WO2015046500A1 - 情報処理装置、情報処理方法、プログラム及び情報記憶媒体 - Google Patents
情報処理装置、情報処理方法、プログラム及び情報記憶媒体 Download PDFInfo
- Publication number
- WO2015046500A1 WO2015046500A1 PCT/JP2014/075852 JP2014075852W WO2015046500A1 WO 2015046500 A1 WO2015046500 A1 WO 2015046500A1 JP 2014075852 W JP2014075852 W JP 2014075852W WO 2015046500 A1 WO2015046500 A1 WO 2015046500A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- subject
- image
- partial region
- partial
- information processing
- Prior art date
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 76
- 238000003672 processing method Methods 0.000 title claims abstract description 6
- 238000000034 method Methods 0.000 claims description 54
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 description 14
- 238000001914 filtration Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 102000002273 Polycomb Repressive Complex 1 Human genes 0.000 description 7
- 108010000598 Polycomb Repressive Complex 1 Proteins 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 101100465401 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) SCL1 gene Proteins 0.000 description 6
- 238000013500 data storage Methods 0.000 description 5
- 101100160255 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) YLR154C-H gene Proteins 0.000 description 3
- 125000002066 L-histidyl group Chemical group [H]N1C([H])=NC(C([H])([H])[C@](C(=O)[*])([H])N([H])[H])=C1[H] 0.000 description 2
- 101100212791 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) YBL068W-A gene Proteins 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 101100409551 Arabidopsis thaliana PAC1 gene Proteins 0.000 description 1
- 101100409537 Arabidopsis thaliana PAG1 gene Proteins 0.000 description 1
- 101100410162 Caenorhabditis elegans ptc-3 gene Proteins 0.000 description 1
- 101000974343 Homo sapiens Nuclear receptor coactivator 4 Proteins 0.000 description 1
- 102100022927 Nuclear receptor coactivator 4 Human genes 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/012—Head tracking input arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
Definitions
- the present invention relates to an information processing apparatus, an information processing method, a program, and an information storage medium.
- an information processing apparatus that uses an image of a subject as an input interface.
- an information processing apparatus that specifies a motion of a subject based on a difference between a plurality of frame images captured at different timings and executes a process according to the motion.
- the user can input to the information processing apparatus by bringing his / her finger into contact with the face.
- the detection accuracy of whether or not an object is in contact with the object is low. For this reason, it is difficult to distinguish between a situation in which the user actually touches the face with the face and a situation in which the user pretends to make the finger touch the face.
- the present invention has been made in view of the above problems, and one of its purposes is an information processing apparatus, an information processing method, a program, and information in which the accuracy of detecting the presence or absence of contact of an object with a subject is improved as compared with the prior art. It is to provide a storage medium.
- an information processing apparatus includes a frame image acquisition unit that acquires a plurality of frame images captured at different timings, each including a subject region in which an image of a subject is captured.
- a subject partial area specifying unit that specifies a plurality of subject partial areas that are different from each other in the subject area, which is a part of the subject area, and the subject that is associated with each other in each frame image
- a partial region feature amount specifying unit that specifies a partial region feature amount indicating a variation in an image feature amount of an image that occupies the subject partial region based on an image feature amount of an image that occupies each partial region; and the plurality of subject partial regions Presence or absence of contact of the object with the subject based on the relationship between the partial region feature values associated with each of A contact determination unit, characterized in that it comprises a.
- the information processing method includes a step of acquiring a plurality of frame images captured at different timings, each including a subject region in which an image of a subject is captured, and each of the frame images. Based on the step of identifying a plurality of subject partial areas that are different from each other in the subject area and the image feature amount of an image that occupies each of the subject partial areas that are associated with each other in each frame image , Based on the relationship between the partial region feature amount indicating the variation of the image feature amount of the image occupying the subject partial region and the partial region feature amount associated with each of the plurality of subject partial regions, Determining whether or not the object is in contact with the subject.
- the program according to the present invention includes a procedure for obtaining a plurality of frame images captured at different timings including a subject region in which an image of a subject is captured, and each of the frame images is a part of the subject region. Based on a procedure for identifying a plurality of subject partial areas whose positions in the subject area are different from each other, and image feature amounts of images occupying each of the subject partial areas associated with each other in each frame image, The object contact with the subject based on the procedure for identifying the partial region feature value indicating the variation of the image feature value of the image occupying the region, and the relationship between the partial region feature values associated with each of the plurality of subject partial regions And a procedure for determining whether or not there is a computer.
- the information storage medium includes a procedure for acquiring a plurality of frame images captured at different timings including a subject region in which an image of a subject is captured, and each of the frame images is a part of the subject region. Based on a procedure for identifying a plurality of subject partial areas whose positions in the subject area are different from each other, and an image feature amount of an image occupying each of the subject partial areas associated with each other in each frame image An object for the subject based on a procedure for identifying a partial region feature amount indicating a variation in an image feature amount of an image that occupies the subject partial region, and a relationship between the partial region feature amounts associated with each of the plurality of subject partial regions. A program for causing a computer to execute a procedure for determining the presence or absence of contact with a computer is described. A computer readable information storage medium.
