WO2012043291A1 - 広告配信対象者特定装置、および、広告配信装置 - Google Patents
広告配信対象者特定装置、および、広告配信装置 Download PDFInfo
- Publication number
- WO2012043291A1 WO2012043291A1 PCT/JP2011/071307 JP2011071307W WO2012043291A1 WO 2012043291 A1 WO2012043291 A1 WO 2012043291A1 JP 2011071307 W JP2011071307 W JP 2011071307W WO 2012043291 A1 WO2012043291 A1 WO 2012043291A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- person
- advertisement
- advertisement distribution
- score
- target person
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0261—Targeted advertisements based on user location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09F—DISPLAYING; ADVERTISING; SIGNS; LABELS OR NAME-PLATES; SEALS
- G09F19/00—Advertising or display means not otherwise provided for
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09F—DISPLAYING; ADVERTISING; SIGNS; LABELS OR NAME-PLATES; SEALS
- G09F27/00—Combined visual and audible advertising or displaying, e.g. for public address
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Definitions
- the present invention relates to an advertisement distribution target person identification device, an advertisement distribution apparatus, an advertisement distribution target person identification method, an advertisement distribution method, a program, and a recording medium.
- the present invention relates to an advertisement distribution target person specifying device, an advertisement distribution apparatus, an advertisement distribution target person specifying method, an advertisement distribution method, a program, and a recording that can improve the advertising effect by specifying the target person of the advertisement distribution.
- the purpose is to provide a medium.
- the advertisement distribution target person specifying device of the present invention includes: Image acquisition means for acquiring images of people present within and outside the visible range of the advertisement; An expected movement range calculating means for calculating a future expected movement range of the person from the image; Score calculating means for calculating a score from the relationship between the visible range of the advertisement and the calculated expected movement range; And an advertisement distribution target person specifying means for specifying a person who is to distribute an advertisement from the calculated score.
- the advertisement distribution apparatus of the present invention A means for identifying the target of the advertisement distribution, Ad delivery means, The advertisement distribution means selects an advertisement to be distributed according to the attribute of the advertisement distribution target specified by the advertisement distribution target specifying means,
- the advertisement distribution target person specifying means is the advertisement distribution target person specifying device of the present invention.
- the advertisement distribution target person identification method includes: An image acquisition process for acquiring images of people present within and outside the visible range of the advertisement; From the image, an expected movement range calculation step for calculating a future movement range of the person, A score calculation step of calculating a score from the relationship between the visible range of the advertisement and the calculated expected movement range; An advertisement distribution target person specifying step of specifying a person who is to distribute an advertisement from the calculated score.
- the advertisement distribution method of the present invention includes: The process of identifying the target audience, Ad delivery process, In the advertisement distribution step, select an advertisement to be distributed according to the attribute of the advertisement distribution target person specified in the advertisement distribution target person specifying step,
- the advertisement distribution target person specifying step uses the advertisement distribution target person specifying method of the present invention.
- the program of the present invention is characterized by causing a computer to execute the advertisement distribution target person specifying method of the present invention or the advertisement distribution method of the present invention.
- the recording medium of the present invention records the program of the present invention.
- an advertisement distribution target person specifying device an advertisement distribution apparatus, an advertisement distribution target person specifying method, an advertisement distribution method, a program, and a recording capable of improving the advertising effect by specifying the advertisement distribution target person Media can be provided.
- FIG. 1 is a diagram illustrating the visible range of an advertisement.
- FIG. 2 is a block diagram showing the configuration of the first embodiment of the advertisement distribution target person specifying device of the present invention.
- FIG. 3 is a flowchart showing processing performed by the advertisement distribution target person specifying device according to the first embodiment of the present invention.
- FIG. 4 is a flowchart showing details of the process of the predicted movement range calculation step in FIG.
- FIG. 5 is a diagram for explaining a movement distance of a person between frames.
- FIG. 6 is a diagram for explaining a difference in the size of a person's head between frames.
- FIG. 7 is a diagram illustrating an example of a grid map of predicted movement range definition information held by the predicted movement range calculation unit.
- FIG. 1 is a diagram illustrating the visible range of an advertisement.
- FIG. 2 is a block diagram showing the configuration of the first embodiment of the advertisement distribution target person specifying device of the present invention.
- FIG. 3 is a flowchart showing processing performed by the advertisement
- FIG. 8 is a diagram illustrating an example of a grid map in which progress information is added to the predicted movement range definition information.
- FIG. 9 is a diagram for explaining a visible range of an advertisement in the second embodiment.
- FIG. 10 is a block diagram showing a configuration of the second embodiment of the advertisement distribution subject person specifying device of the present invention.
- FIG. 11 is a flowchart showing processing performed by the advertisement distribution target person specifying device according to the second embodiment of the present invention.
- FIG. 12 is a diagram illustrating an example of a grid map in which environment information is added to the predicted movement range definition information.
- FIG. 13 is a block diagram illustrating a configuration of the advertisement distribution apparatus according to the third embodiment of the present invention.
- FIG. 14 is a flowchart illustrating processing performed by the advertisement distribution apparatus according to the third embodiment.
- the predicted movement range calculation means calculates a future predicted movement range from the person position information, the person progress information, and the person attribute information.
- the score calculation means calculates a score by adding the environmental information in the visible range.
- the score calculation means calculates a score by weighting the person.
- the predicted movement range calculation means includes a grid map creation means for the person.
- the advertisement distribution target person specifying device the advertisement distribution apparatus, the advertisement distribution target person specifying method, and the advertisement distribution method of the present invention will be described in detail.
- the present invention is not limited to the following embodiments.
- symbol is attached
- FIG. 1 is a diagram illustrating the concept of an advertisement distribution target person specifying device 10 according to the first embodiment.
