WO2021038800A1 - 広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置 - Google Patents

広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置 Download PDF

Info

Publication number
WO2021038800A1
WO2021038800A1 PCT/JP2019/033945 JP2019033945W WO2021038800A1 WO 2021038800 A1 WO2021038800 A1 WO 2021038800A1 JP 2019033945 W JP2019033945 W JP 2019033945W WO 2021038800 A1 WO2021038800 A1 WO 2021038800A1
Authority
WO
WIPO (PCT)
Prior art keywords
advertisement
person
viewing
frames
time
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/JP2019/033945
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
山中良祐
堀之内省吾
増田拓哉
半谷敏規
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujitsu Ltd
Original Assignee
Fujitsu Ltd
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 Fujitsu Ltd filed Critical Fujitsu Ltd
Priority to JP2021541905A priority Critical patent/JP7265202B2/ja
Priority to PCT/JP2019/033945 priority patent/WO2021038800A1/ja
Priority to EP19943279.0A priority patent/EP4024313A4/en
Publication of WO2021038800A1 publication Critical patent/WO2021038800A1/ja
Anticipated expiration legal-status Critical
Priority to JP2022183505A priority patent/JP7421149B2/ja
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements
    • G06Q30/0246—Traffic
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06V40/18—Eye characteristics, e.g. of the iris
    • G06V40/193—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06T2207/30196—Human being; Person