- the inventor of the present invention has an image feature of an image that occupies a plurality of subject partial areas in a situation where an object actually contacts the subject and a situation where the user pretends to contact the subject with the subject. It was found that the relationship between the partial region feature amounts indicating the variation of the amount is different.
- the presence / absence of contact of the object with the subject is determined based on the relationship between the partial region feature amounts associated with each of the plurality of subject partial regions. Therefore, according to the present invention, the accuracy of detecting the presence / absence of contact of an object with a subject is improved as compared with the prior art.
- the contact determination unit occupies the subject partial region based on the relationship between the partial region feature values associated with each of the subject partial regions associated with the subject partial region. It is determined whether or not an object is in contact with a part of the subject in which an image appears in the image.
- the contact determination unit occupies the subject partial region different from the subject partial regions based on the relationship between the partial region feature amounts associated with the subject partial regions. It may be determined whether or not an object touches a part of the subject on which an image appears.
- the contact determination unit may be configured based on a magnitude relationship between the magnitudes of fluctuations in the image feature amount indicated by the partial region feature amount associated with each of the plurality of subject partial regions. It is determined whether or not an object touches the subject.
- the contact determination unit is based on a temporal context regarding a change in the image feature amount indicated by the partial region feature amount associated with each of the plurality of subject partial regions. The presence / absence of contact of the object with the subject is determined.
- an audio data acquisition unit that acquires audio data is further included, and the contact determination unit is configured to determine the subject based on the relationship between the partial region feature amount and the acquired audio data. The presence or absence of the contact of the object with respect to is determined.
- FIG. 1 is a diagram illustrating an example of the overall configuration of an information processing system 10 according to an embodiment of the present invention.
- the information processing system 10 includes, for example, an information processing device 12, an imaging device 14, a sound collection device 16, and a display device 18.
- the information processing apparatus 12 is a computer such as a game console, for example.
- the imaging device 14 is a camera that outputs an image obtained by imaging a subject to the information processing device 12.
- the sound collection device 16 is a microphone or the like that acquires ambient sound, converts the sound into sound data in a PCM format, and outputs the sound data to the information processing device 12.
- the display device 18 is a liquid crystal display or the like, and displays a screen generated by the information processing device 12, an image captured by the imaging device 14, and the like.
- the information processing device 12, the imaging device 14, and the sound collecting device 16 are connected via, for example, a USB cable, an AV cable, an HDMI (registered trademark) (High-Definition Multimedia Interface) cable, or the like.
- the information processing device 12 and the display device 18 are connected via, for example, an AV cable, an HDMI cable, or the like.
- the imaging device 14 sequentially captures images of a subject arranged in front of the imaging device 14 at a predetermined frame rate.
- the image is referred to as a frame image 20 (see FIGS. 2A, 2B, and 2C).
- the subject in the present embodiment is assumed to be the user's face.
- the frame rate is 60 fps. That is, the frame period in this embodiment is 1/60 second.
- FIG. 2A, 2B, and 2C are diagrams each showing an example of a frame image 20 captured by the imaging device 14.
- the user's finger contacts the face at the timing when the frame image 20 illustrated in FIG. 2B is captured and the timing when the frame image 20 illustrated in FIG. 2C is captured.
- the present embodiment based on the frame image 20 captured by the image capturing device 14 and the sound acquired by the sound collecting device 16, it is determined whether or not the object is in contact with the subject. For example, in the present embodiment, for each of a plurality of preset image contact determination periods, whether or not the frame image 20 captured during the image contact determination period satisfies an image contact determination condition (see FIG. 7) described later. Is determined. In the present embodiment, for each of a plurality of preset voice contact determination periods, it is determined whether or not the voice acquired during the voice contact determination period satisfies a voice contact determination condition described later. FIG.
- the image contact determination period P1 determined to satisfy the image contact determination condition and the sound contact determination period P2 determined to satisfy the sound contact determination condition.
- a period P3 in which the image contact determination period P1 and the audio contact determination period P2 overlap is specified.
- the period P3 is finally specified as a period in which the object is in contact with the subject. For example, in a period including the timing when the frame image 20 illustrated in FIG. 2B is captured and a period including the timing when the frame image 20 illustrated in FIG. 2C is included, it is determined that the object is in contact with the subject. It becomes.
- FIG. 4 is an explanatory diagram for explaining an example of setting patterns for an image contact determination period and an audio contact determination period (in FIG. 4, expressed as a contact determination period).
- the image contact determination period and the audio contact determination period may be set at a predetermined time interval as shown in pattern 1 of FIG. 4, or may be a part of each other as shown in pattern 2 of FIG. May be set to overlap.