- FIG. 1A is a diagram illustrating a state in which an electronic advertisement distribution device (advertisement distribution device) is provided on an outer wall or the like.
- a large screen display 100a and a camera 100b constituting the electronic advertisement distribution apparatus are installed outside the outer wall.
- the inside of the line surrounded by the rectangular parallelepiped shape indicates the visible range (space) of the advertisement.
- the visible range can be determined for each display installation location in consideration of the size of the display, the presence or absence of obstacles such as a roof, the position of the roadway, and the like.
- FIG. 1A shows a state where two persons A and B are representatively in the visible range.
- the person A is slowly walking in a place away from the display 100a (a place where the display 100a is difficult to see), and the person B is walking fast in a place relatively close to the display 100a (a place where the display 100a is easy to see).
- Both the persons A and B are in a state where image information is acquired by the camera 100b.
- FIG. 1B is a diagram illustrating a state in which the movements of the persons A and B are viewed from above.
- the arrows in FIG. 1 (b) indicate the direction and speed in which each person is moving. Here, the longer the arrow, the faster the moving speed.
- the hatched box is a range in which the future movement position of each person is predicted.
- the target target
- it is effective to deliver the advertisement
- It is a feature of the present invention that it can be determined.
- the present embodiment will be described with reference to a block diagram of the advertisement distribution target person specifying device and a flowchart showing processing performed by the advertisement distribution target person specifying device.
- FIG. 2 shows a block diagram of a configuration of the advertisement distribution target person specifying device in the present embodiment.
- FIG. 3 shows a flowchart of the advertisement distribution target person specifying method in this embodiment.
- the advertisement distribution target person specifying device 10 of the present embodiment includes an image acquisition means 11, an expected movement range calculation means 12, a score calculation means 13, an advertisement distribution target person specification means 14, and an attribute.
- An information database 15 and a score calculation information database 16 are provided.
- the image acquisition unit 11 is connected to the expected movement range calculation unit 12.
- the expected movement range calculation unit 12 is connected to the score calculation unit 13.
- the score calculation means 13 is connected to the advertisement distribution target person specifying means 14.
- the expected movement range calculation means 12 is connected to the attribute information database 15.
- the score calculation means 13 is connected to the score calculation information database 16.
- the advertisement distribution target person specifying device of this embodiment includes an output unit as an arbitrary component.
- each component of the image acquisition unit 11, the predicted movement range calculation unit 12, the score calculation unit 13, and the advertisement distribution target person identification unit 14 indicates a functional unit block, not a hardware unit configuration.
- Each component of the advertisement distribution target person specifying device 10 includes a central processing unit (CPU) of an arbitrary computer, a memory, a program that realizes the components shown in the figure loaded in the memory, and a random access memory that stores the program ( (RAM), read-only memory (ROM), hard disk (HD), optical disk, floppy disk (FD), etc. Is done.
- the attribute information database 15 and the score calculation information database 16 may be a device built-in type or an external type such as an external storage device.
- the both databases may be stored in a server on the network via the network connection interface.
- the output means include a monitor that outputs an image (for example, various image display devices such as a liquid crystal display (LCD) and a cathode ray tube (CRT) display), a printer that outputs by printing, and the like.
- LCD liquid crystal display
- CRT cathode ray tube
- the image acquisition unit 11 acquires image information of a person who exists within and outside the visible range of the advertisement (step S10).
- the image information includes, for example, position information and progress information.
- the progress information can include, for example, a traveling speed, a traveling direction, and the like.
- the image acquisition means 11 includes, for example, a CCD (Charge Coupled Device) camera, a CMOS (Complementary Metal Oxide Semiconductor) camera, an image scanner, and the like.
- the image acquisition means 11 preferably includes two or more cameras. In this way, the image acquisition unit 11 can calculate the position information with high accuracy by processing the image information generated by each of the two or more cameras while associating them with each other. In addition, the accuracy of matching with attribute information in the expected movement range calculation means described later can be increased.
- the traveling speed and traveling direction of a specific person can be calculated from the history of the position information of the person, for example.
- the history of the position information of the person is stored in association with information for identifying the person, for example, feature data of the person's face.
- the image acquisition unit 11 detects position information of a person
- the image acquisition unit 11 also detects feature data of the person's face.
- the image acquisition unit 11 searches the data stored in the image acquisition unit 11 for the same feature data as the facial feature data detected this time.
- the image acquisition unit 11 stores the newly detected position information in association with the searched feature data. By repeating this process, the image acquisition means 11 stores a history of human position information.
- the information indicating the history of the person's position information includes, for example, the movement distance, comparison with the predicted position, head size, head orientation, clothing commonality, face similarity, gender It may be calculated based on parameters such as degree and age.
- the following tracking processing is performed by the image acquisition unit 11. Examples of the parameter of the object data for determining the identity of a person include the following. However, the parameters of the object data are not limited to these parameters.
- ⁇ Comparison with predicted position> It can be predicted which position the person in the image of a certain frame moves to in the image of the next frame. For example, the position in which the person shown in the image of the (n ⁇ 1) th frame moves in the next nth frame is determined from the image of the (n ⁇ 1) th frame and the image of the n ⁇ 2th frame or earlier. Predictable. It is considered that the identity of a person is higher as the distance between the two points between the position of the person in the nth frame image predicted in the (n ⁇ 1) th frame and the actual position in the nth frame is smaller.
- ⁇ Head size> Usually, the size of the head of the same person does not change abruptly between successive frames. For example, as shown in FIG. 6, assuming that the head size of an arbitrary person in the (n ⁇ 1) th frame is h n ⁇ 1 and the head size in the nth frame is h n , these sizes are as follows. The smaller the difference in diff head-size , the higher the identity of the person.
