WO2014050432A1 - 情報処理システム、情報処理方法及びプログラム - Google Patents
情報処理システム、情報処理方法及びプログラム Download PDFInfo
- Publication number
- WO2014050432A1 WO2014050432A1 PCT/JP2013/073354 JP2013073354W WO2014050432A1 WO 2014050432 A1 WO2014050432 A1 WO 2014050432A1 JP 2013073354 W JP2013073354 W JP 2013073354W WO 2014050432 A1 WO2014050432 A1 WO 2014050432A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- person
- time
- persons
- correspondence
- information processing
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Definitions
- Some aspects according to the present invention relate to an information processing system, an information processing method, and a program.
- Patent Document 1 discloses an apparatus that can appropriately perform tracking (monitoring) of a person across cameras using connection relationship information between cameras. This apparatus obtains the correspondence between persons according to the similarity of the person feature amount between a point appearing in the camera field of view (In point) and a point disappearing from the camera field of view (Out point).
- Some aspects of the present invention have been made in view of the above-described problems, and provide an information processing system, an information processing method, and a program capable of suitably estimating the correspondence of a person appearing in a video.
- the information processing system includes one or more persons appearing in images captured by a plurality of video cameras at a first time, and the plurality of video cameras at a second time later than the first time.
- Receiving the response information related to And an input unit said first computing means, based on the correspondence information that has been inputted from said input unit, defines at least a portion of the scales.
- the information processing method includes one or more persons appearing in images captured by a plurality of video cameras at a first time and the plurality of video cameras at a second time later than the first time. Determining a scale indicating the possibility that one or more persons appearing in each captured image are associated with each other; and at least one person appearing at one of the first time and the second time; Estimating the correspondence between the person shown at the first time and the person shown at the second time in consideration of all the scales related to all persons related to the other time; Input of correspondence information relating to whether or not at least a part of one or more persons photographed at a time and at least a part of one or more persons photographed at the second time correspond or do not correspond Step and emotion Performs the processing system, at least a portion of said measure is determined based on the correspondence information that has been input.
- the program according to the present invention captures one or more persons appearing in images respectively captured by a plurality of video cameras at a first time and the plurality of video cameras at a second time later than the first time.
- Processing for determining a scale indicating the possibility that one or more persons appearing in the recorded video are associated with each other, at least one person appearing at one of the first time and the second time, and the other A process for estimating the correspondence between the person appearing at the first time and the person appearing at the second time in consideration of all the scales related to all persons relating to the time of the first time, and the first time
- “part”, “means”, “apparatus”, and “system” do not simply mean physical means, but “part”, “means”, “apparatus”, “system”. This includes the case where the functions possessed by "are realized by software. Further, even if the functions of one “unit”, “means”, “apparatus”, and “system” are realized by two or more physical means or devices, two or more “parts” or “means”, The functions of “device” and “system” may be realized by a single physical means or device.
- an information processing system an information processing method, and a program capable of suitably estimating the association of persons appearing in a video.
- FIG. 1 is a block diagram showing a system configuration of the monitoring system 1.
- the monitoring system 1 is broadly divided into an information processing server 100 and a plurality of video cameras 200 that capture (capture) video (moving images) (video cameras 200A to 200N are collectively referred to as video cameras 200). It comprises a display device 300 and an input device 400.
- the monitoring system 1 will be described as a system for monitoring a person photographed by the video camera 200, but the monitoring target may be applied to a moving body such as a car, a bicycle, or a motorcycle.
- the video camera 200 captures a video (moving image), determines whether or not there is a person in the captured video, and then acquires information such as a position and a feature amount related to the person together with the captured moving image. It transmits to the processing server 100.
- the video camera 200 can also track a person in a moving image by comparing the captured moving images between frames. It should be noted that processes such as person detection, feature extraction, and person tracking in the camera may be performed on the information processing server 100 or other information processing apparatus (not shown), for example.
- the information processing server 100 performs various processes such as detection of a person, registration of a person to be tracked, and tracking of a registered person by analyzing a moving image captured by the video camera 200.
- the storage device It is also conceivable to track (analyze) moving images stored in an HDD (Hard Disk Drive) or VCR (Video Cassette Recorder). Furthermore, it is conceivable that the moving images stored in the storage device are reproduced in reverse order (reverse reproduction) and tracked. Normally, when a person takes a suspicious action, it is necessary to investigate what route the person has taken and how the action was taken. Enabling tracking is very useful.
- the information processing server 100 outputs a monitoring screen to the display device 300 and receives operation signals related to various operation inputs related to person monitoring from the input device 400. More specifically, for example, on a monitoring screen (a specific example is shown in FIG. 3 to be described later) displayed on the display device 300, a plurality of images input from the video camera 200 are displayed, so that the person to be monitored is displayed. The user who is the monitor can grasp where the person is now.
- a user who is a monitor looks at the display device 300, and when the person to be monitored shown in the video (moving image) of a certain video camera 200 appears in the video of another video camera 200, the user turns the input device 400 on.
- the two persons are associated with each other as being the same person.
- This processing and advantages will be described later.
- the display device 300 is, for example, a display that displays an image on a liquid crystal, an organic EL (Electro Luminescence), or the like.
- the display device 300 displays the monitoring screen output from the information processing server 100.
- the input device 400 is a device for a user (monitor) to input various information.
- a pointing device such as a mouse, a touch pad, or a touch panel, a keyboard, and the like correspond to the input device 400.
- Various processes such as registration of a monitoring target person and association of the registered person with a person newly appearing in the video camera 200 (input as the same person and input that they are not the same person) are input by the user. This is done based on an operation on the device 400.
- the display device 300 and the input device 400 may be realized as a single client, or the functions of the information processing server 100, the display device 300, and the input device 400 may be realized by four or more information processing devices. It may be realized.
- the client may have some functions of the information processing server 100 according to the present embodiment.
- the information processing server 100 includes an input unit 110, a similarity calculation unit 120, a tracking person registration unit 130, a correspondence relationship estimation unit 140, a display control unit 150, and a database (DB) 160.
- the functions of the information processing server 100 may be realized by a plurality of information processing apparatuses (computers).
