of the WiFi terminal in the detection area of the detection area, and output a correspondence between the detected unique identification information and the detection time of the unique identification information.
  • a processing server configured to obtain a plurality of specified video recordings including the target person based on the video recording output by the image capturing device; determine a plurality of first image capturing devices that capture the specified video recording; according to the preset intersection manner, At least two first image capturing devices in the first image capturing device: respectively obtaining the occurrence moments of the target person in the specified video recording, respectively determining the detection time interval including the occurrence time, and respectively outputting according to the WiFi detector Corresponding relationship between the unique identification information and the detection time of the unique identification information, obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval, and the obtained WiFi terminal is unique
  • the set of the identification information is subjected to the intersection processing to obtain the intersection of the unique identification information; the unique identification information of the WiFi terminal in which the unique identification information is centralized is determined as the unique identification information of the target person; and all the WiFi detections in which the unique identification information of the target person is detected are obtained.
  • Image acquisition device where the device
  • the processing server is specifically configured to: between the unique identification information outputted by the WiFi detector to the identifier memory and the detection time of the unique identifier information, between the unique identifier information obtained from the identifier memory and the detection time of the unique identifier information Corresponding relationship, and based on the correspondence, obtain a set of unique identification information of the WiFi terminal detected by the WiFi detector in the detection time interval.
  • the video capture captured by the image capture device will include the target person; if the WiFi terminal carried by the target person is located in the WiFi detection area of the WiFi detector of the image capture device
  • the WiFi detector can detect the unique identification information of the WiFi terminal, and record the correspondence between the unique identification information of the WiFi terminal and the detection time of the unique identification information.
  • the WiFi terminal carried by the target person periodically sends a WiFi signal, and the WiFi detector can periodically detect the WiFi signal from the WiFi terminal, and parse the unique identification information of the WiFi terminal from the WiFi signal. Based on this, when the WiFi terminal is located in the WiFi detection area of the WiFi detector, the WiFi detector can detect the unique identification information of the WiFi terminal, and record the currently identified unique identification information of the WiFi terminal and the unique identification information. The correspondence between the detection times.
  • the WiFi detector 1 can detect the unique identification information of the WiFi terminal 1, and The correspondence between the unique identification information of the WiFi terminal 1 and the detection time 1 is recorded.
  • the WiFi detector may detect unique identification information of multiple WiFi terminals and record Correspondence between the unique identification information of the plurality of WiFi terminals and the detection time.
  • the WiFi detector 1 can detect the unique identifier of the WiFi terminal 1.
  • the information, the unique identification information of the WiFi terminal 2, and the unique identification information of the WiFi terminal 3 record the unique identification information of the WiFi terminal 1, the unique identification information of the WiFi terminal 2, and the correspondence between the unique identification information of the WiFi terminal 3 and the detection time 1. relationship.
  • the user can know which video recordings include the target person, and assign the information of the video recording including the target person to the processing server, and the processing server can obtain the information based on the information of the video recording of the target person specified by the user. Multiple specified video recordings of the target person. Among them, the user only needs to select a part of the video recording from all the video recordings containing the target person, and specify to the processing server a plurality of video recordings including the target person. For example, when the user assigns the information of the video recording 1, video recording 2, video recording 3, and video recording 4 including the target person to the processing server, the processing server obtains the video recording including the target person as video recording 1, video recording 2, and video. Video 3 and video recording 4.
  • the processing server can learn the first image capturing devices corresponding to the video recordings of the target person. For example, the processing server learns the video recording.
  • the video recording 2 corresponds to the first image capturing device 2
  • the video recording 3 corresponding to the first image capturing device 3
  • the video recording 4 corresponding to the first image capturing device 4.
  • the processing server is specifically configured to: when the preset intersection mode is an intersection of all the sets, for the plurality of first image capturing devices (including the plurality of first image capturing devices corresponding to the plurality of specified video recordings of the target person) All the first image acquisition devices in the system: respectively obtaining the occurrence moments of the target person in the specified video recording, respectively determining the detection time interval including the appearance time, and respectively obtaining the WiFi detector of the first image acquisition device at the detection time a set of unique identification information of the WiFi terminal detected by the interval; performing intersection processing on the set of unique identification information of the WiFi terminal respectively obtained by all the first image collection devices in the plurality of first image collection devices, to obtain the intersection of the unique identification information .
  • the processing server is specifically configured to: when the preset intersection mode is a loop intersection intersection, A, from the plurality of first image collection devices (including a plurality of first image collections corresponding to the plurality of specified video recordings of the target person) Selecting two first image acquisition devices in the device: respectively obtaining the occurrence moments of the target person in the specified video recording, respectively determining the detection time interval including the occurrence time, and respectively obtaining the WiFi detector of the first image acquisition device Detecting a set of unique identification information of the WiFi terminal detected in the time interval; B, performing intersection processing on the set of unique identification information of the WiFi terminal respectively obtained by the two first image collection devices of the plurality of first image collection devices, and obtaining The first unique identification information intersection; C, determining whether the number of unique identification information of the WiFi terminal in the first unique identification information intersection is equal to 1; if yes, determining the intersection of the first unique identification information as the final unique identification information intersection End the process; if not, execute D; D, from multiple first images Selecting an unselected first image capturing device in the
  • the detection time interval may be the difference between the appearance time and the 1 second to the sum of the appearance time and 1 second.
  • the corresponding detection time interval is 17:29:59 on May 28, 2015 and 17:30:01 on May 28, 2015.
  • the processing server may obtain the WiFi detector of the first image acquisition device to detect A set of unique identification information of the WiFi terminal detected in the time interval.
  • the processing server can learn each of the outputs of the WiFi detector 1 Whether the detection time of the unique identification information is located in the detection time interval; if it is located in the detection time interval, the unique identification information includes the unique identification information; if not located in the detection time interval, the unique identification information is not included in the collection This unique identification information.