- ⁇ Head orientation> In general, since a human moves in a certain direction, it is rare that the head orientation in one frame and the head orientation in the next frame are extremely different. Therefore, the identity of the person can be determined by comparing the head direction in the (n-1) th frame with the head direction in the nth frame. The smaller the difference between the head direction in the (n-1) th frame and the head direction in the nth frame, the higher the identity of the person.
- the direction in which the head is facing when moving is considered to coincide with the traveling direction of the person. Therefore, the identity of the person is determined by comparing the direction of movement predicted from the head direction of the (n-1) th frame and the direction of movement between the (n-1) th frame and the nth frame. it can. The smaller the difference between the head direction in the (n ⁇ 1) th frame and the direction moved from the (n ⁇ 1) th frame to the nth frame, the higher the identity of the person.
- ⁇ Facial similarity> The face of the same person does not change abruptly between successive frames. Therefore, the identity of the person can be determined based on the face of the person shown in the frame image.
- the difference in person's face between frames can be quantified by template matching or the like. The smaller the value quantified by these methods, the higher the identity of the person.
- ⁇ Gender degree> The ceremoniity and masculinity of the face of the same person does not change abruptly between successive frames. Therefore, it is possible to determine the identity of a person based on the americanity and masculinity of the person shown in the frame image.
- the gender degree can be output based on the face image by the classifier. For example, a value close to 0 may be output as the face of a person in the frame image looks feminine, and a value close to 1 may be output as it looks like a man.
- the gender degree is output as described above, it is considered that the smaller the difference between the gender degree in the (n-1) th frame and the gender degree in the nth frame, the higher the identity of the person.
- ⁇ Age> The age of the same person does not change abruptly between successive frames. Therefore, the identity of the person can be determined based on the age of the person shown in the frame image.
- the human age can be estimated based on the face image by a discriminator that handles continuous quantities. The smaller the difference between the age estimated in the (n-1) th frame and the age estimated in the nth frame, the higher the identity of the person.
- whether or not to use it for tracking a person can be individually set.
- determining whether or not a plurality of images detected between a plurality of frames are the same person it is preferable to use a plurality of pieces of information among the information of each parameter described above.
- Whether or not a person shown in a certain frame image is shown in the previous frame image can be determined by, for example, the level of correlation of the object data. For example, it is assumed that one person W is detected in the nth frame image and three persons A, B, and C are detected in the n ⁇ 1th frame image.
- the predicted movement range calculation means 12 calculates the future predicted movement range of the person from the image information obtained by the image acquisition means 11 (step S20).
- the predicted movement range calculation means 12 preferably calculates the predicted movement range of the person in the future from the position information and progress information of the image information and the attribute information of the person.
- the position information includes the history of position information described above.
- the attribute information of the person is acquired by referring to the image information obtained by the image acquisition unit 11 in the attribute information database 15 and matching the image information.
- the person attribute information includes information selected from age, sex, orientation (front, back, etc.), past history, and the like. In this embodiment, the attribute includes at least age.
- the predicted movement range calculation means 12 calculates the predicted movement range using the movement direction of the person, preferably the movement speed, calculated based on the position information history stored in the attribute information database 15.
- the expected movement range definition information is a grid map for each attribute according to age group. This grid map shows what kind of probability distribution is made in the area around the person. In each grid map, the grid corresponding to the current position of the person has the highest probability of movement, and the probability of movement decreases as the distance from the current position increases. The rate of the probability decrease varies depending on, for example, the age group. That is, the expected movement range calculation unit 12 changes the expected movement range according to the age group.
- FIG. 8 shows an example of a grid map in which the progress information of the person calculated based on the history of the position information is added to the expected movement range definition information for each attribute by age group.
- a region with a high probability spreads in the calculated moving direction. Even when the progress information is taken into account, the region with a higher probability is larger for the infant than for the adult.
- the predicted moving range calculation means 12 may store predicted moving range information for each age group for each moving direction of the person.
- the predicted movement range calculation unit 12 may store predicted movement range information for each age group and information indicating how to change the predicted movement range according to the movement direction of the person. These pieces of information may be stored in the attribute information database 15, for example.
- the score calculation means 13 calculates a score from the relationship between the visible range of the advertisement and the calculated expected movement range of the person (step S30). Specifically, for example, the score can be calculated from the size of the overlap area between the obtained grid map and the visible range. Information regarding the visible range may be stored in the score calculation information database 16. In this case, the score calculation means 13 refers to the data stored in the score calculation information database 16 and calculates the score.
- the advertisement distribution target person specifying unit 14 selects the highest score from a plurality of scores calculated for each person from whom the image is acquired. Then, the person corresponding to the highest score is specified as the advertisement distribution target person (step S40). It can be determined that a person with a high score is highly likely to be particularly interested in the advertisement video from the movement pattern and attribute indicated in the expected movement range.
- FIG. 4 is an example of a detailed flowchart of step S20 for calculating the expected movement range shown in FIG.
- the expected movement range calculation unit 12 first acquires the image information acquired by the image acquisition unit 11 (step S21). From the acquired image information, the attribute information database 15 is referenced to generate position information, progress information, and attribute information of the person from whom the image was acquired (step S22). Further, a grid map is created from the generated information (step S23). And the said grid map is output to the score calculation means 13 as estimated moving range information (step S24). For example, when information on the movement direction and age group of the person is generated in step S22, the predicted movement range calculation unit 12 calculates the predicted movement range using the movement direction and age group of the person. When the moving speed is further calculated in step S22, the predicted moving range calculation means 12 calculates the predicted moving range using the moving direction and moving speed of the person and the age group.