- the image contact determination period is set at 64 frames, that is, at intervals of about 1 second.
- frame numbers from 1 to 64 are sequentially set in the frame image 20 according to the imaging order within the image contact determination period.
- voice contact determination periods are set at intervals of 1 millisecond.
- the image contact determination period and the audio contact determination period are set independently.
- an area in the frame image 20 where the subject is shown is referred to as a subject area R.
- the image occupying the subject region R generally includes an image of the user's face.
- the positions of the users when the frame images 20 shown in FIGS. 2A to 2C are captured are different. Therefore, the position of the subject image in the frame image 20 shown in FIGS. 2A to 2C is different.
- the user and the imaging device 14 are more likely to be captured when the frame image 20 illustrated in FIG. 2B or the frame image 20 illustrated in FIG. 2C is captured than when the frame image 20 illustrated in FIG. 2A is captured.
- the distance to is short.
- the subject image is larger in the frame image 20 shown in FIG. 2B and the frame image 20 shown in FIG. 2C than in the frame image 20 shown in FIG. 2A. That is, the subject area R occupying the frame image 20 shown in FIGS. 2B and 2C is larger than the subject area R occupying the frame image 20 shown in FIG. 2A.
- the inventor has found that the image feature amount of the image occupying the subject region R in the image contact determination period in the situation where the user actually touches the face with the face and the situation where the user pretend to contact the face within the image contact determination period. It was found that the fluctuations of are different. Focusing on this, in the present embodiment, as described below, it is determined whether or not an object actually touches the subject.
- the subject region R is divided into a plurality of subject partial regions SR (see FIG. 5).
- FIG. 5 is a diagram illustrating an example of the relationship between the subject region R and the subject partial region SR.
- the subject partial region SR is a region that occupies a part of the subject region R.
- the positions of the subject partial areas SR included in one subject area R in the subject area R are different from each other.
- the subject region R is equally divided into a total of 16 subject partial regions SR, 4 vertical ⁇ 4 horizontal.
- an identification number is assigned to the subject partial region SR.
- 0 to 3, 4 to 7, 8 to 11, and 12 in order from the left to the subject partial region SR in the top, second from the top, third from the top, and bottom row, respectively.
- Identification numbers of ⁇ 15 are assigned.
- the subject partial region SR to which the identification number i is assigned is expressed as SRi.
- the identification number is associated with a position in the subject area R.
- the identification number is not assigned to the subject partial area SR depending on the frame image 20. That is, regardless of the frame image 20, the subject partial region SR at the upper left end in the subject region R becomes the subject partial region SR0, for example.
- the information processing apparatus 12 determines that an object has contacted the subject, the information processing apparatus 12 performs processing according to the contact.
- the subject partial region SR associated with the contact position of the object is also specified.
- the subject partial region SR associated with the contact position of the finger is identified as SR0.
- the subject partial area SR associated with the contact position of the finger is identified as SR3.
- the information processing apparatus 12 according to the present embodiment executes processing according to the subject partial region SR associated with the contact position of the object with respect to the subject.
- the process executed according to the contact of the object with the subject is not particularly limited.
- a process for starting a program installed in the information processing apparatus 12, a process for stopping the information processing apparatus 12, a command execution process for a program executed by the information processing apparatus 12, and the like correspond to the processes.
- the information processing apparatus 12 executes a process for starting a program installed in the information processing apparatus 12.
- the information processing device 12 executes a stop process of the information processing device 12. In this manner, in the information processing system 10 according to the present embodiment, it is possible to input information to the information processing apparatus 12 by bringing an object into contact with a subject.
- FIG. 6 is a functional block diagram illustrating an example of functions implemented by the information processing apparatus 12 according to the present embodiment. Note that the information processing apparatus 12 according to the present embodiment does not have to include all the functions illustrated in FIG. 6, and may include functions other than the functions illustrated in FIG. 6.
- the information processing apparatus 12 includes a control unit that is a program control device such as a CPU that operates according to a program installed in the information processing apparatus 12.
- the information processing apparatus 12 also includes a storage element such as a ROM or RAM and a storage unit such as a hard disk drive.
- the storage unit of the information processing device 12 stores a program executed by the control unit of the information processing device 12.
- the information processing apparatus 12 includes a USB (UniversalUniversSerial Bus) port, an HDMI port, and the like.
- the information processing apparatus 12 functionally includes, for example, a contact determination condition data storage unit 30, a frame image acquisition unit 32, an audio data acquisition unit 34, and a subject area specification.
- the contact determination condition data storage unit 30 is mainly implemented by the storage unit of the information processing apparatus 12.
- Other functions are mainly implemented by the control unit of the information processing apparatus 12.
- the above functions are implemented by causing the control unit of the information processing apparatus 12 to execute a program that is installed in the information processing apparatus 12 that is a computer and that includes instructions corresponding to the above functions.