  • the plurality of first image capturing devices are the first image capturing device 1, the first image capturing device 2, the first image capturing device 3, and the first image capturing device 4, respectively obtaining the first image capturing device
  • the uniqueness of the WiFi terminal detected by the WiFi detector in the detection time interval a set 1 of identification information, a set 2 of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device 2 in the detection time interval, and a WiFi detector of the first image acquisition device 3 detected in the detection time interval a set 3 of unique identification information of the WiFi terminal, a set 4 of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device 4 in the detection time interval, and the set 1, the set 2, the set 3, and the set 4 Intersection processing is performed to obtain an intersection of unique identification information.
  • the plurality of first image capturing devices are the first image capturing device 1, the first image capturing device 2, the first image capturing device 3, and the first image capturing device 4, respectively, obtaining the first image capturing device a set 1 of unique identification information of the WiFi terminal detected by the WiFi detector in the detection time interval, a set 2 of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device 2 in the detection time interval, and The set 1 and the set 2 are subjected to intersection processing to obtain an intersection of the first unique identification information. If the number of unique identification information of the WiFi terminal in the first unique identification information intersection is 1, the intersection of the first unique identification information is determined as the final unique identification information intersection.
  • the set 3 of the unique identification information of the WiFi terminal detected by the WiFi detector of the first image collection device 3 in the detection time interval is obtained, And intersecting the set 3 and the first unique identification information for intersection processing. If the number of unique identification information of the WiFi terminal in the intersection after the intersection processing is 1, the intersection after the intersection processing is determined as the final unique identification information intersection. . If the number of unique identification information of the WiFi terminal in the intersection after the intersection processing is not 1, the intersection after the intersection processing is intersected as the first unique identification information, and so on.
  • the processing server may obtain an image of all the WiFi detectors that detect the unique identification information of the target person.
  • the device is collected, and the track information of the target person is determined according to the location of the image acquisition device where all the WiFi detectors are located.
  • the processing server can obtain the unique identification information detected. All WiFi detectors of 1 are WiFi detector 1-WiFi detector 15, and the track information of the target person is determined according to the location of the image acquisition device where the WiFi detector 1-WiFi detector 15 is located.
  • the initial WiFi detector and the terminating WiFi detector of the trajectory can be determined by the user.
  • the embodiment of the present application has at least the following advantages: in the embodiment of the present application, by associating the information outputted by the video monitoring with the information output by the WiFi detector, the specified inclusion target may be Multiple video recordings of a character (ie, all video recordings in a video recording containing a target person, which may be specified by a user) determine unique identification information of the target person, and obtain unique identification information of the target person.
  • the image acquisition device of all the WiFi detectors and according to the location of the image acquisition device where all the WiFi detectors are located, determine the trajectory information of the target person. In this way, only a small number of video recordings including the target person can be obtained to obtain the target person.
  • the trajectory information does not require analysis of a large number of video recordings, reducing the process of analyzing a large number of video recordings.
  • the second embodiment of the present application proposes a method for determining the trajectory information of a target person, which is applied to a system including a processing server and a plurality of image capturing devices connected to the processing server.
  • the processing server and the plurality of image collection devices are connected by wire or wirelessly.
  • the image capturing device includes a WiFi detector and an image capturing module (such as an intelligent traffic camera with an image capturing function), and the image capturing device captures a video recording through an image capturing module, and the WiFi detector can be built in the image.
  • the WiFi detector in the collection device can also be a WiFi detector deployed separately from the image acquisition device. For convenience of description, the WiFi detector is built in the image acquisition device as an example.
  • the image collection device may The unique identification information of the WiFi terminal is parsed in the WiFi signal, and the unique identification information of the WiFi terminal may specifically include, but is not limited to, the MAC address of the WiFi terminal. Further, based on the WiFi detector, after receiving the WiFi signal from the WiFi terminal, the image capturing device may not respond to the WiFi terminal, and does not provide the WiFi service for the WiFi terminal, as long as the WiFi terminal carried in the WiFi signal can be parsed The unique identification information can be.
  • the method for determining the trajectory information of the target person specifically includes the following steps:
  • step 301 the image capturing device captures the video recording and outputs the video recording.
  • Step 302 The WiFi detector detects the unique identification information of the WiFi terminal in the detection area of the detection, and outputs a correspondence between the detected unique identification information and the detection time of the unique identification information. There is no sequential relationship between step 301 and step 302.
  • Step 305 The processing server determines the unique identification information of the WiFi terminal in which the unique identification information is centralized, as the unique identification information of the target person.
  • the WiFi detector when the correspondence between the unique identification information and the detection time of the unique identification information is output, the WiFi detector directly outputs the correspondence between the unique identification information and the detection time of the unique identification information to the processing. server.
  • the processing server obtains, according to the correspondence between the unique identification information output by the WiFi detector to the processing server and the detection time of the unique identification information, between the detection information of the unique identification information and the unique identification information directly obtained from the processing server. Corresponding relationship, and based on the correspondence, obtain a set of unique identification information of the WiFi terminal detected by the WiFi detector in the detection time interval.
  • the system may further include an identifier memory, and when the WiFi detector outputs a correspondence between the unique identifier information and the detection time of the unique identifier information, the correspondence between the unique identifier information and the detection time of the unique identifier information The relationship is output to the identification memory.
  • the identifier memory receives a correspondence between the unique identification information from the WiFi detector and the detection time of the unique identification information, and stores a correspondence between the unique identification information and the detection time of the unique identification information.
  • the processing server obtains a correspondence between the unique identification information and the detection time of the unique identification information from the identification memory based on the correspondence between the unique identification information outputted by the WiFi detector to the identification memory and the detection time of the unique identification information, And obtaining, according to the correspondence, a set of unique identification information of the WiFi terminal detected by the WiFi detector in the detection time interval.