- the predicted moving range calculation means 12 may determine the predicted moving range using only the moving direction (preferably the moving speed) without using the human attribute.
- FIG. 9 is a diagram illustrating the concept of the advertisement distribution target person specifying device 20 according to the second embodiment.
- FIG. 9A is a diagram of a state where an electronic advertisement distribution device (advertisement distribution device) is provided on an outer wall or the like
- FIG. 9B is a diagram of FIG. 9A viewed from above. is there.
- FIG. 9A is the same as FIG. 1 except that a ticket gate of a station exists in the visible range.
- the advertisement can be seen from the premises of the illustrated station. However, although the person B in the station premises acquires image information with the camera 100b, the ticket gate becomes an obstacle and the display 100a is difficult to see.
- FIG. 10 shows a block diagram of a configuration of the advertisement distribution target person specifying device 20 in the present embodiment.
- FIG. 11 shows a flowchart of the advertisement distribution target person specifying method in this embodiment.
- the advertisement distribution target person specifying device 20 according to the present embodiment is the advertisement distribution target person specifying device according to the first embodiment, except that the score calculation information database 26 includes the environmental information data in the visible range. 10 is the same configuration.
- the advertisement distribution target person identifying method in the present embodiment includes the environment information of the visible range before calculating a score from the relationship between the visible range of the advertisement and the calculated expected movement range of the person (step S30). In this case (step S26: Yes), the information is acquired (step S28), and the score is calculated by taking into consideration the obtained environment information of the visible range (step S30).
- FIG. 12 shows an example of a grid map in which the environment information of the visible range is added to the predicted movement range definition information described in the first embodiment.
- black portions represent station ticket gates.
- the right side of the ticket gate is the station premises.
- white circles represent persons X and Y.
- the persons X and Y are virtual persons having the same attribute, the person X is in a place where the display 100a outside the station is easily visible, and the person Y is close to the display 100a. However, it is in a place where the display 100a is difficult to see because it is inside the station.
- the environmental information in the visible range is data having a coefficient that gives a lower score in the station yard than in the outside of the station.
- the grid map in which the environment information of the visible range is added to the predicted movement range definition information of the person Y has a low probability as a whole. Therefore, in the score calculation, the score is lower than that of the person X. Note that the expected movement range definition information of the person Y is deformed along the ticket gate because there is a ticket gate.
- the environmental information includes, for example, spatial environment data such as a wall or a ticket gate nearby, and data such as time, weather, season, and the like.
- the environment information may be, for example, visible range data constituted by coefficients such that the vicinity of the front of the display has a high score and the vicinity of the side of the display has a low score within the visible range. If such data is used, the score of the person who is in a position where the advertisement is more easily seen increases, and the person who can easily see the advertisement can be specified as the advertisement distribution target person.
- the score calculation information database 26 may store advertisement distribution target person information and the like in addition to the environment information, and use this information when calculating the score.
- the score calculation means 13 calculates a score from the relationship between the visible range of the advertisement and the calculated expected movement range of the person (step S30). Specifically, for example, the score can be calculated from the size of the overlap area between the obtained grid map and the visible range. Information regarding the visible range may be stored in the score calculation information database 26. In this case, the score calculation means 13 calculates a score with reference to data (visible range data, size of area in grid map, human attribute, environmental information, etc.) stored in the score calculation information database 26.
- the same effect as that in Embodiment 1 can be obtained. Moreover, since the score is calculated using the environmental information, the advertisement distribution target person can be specified with higher accuracy.
- the score calculation means 13 can also calculate the score by referring to data stored in the score calculation information database 26 and weighting according to a predetermined rule. For example, for a person near the front within a certain distance from the display based on the position information of the person, the score is uniformly added regardless of the attribute. It is possible to uniformly add scores to all persons except for children, regardless of position information. By performing weighting and calculating the score, it is possible to accurately specify the advertisement distribution target person.
- FIG. 13 is a block diagram illustrating a configuration of an example of the advertisement distribution apparatus according to the present invention.
- FIG. 14 is a flowchart illustrating processing performed by the advertisement distribution apparatus according to the present embodiment.
- the advertisement distribution device 100 of this embodiment includes an advertisement distribution target person specifying unit 110, an advertisement distribution unit 120, and an advertisement database 130.
- the advertisement distribution target person specifying unit 110 is connected to the advertisement distribution unit 120.
- the advertisement distribution unit 120 is connected to the advertisement database 130.
- the advertisement distribution target person specifying unit 110 is the advertisement distribution target person specifying apparatus according to the first embodiment described above, and distributes the advertisement from step S10 that acquires image information of a person who exists within and outside the visible range of the advertisement.
- the process up to step S40 for specifying the person (advertisement delivery target person) to be performed is performed.
- the advertisement delivery means 120 selects the advertisement delivered according to the attribute of the advertisement delivery target person specified by the advertisement delivery target person specifying means 110 from the advertisement database 130 (Step S50) and delivers it (Step S60).
- the specified advertisement distribution target person is a male in his twenties, an advertisement image of a product for young men may be selected and displayed on the advertisement screen.
- the advertisement distribution target person specifying means 110 for example, if there is environmental information of "cold", a warm drink, a warm clothing, etc. according to the attribute of the specified advertisement distribution target person An advertisement can also be distributed, and the advertising effect can be further improved.
- the present embodiment is a program capable of executing the above-described advertisement distribution target person specifying method or the above-described advertisement distribution method on a computer.
- the program of this embodiment may be recorded on a recording medium, for example.
- the recording medium is not particularly limited, and examples thereof include a random access memory (RAM), a read-only memory (ROM), a hard disk (HD), an optical disk, and a floppy (registered trademark) disk (FD).