- the input unit 110 registers the information received from the video camera 200 and the information of the person detection result in the DB 160 as the captured moving image 163, the detected person information 165, and the person tracking information 167.
- the detected person information 165 registered in the DB 160 by the input unit 110 includes information on the feature amount of the person detected by the video camera 200.
- information on the in-camera tracking result indicating how the person detected by the video camera 200 has moved in the one video camera 200. Etc. are included.
- the similarity calculation unit 120 calculates the similarity between the person shown in the moving image input from the video camera 200 and the person registered in the detected person information 165. At this time, the similarity calculation unit 120 selects a person in the moving image input from the video camera 200 from a plurality of person images related to each registered person (person images related to a plurality of timings of the same person). The similarity may be calculated after selecting a person image having a similar posture to the image. By mounting in this way, it is possible to increase the accuracy of similarity calculation.
- the tracking person registration unit 130 selects a person shown in the captured moving image input from the video camera 200 based on a user operation input from the input device 400 and the like. Registered in the person tracking information 167 of the DB 160 as a tracking target person). In addition, the tracking person registration unit 130 indicates that the person shown in the captured video input from the video camera 200 is the same person as the person already registered in the person tracking information 167 or is not the same person. If it is determined, the information can be registered in the person tracking information 167.
- Correspondence relationship estimation section 140 is based on the user input indicating that it is the same person as the person already registered in person tracking information 167 and that it is not the same person. And the result is registered in the person tracking information 167. The specific method will be described later with reference to FIG. 2 and the like. However, when the user inputs that the person is the same person / not the same person, the correspondence estimation unit 140 determines whether the person is another person. Correspondence of whether or not they are the same person is also predicted.
- the display control unit 150 causes the display device 300 to display various display screens such as a monitoring screen.
- the display control unit 150 includes a moving image display unit 151, a UI generation unit 153, and a movement history generation unit 155.
- the moving image display unit 151 causes the display device 300 to display the captured video input by the input unit 110.
- a video area to be displayed by the moving image display unit 151 is provided in a part of the monitoring screen. Note that the video displayed by the moving image display unit 151 on the display device 300 may not be a real-time video. If the recorded video is displayed on the display device 300, the moving image display unit 151 reads the captured moving image 163 from the DB 160 and displays it on the display device 300.
- the UI generation unit 153 generates various display screens whose specific examples are shown in FIG. 3 and FIG.
- a GUI Graphic User Interface
- the movement history generation unit 155 Based on the person tracking information 167, the movement history generation unit 155 generates a movement history of the monitoring target person to be displayed on a movement history display screen shown in a specific example in FIG.
- the DB 160 is constructed on various storage devices such as an HDD (not shown).
- the DB 160 stores camera arrangement information 161, a captured moving image 163, detected person information 165, and person tracking information 167.
- the camera arrangement information 161 includes information such as the adjacency relationship between cameras and the distance between cameras (or the average time required for movement between cameras).
- the camera arrangement information 161 is used for estimation of correspondence by the correspondence estimation unit 140, generation of movement history by the movement history generation unit 155, and the like.
- the person tracking information 167 includes tracking information related to each person (not only a person to be monitored but all detected persons) photographed by the video camera 200. More specifically, in-camera tracking information of a person detected by the video camera 200 (information indicating what route the person has moved with the same angle of view) or a person reflected in a certain video camera 200 Which video camera 200 has moved to the shooting range (corresponding to correspondence information on how each person reflected in each video camera 200 corresponds), and how the user performs the association
- the person tracking information 167 includes information such as “taka”.
- the monitoring system 1 when the user looks at the display screen of the display device 300, the person to be monitored (person registered as the monitoring target) reflected in the video of a certain video camera 200 is other. , The input device 400 is operated to associate the two persons as the same person. If the person is not the person to be monitored, the input device 400 is operated to input that the two persons are not the same person. By making it possible for the user to input the fact that they are the same person and not the same person, the monitoring system 1 obtains a highly likely correspondence among the possible person correspondences. .
- a person A, a person B, and a person C are reflected in the images of three video cameras 200 corresponding to “Camera 001”, “Camera 002”, and “Camera 003”, respectively.
- a person X and a person Y are shown in “Camera001” and “Camera002”, respectively.
- the person X since only the person B has similar characteristics, the person X and the person B are likely to be the same person.
- the person Y since there are two similar characteristics (person A and person C), it is difficult to determine which person Y corresponds to. However, the user can easily determine that the person Y is not at least the person B.
- the monitoring system 1 can suitably estimate possible (highly likely) combinations of person correspondences. A method for estimating the correspondence between persons will be described later with reference to FIGS.
- FIG. 3 is a diagram illustrating a specific example of a display screen (hereinafter, also referred to as a monitoring screen 30) that the display device 300 displays for person monitoring.
- video areas 31A to 31D (hereinafter also collectively referred to as video areas 31) for displaying captured video input from a plurality of video cameras 200, and a person to be monitored are displayed. And a monitoring subject display area 33 to be displayed.
- the video area 31 displays multi-camera video input from a plurality of video cameras 200 as described above.
- the video of the video camera 200 displayed in each video area 31 may be switched at any time.
- the UI generation unit 153 and the moving image display unit perform control such as switching to the video of the video camera 200 that can be predicted that the person will appear next when the person moves. 151 may be performed.
- the monitoring target person display area 33 is an area in which the person selected as the monitoring target among the persons shown in the video area 31 by the user who is the monitoring person is registered. As in the example of FIG. 3, a plurality of monitoring subjects can be selected (three in the example of FIG. 3). Further, for each person, a plurality of person images (two in the example of FIG. 3) having different postures such as the front and the back are displayed in the monitoring target person display area 33.
- a pop-up window 35 is displayed above the person P shown in the video area 31D.
- the pop-up window 35 selects whether or not the person P is to be monitored and whether or not the person already registered in the monitoring target person display area 33 as the monitoring target is the same person or not. It is for making possible.
- the pop-up window 35 is displayed in the vicinity of the newly detected person P, and the position of the pop-up window 35 moves with the movement (movement) of the person P.