Definitions

  • the present invention relates to an advertisement browsing information output method, an advertisement browsing information output program, and an information processing device.
  • Non-Patent Document 1 a technique for outputting the orientation of a face from a head image using a learning model
  • Patent Document 2 a technique for tracking a person between frames of a moving image is also known (see, for example, Non-Patent Document 2, Patent Document 1, etc.).
  • the person in the frame is the direction of the advertisement. It is thought that it can be estimated whether or not it is facing.
  • the estimation results in a plurality of frames obtained within a predetermined time the number of people who were facing the direction of the advertisement within the predetermined time and the time when the person was facing the direction of the advertisement can be obtained. Is thought to be possible.
  • the present invention provides an advertisement browsing information output method, an advertisement browsing information output program, and an information processing device capable of outputting accurate information that contributes to measuring the effectiveness of an advertisement from video information obtained from a camera.
  • the purpose is to provide.
  • the advertisement viewing information output method acquires video information taken by a camera that shoots an area near the place where the advertisement is installed, and in each frame of the video information, the head area of each photographed person is obtained.
  • Each of the persons is extracted, the line-of-sight direction of each of the persons is estimated based on the extracted head area, and each of the persons is based on the relationship between the position of each person and the place where the advertisement is installed and the line-of-sight direction of each of the persons. It is specified whether or not the advertisement is included in the field of view, and for each person who is determined to be the same person in a plurality of frames, whether or not the advertisement is viewed is determined based on the specified result in the plurality of frames, and the determination is made.
  • This is an advertisement browsing information output method in which a computer executes a process of generating advertisement browsing information regarding the number of people viewing the advertisement and outputting the advertisement browsing information based on the determination result of the processing.
  • FIG. 3A is a diagram showing the hardware configuration of the server
  • FIG. 3B is a diagram showing the hardware configuration of the user terminal.
  • FIG. 5 (a) to 5 (d) are diagrams for explaining the visual determination of each person in the frame.
  • 6 (a) to 6 (d) are diagrams for explaining person tracking.
  • FIG. 20A is a diagram showing an example of a visual recognition judgment result table in a modified example in which the attribute of a person is considered
  • FIG. 20B is an example of a browsing judgment result table in a modified example in which the attribute of a person is considered.
  • 21 (a) and 21 (b) are diagrams showing an example of an output screen in a modified example in which the attributes of a person are taken into consideration.
  • FIG. 28A is a diagram showing a browsing determination result table in a modified example in which the attributes of a person are taken into consideration
  • FIG. 29B is a diagram showing an example of an output screen. It is a figure which shows the modification of the advertisement effect measurement system.
  • FIG. 1 schematically shows the configuration of the advertising effectiveness measurement system 100 according to the first embodiment.
  • the advertisement effectiveness measurement system 100 of the first embodiment automatically detects how much a passerby is viewing an advertisement (regardless of format such as paper media or digital signage) installed in the city or in a station yard. It is a system that judges and outputs.
  • the advertising effectiveness measurement system 100 includes a camera 50, a server 10 as an information processing device, and a user terminal 70.
  • the camera 50, the server 10, and the user terminal 70 are connected to a network 80 such as the Internet.
  • the camera 50 is, for example, a camera (surveillance camera) installed at a station, and as shown in FIG. 2, it is assumed that the camera 50 is installed in the vicinity of the advertisement 110 provided on a pillar in the station yard.
  • the location of the camera may be any place where the area where the advertisement can be viewed can be photographed. For example, it may be installed facing the advertisement 110.
  • the shooting range (angle of view) of the camera 50 is assumed to include, for example, a region near the advertisement 110 as shown by a broken line frame in FIG.
  • the server 10 acquires the video information (moving image) taken by the camera 50, identifies the person who is facing the advertisement, and identifies the person who is viewing the advertisement 110. Further, the server 10 generates information about the number of people viewing the advertisement 110 and outputs the information to the user terminal 70.
  • the case where the person is facing the advertisement (the head is facing the advertisement) is expressed as "visualizing".
  • the direction of the head is represented by the deviation of the angle with respect to the reference direction.
  • the reference direction is the direction in which the face is directed straight toward the lens of the camera without twisting or moving the neck up and down.
  • the three-dimensional angles (Pitch, Roll, Yaw) indicating the direction of the head are all zero.
  • the face orientation and the line-of-sight direction can be estimated from the face orientation
  • the head orientation and the advertisement From the installation position, it can be determined whether or not the person is visually recognizing the advertisement. Therefore, in the first embodiment, the fact that the direction of the head at a certain point in time is toward the place where the advertisement is installed is regarded as the person "visualizing" the advertisement. Estimating the direction of the head in this way corresponds to estimating the direction of the line of sight.
  • a person is “visualizing” an ad, it means that the ad is likely to be in the person's field of view. Further, in the first embodiment, when the state in which the person "visualizes” the advertisement continues for a certain period of time or more (more than the minimum viewing time described later), it is assumed that the person "views” the advertisement. When a person "views” an advertisement, it is highly likely that the content of the advertisement can be confirmed, that is, it means that the person has viewed the advertisement.
  • the user terminal 70 is, for example, a terminal such as a business operator that provides a posting space (advertising space) for the advertisement 110 or a PC (Personal Computer) used by the advertiser of the advertisement 110.
  • the user terminal 70 requests the server 10 to output information in response to an input from the user, and receives and displays the information output from the server 10.
  • FIG. 3B schematically shows the hardware configuration of the user terminal 70.
  • the user terminal 70 includes a CPU (Central Processing Unit) 190, a ROM (Read Only Memory) 192, a RAM (Random Access Memory) 194, and a storage unit (here, an HDD (Hard Disk Drive)). )) 196, network interface 197, display unit 193, input unit 195, portable storage medium drive 199 and the like capable of reading programs, data and the like from the portable storage medium 191.
  • the display unit 193 includes a liquid crystal display and the like
  • the input unit 195 includes a keyboard, a mouse, a touch panel and the like.
  • Each component of the user terminal 70 is connected to the bus 198.
  • FIG. 3A schematically shows the hardware configuration of the server 10.
  • the server 10 includes a CPU 90, a ROM 92, a RAM 94, a storage unit (HDD) 96, a network interface 97, a portable storage medium drive 99, and the like.
  • Each component of the server 10 is connected to the bus 98.
  • a program stored in the ROM 92 or HDD 96 (including an advertisement viewing information output program) or a program read from the portable storage medium 91 by the portable storage medium drive 99 (including an advertisement viewing information output program).
  • the CPU 90 executing the above, the functions of the respective parts shown in FIG. 4 are realized. Note that FIG.
  • FIG. 4 also shows a visual recognition determination result table 40 and a browsing determination result table 42 stored in the HDD 96 or the like of the server 10.
  • the functions of each part in FIG. 4 may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • FIG. 4 shows a functional block diagram of the server 10.
  • the server 10 when the CPU 90 executes the program, the video acquisition unit 20 as the acquisition unit, the advertisement visual recognition determination unit 22, the advertisement viewing determination unit 24 as the determination unit, and the output as the generation unit.
  • the functions as the information generation unit 26 and the output unit 28 as the output processing unit are realized.
  • the CPU 90 functions as a moving image acquisition unit 20, an advertisement visual recognition determination unit 22, an advertisement viewing determination unit 24, and an output information generation unit 26.
  • the network interface 197 or the display unit 193 functions as an output unit 28.
  • the moving image acquisition unit 20 acquires the moving image taken by the camera 50 at predetermined time intervals and stores it in the moving image DB 38.
  • the advertisement visual recognition determination unit 22 acquires a necessary video from the video stored in the video DB 38 based on the instruction from the user terminal 70, and whether or not each person in the acquired video visually recognizes the advertisement. The process of determining whether or not is executed. For example, a video in a time zone specified by the user or a video in a predetermined time width is acquired. The advertisement visual recognition determination unit 22 stores the determination result in the visual recognition determination result table 40.
  • FIG. 5 and 6 show an outline of processing by the advertisement visual recognition determination unit 22.
  • the advertisement visual recognition determination unit 22 detects a person in each frame cut out from the moving image, and extracts the head region of each person as shown by the broken line frame in FIG. 5A. Then, the rotation angle (pitch, roll, yaw) in three dimensions is estimated as the direction of the head with respect to the reference direction from the image of the head region of each person. In the following, this rotation angle will be referred to as a "three-dimensional angle". As described above, the line-of-sight direction can be estimated based on the three-dimensional angle indicating the direction of the head. In FIG. 5B, the three-dimensional angle is indicated by an arrow.