- This program is supplied to the information processing apparatus 12 via a computer-readable information storage medium such as an optical disk, a magnetic disk, a magnetic tape, a magneto-optical disk, or a flash memory, or via communication means such as the Internet.
- the contact determination condition data storage unit 30 stores contact determination condition data indicating a condition for determining whether or not an object is in contact with a subject.
- the contact determination condition data storage unit 30 stores, as an example of the contact determination condition data, image contact determination condition data indicating a condition for determining whether or not an object contacts the subject based on the frame image 20. ing.
- the contact determination condition data storage unit 30 also stores voice contact determination condition data indicating conditions for determining whether or not an object is in contact with the subject based on the acquired sound. In the voice contact determination condition data, for example, the range of the frequency domain and the volume level are indicated as conditions.
- FIG. 7 shows an example of image contact determination condition data.
- the image contact determination condition data includes, for example, an identification number associated with a position in the subject region R and a partial region feature amount PRC specified based on an image occupying the subject partial region SR associated with the identification number.
- Image contact determination conditions are associated with each other.
- the identification number In the image contact determination condition data shown in FIG. 7, only the image contact determination condition associated with the identification numbers 0 and 3 is clearly shown.
- the identification number 1 It is assumed that image contact determination conditions associated with 2, 4 to 15 are shown.
- the image contact determination condition associated with the identification number 0 is used when determining whether or not an object touches a part of a subject whose image appears in an image occupying the subject partial region SR0.
- the image contact determination condition associated with the identification number 3 is used when determining whether or not an object touches a part of a subject whose image appears in the image occupying the subject partial region SR3.
- a plurality of conditions are associated with the identification number as image contact determination conditions.
- the image contact determination condition in this embodiment corresponds to the logical product of these multiple conditions.
- a partial region feature amount PRCi described later satisfies all of a plurality of conditions associated with the identification number i, an object appears in a part of the subject that is imaged in an image that occupies the subject partial region SRi region. Is determined to have touched.
- the frame image acquisition unit 32 acquires the frame image 20 captured by the imaging device 14. In the present embodiment, the frame image acquisition unit 32 acquires the frame images 20 at 1/60 second intervals.
- the audio data acquisition unit 34 acquires audio data from the sound collection device 16, for example.
- the audio data acquisition unit 34 holds the acquired audio data until at least the contact determination period to which the timing at which the audio is acquired ends.
- the subject area specifying unit 36 specifies the subject area R in the frame image 20.
- the subject region specifying unit 36 specifies a subject region R in which an image of the user's face is captured, for example, by a tracking technique such as a known face recognition technique. Note that the subject area R in the frame image 20 is set in advance, and the user may adjust the position of the face so that an image of the user's face is captured in the subject area R.
- the subject partial area specifying unit 38 specifies the subject partial area SR based on the subject area R. In the present embodiment, for example, by dividing the subject region R into four vertically and four horizontally, each of the frame images 20 has 16 subject partial regions SR ( SR0 to SR15) are specified.
- the partial region feature amount specifying unit 40 specifies a partial region feature amount PRC indicating a variation in the image feature amount of an image occupying the subject partial region SR.
- the image feature amount of the image occupying the subject partial region SR indicates, for example, statistical information according to the pixel value of the pixel in the image. An example of the statistical information is an average pixel value of pixels in the image.
- the partial region feature amount PRC is specified for each identification number assigned to the subject partial region SR.
- the partial region feature amount specifying unit 40 specifies a larger value as the partial region feature amount PRCi in the contact determination period as the variation in the image feature amount of the image occupying the subject partial region SRi in the contact determination period increases. To do.
- the partial region feature PRCi is a scalar, but the partial region feature PRCi may be a vector. Further, the partial region feature amount specifying unit 40 may specify only the partial region feature amount PRCi indicated as the image contact determination condition.
- the contact determination unit 42 determines whether or not an object has touched the subject based on at least one of the relationship between the partial region feature amounts PRC0 to PRC15 associated with a plurality of positions and the audio data acquired by the audio data acquisition unit 34. Determine. In the present embodiment, the contact determination unit 42 determines, for each subject partial region SR, whether or not an object has touched a part of the subject whose image appears in the image that occupies the region.
- the frame image acquisition unit 32 acquires the frame image 20 (S101).
- the subject area specifying unit 36 specifies the subject area R in the frame image 20 acquired by the process shown in S101 (S102).
- the subject partial area specifying unit 38 divides the subject area R specified in the process shown in S102 into 16 parts, and specifies 16 subject partial areas SR (SR0 to SR15) (S103).
- the partial region feature amount specifying unit 40 sets the value of the variable i to 0 (S104). Then, the partial region feature amount specifying unit 40 specifies pixel values of pixels included in the subject partial region SRi (S105). In the process shown in S105, the partial region feature amount specifying unit 40 specifies, for example, the R component pixel value, the G component pixel value, and the B component pixel value of all the pixels included in the subject partial region SR0. .