- the advertisement effect can be improved by specifying an appropriate person as an advertisement distribution target from the relationship between the advertisement visible range and the expected movement range of the person.
- the advertisement distribution target person specifying device, the advertisement distribution apparatus, the advertisement distribution target person specifying method, the advertisement distribution method, the program, and the recording medium of the present invention are used only when distributing an advertisement on a display or the like provided in a place where a large number of people gather. It is also effective when it is desired to specify a distribution target, and can be applied in a wide range of applications.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
- Image Processing (AREA)
Abstract
Description
広告の可視範囲内外に存在する人の画像を取得する画像取得手段と、
前記画像から、前記人の将来の予想移動範囲を算出する予想移動範囲算出手段と、
前記広告の可視範囲と算出された前記予想移動範囲との関係からスコアを算出するスコア算出手段と、
算出されたスコアから広告を配信する対象となる人を特定する広告配信対象者特定手段と、を含むことを特徴とする。
広告配信対象者特定手段と、
広告配信手段とを含み、
前記広告配信手段は、前記広告配信対象者特定手段で特定された広告配信対象者の属性に応じて配信する広告を選択し、
前記広告配信対象者特定手段が、前記本発明の広告配信対象者特定装置であることを特徴とする。
広告の可視範囲内外に存在する人の画像を取得する画像取得工程と、
前記画像から、前記人の将来の予想移動範囲を算出する予想移動範囲算出工程と、
前記広告の可視範囲と算出された前記予想移動範囲との関係からスコアを算出するスコア算出工程と、
算出されたスコアから広告を配信する対象となる人を特定する広告配信対象者特定工程と、を含むことを特徴とする。
広告配信対象者特定工程と、
広告配信工程とを含み、
前記広告配信工程において、前記広告配信対象者特定工程で特定された広告配信対象者の属性に応じて配信する広告を選択し、
前記広告配信対象者特定工程が、前記本発明の広告配信対象者特定方法を用いるものであることを特徴とする。
図1は、実施形態1に係る広告配信対象者特定装置10の概念を説明する図である。図1(a)は、電子広告配信装置(広告配信装置)が外壁等に設けられている状態の図である。本実施形態においては、前記電子広告配信装置を構成する大画面のディスプレイ100aおよびカメラ100bが、前記外壁の外側に設置されている。直方体形状に囲んだ線の内部は、広告の可視範囲(空間)を示している。前記可視範囲は、ディスプレイの大きさ、屋根等の障害物の有無、車道の位置等を勘案して、ディスプレイの設置場所毎に定めることができる。前記可視範囲内では、一般に、多数の人が通り、または、立ち止まることが可能である。図1(a)においては、代表的にA、Bの2名の人物が前記可視範囲内にいる様子を示している。人物Aは、ディスプレイ100aから離れた場所(ディスプレイ100aが見えにくい場所)をゆっくり歩いており、人物Bは、ディスプレイ100aに比較的近い場所(ディスプレイ100aが見えやすい場所)を速く歩いている。人物A、Bとも、カメラ100bにより画像情報が取得される状態である。図1(b)は、人物AおよびBの動きを上から見た様子を示す図である。図1(b)中の矢印は、各人物が動いている方向と速さを示している。ここで、矢印の長さが長い方が、移動速度が速いことを意味する。図1(b)において、斜線を付した囲みは、各人物の将来の移動位置を予想した範囲である。このように、例えば複数の人物が、広告の可視範囲内もしくは可視範囲内に入ってくる可能性のある範囲にいる場合に、どの人物を対象(ターゲット)として広告を配信すると効果的であるかの決定を可能とすることが、本発明の特徴である。以下、広告配信対象者特定装置のブロック図、および広告配信対象者特定装置が行う処理を示すフローチャートで、本実施形態を説明する。
通常、同一人物の位置は、連続するフレーム間で急激に変化しない。例えば、図5に示すように、n-1番目のフレームにおける任意の候補者の位置を(Xn-1,Yn-1)、n番目のフレームにおける人物の位置を(Xn,Yn)とした場合に、これらの2点間の距離diffdist=[(Xn-1-Xn)2+(Yn-1-Yn)2]1/2が小さいほど、人物の同一性が高いと考えられる。
あるフレームの画像に写っている人物が、次のフレームの画像においてどの位置に移動するかは、予測可能である。例えば、n-1番目のフレームの画像に写っている人物が次のn番目のフレームでどの位置に移動するかは、n-1番目のフレームの画像およびn-2番目以前のフレームの画像から予測可能である。n-1番目のフレームにおいて予測したn番目のフレーム画像での人物の位置と、n番目のフレームにおける実際の位置との2点間の距離が小さいほど、人物の同一性が高いと考えられる。
通常、同一人物の頭部の大きさは、連続するフレーム間で急激に変化しない。例えば、図6に示すように、n-1番目のフレームにおける任意の人物の頭部の大きさをhn-1、n番目のフレームにおける頭部の大きさをhnとすると、これらの大きさの差(diffhead-size)が小さいほど、人物の同一性が高いと考えられる。
一般的に、人間は一定の方向を向いて移動するため、あるフレームにおける頭部の向きとその次のフレームにおける頭部の向きが極端に異なることは稀である。よって、n-1番目のフレームにおける頭部の向きと、n番目のフレームにおける頭部の向きとを比較することで、人物の同一性を判定可能である。n-1番目のフレームにおける頭部の向きと、n番目のフレームにおける頭部の向きとの差が小さいほど、人物の同一性が高いと考えられる。
同一人物の衣服は、連続するフレーム間で急激に変化しない。よって、フレーム画像に写っている人物の服装を基に、人物の同一性を判定可能である。フレーム画像において人物の頭部を検出した場合、その直下の部分はその人物の胸部であると推定できる。したがって、あるフレーム画像における人物の頭部の直下の部分(胸部領域)における色成分のヒストグラム分布と、その後のフレーム画像における胸部領域における色成分のヒストグラム分布とは、同一人物であればほぼ同じとなる。したがって、n-1番目のフレームにおける胸部領域の色成分のヒストグラム分布と、n番目のフレームにおける胸部領域の色成分のヒストグラム分布との差が小さいほど、人物の同一性が高いと考えられる。
同一人物の顔は、連続するフレーム間で急激に変化しない。よって、フレーム画像に写っている人物の顔を基に、人物の同一性を判定可能である。フレーム間での人物の顔の相違は、テンプレートマッチング等によって数値化できる。これらの方法で数値化した値が小さいほど、人物の同一性が高いと考えられる。