  • the video storage and the identifier storage may be deployed on the same device or on different devices.
  • the processing server can learn the first image capturing devices corresponding to the video recordings of the target person, for example, The processing server learns that the video recording 1 corresponds to the first image capturing device 1, the video recording 2 corresponds to the first image capturing device 2, the video recording 3 corresponds to the first image capturing device 3, and the video recording 4 corresponds to the first image acquisition device 4.
  • the processing server for the processing server, according to the preset intersection manner, for at least two first image capturing devices of the plurality of first image capturing devices: respectively obtaining the appearance moments of the target person in the specified video recording, respectively Determining a detection time interval including the occurrence time, and obtaining a detection interval of the WiFi detector of the first image acquisition device according to the correspondence between the unique identification information output by the WiFi detector and the detection time of the unique identification information And the set of the unique identification information of the obtained WiFi terminal, the process of the intersection of the obtained unique identification information of the WiFi terminal, and the process of obtaining the unique identification information, which may include, but is not limited to, the following two situations:
  • Case 1 When the preset intersection mode is the intersection of all the sets, the processing server is all for all the first image capturing devices (including the plurality of first image capturing devices corresponding to the plurality of specified video recordings of the target person)
  • the first image capturing device respectively obtains the occurrence moments of the target person in the specified video recording, respectively determines the detection time interval including the occurrence time, and respectively obtains the detection of the WiFi detector of the first image acquisition device in the detection time interval.
  • a set of unique identification information of the WiFi terminal the set of unique identification information of the WiFi terminal respectively obtained for all the first image collection devices of the plurality of first image collection devices is subjected to intersection processing to obtain an intersection of the unique identification information.
  • Step A The processing server selects two first image capturing devices from a plurality of first image capturing devices (including a plurality of first image capturing devices corresponding to the plurality of specified video recordings of the target person): respectively obtaining the target person in the specified
  • the occurrence time in the video recording respectively determines the detection time interval including the occurrence time, and obtains the set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval, respectively.
  • Step B The processing server performs intersection processing on the set of unique identification information of the WiFi terminal respectively obtained by the two first image collection devices of the plurality of first image collection devices, to obtain the intersection of the first unique identification information.
  • Step D The processing server selects an unselected first image capturing device from the plurality of first image capturing devices: obtaining an appearance moment of the target person in the specified video recording, and determining to include And detecting a time interval of the moment of occurrence, and obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval.
  • Step E The processing server performs intersection processing on the intersection of the set of unique identification information of the WiFi terminal obtained by the first image collection device and the first unique identification information, and determines the unique identification information of the WiFi terminal in the intersection after the intersection processing. Whether the number is equal to 1; if yes, the intersection after the intersection processing is determined as the final unique identification information intersection; if not, the intersection after the intersection processing is intersected as the first unique identification information, and step D is performed.
  • the processing server can directly determine the appearance time of the target person in the video recording. After the processing server determines the appearance time of the target person in the video recording, the processing server may also determine the detection time interval including the appearance time.
  • the detection time interval may be: a sum of the occurrence time to the occurrence time and the first value, or the difference between the appearance time and the second value to the appearance time, or the difference between the appearance time and the third value to the appearance time and the The sum of the four values.
  • the first value, the second value, the third value, and the fourth value can all be arbitrarily selected according to actual experience.
  • the detection time interval may be the difference between the appearance time and the 1 second to the sum of the appearance time and 1 second.
  • the corresponding detection time interval is 17:29:59 on May 28, 2015 and 17:30:01 on May 28, 2015.
  • the processing server may obtain the WiFi detector of the first image acquisition device to detect A set of unique identification information of the WiFi terminal detected in the time interval. For example, based on the correspondence between the unique identification information output by the WiFi detector 1 in the first image capturing device 1 and the detection time of the unique identification information, and the detection time interval, the processing server learns each unique output of the WiFi detector 1 Whether the detection time of the identification information is located in the detection time interval; if it is located in the detection time interval, the unique identification information includes the unique identification information; if not located in the detection time interval, the collection of unique identification information does not include the Unique identification information.
  • the plurality of first image capturing devices are the first image capturing device 1, the first image capturing device 2, the first image capturing device 3, and the first image capturing device 4, respectively obtaining the first image capturing device
  • the WiFi detector of 1 detects the set of unique identification information of the WiFi terminal detected in the detection time interval
  • the WiFi detector of the first image acquisition device 2 detects the detection time interval a set 2 of unique identification information of the WiFi terminal to which the WiFi detector of the first image acquisition device 3 detects the set of unique identification information of the WiFi terminal detected in the detection time interval
  • the WiFi detector of the first image acquisition device 4 is The set 4 of the unique identification information of the WiFi terminal detected in the time interval is detected, and the set 1, the set 2, the set 3, and the set 4 are subjected to intersection processing to obtain an intersection of the unique identification information.
  • the plurality of first image capturing devices are the first image capturing device 1, the first image capturing device 2, the first image capturing device 3, and the first image capturing device 4, respectively, obtaining the first image capturing device a set 1 of unique identification information of the WiFi terminal detected by the WiFi detector in the detection time interval, a set 2 of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device 2 in the detection time interval, and The set 1 and the set 2 are subjected to intersection processing to obtain an intersection of the first unique identification information. If the number of unique identification information of the WiFi terminal in the first unique identification information intersection is 1, the intersection of the first unique identification information is determined as the final unique identification information intersection.