- By displaying in the vicinity in this way it is possible to easily identify the person P to be newly registered, to easily compare the person P with the person to be monitored, and to narrow the operation range. It becomes possible.
- the pop-up window 35 is not necessarily moved in accordance with the movement of the person P. For example, it may be displayed at a fixed position for at least a fixed time. This makes it easier to input than when the pop-up window 35 moves.
- the pop-up window 35 is displayed, the video area 31 overlapping the pop-up window 35 cannot be seen and the visibility may deteriorate. Therefore, when the outside of the pop-up window 35 is clicked (selected), the pop-up window 35 is displayed.
- a function for displaying the pop-up window 35 may be added by clicking the area (person area) including the periphery of the person P in the video area 31.
- FIG. 4 is a diagram showing a specific example of the pop-up window 35.
- person images 41A to 41C (hereinafter also collectively referred to as person images 41), which are thumbnails of monitoring subjects to which ID1, ID2, and ID3 are assigned, and a blank to which ID4 is assigned.
- the image 43 is arranged in parallel.
- the tracking person registration unit 130 associates the monitoring target person corresponding to the person image 41 and the person P shown in the video (moving image) as the same person.
- the tracking person registration unit 130 registers the person P shown in the video as a new monitoring target person having ID4.
- registration buttons 45A to 45C for the user to register that they are not the same person (indicated by “rem” meaning remove in the figure. Hereinafter, they are collectively referred to as registration).
- the button 45 is also used by the user to register that the person to be monitored corresponding to ID1, ID2 and ID3 already registered and the person P shown in the video are not the same person.
- the persons arranged on the pop-up window 35 may be arranged in the order of high or low possibility of matching with the person P.
- the possibility of matching with the person P can be estimated (calculated) by the correspondence relationship estimation unit 140.
- a person who is unlikely to match may not be displayed in the pop-up window 35 in advance.
- FIGS. 5 to FIG. 7 are diagrams for explaining a method of estimating the correspondence between persons imaged by the video camera 200.
- the left side of the drawing represents a person at time t
- the right side of the drawing represents a person at time t + 1.
- the persons A to C detected at time t are 1: 1 associated with one of the items on the right side indicating the state at time t + 1
- the person X and person detected at time t + 1 are detected.
- Y is associated with one of the items on the left side indicating the state at time t 1: 1.
- Numeral values written on the line represent the costs when associated with each other. The higher the numerical value is less likely to be associated, and the lower the numerical value is more likely to be associated.
- the person A is described as an example. The person A is most likely to be associated with the person X (cost 5), and is more likely not to appear (cost 10). The possibility of being associated is the lowest (cost 20).
- Such a cost is calculated based on the similarity of the feature quantity between each detected person (person X and person Y) and person A, the elapsed time from time t to time t + 1, and the position from which person A was detected.
- Correspondence estimation section 140 calculates in accordance with, for example, a comparison with the photographing position where X is detected or the average time to reach the photographing position where person Y is detected. For example, if the similarity between the feature amounts of the person A and the person X is high, the possibility that the person A and the person X are associated with each other increases (the cost decreases).
- the time for moving between the shooting ranges of the camera can be acquired or calculated from the camera arrangement information 161 or the like.
- an optimum correspondence can be obtained by, for example, the Hungarian method. That is, a combination that reduces the sum of these costs may be obtained.
- the correspondence relationship estimation unit 140 can estimate the correspondence relationship as the most likely correspondence relationship.
- FIG. 6 is a diagram for describing a correspondence estimation method when the user associates the person A with the person X.
- the cost of the person A and the person X being the same person is zero.
- the total cost is reduced because the person A corresponds to the person X, the person B corresponds to the person Y, and the person C The combination is “outside”.
- FIG. 6 shows a case where the user inputs “I am the same person”, but there is a case where the user is “not the same person”.
- FIG. 7 shows an example in which the user performs input when “person C and person X are not the same person”.
- the cost of the person C and the person X being the same person is infinite (note that even if not infinite, a sufficiently large cost is set. It should be) Under this assumption, when the correspondence is obtained by the Hungarian method, the total cost is reduced because the person A corresponds to the person X, the person B corresponds to the person Y, and the person C The combination is “outside”.
- the user inputs “is the same person” and “not the same person”, and further predicts the correspondence of the person based on the input, so that all the monitoring target persons can be targeted.
- the prediction result of a suitable correspondence can be obtained.
- the correspondence is estimated based on the cost.
- the present invention is not limited to this.
- the combination of associations is predicted in a lump, but the present invention is not limited to this.
- the probability that the person X corresponds, the probability that the person Y corresponds, and the probability of not appearing or out of the area may be calculated.
- Several methods are conceivable. For example, it is conceivable to calculate by one of the following formulas.
- the certainty of a specific correspondence is calculated as the product of all likelihoods assigned in the assignment problem.
- the likelihood of the correspondence shown in the lower part of FIG. 5 includes the likelihood that the person A is “Not Appearing / Out of Area”, the likelihood that the person B is the person Y, and the likelihood that the person C is the person X. It can be calculated as a product.
- the likelihood of the correspondence shown in the lower part of FIG. 6 is that the likelihood that the person A is the person X, the likelihood that the person B is the person Y, and the likelihood that the person C is “not appearing / out of area”. It can be calculated as a product.
- the probability that the person X corresponds to the person A, the probability that the person X corresponds to the person B, the probability that the person X is person monitoring, and the probability that the person X is a new person / false detection are calculated. be able to. Based on this probability, it is conceivable that the top N pieces are presented to the user on the pop-up window 35 or the like as persons who are likely to correspond to the person X. The same applies to the person Y.
- FIG. 8 is a diagram illustrating a specific example of the movement history display screen 80 generated by the movement history generation unit 155.
- the movement history display screen 80 in FIG. 8 receives, for example, designation of the monitoring target person from the user on the monitoring target person display area 33 in the monitoring screen 30 illustrated in FIG. 3 and the movement of the monitoring target person.
- the movement history generation unit 155 generates the history.
- an instruction from the user is input to the information processing server 100 as an operation signal from the input device 400.