  • This three-dimensional angle estimation is called three-dimensional head pose estimation, head pose estimation, or the like, and the technique disclosed in Non-Patent Document 1 described above can be adopted.
  • a learning model that inputs an image of the head region and outputs the direction of the head with respect to the reference direction is prepared in advance. Then, at the time of head pose estimation, a three-dimensional angle indicating the direction of the head is obtained by inputting an image of the head region of the person to be estimated into the learning model.
  • the administrator of the system according to the present embodiment sets a plurality of (for example, three) areas A, B, and C for the shooting area of the camera 50, for example, as shown in FIG. 5 (c). .. Then, the administrator sets the angle ranges ⁇ , ⁇ , and ⁇ in which there is a high possibility that the person existing in each of the areas A to C is visually recognizing the advertisement.
  • the advertisement visual recognition determination unit 22 determines that the advertisement is visually recognized if the direction (three-dimensional angle) in which the person is facing is within the angle range ⁇ . Specifically, for each of the pitch, roll, and yaw, the angle range conditions ⁇ 1 (pitch), ⁇ 2 (roll), and ⁇ 3 (yaw) are set as the angle range ⁇ . The advertisement visibility determination unit 22 determines that a person is visually recognizing an advertisement if all of the pitch angle, roll angle, and yaw angle constituting the head direction (three-dimensional angle) are within the designated angle ranges. To do.
  • the advertisement visual recognition determination unit 22 may determine whether or not it is within the angle range ⁇ specified in advance by using only the yaw angle among the pitch angle, the roll angle, and the yaw angle. Further, when the person is present in the area B, the advertisement visual recognition determination unit 22 determines that the advertisement is visually recognized if the direction (three-dimensional angle) in which the person is facing is within the angle range ⁇ . In this case as well, as in the case of area A, it may be determined whether the person is visually recognizing the advertisement by using all the three-dimensional angles (pitch, roll, yaw), or the person may use only the yaw angle. You may determine if you are viewing the advertisement.
  • the advertisement visual recognition determination unit 22 determines that the advertisement is visually recognized when the person is present in the area C and the direction (three-dimensional angle) in which the person is facing is within the angle range ⁇ . In this case as well, as in the case of areas A and B, it may be determined whether the person is visually recognizing the advertisement by using all three-dimensional angles (pitch, roll, yaw), or only the yaw angle is used. You may determine if the person is viewing the advertisement. In FIG. 5D, as a result of the above determination, a person who is determined to have a high possibility of visually recognizing the advertisement is shown with "true", and a person who is not is shown with "false". The number of areas set within the shooting range may be other than three.
  • each area does not have to be the same area, and the shooting range may be divided into the vertical direction and the horizontal direction. Further, the area and the angle range may be set manually by the system administrator, or the server 10 automatically sets the area and the angle range based on the relationship between the position of the advertisement and the shooting range input by the system administrator. May be good.
  • the advertisement visual recognition determination unit 22 performs person tracking using the appearance similarity of each person in each frame, and identifies the same person in each frame.
  • tracking will be described with reference to FIGS. 6 (a) to 6 (d).
  • FIG. 6A it is assumed that frames n-2, n-1, and n are obtained in chronological order in chronological order.
  • the advertisement visual recognition determination unit 22 detects a person by using an existing object detection model (for example, Faster R-CNN or SSD (Single Shot MultiBox Detector)) (see the broken line frame in FIG. 6B). ..
  • the advertisement visual recognition determination unit 22 obtains an N-dimensional vector from the whole body image of the person using the similarity learning model (see FIG. 6C), and groups in the time series direction based on the obtained N-dimensional vector. Is executed to identify the same person between frames (see FIG. 6D). It should be noted that such a tracking technique is described in Non-Patent Document 2 and Patent Document 1.
  • the advertisement visual recognition determination unit 22 obtains the "true” and "false” information of each person obtained in FIG. 5D and the information of the same person between the frames obtained by tracking as the visual recognition determination result. Summarize in table 40.
  • the visual recognition determination result table 40 has a structure as shown in FIG. 7. Specifically, the "personal ID”, “time stamp”, and “visual recognition determination” are stored in association with each other in the visual recognition determination result table 40.
  • the "personal ID” is identification information assigned to each person. The same personal ID is assigned to a person identified as the same person among a plurality of frames.
  • the "time stamp” is a time stamp attached to the frame cut out from the moving image, and stores the time stamp attached to the frame used when visually determining each person.
  • the "visual determination” stores the "true” and "false” information obtained by the visual determination in FIG. 5D.
  • the advertisement viewing determination unit 24 refers to the visual recognition determination result table 40 and determines whether or not each person has viewed the advertisement. For example, assume that the user is an advertiser who displays an advertisement for 30 seconds using digital signage. In this case, the user may want to know how many people were viewing the advertisement while displaying his / her advertisement. In such a case, the user specifies the 30 seconds from the user terminal 70 and requests the server 10 to output information on the number of viewers.
  • the advertisement visibility determination unit 22 receives the request, the advertisement visibility determination unit 22 refers to the data corresponding to the specified time in the visibility determination result table 40 and executes the browsing determination process of each person.
  • the server 10 stores the time schedule for displaying a plurality of advertisements
  • the user sends information for identifying the advertisement to be analyzed to the server 10, so that the advertisement is displayed on the server 10. Identify the time zone. Then, the server 10 generates the advertisement browsing information in the specified time zone.
  • the advertisement viewing determination unit 24 extracts the visual recognition determination result (having a common personal ID) of the same person within the specified time from the visual recognition determination result table 40, and the extracted visual recognition determination result is a specific condition. If the above conditions are satisfied, it is determined that the person is viewing the advertisement.
  • the "specific condition" is a case where the total value of the time when the person is viewing the advertisement is equal to or longer than the predetermined time (minimum viewing time).
  • the advertisement browsing determination unit 24 stores the result of the browsing determination executed as described above in the browsing determination result table 42.
  • the browsing determination result table 42 has a structure as shown in FIG. Specifically, the browsing determination result (true / false) is stored in the browsing determination result table 42 in association with the personal ID.
  • the output information generation unit 26 refers to the browsing determination result table 42, generates advertisement browsing information corresponding to the instruction from the user terminal 70, and passes it to the output unit 28. For example, as advertisement viewing information, information regarding the number of people viewing the advertisement is generated. Advertisement browsing information is information that contributes to measuring the effectiveness of advertisements.
  • the output unit 28 transmits (outputs) the advertisement viewing information received from the output information generation unit 26 to the user terminal 70.
  • the processing of the advertisement visual recognition determination unit 22 will be described with reference to the flowchart of FIG.
  • the moving image acquisition unit 20 acquires the moving image taken by the camera 50 at any time and stores it in the moving image DB 38. Further, it is assumed that the process of FIG. 9 is started at the timing when a new moving image is stored in the moving image DB 38.
  • step S10 the advertisement visual recognition determination unit 22 cuts out one frame from the moving image newly stored in the moving image DB 38 while holding the time stamp.
  • step S12 the advertisement visual recognition determination unit 22 extracts the head region in the cut out frame. After that, the advertisement visual recognition determination unit 22 executes steps S14 and S16 and step S18 in parallel at the same time.
  • step S14 the advertisement visual recognition determination unit 22 estimates the three-dimensional angle by the three-dimensional head pose estimation. That is, as described above, since the line-of-sight direction (the direction of the arrow shown in FIG. 5B) can be estimated from the three-dimensional angle of the head direction, the three-dimensional angle of the head direction is estimated in step S14. To do.
  • step S16 the advertisement visual recognition determination unit 22 makes a visual determination from a three-dimensional angle. In this case, the advertisement visual recognition determination unit 22 confirms in which area of FIG. 5A the position of each person is, and the three-dimensional angle of each person is included in the angle range set in the area. If so, it is determined that the advertisement is visually recognized.
  • the three-dimensional angle indicating the direction of the head is the three-dimensional equivalent to the line-of-sight direction.
  • the process of converting to an angle is performed between steps S14 and S16.
  • step S18 the advertisement visual recognition determination unit 22 assigns a personal ID by tracking.
  • step S18 is executed for the first time after starting the process of FIG. 9, a new personal ID is assigned to each person in the frame.