  • the set 3 of the unique identification information of the WiFi terminal detected by the WiFi detector of the first image collection device 3 in the detection time interval is obtained, And intersecting the set 3 and the first unique identification information for intersection processing. If the number of unique identification information of the WiFi terminal in the intersection after the intersection processing is 1, the intersection after the intersection processing is determined as the final unique identification information intersection. . If the number of unique identification information of the WiFi terminal in the intersection after the intersection processing is not 1, the intersection after the intersection processing is intersected as the first unique identification information, and so on.
  • the processing server may obtain an image of all the WiFi detectors that detect the unique identification information of the target person.
  • the device is collected, and the track information of the target person is determined according to the location of the image acquisition device where all the WiFi detectors are located.
  • the processing server can obtain the unique identification information detected. All WiFi detectors of 1 are WiFi detector 1-WiFi detector 15, and the track information of the target person is determined according to the location of the image acquisition device where the WiFi detector 1-WiFi detector 15 is located.
  • the trajectory information of the target person determined by the processing server is the initial trajectory information, and the initial Track information is corrected to get the final track letter interest.
  • the initial WiFi detector of the trajectory and the termination WiFi detector may be determined, and the first detection moment of the initial identification information of the target person detected by the initial WiFi detector is determined, and the detection of the WiFi detector is terminated.
  • the second detection time to the unique identification information of the target person. For other WiFi detectors in the initial track information, if other WiFi detectors detect that the detection time of the unique identification information of the target person is between the first detection time and the second detection time, the other track is retained in the final track information.
  • the initial WiFi detector and the terminating WiFi detector of the trajectory can be determined by the user.
  • the embodiment of the present application has at least the following advantages: in the embodiment of the present application, by associating the information outputted by the video monitoring with the information output by the WiFi detector, the specified inclusion target may be Multiple video recordings of a character (ie, all video recordings in a video recording containing a target person, which may be specified by a user) determine unique identification information of the target person, and obtain unique identification information of the target person.
  • the image acquisition device of all the WiFi detectors and according to the location of the image acquisition device where all the WiFi detectors are located, determine the trajectory information of the target person. In this way, only a small number of video recordings including the target person can be obtained to obtain the target person.
  • the trajectory information does not require analysis of a large number of video recordings, reducing the process of analyzing a large number of video recordings.
  • a method for determining the trajectory information of the target person is proposed in the third embodiment of the present application, which is applied to the processing server, and the processing server is connected to the plurality of image capturing devices.
  • the processing server and the plurality of image collection devices are connected by wire or wirelessly.
  • the image capturing device includes a WiFi detector and an image capturing module (such as an intelligent traffic camera with an image capturing function), and the image capturing device captures a video recording through an image capturing module, and the WiFi detector can be built in the image.
  • the WiFi detector in the collection device can also be a WiFi detector deployed separately from the image acquisition device. For convenience of description, the WiFi detector is built in the image acquisition device as an example.
  • the image collection device may parse the unique identification information of the WiFi terminal from the WiFi signal, and the unique identification information of the WiFi terminal may specifically Package This includes but is not limited to: the MAC address of the WiFi terminal. Further, based on the WiFi detector, after receiving the WiFi signal from the WiFi terminal, the image capturing device may not respond to the WiFi terminal, and does not provide the WiFi service for the WiFi terminal, as long as the WiFi terminal carried in the WiFi signal can be parsed The unique identification information can be.
  • the method for determining the trajectory information of the target person may specifically include the following steps:
  • step 401 the processing server obtains a plurality of specified video recordings including the target person.
  • the user can know which video recording contains the target person, and assigns the information of the video recording containing the target person to the processing server, and the processing server can obtain multiple designations including the target person based on the information specified by the user including the video recording of the target person.
  • Video recording the user only needs to select a part of the video recording from all the video recordings containing the target person, and specify to the processing server a plurality of video recordings including the target person. For example, when the user assigns the information of the video recording 1, video recording 2, video recording 3, and video recording 4 including the target person to the processing server, the processing server obtains the video recording including the target person as video recording 1, video recording 2, and video. Video 3 and video recording 4.
  • Step 402 The processing server determines to capture a plurality of first image capturing devices of the specified video recording.
  • the processing server can learn the first image capturing devices corresponding to the video recordings of the target person.
  • video recording 1 corresponds to the first image capturing device 1
  • the video recording 2 corresponds to the first image capturing device 2
  • the video recording 3 corresponds to the first image capturing.
  • the device 3 and the video recording 4 correspond to the first image capturing device 4.
  • Step 403 The processing server is configured to: at least two first image capturing devices of the plurality of first image capturing devices according to the preset intersection manner: respectively obtaining the occurrence moments of the target person in the specified video recording, and respectively determining to include the Obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval; respectively, obtaining the set of the unique identification information of the obtained WiFi terminal, and obtaining the intersection of the obtained identification information of the WiFi terminal Unique identification information intersection.
  • the step 403 may include, but is not limited to, the following two situations:
  • Case 1 When the preset intersection mode is the intersection of all the sets, the processing server is all for all the first image capturing devices (including the plurality of first image capturing devices corresponding to the plurality of specified video recordings of the target person)
  • First image acquisition device respectively obtain the target character in the specified video The occurrence time in the video, respectively determining the detection time interval including the occurrence time, and respectively obtaining the set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval;
  • a set of unique identification information of the WiFi terminal obtained by all the first image collection devices in an image acquisition device is subjected to intersection processing to obtain an intersection of unique identification information.
  • Step A The processing server selects two first image capturing devices from a plurality of first image capturing devices (including a plurality of first image capturing devices corresponding to the plurality of specified video recordings of the target person): respectively obtaining the target person in the specified
  • the occurrence time in the video recording respectively determines the detection time interval including the occurrence time, and obtains the set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval, respectively.