- the movement history of the monitoring subject is represented by connecting a solid line and a broken line.
- the solid line portion indicates the result of the camera 200 tracking within the camera
- the broken line portion indicates the movement path determined based on the correspondence relationship estimated by the correspondence relationship estimation unit 140.
- FIG. 9 is a flowchart showing a processing flow of the information processing server 100 according to the present embodiment.
- Each processing step to be described later can be executed in any order or in parallel as long as there is no contradiction in processing contents, and other steps can be added between the processing steps. good. Further, a step described as a single step for convenience can be executed by being divided into a plurality of steps, and a step described as being divided into a plurality of steps for convenience can be executed as one step.
- the input unit 110 determines whether or not a person as a detection target object is reflected in the video captured by the video camera 200 (S901). As a result, when a person is detected (Yes in S901), the similarity calculation unit 120 reads the person tracking information 167 (S903), and the feature amount of the person already detected by another video camera 200 Then, the degree of similarity is calculated by comparing the feature amount of the person detected this time (S905).
- the correspondence relationship estimation unit 140 calculates the cost for association (described above with reference to FIGS. 5 to 7) according to the similarity calculated in S905, the relationship between the elapsed time and the inter-camera distance, and the like. (S907). Further, based on the cost (the likelihood and the information amount are the same), the probability of matching between persons is calculated.
- the UI generation unit 153 displays a pop-up window 35 in which the monitoring subjects are arranged in the order of the high possibility of corresponding to the person shown in the video being displayed in the video area 31 according to the probability calculated in S907 (S909).
- the correspondence estimation unit 140 responds to the person according to the input. After recalculating the cost related to the attachment (S913), based on the cost, the correspondence relationship related to all persons is predicted (S915). Further, the correspondence relationship estimation unit 140 registers the predicted correspondence relationship of the person in the DB 160 as the person tracking information 167.
- the information processing server 100 includes a processor 1001, a memory 1003, a storage device 1005, an input interface (I / F) 1007, a data I / F 1009, a communication I / F 1011, and a display device 1013.
- a processor 1001 a memory 1003, a storage device 1005, an input interface (I / F) 1007, a data I / F 1009, a communication I / F 1011, and a display device 1013.
- the processor 1001 controls various processes in the information processing server 100 by executing programs stored in the memory 1003. For example, the processes related to the input unit 110, the similarity calculation unit 120, the tracking person registration unit 130, the correspondence relationship estimation unit 140, and the display control unit 150 described with reference to FIG. Further, it can be realized as a program operating on the processor 1001.
- the memory 1003 is a storage medium such as a RAM (Random Access Memory).
- the memory 1003 temporarily stores a program code of a program executed by the processor 1001 and data necessary for executing the program. For example, in the storage area of the memory 1003, a stack area necessary for program execution is secured.
- the storage device 1005 is a non-volatile storage medium such as a hard disk or flash memory.
- the storage device 1005 is stored as an operating system, various programs for realizing the input unit 110, the similarity calculation unit 120, the tracking person registration unit 130, the correspondence relationship estimation unit 140, and the display control unit 150, and the DB 160.
- Various data including camera arrangement information 161, captured moving image 163, detected person information 165, and person tracking information 167 are stored.
- Programs and data stored in the storage device 1005 are referred to by the processor 1001 by being loaded into the memory 1003 as necessary.
- the input I / F 1007 is a device for receiving input from the user.
- the input device 400 described in FIG. 1 can also be realized by the input I / F 1007.
- Specific examples of the input I / F 1007 include a keyboard, a mouse, a touch panel, and various sensors.
- the input I / F 1007 may be connected to the information processing server 100 via an interface such as USB (Universal Serial Bus), for example.
- USB Universal Serial Bus
- the data I / F 1009 is a device for inputting data from outside the information processing server 100.
- Specific examples of the data I / F 1009 include a drive device for reading data stored in various storage media.
- the data I / F 1009 may be provided outside the information processing server 100. In this case, the data I / F 1009 is connected to the information processing server 100 via an interface such as USB.
- the communication I / F 1011 is a device for data communication with a device external to the information processing server 100, for example, a video camera 200 or the like by wire or wireless.
- the communication I / F 1011 may be provided outside the information processing server 100. In this case, the communication I / F 1011 is connected to the information processing server 100 via an interface such as USB.
- the display device 1013 is a device for displaying various information.
- the display device 300 described in FIG. 1 can also be realized by the display device 1013.
- Specific examples of the display device 1013 include a liquid crystal display and an organic EL (Electro-Luminescence) display.
- the display device 1013 may be provided outside the information processing server 100. In that case, the display device 1013 is connected to the information processing server 100 via, for example, a display cable.
- the monitoring system 1 it is possible to receive input from the user that the person is the same person and that the person is not the same person.
- the correspondence between people can be estimated. In particular, even if an input is made for one person, it can affect the prediction of the correspondence between other persons.
- FIG. 11 is a block diagram illustrating a functional configuration of a monitoring device 1100 that is an information processing system. As illustrated in FIG. 11, the monitoring device 1100 includes an input unit 1110, a first calculation unit 1120, and a second calculation unit 1130.
- the input unit 1110 corresponds to at least a part of one or more persons photographed at a first time by a video camera (not shown) and at least a part of one or more persons photographed at a second time; Alternatively, it is possible to receive input of correspondence information related to non-correspondence. Here, it is assumed that the second time is later than the first time.
- the first arithmetic unit 1120 includes one or more persons appearing in images taken by a plurality of video cameras at a first time, and 1 appearing in images taken by the plurality of video cameras at a second time. A scale indicating the possibility that the above persons are associated with each other is determined. In addition, the first calculation unit 1120 determines at least a part of the scale based on the correspondence information input from the input unit 1110.
- the second calculation unit 1130 considers all the scales related to at least one person appearing at one time of the first time or the second time and all persons related to the other time. The correspondence between the person shown at the time 1 and the person shown at the time 2 is estimated. By implementing in this way, according to the monitoring apparatus 1100 according to the present embodiment, it is possible to suitably estimate the association of persons appearing in the video.