  • step S18 is executed for the second time or later, the same personal ID is given to the same person as the person included in the frames before that. Numbers are assigned, and new personal IDs are assigned to new persons.
  • step S20 the advertisement visual recognition determination unit 22 stores the visual recognition determination result in the visual recognition determination result table 40 in association with the personal ID. ..
  • the advertisement visibility determination unit 22 has the time stamp "2019/7" of the visibility determination result table 40 of FIG.
  • the personal ID (result of S18) and the result of visual recognition determination (result of S16) are stored in association with "/ 24 14:30:30".
  • step S22 the advertisement visual recognition determination unit 22 determines whether or not all the frames have been cut out from the moving image stored in the moving image DB 38. If the determination in step S22 is denied, the process returns to step S10. On the other hand, if the determination in step S22 is affirmed as a result of repeating steps S10 to S22, the entire process of FIG. 9 is terminated. At the stage when the processing of FIG. 9 is completed, the viewing determination for all the frames of the moving image newly stored in the moving image DB 38 is completed, and the visual recognition determination result is stored in the visual recognition determination result table 40 of FIG.
  • the process of FIG. 10 is the timing at which the user terminal 70 receives the output request of the advertisement viewing information at a specified time.
  • the user specifies, for example, from 14:30:30 on July 24, 2019 to 14:31:00 on the same day, via the user terminal 70, and the number of people viewing the advertisement. It is assumed that a request to output information has been made.
  • step S30 the advertisement viewing determination unit 24 uses the time zone (July 24, 2019, 14:30:30 to 14:31:00) specified from the visual determination result table 40. Extract data (up to seconds).
  • step S32 the advertisement viewing determination unit 24 selects one personal ID.
  • the advertisement viewing determination unit 24 selects the smallest number (for example, "001") among the personal IDs included in the extracted data.
  • the advertisement viewing determination unit 24 identifies the "false" or missing time from the data associated with the selected personal ID in chronological order.
  • the missing time means a time during which the line-of-sight direction of the person with the selected personal ID cannot be specified.
  • the line-of-sight direction cannot be specified, for example, when a person is not photographed or when the head area cannot be extracted.
  • step S36 the advertisement viewing determination unit 24 determines whether or not the specified time is less than the correction maximum time.
  • the advertisement is only for that short time. It is not realistic to say that you did not see.
  • the advertisement is visually recognized during that short period of time. It is considered reasonable to assume that it was.
  • the visual determination of that time is changed to "true".
  • the maximum correction time can be set by the system administrator or the like, and can be, for example, 0.5 sec or the like.
  • step S36 determines whether the advertisement viewing determination unit 24 is affirmed. If the determination in step S36 is affirmed, the process proceeds to step S38, and the advertisement viewing determination unit 24 corrects the visual recognition determination to "true". That is, the advertisement viewing determination unit 24 considers the "false” or missing time to be “true”. After that, the process proceeds to step S40. On the other hand, if the determination in step S36 is denied, the advertisement viewing determination unit 24 shifts to step S40 without correcting the visual determination result at the specified time.
  • the determination in step S36 is whether or not the number of frames determined to be "false” existing between the frames determined to be “true” among the visual determination results of the selected personal ID is less than a predetermined number. It can be said that it is judging. Further, it can be said that the determination in step S36 determines whether or not the number of missing frames among the frames determined to be "true” is less than a predetermined number.
  • step S40 the advertisement viewing determination unit 24 determines whether or not all the "false” or missing times have been specified. If the determination in step S40 is denied, the process returns to step S34, the next old "false” or missing time is specified, and the subsequent processes and determinations in steps S36 to S40 are executed. Then, when the determination in step S40 is affirmed, the process proceeds to step S42.
  • the advertisement browsing determination unit 24 executes the subroutine of the browsing determination process. Specifically, the advertisement viewing determination unit 24 executes the process according to the flowchart of FIG.
  • the advertisement viewing determination unit 24 first confirms the visual determination results in chronological order in step S50, and calculates the time during which "true" is continuous.
  • step S52 the advertisement viewing determination unit 24 accumulates the calculated time.
  • step S54 the advertisement viewing determination unit 24 determines whether or not all the data have been confirmed. If the determination in step S54 is denied, the process returns to step S50, the processing in steps S50 and S52, and the determination in step S54 are repeated. Then, when the determination in step S54 is affirmed, the process proceeds to step S56. When the determination in step S54 is affirmed, the cumulative value (integrated value) of the time during which the person with the selected personal ID is visually recognizing the advertisement is obtained.
  • step S56 the advertisement viewing determination unit 24 determines whether or not the accumulated time is equal to or longer than the minimum viewing time.
  • the minimum browsing time is a threshold value for determining the presence or absence of browsing from the accumulated time, and if the accumulated time is equal to or longer than the minimum browsing time, it is determined that the user has browsed.
  • the minimum browsing time can be set in advance by the system administrator, and can be set to, for example, 0.6 sec. If the determination in step S56 is affirmed, the process proceeds to step S58, and the advertisement viewing determination unit 24 determines that the person with the selected personal ID has viewed the advertisement, and the browsing determination result table 42 indicates that fact. To store.
  • step S56 determines whether the determination in step S56 is denied. If the determination in step S56 is denied, the process proceeds to step S60, and the advertisement browsing determination unit 24 determines that the person with the selected personal ID is not viewing the advertisement, and the browsing determination result table. That fact is stored in 42. After that, all the processing of FIG. 11 is completed, and the process proceeds to step S44 of FIG.
  • step S44 the advertisement viewing determination unit 24 determines whether or not all the personal IDs have been selected. If the determination in step S44 is denied, the process returns to step S22. Then, when the processing related to all the personal IDs included in the extracted data is completed, all the processing of FIG. 10 is completed.
  • step S70 the output information generation unit 26 refers to the browsing determination result table 42 and totals the number of personal IDs whose browsing determination result is “true”.
  • step S72 the output information generation unit 26 refers to the browsing determination result table 42 and totals the number of personal IDs whose browsing determination result is “false”.
  • step S74 the output information generation unit 26 generates an output screen as shown in FIG. 13 using the number aggregated in step S70 and the aggregated number in step S72, and delivers the output screen to the output unit 28. ..
  • the output unit 28 When the output unit 28 receives the output screen of FIG. 13 from the output information generation unit 26, the output unit 28 transmits it to the user terminal 70.
  • the output screen of FIG. 13 is displayed on the display unit 93 of the user terminal 70, the user can grasp the number of people who have viewed his / her own advertisement and the viewing ratio of the advertisement. (The percentage of people who were browsing the advertisement among the people who were passing near the advertisement) can be grasped. Therefore, the user can determine from the output screen of FIG. 13 whether or not to continue posting the advertisement, whether or not the cost-effectiveness of the advertisement is appropriate, and the like.
  • the output screen of FIG. 13 is an example. For example, only one of the number of people viewing the advertisement and the viewing ratio may be displayed. In addition, information other than the number of people viewing the advertisement and the viewing ratio may be displayed.
  • the advertisement visual field determination unit 22 extracts the head area of each photographed person in each frame of the moving image, and the extracted head.
  • the advertisement visual recognition determination unit 22 extracts the head area of each person photographed in each frame of the moving image (S12), and the person is extracted from the extracted head area. Each line-of-sight direction (three-dimensional angle) is estimated (S14). Further, the advertisement visual recognition determination unit 22 determines whether or not each person is visually recognizing the advertisement based on the relationship between the position of each person and the place where the advertisement is installed and the line-of-sight direction (three-dimensional angle) of each person (3D angle). S16). In addition, the advertisement viewing determination unit 24 determines the viewing of the advertisement for each person determined to be the same person in the plurality of frames (for each person with the same personal ID numbered) based on the visual recognition determination results in the plurality of frames.
  • the output information generation unit 26 totals the number of people who have viewed the advertisement (S70), and outputs information regarding the number of people viewing the advertisement to the user terminal 70 via the output unit 28 (S74). ..
  • the case cannot be regarded as the viewing of the advertisement (for example, the person). It is possible to prevent it from being judged as browsing (for example, when the direction of the advertisement is turned for a moment).
  • the value of the advertising space can be expressed as a numerical value, so that the company that manages the advertising space determines the price when providing the advertising space to the advertiser, and appeals the effect when the advertising space is used. It can be used.