  • Step B The processing server performs intersection processing on the set of unique identification information of the WiFi terminal respectively obtained by the two first image collection devices of the plurality of first image collection devices, to obtain the intersection of the first unique identification information.
  • Step C The processing server determines whether the number of unique identification information of the WiFi terminal in the intersection of the first unique identification information is equal to 1; if yes, the intersection of the first unique identification information is determined as the final unique identification information intersection, and the process ends. If not, perform step D.
  • Step D The processing server selects an unselected first image capturing device from the plurality of first image capturing devices: obtaining an appearance time of the target person in the specified video recording, determining a detection time interval including the occurrence time, and Obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval.
  • Step E The processing server performs intersection processing on the intersection of the set of unique identification information of the WiFi terminal obtained by the first image collection device and the first unique identification information, and determines the unique identification information of the WiFi terminal in the intersection after the intersection processing. Whether the number is equal to 1; if yes, the intersection after the intersection processing is determined as the final unique identification information intersection; if not, the intersection after the intersection processing is intersected as the first unique identification information, and step D is performed.
  • the processing server can directly determine the appearance time of the target person in the video recording. After the processing server determines the appearance time of the target person in the video recording, the processing server may also determine the detection time interval including the appearance time.
  • the detection time interval may be: a sum of the occurrence time to the occurrence time and the first value, or a difference between the appearance time and the second value to the appearance time, or the difference between the appearance time and the third value is The sum of the current moment and the fourth value.
  • the first value, the second value, the third value, and the fourth value can all be arbitrarily selected according to actual experience.
  • the detection time interval may be the difference between the appearance time and the 1 second to the sum of the appearance time and 1 second.
  • the corresponding detection time interval is 17:29:59 on May 28, 2015 and 17:30:01 on May 28, 2015.
  • the processing server may obtain the WiFi detector of the first image acquisition device to detect A set of unique identification information of the WiFi terminal detected in the time interval. For example, based on the correspondence between the unique identification information output by the WiFi detector 1 in the first image capturing device 1 and the detection time of the unique identification information, and the detection time interval, the processing server learns each unique output of the WiFi detector 1 Whether the detection time of the identification information is located in the detection time interval; if it is located in the detection time interval, the unique identification information includes the unique identification information; if not located in the detection time interval, the collection of unique identification information does not include the Unique identification information.
  • the plurality of first image capturing devices are the first image capturing device 1, the first image capturing device 2, the first image capturing device 3, and the first image capturing device 4, respectively obtaining the first image capturing device a set 1 of unique identification information of the WiFi terminal detected by the WiFi detector in the detection time interval, and a set 2 of the unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device 2 in the detection time interval, a set 3 of unique identification information of the WiFi terminal detected by the WiFi detector of the image acquisition device 3 in the detection time interval, and the unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device 4 in the detection time interval Set 4, and set the collection 1, the collection 2, the collection 3, and the collection 4 to obtain an intersection of the unique identification information.
  • the plurality of first image capturing devices are the first image capturing device 1, the first image capturing device 2, the first image capturing device 3, and the first image capturing device 4, respectively, obtaining the first image capturing device a set 1 of unique identification information of the WiFi terminal detected by the WiFi detector in the detection time interval, a set 2 of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device 2 in the detection time interval, and The set 1 and the set 2 are subjected to intersection processing to obtain an intersection of the first unique identification information. If the number of unique identification information of the WiFi terminal in the first unique identification information intersection is 1, the intersection of the first unique identification information is determined as the final unique identifier. Information intersection.
  • the set 3 of the unique identification information of the WiFi terminal detected by the WiFi detector of the first image collection device 3 in the detection time interval is obtained, And intersecting the set 3 and the first unique identification information for intersection processing. If the number of unique identification information of the WiFi terminal in the intersection after the intersection processing is 1, the intersection after the intersection processing is determined as the final unique identification information intersection. . If the number of unique identification information of the WiFi terminal in the intersection after the intersection processing is not 1, the intersection after the intersection processing is intersected as the first unique identification information, and so on.
  • Step 404 The processing server determines the unique identification information of the WiFi terminal in which the unique identification information is centralized, as the unique identification information of the target person.
  • Step 405 The processing server obtains an image collection device in which all WiFi detectors that detect the unique identification information of the target person are located, and determines the trajectory information of the target person according to the location of the image collection device where all the WiFi detectors are located.
  • the processing server may obtain an image of all the WiFi detectors that detect the unique identification information of the target person.
  • the device is collected, and the track information of the target person is determined according to the location of the image acquisition device where all the WiFi detectors are located.
  • the processing server can obtain the unique identification information detected. All WiFi detectors of 1 are WiFi detector 1-WiFi detector 15, and the track information of the target person is determined according to the location of the image acquisition device where the WiFi detector 1-WiFi detector 15 is located.
  • the trajectory information of the target person determined by the processing server is the initial trajectory information, and the initial The trajectory information is corrected to obtain the final trajectory information.
  • the initial trajectory information is corrected, the initial WiFi detector of the trajectory and the termination WiFi detector may be determined, and the first detection moment of the initial identification information of the target person detected by the initial WiFi detector is determined, and the detection of the WiFi detector is terminated.
  • the second detection time to the unique identification information of the target person. For other WiFi detectors in the initial track information, if other WiFi detectors detect that the detection time of the unique identification information of the target person is between the first detection time and the second detection time, the other track is retained in the final track information.
  • the embodiment of the present application has at least the following advantages: in the embodiment of the present application, by associating the information outputted by the video monitoring with the information output by the WiFi detector, the specified inclusion target may be Multiple video recordings of a character (ie, all video recordings in a video recording containing a target person, which may be specified by a user) determine unique identification information of the target person, and obtain unique identification information of the target person.