同一人物の顔の女性らしさや男性らしさは、連続するフレーム間で急激に変化しない。よって、フレーム画像に写っている人物の女性らしさや男性らしさを基に、人物の同一性を判定可能である。ここで、女性らしさや男性らしさを性別度として定義すると、性別度は識別器によって顔画像を基に出力可能である。例えば、フレーム画像に写っている人物の顔が女性らしいほど0に近い値を出力し、男性らしいほど1に近い値を出力するようにすればよい。上記のように性別度を出力する場合、n-1番目のフレームにおける性別度と、n番目のフレームにおける性別度との差が小さいほど、人物の同一性が高いと考えられる。
同一人物の年齢は、連続するフレーム間で急激に変化しない。よって、フレーム画像に写っている人物の年齢を基に、人物の同一性を判定可能である。人間の年齢は連続量を扱う識別器によって、顔画像を基に推定可能である。n-1番目のフレームにおいて推定された年齢と、n番目のフレームにおいて推定された年齢との差が小さいほど、人物の同一性が高いと考えられる。
実施形態2は、前記スコア算出手段が、前記可視範囲の環境情報を加えてスコアを算出する態様である。図9は、実施形態2に係る広告配信対象者特定装置20の概念を説明する図である。図9(a)は、電子広告配信装置(広告配信装置)が外壁等に設けられている状態の図であり、図9(b)は図9(a)を上から見た状態の図である。図9(a)においては、前記可視範囲内に駅の改札口が存在する以外は、図1と同様である。図示した駅の構内からも、距離的には広告が見える状態にある。しかし、駅構内にいる人物Bは、カメラ100bにより画像情報が取得されるものの、改札口が障害となってディスプレイ100aは見えにくい状況にある。
スコア算出手段13は、スコア算出情報データベース26に格納されたデータを参照し、予め定められたルールに従って重み付けをして、スコアを算出することもできる。例えば、人の位置情報に基づき、ディスプレイからの距離が一定の範囲内の正面付近にいる人物については、属性にかかわらず一律にスコア加算したり、また、人の属性情報に基づき、15歳以下の子供を除く人物全員には、位置情報にかかわらず一律にスコア加算したりすることができる。重み付けをしてスコア算出を行うことにより、広告配信対象者を精度よく特定できる。
図13は、本発明の広告配信装置の一例の構成を示すブロック図である。また、図14は、本実施形態の広告配信装置が行う処理を示すフローチャートである。図13に示すように、本実施形態の広告配信装置100は、広告配信対象者特定手段110と、広告配信手段120と、広告データベース130とを備える。広告配信対象者特定手段110は、広告配信手段120に接続されている。広告配信手段120は、広告データベース130に接続されている。
本実施形態は、前述の広告配信対象者特定方法または、前述の広告配信方法を、コンピュータ上で実行可能なプログラムである。本実施形態のプログラムは、例えば、記録媒体に記録されてもよい。前記記録媒体は、特に限定されず、例えば、ランダムアクセスメモリ(RAM)、読み出し専用メモリ(ROM)、ハードディスク(HD)、光ディスク、フロッピー(登録商標)ディスク(FD)等があげられる。
11 画像取得手段
12 予想移動範囲算出手段
13 スコア算出手段
14 広告配信対象者特定手段
15 属性情報データベース(DB)
16、26 スコア算出情報データベース(DB)
100 広告配信装置
100a ディスプレイ
100b カメラ
110 広告配信対象者特定手段
120 広告配信手段
130 広告データベース(広告DB)
Claims (16)
- 広告の可視範囲内外に存在する人の画像を取得する画像取得手段と、
前記画像から、前記人の将来の予想移動範囲を算出する予想移動範囲算出手段と、
前記広告の可視範囲と算出された前記予想移動範囲との関係からスコアを算出するスコア算出手段と、
算出されたスコアから広告を配信する対象となる人を特定する広告配信対象者特定手段と、を含むことを特徴とする広告配信対象者特定装置。 - 前記予想移動範囲算出手段は、前記人の位置情報、前記人の進行情報及び前記人の属性情報から将来の予想移動範囲を算出することを特徴とする、請求項1記載の広告配信対象者特定装置。
- 前記スコア算出手段が、前記可視範囲の環境情報を加えてスコアを算出することを特徴とする、請求項1または2記載の広告配信対象者特定装置。
- 前記スコア算出手段が、前記人について重み付けをしてスコアを算出することを特徴とする、請求項1から3のいずれか一項に記載の広告配信対象者特定装置。
- 前記予想移動範囲算出手段が、前記人のグリッドマップ作成手段を含むことを特徴とする、請求項1から4のいずれか一項に記載の広告配信対象者特定装置。
- 広告配信対象者特定手段と、
広告配信手段とを含み、
前記広告配信手段は、前記広告配信対象者特定手段で特定された広告配信対象者の属性に応じて配信する広告を選択し、
前記広告配信対象者特定手段が、請求項1から5のいずれか一項に記載の広告配信対象者特定装置であることを特徴とする広告配信装置。 - 広告の可視範囲内外に存在する人の画像を取得する画像取得工程と、
前記画像から、前記人の将来の予想移動範囲を算出する予想移動範囲算出工程と、
前記広告の可視範囲と算出された前記予想移動範囲との関係からスコアを算出するスコア算出工程と、
算出されたスコアから広告を配信する対象となる人を特定する広告配信対象者特定工程と、を含むことを特徴とする広告配信対象者特定方法。 - 前記予想移動範囲算出工程において、前記人の位置情報、前記人の進行情報及び前記人の属性情報から将来の予想移動範囲を算出することを特徴とする、請求項7記載の広告配信対象者特定方法。
- 前記スコア算出工程において、前記可視範囲の環境情報を加えてスコアを算出することを特徴とする、請求項7または8記載の広告配信対象者特定方法。
- 前記スコア算出工程において、前記人について重み付けをしてスコアを算出することを特徴とする、請求項7から9のいずれか一項に記載の広告配信対象者特定方法。
- 前記予想移動範囲算出工程が、前記人のグリッドマップ作成工程を含むことを特徴とする、請求項7から10のいずれか一項に記載の広告配信対象者特定方法。
- 広告配信対象者特定工程と、
広告配信工程とを含み、
前記広告配信工程において、前記広告配信対象者特定工程で特定された広告配信対象者の属性に応じて配信する広告を選択し、
前記広告配信対象者特定工程が、請求項7から11のいずれか一項に記載の広告配信対象者特定方法を用いるものであることを特徴とする広告配信方法。 - 請求項7から11のいずれか一項に記載の広告配信対象者特定方法をコンピュータに実行させることを特徴とする、プログラム。
- 請求項12記載の広告配信方法をコンピュータに実行させることを特徴とする、プログラム。
- 請求項13記載のプログラムを記録していることを特徴とする記録媒体。
- 請求項14記載のプログラムを記録していることを特徴とする記録媒体。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201180046543.1A CN103238163B (zh) | 2010-09-30 | 2011-09-20 | 用于规定作为广告分发对象的设备,以及广告分发设备 |
US13/824,361 US9031862B2 (en) | 2010-09-30 | 2011-09-20 | Advertisement delivery target identifying apparatus, advertisement delivery apparatus, advertisement delivery target identifying method, advertisement delivery method, program, and recording medium |