  • the advertisement viewing determination unit 24 browses the advertisement when the cumulative value of the time determined to be visually recognizing the advertisement is equal to or more than the minimum viewing time (S56: affirmative). It is determined that it was (S58). As a result, when a person turns to the direction of the advertisement for a moment, it is possible not to determine that the advertisement is viewed.
  • the advertisement viewing determination unit 24 identifies the “false” or missing time (S34), and visually recognizes the specified time when it is less than the correction maximum time (S36: affirmative).
  • the determination result is corrected to "true” (S38).
  • the advertisement visual recognition determination unit 22 specifies an area in the frame in which the person is located, and the line-of-sight direction (three-dimensional angle) of the person is predetermined for the specified area. It is determined that the advertisement is visually recognized when the person is facing the direction in which the advertisement is displayed. As a result, even when the camera 50 and the advertisement 110 are separated from each other, it can be easily determined whether or not the person is visually recognizing the advertisement.
  • the camera 50 may be provided on the opposite side of the advertisement 110.
  • the advertisement visual recognition determination unit 22 extracts the head region from each frame and estimates the three-dimensional angle of the head direction in which the line-of-sight direction can be estimated.
  • the advertisement visual recognition determination unit 22 uses only the head region, and thus can be said to be a technique that takes more privacy into consideration.
  • the first embodiment uses only the head region, and thus can be said to be a technique that takes more privacy into consideration.
  • the image of a camera provided independently of the place where the advertisement is installed such as a surveillance camera, there are many passers-by whose face is not reflected in the surveillance camera. Even in such a case, the first embodiment can estimate the line-of-sight direction, and is highly versatile as compared with the technique that requires that the face is reflected.
  • step S156 the advertisement viewing determination unit 24 determines whether or not the time extracted in step S155 is equal to or longer than the minimum viewing time. If the determination in step S156 is affirmed, the process proceeds to step S58, and the advertisement viewing determination unit 24 determines that the person with the selected personal ID has viewed the advertisement, and displays the advertisement viewing determination result table 42. Store that effect. On the other hand, if the determination in step S156 is denied, the process proceeds to step S60, and the advertisement browsing determination unit 24 determines that the person with the selected personal ID is not viewing the advertisement, and the browsing determination result table. That fact is stored in 42. After that, all the processing of FIG. 14 is completed.
  • the browsing judgment is performed using the longest time among the times in which "true” is continuous in the visual recognition judgment result of the selected personal ID. Even in this way, as in the first embodiment, the person who viewed the advertisement can be identified with high accuracy.
  • step S250 the advertisement viewing determination unit 24 confirms the visual recognition determination results in chronological order, and identifies the time when it is first determined to be “true”.
  • step S252 the advertisement viewing determination unit 24 confirms the visual recognition determination results in chronological order, and finally identifies the time when it is determined to be “true”.
  • step S254 the advertisement viewing determination unit 24 calculates the time between the specified times. That is, the advertisement viewing determination unit 24 calculates the time from the determination that the advertisement is first viewed to the final determination that the advertisement is visually recognized.
  • step S256 the advertisement viewing determination unit 24 determines whether or not the time calculated in step S254 is equal to or longer than the minimum viewing time. If the determination in step S256 is affirmed, the process proceeds to step S58, and the advertisement viewing determination unit 24 determines that the person with the selected personal ID has viewed the advertisement, and displays the advertisement viewing determination result table 42. Store that effect. On the other hand, if the determination in step S256 is denied, the process proceeds to step S60, and the advertisement browsing determination unit 24 determines that the person with the selected personal ID is not viewing the advertisement, and the browsing determination result table. That fact is stored in 42. After that, all the processing of FIG. 15 is completed.
  • the browsing determination is performed using the time from the determination that the advertisement is first visually recognized to the final determination that the advertisement is visually recognized. Even in this way, it is possible to accurately identify the person who has viewed the advertisement, as in the case of the first embodiment and the modification 1 of the browsing determination process.
  • steps S34, S36, S38, and S40 of FIG. 10 may be omitted.
  • Output modification 1 In the first embodiment, the case where the server 10 executes the process of FIG. 10 by designating the time zone while displaying one advertisement on the user terminal 70 has been described, but the present invention is limited to this. It is not something that can be done. For example, it is possible to specify on the user terminal 70 to specify a certain day and total the number of people viewing the advertisement for each hour in that day.
  • the specified one-day data is extracted from the visual recognition judgment result table 40, and the processing of FIG. 10 is executed using the one-hour data, so that the one-hour browsing judgment result table 42 To get. Then, by repeatedly executing the process of FIG. 10 using the data for the next hour, the process of FIG. 10 using the data for the next hour, and so on, 1
  • the browsing determination result table 42 for each hour can be obtained.
  • the output information generation unit 26 can generate an output screen as shown in FIG. 16 by totaling, for example, the number of personal IDs whose browsing determination result is "true" at each time and graphing them. it can.
  • the screen as shown in FIG. 16 is displayed on the user terminal 70, the advertiser or the like can grasp at what time zone the advertisement is being viewed.
  • the provider of the advertising space can appropriately adjust the price (rental fee) of the advertising space according to the number of viewers per hour. For example, in FIG. 16, the rental fee for a time zone with 150 or more viewers can be increased, and the rental fee for a time zone with less than 150 viewers can be reduced.
  • the average value of the number of viewers in each time zone in a predetermined period may be displayed.
  • the number of viewers in each time zone of a plurality of days may be displayed separately.
  • the average value of the number of viewers in each time zone on weekdays, the average value of the number of viewers in each time zone on Saturday, and the average value of the number of viewers in each time zone on Sunday are displayed separately. And so on.
  • the output information generation unit 26 may generate a log listing the personal IDs of persons who are determined to be viewing the advertisement at each time.
  • the log of FIG. 18 is output from the server 10 to the user terminal 70, the log is analyzed by the user terminal 70, and the same screens as those in FIGS. 13, 16 and 17 are displayed on the display unit 193 as the analysis result. It may be displayed.
  • the attributes (gender and age) of each person are estimated at the time of visual recognition determination, and the advertisement viewing information is organized based on the attributes of each person when generating the advertisement viewing information. It may be that.
  • the advertisement visual recognition determination unit 22 executes the process of FIG. 19 instead of the process of FIG.
  • the advertisement visual recognition determination unit 22 executes the process of step S19 in parallel with the processes of steps S14 and S16 and step S18.
  • step S19 the advertisement visual recognition determination unit 22 estimates the attributes (gender, age) of the person from the head region.
  • AI Artificial Intelligence
  • the browsing determination result table 42 obtained as a result of the processing of FIG. 10 by the advertisement browsing determination unit 24 is a table as shown in FIG. 20 (b).
  • gender and age are associated with the personal ID.
  • the output information generation unit 26 aggregates the browsing determination results “true” and “false” by gender and age from the browsing determination result table 42 in FIG. 20 (b), as shown in FIG. 21 (a). You can generate a screen. By displaying the screen as shown in FIG. 21A on the user terminal 70, the advertiser or the like can accurately grasp the age group and gender of viewing the advertisement.
  • the output information generation unit 26 aggregates the browsing determination results for each time for both men and women and for both men and women. It is possible to generate an output screen as shown in FIG. 21 (b). By displaying the screen as shown in FIG. 21B on the user terminal 70, the advertiser or the like can grasp which of the men and women is viewing the advertisement more in which time zone. As a result, the advertiser or the like can determine what kind of advertisement should be placed at what time zone. In addition, the provider of the advertising space can adjust the price (rental fee) of the advertising space according to the number of viewers and the attributes of the person who is browsing.
  • Second Embodiment will be described in detail with reference to FIGS. 22 to 26.
  • the configuration of the advertisement effectiveness measurement system 100 of the second embodiment is the same as that of the first embodiment, but the point that the advertisement viewing determination unit 24 determines the viewing time length of the advertisement by each person and the output information generation.
  • the difference from the first embodiment is that the unit 26 generates an output screen regarding the viewing time of the advertisement.
  • the points different from the first embodiment will be described in detail, and the same or equivalent points as those of the first embodiment will be omitted or simplified.
  • FIG. 22 shows the processing of the advertisement viewing determination unit 24 according to the second embodiment. As a premise that the processing of FIG. 22 is performed, it is assumed that the processing of FIG. 9 is executed by the advertisement visual recognition determination unit 22, and the data is stored in the visual recognition determination result table 40 as shown in FIG.