- the partial region feature amount specifying unit 40 specifies the image feature amount PCi (k) corresponding to the pixel value specified in the process shown in S105 (S106).
- the partial region feature value specifying unit 40 holds data indicating the image feature value PCi (k) specified in the process shown in S106 until the contact determination period to which the frame period belongs ends.
- the partial region feature amount specifying unit 40 for example, average values of the R component, G component, and B component of the pixel values of the pixels included in the subject partial region SRi in the frame image 20 of the frame number k.
- a three-dimensional vector having as a component is specified.
- the partial region feature amount specifying unit 40 specifies the image feature amount PCi (k) based on the specified three-dimensional vector.
- Examples of the image feature amount PCi (k) include the sum of the values of the three components of the above-described three-dimensional vector, the average value thereof, and the square root of the square sum of the three components of the above-described three-dimensional vector. This is not the case.
- the partial region feature amount specifying unit 40 checks whether or not the value of the variable i is 15 (S107). When it is confirmed that the value of the variable i is not 15 (S107: N), the partial region feature amount specifying unit 40 increments the value of the variable i by 1 (S108), and executes the processing from S105 onward again. To do. If it is confirmed that the value of the variable i is 15 (S107: Y), the processing shown in this processing example is terminated.
- FIG. 9 is a diagram schematically illustrating an example of the image feature amount PC0 (k) associated with the subject partial region SR0 in the frame image 20 with the frame number k.
- the information processing apparatus 12 executes the processes shown in S101 to S108 for each frame image 20 captured within one contact determination period.
- the image feature amounts PC0 (1) to PC0 (64), PC1 (1) to PC1 (64),..., PC15 (1) to PC15 (64) are specified.
- FIG. 10 shows an example of a process flow for determining whether or not the image contact determination condition associated with the identification number 0 in the image contact determination condition data associated with the subject partial region SR0 is satisfied. Yes.
- the partial region feature quantity specifying unit 40 sets the value of the variable i to 0 (S201). Then, the partial region feature amount specifying unit 40 checks whether or not the partial region feature amount PRCi is indicated as any image contact determination condition included in the image contact determination condition data (S202).
- the partial region feature value specifying unit 40 performs the filtered image based on the stored image feature values PCi (1) to PCi (64).
- the feature amounts PC′i (1) to PC′i (64) are calculated (S203).
- the partial region feature amount specifying unit 40 regards the image feature amounts PCi (1) to PCi (64) as time-series data and applies the image feature amounts PCi (1) to PCi (64). For example, filtering by a band pass filter is performed. In the filtering, for example, smoothing is performed to remove a component having a frequency higher than a predetermined frequency.
- FIG. 11 schematically shows an example of the filtered image feature quantity PC′0 (k) associated with the subject partial region SR0.
- the partial region feature amount specifying unit 40 is a portion associated with the subject partial region SRi based on the post-filtering image feature amounts PC′i (1) to PC′i (64) calculated in the process shown in S203.
- the region feature amount PRCi is specified (S204).
- the partial region feature amount specifying unit 40 specifies the value of the partial region feature amount PRCi so that the larger the change in the pixel value of the pixel included in the subject partial region SRi in the contact determination period, the larger the value.
- the partial region feature amount specifying unit 40 specifies a value obtained by subtracting the minimum value from the maximum value of PC′i (1) to PC′i (64) as the partial region feature amount PRCi.
- the partial region feature PRCi is not indicated as any image contact determination condition included in the image contact determination condition data (S202: N), or when the process shown in S204 is finished, the partial region feature The quantity identification unit 40 checks whether or not the value of the variable i is 15 (S205). When it is confirmed that the value of the variable i is not 15 (S205: N), the partial region feature amount specifying unit 40 increases the value of the variable i by 1 (S206), and executes the processing from S202 onward again. To do.
- the contact determination unit 42 includes a plurality of image contact determination conditions associated with the identification number 0 in the image contact determination condition data. It is confirmed whether or not any of the conditions is satisfied (S206). In the process shown in S206, whether or not the condition for which the process shown in S206 has not been performed is satisfied is confirmed. For example, whether or not any of the conditions such as PRC0> PRC1,..., PRC3> PRC2 is satisfied is confirmed.
- the contact determination unit 42 determines that the image contact determination condition associated with the identification number 0 is not satisfied (S207). Then, the processing shown in this processing example is finished.
- the process shown in S206 is performed among the plurality of conditions associated with the identification number 0 in the image contact determination condition data. It is confirmed whether or not there is any (S208). If it exists (S208: Y), the processing shown in S206 and subsequent steps is executed again. If it does not exist (S208: N), the contact determination unit 42 determines that the image contact determination condition associated with the identification number 0 is satisfied (S209), and ends the processing shown in this processing example.