JP2012536351A JP5511035B2 (ja) | 2010-09-30 | 2011-09-20 | 広告配信対象者特定装置、および、広告配信装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2010-222361 | 2010-09-30 | ||
JP2010222361 | 2010-09-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012043291A1 true WO2012043291A1 (ja) | 2012-04-05 |
Family
ID=45892755
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2011/071307 WO2012043291A1 (ja) | 2010-09-30 | 2011-09-20 | 広告配信対象者特定装置、および、広告配信装置 |
Country Status (4)
Country | Link |
---|---|
US (1) | US9031862B2 (ja) |
JP (1) | JP5511035B2 (ja) |
CN (1) | CN103238163B (ja) |
WO (1) | WO2012043291A1 (ja) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017021855A (ja) * | 2016-10-19 | 2017-01-26 | 株式会社Agoop | 情報処理システム、人口流量推定装置、プログラム、情報処理方法及び人口流量を推定する方法 |
WO2019198139A1 (ja) * | 2018-04-10 | 2019-10-17 | 三菱電機株式会社 | 情報表示システム及び情報表示方法 |
WO2020166693A1 (ja) * | 2019-02-15 | 2020-08-20 | 株式会社電通 | 広告接触判定システム、広告接触判定装置及びプログラム |
JP2020140456A (ja) * | 2019-02-28 | 2020-09-03 | Kddi株式会社 | 広告成果評価方法、装置およびプログラム |
CN115392980A (zh) * | 2022-09-06 | 2022-11-25 | 杭州储秀网络科技股份有限公司 | 一种新媒体广告精准投放系统 |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015042655A1 (en) * | 2013-09-05 | 2015-04-02 | Brett Thornton | Variable speed and detection automated media display |
JP6617013B2 (ja) * | 2015-11-26 | 2019-12-04 | ロボットスタート株式会社 | ロボット広告システム、ロボット、ロボット広告方法及びプログラム |
US10497014B2 (en) * | 2016-04-22 | 2019-12-03 | Inreality Limited | Retail store digital shelf for recommending products utilizing facial recognition in a peer to peer network |
CN111160945A (zh) * | 2019-02-27 | 2020-05-15 | 浙江诸暨美数信息科技有限公司 | 基于视频技术的广告精准投放方法和系统 |
CN111246296A (zh) * | 2020-01-17 | 2020-06-05 | 北京市商汤科技开发有限公司 | 数据推送方法、装置、电子设备和计算机存储介质 |
US11985372B2 (en) * | 2021-12-13 | 2024-05-14 | Samsung Electronics Co., Ltd. | Information pushing method and apparatus |
CN114884992B (zh) * | 2022-05-07 | 2023-09-22 | 南京欣威视通信息科技股份有限公司 | 基于物联网技术下的5g联动式的广告设备 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002269290A (ja) * | 2001-03-09 | 2002-09-20 | Sony Corp | 広告配信システム |
JP2008112401A (ja) * | 2006-10-31 | 2008-05-15 | Mitsubishi Electric Corp | 広告効果測定装置 |
US20080172781A1 (en) * | 2006-12-15 | 2008-07-24 | Terrance Popowich | System and method for obtaining and using advertising information |
JP2010039333A (ja) * | 2008-08-07 | 2010-02-18 | Seiko Epson Corp | 広告装置、広告装置の制御方法及び制御プログラム |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030004743A1 (en) * | 2001-03-19 | 2003-01-02 | Jeff Callegari | Methods for providing a location based merchant presence |
EP1566788A3 (en) | 2004-01-23 | 2017-11-22 | Sony United Kingdom Limited | Display |
US20070273583A1 (en) * | 2005-09-17 | 2007-11-29 | Outland Research, Llc | Pointing interface for person-to-person interaction through ad-hoc networks |
-
2011
- 2011-09-20 JP JP2012536351A patent/JP5511035B2/ja active Active
- 2011-09-20 WO PCT/JP2011/071307 patent/WO2012043291A1/ja active Application Filing
- 2011-09-20 US US13/824,361 patent/US9031862B2/en not_active Expired - Fee Related
- 2011-09-20 CN CN201180046543.1A patent/CN103238163B/zh active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002269290A (ja) * | 2001-03-09 | 2002-09-20 | Sony Corp | 広告配信システム |
JP2008112401A (ja) * | 2006-10-31 | 2008-05-15 | Mitsubishi Electric Corp | 広告効果測定装置 |
US20080172781A1 (en) * | 2006-12-15 | 2008-07-24 | Terrance Popowich | System and method for obtaining and using advertising information |