  • the image acquisition device of all the WiFi detectors and according to the location of the image acquisition device where all the WiFi detectors are located, determine the trajectory information of the target person. In this way, only a small number of video recordings including the target person can be obtained to obtain the target person.
  • the trajectory information does not require analysis of a large number of video recordings, reducing the process of analyzing a large number of video recordings.
  • a processing server is provided in Embodiment 4 of the present application, and the processing server is connected to multiple image collection devices including a wireless fidelity WiFi detector, wherein the processing server and multiple image collections are The device is connected by wire or wirelessly.
  • the processing server specifically includes:
  • the interface module 11 is configured to obtain a plurality of specified video recordings including the target person, and obtain a correspondence between the unique identification information output by the WiFi detector and the detection time of the unique identification information.
  • the interface module may specifically be a data transceiver having a receiving capability and a transmitting capability.
  • the interface module can interact with a device capable of providing a video recording containing a target person by wire or wirelessly.
  • the interface module interacts with the image capturing device by wire or wirelessly; when the image capturing device outputs the video recording to the video memory, the interface module passes the wired or wireless mode and the video.
  • the memory interacts.
  • the interface module can interact with the device capable of providing a correspondence between the unique identification information and the detection moment of the unique identification information by wire or wirelessly.
  • the interface module interacts with the WiFi detector by wire or wirelessly; the WiFi detector uniquely identifies the information.
  • the interface module is wired or wirelessly Identify the memory to interact.
  • the data processor 12 is configured to determine a plurality of first image capturing devices that capture the specified video recordings; and according to a preset intersection manner, for at least two first image capturing devices of the plurality of first image capturing devices: Obtaining the occurrence moments of the target person in the specified video recording respectively, respectively determining a detection time interval including the appearance time, and respectively obtaining the WiFi detector of the first image acquisition device detected in the detection time interval. a set of unique identification information of the WiFi terminal; performing an intersection process on the obtained set of unique identification information of the WiFi terminal to obtain an intersection of the unique identification information;
  • the data processor may specifically be a CPU (Central Processing Unit) or the like having data processing capability.
  • CPU Central Processing Unit
  • the data processor 12 is configured to: when the preset intersection mode is an intersection of all the sets, for all the first image capturing devices in the plurality of first image capturing devices: respectively obtaining the target person in the office Determining the occurrence time in the specified video recording, respectively determining the detection time interval including the occurrence time, and respectively obtaining the set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval And performing intersection processing on the set of unique identification information of the WiFi terminal respectively obtained by all the first image collection devices in the plurality of first image collection devices, to obtain the intersection of the unique identification information.
  • the data processor 12 is specifically configured to: when the preset intersection mode is a loop take-over intersection,
  • the unique identifier information of the WiFi terminal specifically includes: a media access control MAC address of the WiFi terminal.
  • the modules of the device of the present application may be integrated into one or may be deployed separately.
  • the above modules can be combined into one module, or can be further split into multiple sub-modules.
  • An embodiment of the present application provides an application for performing a method for determining trajectory information of a target person provided by an embodiment of the present application at runtime.
  • a method for determining trajectory information of the target person is applied to a processing server, where the processing server is connected to multiple image collection devices including a wireless fidelity WiFi detector;
  • the method includes:
  • the image capture device captures a video recording and outputs the video recording
  • the WiFi detector detects the unique identification information of the WiFi terminal in its own detection area, and outputs a correspondence between the detected unique identification information and the detection time of the unique identification information;
  • the processing server obtains a plurality of specified video recordings including the target person based on the video recording; determining a plurality of first image capturing devices that capture the specified video recording; and according to the preset intersection manner, for the plurality of first images
  • At least two first image collection devices in the collection device respectively obtaining the occurrence moments of the target person in the specified video recording, respectively determining a detection time interval including the appearance time, and respectively according to the unique identification information
  • Corresponding relationship between the detection moments of the unique identification information obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval, and obtaining the unique identification information of the WiFi terminal
  • the set performs intersection processing to obtain a unique identification information intersection; the unique identification information of the WiFi terminal in which the unique identification information is centralized is determined as the unique identification information of the target person; and all the WiFis that detect the unique identification information of the target person are obtained.
  • the embodiment of the present application provides a storage medium for storing an application for performing a method for determining trajectory information of a target person provided by an embodiment of the present application.
  • the method includes:
  • the method for determining the trajectory information of the target person is applied to a system including a processing server and a plurality of image capturing devices connected to the processing server, and the image capturing device includes wireless Fidelity WiFi detector; the method includes:
  • the image capture device captures a video recording and outputs the video recording
  • the WiFi detector detects the unique identification information of the WiFi terminal in its own detection area, and outputs a correspondence between the detected unique identification information and the detection time of the unique identification information;
  • the processing server obtains a plurality of specified video recordings including the target person based on the video recording; determining a plurality of first image capturing devices that capture the specified video recording; and according to the preset intersection manner, for the plurality of first images
  • At least two first image collection devices in the collection device respectively obtaining the occurrence moments of the target person in the specified video recording, respectively determining a detection time interval including the appearance time, and respectively according to the unique identification information
  • Corresponding relationship between the detection moments of the unique identification information obtaining a set of unique identification information of the WiFi terminal detected by the WiFi detector of the first image acquisition device in the detection time interval, and obtaining the unique identification information of the WiFi terminal
  • the set performs intersection processing to obtain a unique identification information intersection; the unique identification information of the WiFi terminal in which the unique identification information is centralized is determined as the unique identification information of the target person; and all the WiFis that detect the unique identification information of the target person are obtained.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