- Appendix 1 One or more persons appearing in images taken by a plurality of video cameras at a first time, and one or more people appearing in images taken by the plurality of video cameras at a second time later than the first time
- a first calculating means for determining a scale indicating the possibility that each person is associated with each other, at least one person appearing at one of the first time and the second time, and at the other time
- a second computing means for estimating a correspondence relationship between the person shown at the first time and the person shown at the second time in consideration of all the scales related to all the persons;
- Input for receiving input of correspondence information regarding that at least a part of one or more persons photographed at the time corresponds to or does not correspond to at least a part of the one or more persons photographed at the second time
- the first calculation Stage based on the correspondence information that has been inputted from said input unit, defines at least a portion of the scales, the information processing system.
- the first calculation means calculates at least a part of a scale based on an elapsed time from the first time to the second time and information related to a relationship between cameras in which each person appears.
- the information processing system according to 1 or 2
- Appendix 4 The information processing system according to appendix 3, wherein the information related to the relationship between the cameras includes at least one information of an average time required for movement between the shooting ranges of the cameras or a distance between the shooting ranges of the cameras.
- the second calculation means estimates correspondences in consideration of all measures related to all persons related to the first time and all persons related to the second time.
- the information processing system according to any one of appendix 4.
- Appendix 7 The information processing method according to appendix 6, wherein at least a part of the scale is calculated based on a similarity of feature quantities between the person related to the first time and the person related to the second time.
- Appendix 8 The information processing according to appendix 6 or appendix 7, wherein at least a part of the scale is calculated based on an elapsed time from the first time to the second time and information relating to a relationship between the cameras in which each person appears.
- Appendix 9 The information processing method according to appendix 8, wherein the information related to the relationship between the cameras includes at least one information of an average time required for movement between the shooting ranges of the cameras or a distance between the shooting ranges of the cameras.
- Appendix 12 The program according to appendix 11, wherein at least a part of the scale is calculated based on the similarity of the feature amount between the person related to the first time and the person related to the second time.
- Appendix 13 The program according to appendix 11 or appendix 12, wherein at least a part of the scale is calculated based on an elapsed time from the first time to the second time and information related to a relationship between cameras in which each person is shown.
- Appendix 14 14. The program according to appendix 13, wherein the information related to the relationship between the cameras includes at least one information of an average time required for movement between the shooting ranges of the cameras or a distance between the shooting ranges of the cameras.
- DB database
- detected person information 167 ... Person tracking information, 200 ... video 300, display device, 400 ... input device, 1001 ... processor, 1003 ... memory, 1005 ... storage device, 1007 ... input interface (I / F), 1009 ... Data interface, 1011 ... communication interface, 1013 ... display device, 1100 ... monitoring device, 1110 ... input unit, 1120 ... first calculation unit, 1130 ... second calculation Part
Abstract
Description
図1乃至図10は、第1実施形態を説明するための図である。以下、これらの図を参照しながら、以下の流れに沿って本実施形態を説明する。まず「1.1」でシステムの機能構成の概要を示すと共に、「1.2」で動作の概要を、表示画面の具体例等を示しながら説明する。その後、「1.3」で処理の流れを、「1.4」で、本システムを実現可能なハードウェア構成の具体例を示す。最後に、「1.5」以降で、本実施形態に係る効果などを説明する。