- the present embodiment it is confirmed whether or not the relationship between the partial region feature amounts PRC0 to PRC15 satisfies all of the plurality of conditions associated with the identification number 0. In the present embodiment, similarly for other identification numbers, it is confirmed whether or not the relationship between the partial region feature quantities PRC0 to PRC15 satisfies all of the plurality of conditions associated with the identification number.
- the contact determination unit 42 executes a filtering process for extracting a frequency region indicated by the voice contact determination condition data for the voice data acquired by the voice data acquisition unit 34 within the voice contact determination period (S301). And the contact determination part 42 confirms whether the audio
- the contact determination unit 42 determines that the voice contact determination condition is satisfied (S303), and ends the process shown in the present process example.
- the contact determination unit 42 determines that the audio contact determination condition is not satisfied (S304), and ends the process shown in this process example. To do.
- the contact determination unit 42 is determined to satisfy the image contact determination period P ⁇ b> 1 determined to satisfy the image contact determination condition associated with the identification number i and the audio contact determination condition.
- a period P3 in which the voice contact determination period P2 overlaps is specified.
- the contact determination unit 42 determines that there is an object contact with a part of the subject whose image appears in the image occupying the subject partial region SRi in the specified period P3.
- the contact determination unit 42 determines that the voice contact determination period satisfies the image contact determination condition associated with the identification number i and satisfies the voice contact determination condition. It may be determined whether or not a condition that it is a set period is satisfied. Then, the contact determination unit 42 may determine that there is an object contact with a part of the subject whose image appears in the image occupying the subject partial region SRi during the voice contact determination period that satisfies the condition.
- the contact determination unit 42 determines the presence / absence of contact of the object with the subject based on the captured frame image 20 and the acquired audio data, but based on either one, It may be determined whether or not an object touches the subject.
- the contact determination unit 42 is an object to a part of the subject whose image appears in the image occupying the subject partial region SRi during the image contact determination period determined to satisfy the image contact determination condition associated with the identification number i. It may be determined that there has been contact.
- the image that occupies the subject partial areas SR4 to SR7 is highly likely to include an image of the subject's eyes. For this reason, there is a possibility that the fluctuation of the pixel values of the pixels included in the subject partial regions SR4 to SR7 may increase due to the blinking of the user who is the subject, regardless of the contact of the object with the subject. Therefore, in the example of FIG. 7, in the image contact determination conditions associated with the identification numbers 0 and 3, the partial region feature amounts PRC4 to PRC7 are excluded from comparison targets with the partial region feature amount PRC0.
- the partial region feature amounts PRC7, PRC11, and PRC15 are excluded from comparison targets with the partial region feature amount PRC3.
- an image associated with the identification number 0 indicates that the partial region feature amount PRC0 is larger than any of the partial region feature amounts PRC other than the partial region feature amount PRC excluded from the comparison target. It is shown as a contact determination condition. For the same reason, the image contact associated with the identification number 3 indicates that the partial region feature PRC3 is larger than any of the partial region feature PRCs other than the partial region feature PRC excluded from the comparison target. It is shown as a judgment condition.
- FIG. 7 further shows that the partial region feature value PRC2 is smaller than any of the partial region feature values PRC1 and PRC3 as the image contact determination condition associated with the identification number 0. .
- FIG. 7 further shows that the partial region feature amount PRC1 is smaller than any of the partial region feature amounts PRC0 and PRC2 as an image contact determination condition associated with the identification number 3. Yes.
- FIG. 13 schematically shows an example of post-filtering image feature values PC0 ′ (k) to PC15 ′ (k) for a plurality of subject partial regions SR.
- FIG. 13 also shows a partial region feature amount PRC0.
- FIG. 13 shows filtered image feature amounts PC0 ′ (k) to PC15 ′ (k) corresponding to the image feature amount PC shown as the image contact determination condition associated with the identification number 0 in FIG. Has been.
- the partial region feature values PRC0 are the partial region feature values PRC1 to PRC3 and PRC9 to PRC11. , Larger than any of PRC13 to PRC15. Further, the partial region feature amount PRC2 is smaller than any of the partial region feature amounts PRC1 and PRC3. Therefore, in this case, it is determined that the relationship between the partial region feature amounts PRC0 to PRC15 satisfies the image contact determination condition associated with the identification number 0 in the image contact determination condition data. Similarly, it can also be determined whether or not other image contact determination conditions such as the image contact determination condition associated with the identification number 3 are satisfied.
- the presence or absence of an object contact with a subject is determined based on the relationship between image feature amounts associated with a plurality of positions, the accuracy of detecting the presence or absence of the object contact with the subject is improved compared to the conventional case. Will be.