L'invention concerne un procédé, un système et un serveur de traitement pour déterminer des informations de suivi d'une personne cible. Le procédé consiste à : acquérir de multiples enregistrements vidéo désignés ; déterminer de multiples premiers dispositifs de capture d'image qui ont capturé les enregistrements vidéo désignés ; par rapport aux premiers dispositifs de capture d'image, sur la base d'une technique d'intersection préétablie : acquérir des ensembles d'informations d'identification unique détectées par des détecteurs Wi-Fi des premiers dispositifs de capture d'image durant un intervalle de temps de détection ; réaliser un traitement d'intersection des ensembles acquis d'informations d'identification unique pour acquérir un ensemble d'informations d'identification unique ; déterminer les informations d'identification unique d'un terminal W-iFi dans l'ensemble d'identification unique comme étant les informations d'identification unique d'une personne cible ; acquérir l'ensemble des dispositifs de capture d'image à l'endroit où les détecteurs Wi-Fi qui ont détecté les informations d'identification unique de la personne cible sont situés ; et déterminer des informations de suivi de la personne cible sur la base des emplacements de tous les dispositifs de capture d'image à l'endroit où les détecteurs Wi-Fi sont situés. Dans des modes de réalisation de la présente invention, le besoin d'analyser un grand volume d'enregistrements vidéo est écarté.
PCT/CN2016/081596 2015-05-12 2016-05-10 Procédé, système et serveur de traitement pour déterminer des informations de suivi d'une personne cible WO2016180324A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US15/573,519 US10185023B2 (en) 2015-05-12 2016-05-10 Method, system, and processing server for determining track information of target person
EP16792174.1A EP3297276B1 (fr) 2015-05-12 2016-05-10 Procédé, système et serveur de traitement pour déterminer des informations de suivi d'une personne cible