(1.1.1 システム構成概要)
図1を参照しながら、本実施形態に係る情報処理システムである監視システム1のシステム構成を説明する。図1は、監視システム1のシステム構成を示すブロック図である。
なお、人物の検出や特徴量の抽出、カメラ内の人物追跡などの処理は、例えば、情報処理サーバ100や、図示しない他の情報処理装置上で行なっても良い。
以下、本実施形態に係る情報処理サーバ100の構成を説明する。情報処理サーバ100は、図1に示すように、入力部110、類似度算出部120、追跡人物登録部130、対応関係推定部140、表示制御部150、及びデータベース(DB)160を含む。なお、情報処理サーバ100の機能は、複数の情報処理装置(コンピュータ)により実現しても良い。
移動履歴生成部155は、人物追跡情報167に基づき、後述する図8に具体例を示す移動履歴表示画面に表示する、監視対象人物の移動履歴を生成する。
以下、図2乃至図8を参照しながら、監視システム1の機能や動作を説明する。
まず、図2を参照しながら、人物追跡(人物監視)の概略を説明する。
本実施形態に係る監視システム1では、前述の通り、ユーザが表示装置300の表示画面を見て、あるビデオカメラ200の映像に映った監視対象の人物(監視対象として登録済みの人物)が他のビデオカメラ200に映った場合には、入力装置400を操作して、当該2人の人物を同一人物として対応付ける。また、監視対象の人物ではない場合には、入力装置400を操作して、当該2人の人物が同一人物ではないことを入力する。このような同一人物であること、及び同一人物ではないこと、をユーザに入力可能とすることにより、監視システム1では、あり得る人物の対応関係の中で可能性の高い人物の対応関係を求める。
人物の対応関係の推測方法については、図5乃至図7を参照しながら後述する。
以下、図3及び図4を参照しながら、表示装置300が表示する表示画面の具体例を説明する。図3は、表示装置300が、人物監視のために表示する表示画面(以下、監視用画面30ともいう。)の具体例を示す図である。
また、ポップアップウィンドウ35が表示されると、ポップアップウィンドウ35と重なった映像領域31を見ることができずに視認性が悪くなることもあるので、ポップアップウィンドウ35の外側をクリック(選択)するとポップアップウィンドウ35が非表示となる機能や、逆に映像領域31内の人物Pの周辺を含む領域(人物領域)をクリックすると、ポップアップウィンドウ35が表示される機能を追加しても良い。
図4は、ポップアップウィンドウ35の具体例を示す図である。図4の例において、ID1、ID2、及びID3がそれぞれ割り当てられた監視対象者のサムネイルである人物画像41A乃至41C(以下、総称して人物画像41ともいう。)と、ID4が割り当てられた空白画像43とが並列に並べられている。
以下、図5乃至図7を参照しながら、ビデオカメラ200で撮影された人物の対応関係を推定する方法を説明する。図5乃至図7は、ビデオカメラ200で撮像された人物間の対応関係の推定方法を説明するための図である。
ユーザ操作に基づき、対応関係推定部140が推定した人物の対応関係に基づき、移動履歴生成部155は、監視対象人物の移動履歴を表示可能である。図8は、移動履歴生成部155が生成する移動履歴表示画面80の具体例を示す図である。なお、図8の移動履歴表示画面80は、例えば、図3に例示した監視用画面30において監視対象者表示領域33上で、ユーザから監視対象者の指定を受けると共に、当該監視対象者の移動履歴の表示をユーザから指示された場合に、移動履歴生成部155が生成する。ここでユーザからの指示は、入力装置400からの操作信号として情報処理サーバ100に入力される。
次に、情報処理サーバ100の処理の流れを、図9を参照しながら説明する。図9は、本実施形態に係る情報処理サーバ100の処理の流れを示すフローチャートである。
以下、図10を参照しながら、上述してきた情報処理サーバ100をコンピュータにより実現する場合のハードウェア構成の一例を説明する。なお、前述の通り、情報処理サーバ100の機能は、複数の情報処理装置により実現することも可能である。
以上説明したように、本実施形態に係る監視システム1では、ユーザから同一人物である旨、及び同一人物ではない旨の入力を受けることを可能とすることにより、その入力に応じて、好適な人物の対応関係を推定できる。特に、1人にかかる入力を行っただけであっても、他の人物の対応関係の予測にも影響を与えることができる。
以下、第2実施形態を、図11を参照しながら説明する。図11は、情報処理システムである監視装置1100の機能構成を示すブロック図である。図11に示すように、監視装置1100は、入力部1110と、第1の演算部1120と、第2の演算部1130とを含む。
また、第1の演算部1120は、少なくとも一部の尺度を、入力部1110から入力された対応情報に基づいて定める。
このように実装することで、本実施形態に係る監視装置1100によれば、映像に映る人物の対応付けを好適に推定することができる。
なお、前述の実施形態の構成は、組み合わせたり或いは一部の構成部分を入れ替えたりしてもよい。また、本発明の構成は前述の実施形態のみに限定されるものではなく、本発明の要旨を逸脱しない範囲内において種々変更を加えてもよい。
第1の時刻に複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物と、第1の時刻よりも遅い第2の時刻に前記複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物とがそれぞれ対応付けられる可能性を示す尺度を定める第1の演算手段と、前記第1の時刻又は前記第2の時刻の一方の時刻に映る少なくとも1名の人物と、他方の時刻に係る全ての人物とに係る全ての尺度を考慮して、前記第1の時刻に映る人物と前記第2の時刻に映る人物との対応関係を推定する第2の演算手段と、前記第1の時刻に撮影された1以上の人物の少なくとも一部と、前記第2の時刻に撮影された1以上の人物の少なくとも一部とが対応すること又は対応しないことに係る対応情報の入力を受ける入力手段とを備え、前記第1の演算手段は、前記入力部から入力された前記対応情報に基づき、少なくとも一部の尺度を定める、情報処理システム。
前記第1の演算手段は、前記第1の時刻に係る人物と前記第2の時刻に係る人物との特徴量の類似度に基づいて、少なくとも一部の尺度を算出する、付記1記載の情報処理システム。
前記第1の演算手段は、前記第1の時刻から前記第2の時刻までの経過時間と、各人物が映るカメラ間の関係に係る情報とに基づき、少なくとも一部の尺度を算出する、付記1又は付記2記載の情報処理システム。
前記カメラ間の関係に係る情報は、カメラの撮影範囲間の移動に要する平均時間、又はカメラの撮影範囲間の距離の少なくとも一方の情報を含む、付記3記載の情報処理システム。
前記第2の演算手段は、前記第1の時刻に係る全ての人物と、前記第2の時刻に係る全ての人物とに係る全ての尺度を考慮して、対応関係を推定する、付記1乃至付記4のいずれか1項記載の情報処理システム。
第1の時刻に複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物と、第1の時刻よりも遅い第2の時刻に前記複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物とがそれぞれ対応付けられる可能性を示す尺度を定めるステップと、前記第1の時刻又は前記第2の時刻の一方の時刻に映る少なくとも1名の人物と、他方の時刻に係る全ての人物とに係る全ての尺度を考慮して、前記第1の時刻に映る人物と前記第2の時刻に映る人物との対応関係を推定するステップと、前記第1の時刻に撮影された1以上の人物の少なくとも一部と、前記第2の時刻に撮影された1以上の人物の少なくとも一部とが対応すること又は対応しないことに係る対応情報の入力を受けるステップとを情報処理システムが行ない、前記尺度の少なくとも一部は、入力された前記対応情報に基づいて定める、情報処理方法。
前記第1の時刻に係る人物と前記第2の時刻に係る人物との特徴量の類似度に基づいて、少なくとも一部の尺度を算出する、付記6記載の情報処理方法。
前記第1の時刻から前記第2の時刻までの経過時間と、各人物が映るカメラ間の関係に係る情報とに基づき、少なくとも一部の尺度を算出する、付記6又は付記7記載の情報処理方法。
前記カメラ間の関係に係る情報は、カメラの撮影範囲間の移動に要する平均時間、又はカメラの撮影範囲間の距離の少なくとも一方の情報を含む、付記8記載の情報処理方法。
前記第1の時刻に係る全ての人物と、前記第2の時刻に係る全ての人物とに係る全ての尺度を考慮して、対応関係を推定する、付記6乃至付記9のいずれか1項記載の情報処理方法。
第1の時刻に複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物と、第1の時刻よりも遅い第2の時刻に前記複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物とがそれぞれ対応付けられる可能性を示す尺度を定める処理と、前記第1の時刻又は前記第2の時刻の一方の時刻に映る少なくとも1名の人物と、他方の時刻に係る全ての人物とに係る全ての尺度を考慮して、前記第1の時刻に映る人物と前記第2の時刻に映る人物との対応関係を推定する処理と、前記第1の時刻に撮影された1以上の人物の少なくとも一部と、前記第2の時刻に撮影された1以上の人物の少なくとも一部とが対応すること又は対応しないことに係る対応情報の入力を受ける処理とをコンピュータに実行させ、前記尺度の少なくとも一部は、入力された前記対応情報に基づいて定める、プログラム。