- the present embodiment based on the relationship between the partial region feature amounts PRC1 to PRC3, it is determined whether or not an object is in contact with a part of the subject that is imaged in the image occupying the subject partial region SR0. Then, based on the relationship between the partial region feature amounts PRC0 to PRC2, whether or not the object touches a part of the subject whose image appears in the image occupying the subject partial region SR3 is determined. As described above, based on the relationship between the partial region feature amounts PRC associated with a plurality of subject partial regions SR different from the specific subject partial region SR, the subject imaged in the image occupying the specific subject partial region SR. The presence or absence of an object contact with a part is determined. In this way, in the present embodiment, the detection accuracy of the presence or absence of contact of an object with a part of a subject whose image appears in the image occupying the subject partial region SR is improved as compared with the conventional case.
- the voice contact determination period is shorter than the image contact determination period. Therefore, by combining the above-described determination based on the frame image 20 and the above-described determination based on sound, it is possible to accurately specify the timing at which the object contacts the subject.
- the position of the subject region R in the frame image 20 is specified, and the partial region feature amount PRC associated with the position in the subject region R is calculated. Based on the relationship of the partial region feature amount PRC calculated in this way, it is determined whether or not the object has touched the subject. In this way, in this embodiment, even if the distance between the subject and the imaging device 14 or the position of the subject with respect to the imaging device 14 changes within the contact determination period, the presence or absence of an object contact with the subject is accurately detected. Will be able to.
- the above description has focused on determining whether or not the user has touched his / her finger to the face.
- it is determined whether or not an arbitrary object such as a ball has touched the face. Will be able to.
- the information processing apparatus 12 may execute processing according to the combination of the plurality of subject partial areas SR.
- the contact determination unit 42 determines whether or not an object has touched the subject based on the temporal context of the change in the image feature amount indicated by the partial region feature amount PRC associated with each of the plurality of subject partial regions SR. May be determined.
- the frame number PTCi may be specified.
- the image contact determination condition data may include an image contact determination condition indicating the relationship of the frame number PTCi.
- the image contact determination condition data may include PTC0 ⁇ PTC3, PTC0 ⁇ PTC11, PTC0 ⁇ PTC15, and the like as part of the image contact determination condition. Then, the contact determination unit 42 may determine that the object has touched the subject when all the conditions including these conditions are satisfied.
- the period, the start period, and the end period may be the same as the image contact determination period and the audio contact determination period.
- the subject partial region SR does not have to be a single region obtained by dividing the subject region R.
- the subject partial areas SR may overlap each other.
- the information processing device 12 may be a portable game device including a camera and a microphone, for example. Further, the information processing apparatus 12 may be a personal computer, a tablet terminal, a smartphone, or the like. Moreover, the division of roles of the information processing device 12, the imaging device 14, the sound collection device 16, and the display device 18 is not limited to the above. Further, the information processing apparatus 12 may be composed of a plurality of cases.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Studio Devices (AREA)
- User Interface Of Digital Computer (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (9)