  • the browsing time calculation process (S342) is executed instead of the step S42 (browsing determination process) of FIG. 10, and the other processes are the same as those of FIG.
  • step S342 the process according to the flowchart of FIG. 23 is executed.
  • steps S50, S52, S54 point at which the advertisement viewing determination unit 24 accumulates the time during which the visual recognition determination result "true” is continuous
  • step S56 cumulative time is the minimum viewing time.
  • the point of determining whether the time is longer than the time) is the same as that of the first embodiment (FIG. 11).
  • the advertisement browsing determination unit 24 stores the accumulated time as the browsing time length in the browsing determination result table 42.
  • each person can browse in the time zone (for example, the time zone in which the advertisement is displayed) designated by the user terminal 70.
  • the time length is stored in the browsing determination result table 42 (FIG. 24).
  • step S370 the output information generation unit 26 sets the viewing time length range of the aggregation target. For example, it is assumed that "0.6 sec or more and less than 2 sec", “2 sec or more and less than 7 sec", “7 sec or more and less than 15 sec", and the like can be selected as the browsing time length range. In this case, the output information generation unit 26 sets, for example, "0.6 sec or more and less than 2 sec" as the browsing time length range of the aggregation target.
  • step S372 the output information generation unit 26 associates the browsing time length included in the browsing time length range (0.6 sec or more and less than 2 sec) of the aggregation target from the browsing determination result table 42 (FIG. 24). Aggregate the number of personal IDs.
  • step S374 the output information generation unit 26 determines whether or not all the viewing time length ranges have been set as aggregation targets. If the determination in step S374 is denied, the process returns to step S370. After that, the output information generation unit 26 repeats step S372 while changing the viewing time length range of the aggregation target, and proceeds to step S376 when the determination in step S374 is affirmed.
  • the output information generation unit 26 When the process proceeds to step S376, the output information generation unit 26 generates an output screen using the total number of personal IDs and delivers it to the output unit 28.
  • the output information generation unit 26 generates, for example, an output screen as shown in FIG. 26. Since the output unit 28 outputs the output screen of FIG. 26 to the user terminal 70, by checking the output screen displayed on the user terminal 70, how long the person who was viewing the advertisement browses. You can see if you continued to do so.
  • the advertisement visual recognition determination unit 22 extracts the head region of each photographed person in each frame of the moving image (S12), and extracts the head region from the extracted head region.
  • the line-of-sight direction (three-dimensional angle) of each person is estimated (S14). Further, the advertisement visual recognition determination unit 22 determines whether or not each person is visually recognizing the advertisement based on the relationship between the position of each person and the place where the advertisement is installed and the line-of-sight direction (three-dimensional angle) of each person (3D angle). S16).
  • the advertisement viewing determination unit 24 determines the advertisement viewing time length for each person determined to be the same person in the plurality of frames (for each person with the same personal ID numbered) based on the visual recognition determination results in the plurality of frames. Identify (S358, S360). Further, the output information generation unit 26 aggregates the viewing time length of the advertisement of each person, and outputs the information regarding the viewing time length of the advertisement to the user terminal 70 via the output unit 28 (FIG. 25). As a result, in the second embodiment, since the viewing time length is specified from the visual recognition determination results in a plurality of frames for the same person, it cannot be regarded as the viewing of the advertisement (for example, the person is in the advertisement for a moment).
  • the value of the advertising space can be expressed as a numerical value, so that the company that manages the advertising space determines the price when providing the advertising space to the advertiser, and appeals the effect when the advertising space is used. It can be used.
  • the advertisement browsing determination unit 24 browses the cumulative value when the cumulative value of the time determined to be visually recognizing the advertisement is equal to or longer than the minimum browsing time (S56: affirmative).
  • the time length is set to (S358), and in other cases, the browsing time length is set to 0 (S360).
  • the time from the determination that the advertisement is first viewed to the final determination that the advertisement is visually recognized When it is equal to or longer than the minimum viewing time, the time may be set as the viewing time of the advertisement.
  • Output modification 1 In the second embodiment described above, an example of outputting a table (see FIG. 26) that aggregates the browsing time lengths of the time zones while displaying one advertisement has been described, but the present invention is not limited to this.
  • a graph may be generated by aggregating the browsing time length for each hour in a certain day. In this case, for example, a graph as shown in FIG. 27 can be generated.
  • the screen as shown in FIG. 27 is displayed on the user terminal 70, so that the advertiser and the like are viewing the advertisement by how many people are viewing the advertisement in each time zone. It is possible to understand how long a person is watching an advertisement.
  • the provider of the advertising space can appropriately adjust the price (rental fee) of the advertising space according to the tendency of the viewing time length for each time zone.
  • FIG. 27 shows a graph in which the browsing determination result table 42 for one day of the week is aggregated.
  • the browsing determination result table 42 for a plurality of days may be aggregated for each time zone to create a graph.
  • a graph may be created by aggregating the data of each time zone for each day of the week.
  • the output information generation unit 26 may generate a log listing the viewing time lengths of each person.
  • the log When the log is output from the server 10 to the user terminal 70, the log may be analyzed by the user terminal 70, and the same screen as in FIGS. 26 and 27 may be displayed on the display unit 193 as the analysis result. ..
  • the attributes (gender and age) of each person are estimated at the time of visual recognition determination, and the advertisement viewing information is organized based on the attributes of each person when generating the advertisement viewing information. You may do it.
  • the advertisement visual recognition determination unit 22 may execute the same process as in FIG. As a result, as the browsing determination result table 42, a table as shown in FIG. 28A can be obtained.
  • the output information generation unit 26 aggregates the browsing time lengths from the browsing determination result table 42 of FIG. 28 (a) in consideration of gender and age, as shown in FIG. 28 (b), for example.
  • Output screen can be generated.
  • the output screen of FIG. 28B shows the result of totaling the number of people for each viewing time length range for each gender and age.
  • the advertising effect measurement system 100 of the first and second embodiments has described the case where the server 10 that has acquired the moving image captured by the camera 50 performs various processes, but the present invention is not limited to this.
  • the advertising effectiveness measurement system 100'as shown in FIG. 29 may be adopted.
  • the camera 50 is connected to an information processing device 60 such as an edge gateway (for example, a wired connection).
  • the information processing device 60 is provided in the vicinity of the camera 50, and has the functions of the server 10 (each function shown in FIG. 4) described in the first embodiment. That is, the information processing device 60 receives the moving image from the camera 50 and executes the same processing as the server 10 of the first and second embodiments.
  • the information (output screen) generated by the information processing device 60 is transmitted to the server 10 and appropriately transmitted to the user terminal 70.
  • the information processing device 60 does not have to have all the functions shown in FIG.
  • the output information generation unit 26 may be included in the server 10.
  • the information processing device 60 may output the information of the browsing determination result table 42 to the server 10, and the server 10 may generate an output screen based on the browsing determination result table 42. ..
  • the above processing function can be realized by a computer.
  • a program that describes the processing content of the function that the processing device should have is provided.
  • the above processing function is realized on the computer.
  • the program describing the processing content can be recorded on a computer-readable storage medium (excluding the carrier wave).
  • a program When a program is distributed, it is sold in the form of a portable storage medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. It is also possible to store the program in the storage device of the server computer and transfer the program from the server computer to another computer via the network.
  • a portable storage medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. It is also possible to store the program in the storage device of the server computer and transfer the program from the server computer to another computer via the network.
  • the computer that executes the program stores, for example, the program recorded on the portable storage medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes the processing according to the program. The computer can also read the program directly from the portable storage medium and execute the process according to the program. In addition, the computer can sequentially execute processing according to the received program each time the program is transferred from the server computer.
  • Server information processing device
  • Video acquisition department acquisition department
  • Advertisement visibility judgment unit extraction unit, estimation unit, specific unit
  • Advertisement viewing judgment unit judgment unit
  • Output information generation unit generation unit
  • Output processing unit 50 cameras