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN201510241202.X 2015-05-12
CN201510241202 2015-05-12
CN201510308669.1A CN106296724B (zh) 2015-05-12 2015-06-05 一种目标人物的轨迹信息的确定方法、系统及处理服务器
CN201510308669.1 2015-06-05

Publications (1)

Publication Number Publication Date
WO2016180324A1 true WO2016180324A1 (fr) 2016-11-17

Family

ID=57247686

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/081596 WO2016180324A1 (fr) 2015-05-12 2016-05-10 Procédé, système et serveur de traitement pour déterminer des informations de suivi d'une personne cible

Country Status (1)

Country Link
WO (1) WO2016180324A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108540760A (zh) * 2017-03-01 2018-09-14 中国电信股份有限公司 视频监控识别方法、装置和系统
WO2022127553A1 (fr) * 2020-12-16 2022-06-23 深圳云天励飞技术股份有限公司 Procédé et appareil d'analyse d'itinéraire populaire, dispositif électronique et support de stockage

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101325694A (zh) * 2007-06-13 2008-12-17 中国科学院自动化研究所 结合无线射频识别技术的智能视频监控系统及其方法
CN202435522U (zh) * 2011-12-15 2012-09-12 张驰 一种多路监控摄像头追踪目标的装置
CN104092974A (zh) * 2014-05-27 2014-10-08 浙江工业大学 基于运动物体身份标识的多路视频剪辑拼接系统及其方法
US20150023562A1 (en) * 2013-07-18 2015-01-22 Golba Llc Hybrid multi-camera based positioning

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101325694A (zh) * 2007-06-13 2008-12-17 中国科学院自动化研究所 结合无线射频识别技术的智能视频监控系统及其方法
CN202435522U (zh) * 2011-12-15 2012-09-12 张驰 一种多路监控摄像头追踪目标的装置
US20150023562A1 (en) * 2013-07-18 2015-01-22 Golba Llc Hybrid multi-camera based positioning
CN104092974A (zh) * 2014-05-27 2014-10-08 浙江工业大学 基于运动物体身份标识的多路视频剪辑拼接系统及其方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3297276A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108540760A (zh) * 2017-03-01 2018-09-14 中国电信股份有限公司 视频监控识别方法、装置和系统
WO2022127553A1 (fr) * 2020-12-16 2022-06-23 深圳云天励飞技术股份有限公司 Procédé et appareil d'analyse d'itinéraire populaire, dispositif électronique et support de stockage

Similar Documents

Publication Publication Date Title
CN106296724B (zh) 一种目标人物的轨迹信息的确定方法、系统及处理服务器
US11374757B2 (en) Blockchain-based patrol inspection proof storage method, apparatus, and electronic device
US20200059978A1 (en) Method and apparatus for connecting to wireless access point
EP2688296B1 (fr) Système et procédé de surveillance vidéo
US10043079B2 (en) Method and apparatus for providing multi-video summary
US10372995B2 (en) System and method for previewing video
EP3296975A1 (fr) Procédé, dispositif, système et serveur de collecte et de fourniture de données d'image de véhicule
US11138171B2 (en) Passenger flow information collection method and apparatus, and passenger flow information processing method and apparatus
US9842258B2 (en) System and method for video preview
US20160189395A1 (en) Information processing apparatus, recording medium, and information processing method
US11048950B2 (en) Method and device for processing images of vehicles
CN111401238B (zh) 一种视频中人物特写片段的检测方法及装置
CN109413760B (zh) 一种无线连接方法及设备
JP2018181081A (ja) 画像認識エンジン連携装置およびプログラム
US20190116310A1 (en) Method of processing object in image and apparatus for same
WO2016180324A1 (fr) Procédé, système et serveur de traitement pour déterminer des informations de suivi d'une personne cible
US20180173704A1 (en) Information processing apparatus, information processing method, and program
CN108540747B (zh) 视频监控方法、装置和系统
US20170126951A1 (en) Updating an exposure table of an image sensor
US20170033877A1 (en) Method and Device for Triggering Specified Operation
US9916418B2 (en) Uploading measurement data of non-connected medical measuring devices
CN109246800B (zh) 一种无线连接的方法及设备
KR102656084B1 (ko) 이동경로 기반 객체 매핑 방법 및 장치
KR101706114B1 (ko) 영상 촬영 장치, 영상 분석 장치 및 방법과 이를 이용한 영상 분석 시스템
CN113469138A (zh) 对象检测方法和装置、存储介质及电子设备

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: 16792174

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15573519

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2016792174

Country of ref document: EP