前記第1の時刻に係る人物と前記第2の時刻に係る人物との特徴量の類似度に基づいて、少なくとも一部の尺度を算出する、付記11記載のプログラム。
前記第1の時刻から前記第2の時刻までの経過時間と、各人物が映るカメラ間の関係に係る情報とに基づき、少なくとも一部の尺度を算出する、付記11又は付記12記載のプログラム。
前記カメラ間の関係に係る情報は、カメラの撮影範囲間の移動に要する平均時間、又はカメラの撮影範囲間の距離の少なくとも一方の情報を含む、付記13記載のプログラム。
前記第1の時刻に係る全ての人物と、前記第2の時刻に係る全ての人物とに係る全ての尺度を考慮して、対応関係を推定する、付記11乃至付記14のいずれか1項記載のプログラム。
Claims (7)
- 第1の時刻に複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物と、第1の時刻よりも遅い第2の時刻に前記複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物とがそれぞれ対応付けられる可能性を示す尺度を定める第1の演算手段と、
前記第1の時刻又は前記第2の時刻の一方の時刻に映る少なくとも1名の人物と、他方の時刻に係る全ての人物とに係る全ての尺度を考慮して、前記第1の時刻に映る人物と前記第2の時刻に映る人物との対応関係を推定する第2の演算手段と、
前記第1の時刻に撮影された1以上の人物の少なくとも一部と、前記第2の時刻に撮影された1以上の人物の少なくとも一部とが対応すること又は対応しないことに係る対応情報の入力を受ける入力手段と
を備え、
前記第1の演算手段は、前記入力部から入力された前記対応情報に基づき、少なくとも一部の尺度を定める、
情報処理システム。 - 前記第1の演算手段は、前記第1の時刻に係る人物と前記第2の時刻に係る人物との特徴量の類似度に基づいて、少なくとも一部の尺度を算出する、
請求項1記載の情報処理システム。 - 前記第1の演算手段は、前記第1の時刻から前記第2の時刻までの経過時間と、各人物が映るカメラ間の関係に係る情報とに基づき、少なくとも一部の尺度を算出する、
請求項1又は請求項2記載の情報処理システム。 - 前記カメラ間の関係に係る情報は、カメラの撮影範囲間の移動に要する平均時間、又はカメラの撮影範囲間の距離の少なくとも一方の情報を含む、
請求項3記載の情報処理システム。 - 前記第2の演算手段は、前記第1の時刻に係る全ての人物と、前記第2の時刻に係る全ての人物とに係る全ての尺度を考慮して、対応関係を推定する、
請求項1乃至請求項4のいずれか1項記載の情報処理システム。 - 第1の時刻に複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物と、第1の時刻よりも遅い第2の時刻に前記複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物とがそれぞれ対応付けられる可能性を示す尺度を定めるステップと、
前記第1の時刻又は前記第2の時刻の一方の時刻に映る少なくとも1名の人物と、他方の時刻に係る全ての人物とに係る全ての尺度を考慮して、前記第1の時刻に映る人物と前記第2の時刻に映る人物との対応関係を推定するステップと、
前記第1の時刻に撮影された1以上の人物の少なくとも一部と、前記第2の時刻に撮影された1以上の人物の少なくとも一部とが対応すること又は対応しないことに係る対応情報の入力を受けるステップと
を情報処理システムが行ない、
前記尺度の少なくとも一部は、入力された前記対応情報に基づいて定める、
情報処理方法。 - 第1の時刻に複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物と、第1の時刻よりも遅い第2の時刻に前記複数のビデオカメラでそれぞれ撮影された映像に映る1以上の人物とがそれぞれ対応付けられる可能性を示す尺度を定める処理と、
前記第1の時刻又は前記第2の時刻の一方の時刻に映る少なくとも1名の人物と、他方の時刻に係る全ての人物とに係る全ての尺度を考慮して、前記第1の時刻に映る人物と前記第2の時刻に映る人物との対応関係を推定する処理と、
前記第1の時刻に撮影された1以上の人物の少なくとも一部と、前記第2の時刻に撮影された1以上の人物の少なくとも一部とが対応すること又は対応しないことに係る対応情報の入力を受ける処理と
をコンピュータに実行させ、
前記尺度の少なくとも一部は、入力された前記対応情報に基づいて定める、
プログラム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/431,360 US9589192B2 (en) | 2012-09-27 | 2013-08-30 | Information processing system, information processing method, and program |
JP2014538306A JPWO2014050432A1 (ja) | 2012-09-27 | 2013-08-30 | 情報処理システム、情報処理方法及びプログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012214397 | 2012-09-27 | ||
JP2012-214397 | 2012-09-27 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014050432A1 true WO2014050432A1 (ja) | 2014-04-03 |
Family
ID=50387841
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/073354 WO2014050432A1 (ja) | 2012-09-27 | 2013-08-30 | 情報処理システム、情報処理方法及びプログラム |
Country Status (3)
Country | Link |
---|---|
US (1) | US9589192B2 (ja) |
JP (1) | JPWO2014050432A1 (ja) |
WO (1) | WO2014050432A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016174252A (ja) * | 2015-03-16 | 2016-09-29 | キヤノン株式会社 | 画像処理装置、画像処理システム、画像処理方法及びコンピュータプログラム |
JP2018032950A (ja) * | 2016-08-23 | 2018-03-01 | キヤノン株式会社 | 情報処理装置及びその方法、コンピュータプログラム |
US10445887B2 (en) | 2013-03-27 | 2019-10-15 | Panasonic Intellectual Property Management Co., Ltd. | Tracking processing device and tracking processing system provided with same, and tracking processing method |
WO2022185521A1 (ja) * | 2021-03-05 | 2022-09-09 | 三菱電機株式会社 | 移動経路推定装置、移動経路推定方法、及び、移動経路推定プログラム |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5919665B2 (ja) * | 2011-07-19 | 2016-05-18 | 日本電気株式会社 | 情報処理装置、物体追跡方法および情報処理プログラム |
EP2913997B1 (en) * | 2012-10-29 | 2021-09-29 | NEC Corporation | Information processing system, information processing method, and program |
JP6270433B2 (ja) * | 2013-11-26 | 2018-01-31 | キヤノン株式会社 | 情報処理装置、情報処理方法、情報処理システム |
EP3435665A4 (en) * | 2016-03-25 | 2019-03-20 | Panasonic Intellectual Property Management Co., Ltd. | MONITORING AND MONITORING SYSTEM |
JP7229698B2 (ja) * | 2018-08-20 | 2023-02-28 | キヤノン株式会社 | 情報処理装置、情報処理方法及びプログラム |
SG10201807663PA (en) * | 2018-09-06 | 2020-04-29 | Nec Asia Pacific Pte Ltd | System and method for multi-layer potential associates discovery |