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Multimedia (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Human Computer Interaction (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Ophthalmology & Optometry (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)
PCT/JP2019/033945 2019-08-29 2019-08-29 広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置 Ceased WO2021038800A1 (ja)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2021541905A JP7265202B2 (ja) 2019-08-29 2019-08-29 広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置
PCT/JP2019/033945 WO2021038800A1 (ja) 2019-08-29 2019-08-29 広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置
EP19943279.0A EP4024313A4 (en) 2019-08-29 2019-08-29 ADVERTISEMENT DISPLAY INFORMATION OUTPUT METHOD, ADVERTISEMENT DISPLAY INFORMATION OUTPUT PROGRAM AND INFORMATION PROCESSING DEVICE
JP2022183505A JP7421149B2 (ja) 2019-08-29 2022-11-16 広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2019/033945 WO2021038800A1 (ja) 2019-08-29 2019-08-29 広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置

Publications (1)

Publication Number Publication Date
WO2021038800A1 true WO2021038800A1 (ja) 2021-03-04

Family

ID=74683406

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/033945 Ceased WO2021038800A1 (ja) 2019-08-29 2019-08-29 広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置

Country Status (3)

Country Link
EP (1) EP4024313A4 (https=)
JP (2) JP7265202B2 (https=)
WO (1) WO2021038800A1 (https=)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023074802A1 (ja) * 2021-10-29 2023-05-04 パイオニア株式会社 情報処理装置、情報処理方法、および、情報処理装置用プログラム
JP2023096652A (ja) * 2021-12-27 2023-07-07 Ａｗｌ株式会社 広告閲覧判定システム、情報処理装置、及び広告閲覧判定プログラム
CN118471087A (zh) * 2024-04-29 2024-08-09 太龙智显科技（深圳）有限公司 Led数字标牌、广告信息播放方法、计算机及存储介质
WO2025141694A1 (ja) * 2023-12-26 2025-07-03 株式会社ジェイテクト 広告評価システムおよび広告評価方法

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102775512B1 (ko) * 2024-01-03 2025-03-06 스페이스비전에이아이주식회사 복수의 객체들을 추적하기 위한 사이니지 및 방법
KR102787700B1 (ko) * 2024-01-03 2025-03-28 스페이스비전에이아이주식회사 컨텐츠 시청 통계 데이터를 제공하기 위한 방법 및 장치
KR102665266B1 (ko) * 2023-12-04 2024-05-10 스페이스비전에이아이주식회사 옥외 광고용 컨텐츠를 송출하기 위한 사이니지 및 방법
KR102725289B1 (ko) * 2024-01-03 2024-11-01 스페이스비전에이아이주식회사 컨텐츠 시청 통계 데이터를 획득하기 위한 방법 및 장치
CN117408757B (zh) * 2023-12-14 2024-04-09 江西时刻互动科技股份有限公司 一种用于广告投放效果监测的智能评估系统
JP2025026815A (ja) * 2024-03-13 2025-02-26 三菱電機株式会社 評価支援装置、評価支援システム、評価支援方法およびプログラム
JP7555689B1 (ja) * 2024-03-26 2024-09-25 ジオテクノロジーズ株式会社 広告接触判定方法、広告接触判定プログラム、および広告接触判定装置

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011232876A (ja) * 2010-04-26 2011-11-17 Nippon Telegr & Teleph Corp <Ntt> コンテンツ注目度算出装置、コンテンツ注目度算出方法、およびコンテンツ注目度算出プログラム
JP2011233119A (ja) * 2010-04-30 2011-11-17 Nippon Telegr & Teleph Corp <Ntt> 広告効果測定装置、広告効果測定方法およびプログラム
JP2017151582A (ja) 2016-02-23 2017-08-31 Kddi株式会社 カメラの撮影画像に映る人物を追跡する画像解析装置、プログラム及び方法