JP2010039333A (ja) * | 2008-08-07 | 2010-02-18 | Seiko Epson Corp | 広告装置、広告装置の制御方法及び制御プログラム |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017021855A (ja) * | 2016-10-19 | 2017-01-26 | 株式会社Agoop | 情報処理システム、人口流量推定装置、プログラム、情報処理方法及び人口流量を推定する方法 |
WO2019198139A1 (ja) * | 2018-04-10 | 2019-10-17 | 三菱電機株式会社 | 情報表示システム及び情報表示方法 |
JPWO2019198139A1 (ja) * | 2018-04-10 | 2021-01-14 | 三菱電機株式会社 | 情報表示システム、情報表示方法及びプログラム |
WO2020166693A1 (ja) * | 2019-02-15 | 2020-08-20 | 株式会社電通 | 広告接触判定システム、広告接触判定装置及びプログラム |
JP2020135194A (ja) * | 2019-02-15 | 2020-08-31 | 株式会社電通グループ | 広告接触判定システム、広告接触判定装置及びプログラム |
US11734721B2 (en) | 2019-02-15 | 2023-08-22 | Dentsu Inc. | Advertisement contact determination system, advertisement contact determination device, and program |
JP2020140456A (ja) * | 2019-02-28 | 2020-09-03 | Kddi株式会社 | 広告成果評価方法、装置およびプログラム |
JP7084887B2 (ja) | 2019-02-28 | 2022-06-15 | Kddi株式会社 | 広告成果評価方法、装置およびプログラム |
CN115392980A (zh) * | 2022-09-06 | 2022-11-25 | 杭州储秀网络科技股份有限公司 | 一种新媒体广告精准投放系统 |
Also Published As
Publication number | Publication date |
---|---|
CN103238163A (zh) | 2013-08-07 |
US9031862B2 (en) | 2015-05-12 |
CN103238163B (zh) | 2016-04-06 |
JP5511035B2 (ja) | 2014-06-04 |
JPWO2012043291A1 (ja) | 2014-02-06 |
US20130198003A1 (en) | 2013-08-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5511035B2 (ja) | 広告配信対象者特定装置、および、広告配信装置 | |
CN107808111B (zh) | 用于行人检测和姿态估计的方法和装置 | |
US8636209B2 (en) | System and method for interactive marketing to consumers | |
US7921036B1 (en) | Method and system for dynamically targeting content based on automatic demographics and behavior analysis | |
WO2018059408A1 (zh) | 跨线计数方法和神经网络训练方法、装置和电子设备 | |
EP2918071B1 (en) | System and method for processing visual information for event detection | |
US8107676B2 (en) | Line length estimation | |
US20180365496A1 (en) | Automated classification based on photo-realistic image/model mappings | |
JP6267861B2 (ja) | 対話型広告のための使用測定技法およびシステム | |
JP5224360B2 (ja) | 電子広告装置、電子広告方法及びプログラム | |
US20130063556A1 (en) | Extracting depth information from video from a single camera | |
JP2006254274A (ja) | 視聴層分析装置、販売戦略支援システム、広告支援システム及びtv装置 | |
JP6615800B2 (ja) | 情報処理装置、情報処理方法およびプログラム | |
Huang et al. | Motion detection with pyramid structure of background model for intelligent surveillance systems | |
JP6879379B2 (ja) | 接客支援装置、接客支援方法、及びプログラム | |
CN109961472B (zh) | 3d热力图生成的方法、系统、存储介质及电子设备 | |
CA2670021A1 (en) | System and method for estimating characteristics of persons or things | |
JP2019159468A (ja) | 広告表示システム、表示装置、広告出力装置、プログラム及び広告表示方法 | |
Anisha et al. | Automated vehicle to vehicle conflict analysis at signalized intersections by camera and LiDAR sensor fusion | |
WO2021038800A1 (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 | |
Montero et al. | Multi-camera BEV video-surveillance system for efficient monitoring of social distancing | |
He et al. | A double-region learning algorithm for counting the number of pedestrians in subway surveillance videos | |
CN113724454B (zh) | 移动设备的互动方法、移动设备、装置及存储介质 | |
Han et al. | Real-time multiple people tracking for automatic group-behavior evaluation in delivery simulation training | |
JP5472976B2 (ja) | 対象物検出装置、対象物検出方法、プログラムおよび記録媒体 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201180046543.1 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 11828848 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012536351 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13824361 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 11828848 Country of ref document: EP Kind code of ref document: A1 |