JP2022122498A (ja) * | 2021-02-10 | 2022-08-23 | 富士通株式会社 | 移動履歴変更方法及び移動履歴変更プログラム |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007026744A1 (ja) * | 2005-08-30 | 2007-03-08 | National University Corporation NARA Institute of Science and Technology | 広域分散カメラ間の連結関係推定法および連結関係推定プログラム |
JP2008219570A (ja) * | 2007-03-06 | 2008-09-18 | Matsushita Electric Ind Co Ltd | カメラ間連結関係情報生成装置 |
JP2009098774A (ja) * | 2007-10-15 | 2009-05-07 | Mitsubishi Electric Corp | 人物追跡システム及び人物追跡方法及び人物追跡プログラム |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7450735B1 (en) * | 2003-10-16 | 2008-11-11 | University Of Central Florida Research Foundation, Inc. | Tracking across multiple cameras with disjoint views |
AU2009243528B2 (en) * | 2009-12-04 | 2013-08-01 | Canon Kabushiki Kaisha | Location-based signature selection for multi-camera object tracking |
GB201113633D0 (en) * | 2011-08-08 | 2011-09-21 | Vision Semantics Ltd | User-primed iterative discovery of object associations in distributed multi-source data |
-
2013
- 2013-08-30 WO PCT/JP2013/073354 patent/WO2014050432A1/ja active Application Filing
- 2013-08-30 US US14/431,360 patent/US9589192B2/en active Active
- 2013-08-30 JP JP2014538306A patent/JPWO2014050432A1/ja active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007026744A1 (ja) * | 2005-08-30 | 2007-03-08 | National University Corporation NARA Institute of Science and Technology | 広域分散カメラ間の連結関係推定法および連結関係推定プログラム |
JP2008219570A (ja) * | 2007-03-06 | 2008-09-18 | Matsushita Electric Ind Co Ltd | カメラ間連結関係情報生成装置 |
JP2009098774A (ja) * | 2007-10-15 | 2009-05-07 | Mitsubishi Electric Corp | 人物追跡システム及び人物追跡方法及び人物追跡プログラム |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10445887B2 (en) | 2013-03-27 | 2019-10-15 | Panasonic Intellectual Property Management Co., Ltd. | Tracking processing device and tracking processing system provided with same, and tracking processing method |
GB2529943B (en) * | 2013-03-27 | 2019-11-06 | Panasonic Ip Man Co Ltd | Tracking processing device and tracking processing system provided with same, and tracking processing method |
JP2016174252A (ja) * | 2015-03-16 | 2016-09-29 | キヤノン株式会社 | 画像処理装置、画像処理システム、画像処理方法及びコンピュータプログラム |
EP3272117A4 (en) * | 2015-03-16 | 2018-12-12 | C/o Canon Kabushiki Kaisha | Image processing apparatus, image processing system, method for image processing, and computer program |
US10572736B2 (en) | 2015-03-16 | 2020-02-25 | Canon Kabushiki Kaisha | Image processing apparatus, image processing system, method for image processing, and computer program |
JP2018032950A (ja) * | 2016-08-23 | 2018-03-01 | キヤノン株式会社 | 情報処理装置及びその方法、コンピュータプログラム |
US10719946B2 (en) | 2016-08-23 | 2020-07-21 | Canon Kabushiki Kaisha | Information processing apparatus, method thereof, and computer-readable storage medium |
WO2022185521A1 (ja) * | 2021-03-05 | 2022-09-09 | 三菱電機株式会社 | 移動経路推定装置、移動経路推定方法、及び、移動経路推定プログラム |
JPWO2022185521A1 (ja) * | 2021-03-05 | 2022-09-09 | ||
JP7270855B2 (ja) | 2021-03-05 | 2023-05-10 | 三菱電機株式会社 | 移動経路推定装置、移動経路推定方法、及び、移動経路推定プログラム |
GB2619633A (en) * | 2021-03-05 | 2023-12-13 | Mitsubishi Electric Corp | Movement path estimation device, movement path estimation method, and movement path estimation program |
Also Published As
Publication number | Publication date |
---|---|
US9589192B2 (en) | 2017-03-07 |
US20150262019A1 (en) | 2015-09-17 |
JPWO2014050432A1 (ja) | 2016-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6210234B2 (ja) | 画像処理システム、画像処理方法及びプログラム | |
WO2014050432A1 (ja) | 情報処理システム、情報処理方法及びプログラム | |
US20220124410A1 (en) | Image processing system, image processing method, and program | |
JP6213843B2 (ja) | 画像処理システム、画像処理方法及びプログラム | |
JP6347211B2 (ja) | 情報処理システム、情報処理方法及びプログラム | |
US20210012632A1 (en) | Information processing system, method and computer readable medium for determining whether moving bodies appearing in first and second videos are the same or not | |
JP6575845B2 (ja) | 画像処理システム、画像処理方法及びプログラム | |
WO2014045670A1 (ja) | 画像処理システム、画像処理方法及びプログラム |
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: 13841810 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2014538306 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14431360 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: 13841810 Country of ref document: EP Kind code of ref document: A1 |