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4037130B2 (ja) 2002-02-27 2008-01-23 沖電気工業株式会社 情報配信システムおよび情報配信方法
JP2008112401A (ja) 2006-10-31 2008-05-15 Mitsubishi Electric Corp 広告効果測定装置
JP5103287B2 (ja) 2008-06-10 2012-12-19 日本電信電話株式会社 広告効果測定装置、広告効果測定方法、広告効果測定プログラムおよびそのプログラムを記録した記録媒体
JP5245691B2 (ja) 2008-09-29 2013-07-24 セイコーエプソン株式会社 情報処理装置、サーバ装置およびプログラム
JP2011070629A (ja) 2009-08-25 2011-04-07 Dainippon Printing Co Ltd 広告効果測定システム及び広告効果測定装置
JP2012123727A (ja) 2010-12-10 2012-06-28 Hitachi Solutions Ltd 広告効果測定サーバ、広告効果測定装置、プログラム、広告効果測定システム
US20130342689A1 (en) * 2012-06-25 2013-12-26 Intel Corporation Video analytics test system
US10424103B2 (en) * 2014-04-29 2019-09-24 Microsoft Technology Licensing, Llc Display device viewer gaze attraction
JP2015228145A (ja) 2014-06-02 2015-12-17 隆 平林 表示装置、デジタル表示システム及びデジタル表示プログラム
JP2015015031A (ja) 2014-08-12 2015-01-22 株式会社日立ソリューションズ 広告効果測定サーバ、広告効果測定システム、プログラム
JP2017010524A (ja) 2015-06-22 2017-01-12 株式会社東芝 情報処理装置、情報処理方法およびプログラム
JP2018055248A (ja) * 2016-09-27 2018-04-05 ソニー株式会社 情報収集システム、電子棚札、電子ｐｏｐ、文字情報表示装置
JP2018106229A (ja) 2016-12-22 2018-07-05 キヤノンマーケティングジャパン株式会社 情報処理装置、情報処理装置の制御方法及びプログラム
JP6615800B2 (ja) 2017-01-11 2019-12-04 株式会社東芝 情報処理装置、情報処理方法およびプログラム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011232876A (ja) * 2010-04-26 2011-11-17 Nippon Telegr & Teleph Corp <Ntt> コンテンツ注目度算出装置、コンテンツ注目度算出方法、およびコンテンツ注目度算出プログラム
JP2011233119A (ja) * 2010-04-30 2011-11-17 Nippon Telegr & Teleph Corp <Ntt> 広告効果測定装置、広告効果測定方法およびプログラム
JP2017151582A (ja) 2016-02-23 2017-08-31 Kddi株式会社 カメラの撮影画像に映る人物を追跡する画像解析装置、プログラム及び方法

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
KINEBUCHI, TETSUYA ET AL.: "Image Processing Techniques for Measuring Advertising Effectiveness of Digital Signage", NTT TECHNICAL REVIEW, 2009, pages 1 - 6, XP055893639 *
MICHAEL THOREAUNAVINDA KOTTEGE, ARXIV.ORG, 20 June 2018 (2018-06-20), Retrieved from the Internet <URL:https://arxiv.org/pdf/1806.07592.pdf>
NATANIEL RUIZEUNJI CHONGJAMES M. REHG: "Fine-Grained Head Pose Estimation Without", ARXIV.ORG, 13 April 2018 (2018-04-13), Retrieved from the Internet <URL:https://arxiv.org/pdf/1710.00925.pdf>

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023074802A1 (ja) * 2021-10-29 2023-05-04 パイオニア株式会社 情報処理装置、情報処理方法、および、情報処理装置用プログラム
JPWO2023074802A1 (https=) * 2021-10-29 2023-05-04
JP7665041B2 (ja) 2021-10-29 2025-04-18 パイオニア株式会社 情報処理システム、情報処理方法、および、プログラム
JP2023096652A (ja) * 2021-12-27 2023-07-07 Ａｗｌ株式会社 広告閲覧判定システム、情報処理装置、及び広告閲覧判定プログラム
WO2025141694A1 (ja) * 2023-12-26 2025-07-03 株式会社ジェイテクト 広告評価システムおよび広告評価方法
CN118471087A (zh) * 2024-04-29 2024-08-09 太龙智显科技（深圳）有限公司 Led数字标牌、广告信息播放方法、计算机及存储介质

Also Published As

Publication number Publication date
JP7265202B2 (ja) 2023-04-26
EP4024313A1 (en) 2022-07-06
JP2023016848A (ja) 2023-02-02
JPWO2021038800A1 (https=) 2021-03-04
EP4024313A4 (en) 2022-08-17
JP7421149B2 (ja) 2024-01-24

Similar Documents

Publication Publication Date Title
JP7421149B2 (ja) 広告閲覧情報出力方法及び広告閲覧情報出力プログラム、並びに情報処理装置
US20250258866A1 (en) Automated media analysis for sponsor valuation
JP4934861B2 (ja) 表示システム、表示方法、表示効果測定システム、及び、表示効果測定方法。
JP6185186B2 (ja) コードスキャン結果情報を提供するための方法及びシステム
KR101616652B1 (ko) 디지털 광고 시스템
CN107431828B (zh) 用于识别相关媒体内容的方法和系统
JP6879379B2 (ja) 接客支援装置、接客支援方法、及びプログラム
JP5224360B2 (ja) 電子広告装置、電子広告方法及びプログラム
JP5511035B2 (ja) 広告配信対象者特定装置、および、広告配信装置
JP5113721B2 (ja) メディア情報の注目度測定装置、メディア情報の注目度測定方法、メディア情報の注目度測定プログラムおよびそのプログラムを記録した記録媒体
JP2018198079A (ja) ソーシャルネットワーキングエンジンのユーザにコンテンツを方向付けるためのシステム及び方法
US11227307B2 (en) Media content tracking of users&#39; gazing at screens
US9449231B2 (en) Computerized systems and methods for generating models for identifying thumbnail images to promote videos
JP2014532202A (ja) 仮想広告プラットフォーム
US20140325055A1 (en) System and method for automatic selection of a content format
US20210385426A1 (en) A calibration method for a recording device and a method for an automatic setup of a multi-camera system
KR20150034925A (ko) 매장의 디스플레이 장치를 이용한 광고 방법 및 장치
JP5272214B2 (ja) 広告効果指標測定装置、広告効果指標測定方法およびプログラム
JP5772942B2 (ja) 情報処理装置及び情報処理プログラム
CN108369647A (zh) 基于图像的质量控制
KR20200092630A (ko) 체계화 및 정형화된 교육으로 인증된 청소 작업자를 배출하는 청소 교육 서비스 제공 방법
US11250271B1 (en) Cross-video object tracking
JP6944020B2 (ja) 情報処理装置
US20250004685A1 (en) Information processing device, display system, and information processing method
US20200160400A1 (en) Computer-implemented method of selecting content, content selection system, and computer-readable recording medium

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: 19943279

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021541905

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2019943279

Country of ref document: EP

Effective date: 20220329