- 被写体の像が写る被写体領域が含まれる、それぞれ異なるタイミングに撮像された複数のフレーム画像を取得するフレーム画像取得部と、
前記各フレーム画像について、それぞれ前記被写体領域の一部である、当該被写体領域内における位置が互いに異なる複数の被写体部分領域を特定する被写体部分領域特定部と、
前記各フレーム画像内の互いに対応付けられる前記被写体部分領域それぞれを占める画像の画像特徴量に基づいて、当該被写体部分領域を占める画像の画像特徴量の変動を示す部分領域特徴量を特定する部分領域特徴量特定部と、
複数の前記被写体部分領域のそれぞれに対応付けられる前記部分領域特徴量の関係に基づいて、前記被写体に対する物体の接触の有無を判定する接触判定部と、
を含むことを特徴とする情報処理装置。 - 前記接触判定部は、前記被写体部分領域に関連付けられる、複数の前記被写体部分領域のそれぞれに対応付けられる前記部分領域特徴量の関係に基づいて、当該被写体部分領域を占める画像に像が写る前記被写体の一部に対する物体の接触の有無を判定する、
ことを特徴とする請求項1に記載の情報処理装置。 - 前記接触判定部は、複数の前記被写体部分領域のそれぞれに対応付けられる前記部分領域特徴量の関係に基づいて、当該複数の前記被写体部分領域とは異なる前記被写体部分領域を占める画像に像が写る前記被写体の一部に対する物体の接触の有無を判定する、
ことを特徴とする請求項2に記載の情報処理装置。 - 前記接触判定部は、複数の前記被写体部分領域のそれぞれに対応付けられる前記部分領域特徴量が示す画像特徴量の変動の大きさの大小関係に基づいて、前記被写体に対する物体の接触の有無を判定する、
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情報処理装置。 - 前記接触判定部は、複数の前記被写体部分領域のそれぞれに対応付けられる前記部分領域特徴量が示す画像特徴量の変化についての時間的な前後関係に基づいて、前記被写体に対する物体の接触の有無を判定する、
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情報処理装置。 - 音声データを取得する音声データ取得部、をさらに含み、
前記接触判定部は、前記部分領域特徴量の関係と取得される前記音声データとに基づいて、前記被写体に対する物体の接触の有無を判定する、
ことを特徴とする請求項1から5のいずれか一項に記載の情報処理装置。 - 被写体の像が写る被写体領域が含まれる、それぞれ異なるタイミングに撮像された複数のフレーム画像を取得するステップと、
前記各フレーム画像について、それぞれ前記被写体領域の一部である、当該被写体領域内における位置が互いに異なる複数の被写体部分領域を特定するステップと、
前記各フレーム画像内の互いに対応付けられる前記被写体部分領域それぞれを占める画像の画像特徴量に基づいて、当該被写体部分領域を占める画像の画像特徴量の変動を示す部分領域特徴量を特定するステップと、
複数の前記被写体部分領域のそれぞれに対応付けられる前記部分領域特徴量の関係に基づいて、前記被写体に対する物体の接触の有無を判定するステップと、
ことを特徴とする情報処理方法。 - 被写体の像が写る被写体領域が含まれる、それぞれ異なるタイミングに撮像された複数のフレーム画像を取得する手順、
前記各フレーム画像について、それぞれ前記被写体領域の一部である、当該被写体領域内における位置が互いに異なる複数の被写体部分領域を特定する手順、
前記各フレーム画像内の互いに対応付けられる前記被写体部分領域それぞれを占める画像の画像特徴量に基づいて、当該被写体部分領域を占める画像の画像特徴量の変動を示す部分領域特徴量を特定する手順、
複数の前記被写体部分領域のそれぞれに対応付けられる前記部分領域特徴量の関係に基づいて、前記被写体に対する物体の接触の有無を判定する手順、
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。 - 被写体の像が写る被写体領域が含まれる、それぞれ異なるタイミングに撮像された複数のフレーム画像を取得する手順、
前記各フレーム画像について、それぞれ前記被写体領域の一部である、当該被写体領域内における位置が互いに異なる複数の被写体部分領域を特定する手順、
前記各フレーム画像内の互いに対応付けられる前記被写体部分領域それぞれを占める画像の画像特徴量に基づいて、当該被写体部分領域を占める画像の画像特徴量の変動を示す部分領域特徴量を特定する手順、
複数の前記被写体部分領域のそれぞれに対応付けられる前記部分領域特徴量の関係に基づいて、前記被写体に対する物体の接触の有無を判定する手順、
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を記憶したコンピュータ読み取り可能な情報記憶媒体。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015539419A JP6132925B2 (ja) | 2013-09-30 | 2014-09-29 | 情報処理装置、情報処理方法、プログラム及び情報記憶媒体 |
US15/022,342 US9996740B2 (en) | 2013-09-30 | 2014-09-29 | Information processing device, information processing method, program, and information storage medium |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2013-205042 | 2013-09-30 | ||
JP2013205042 | 2013-09-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015046500A1 true WO2015046500A1 (ja) | 2015-04-02 |
Family
ID=52743623
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/075852 WO2015046500A1 (ja) | 2013-09-30 | 2014-09-29 | 情報処理装置、情報処理方法、プログラム及び情報記憶媒体 |
Country Status (3)
Country | Link |
---|---|
US (1) | US9996740B2 (ja) |
JP (1) | JP6132925B2 (ja) |
WO (1) | WO2015046500A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160328873A1 (en) * | 2013-04-24 | 2016-11-10 | Morpho, Inc. | Image compositing device and image compositing method |
CN106454071A (zh) * | 2016-09-09 | 2017-02-22 | 捷开通讯(深圳)有限公司 | 终端及其基于手势进行自动拍摄的方法 |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018109924A (ja) * | 2017-01-06 | 2018-07-12 | ソニー株式会社 | 情報処理装置、情報処理方法、及びプログラム |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000172163A (ja) * | 1998-09-28 | 2000-06-23 | Matsushita Electric Ind Co Ltd | 手動作分節方法および装置 |
JP2005202653A (ja) * | 2004-01-15 | 2005-07-28 | Canon Inc | 動作認識装置及び方法、動物体認識装置及び方法、機器制御装置及び方法、並びにプログラム |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0991011B1 (en) | 1998-09-28 | 2007-07-25 | Matsushita Electric Industrial Co., Ltd. | Method and device for segmenting hand gestures |
JP6084982B2 (ja) * | 2012-09-19 | 2017-02-22 | 富士フイルム株式会社 | 撮像装置 |
-
2014
- 2014-09-29 JP JP2015539419A patent/JP6132925B2/ja active Active
- 2014-09-29 US US15/022,342 patent/US9996740B2/en active Active
- 2014-09-29 WO PCT/JP2014/075852 patent/WO2015046500A1/ja active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000172163A (ja) * | 1998-09-28 | 2000-06-23 | Matsushita Electric Ind Co Ltd | 手動作分節方法および装置 |
JP2005202653A (ja) * | 2004-01-15 | 2005-07-28 | Canon Inc | 動作認識装置及び方法、動物体認識装置及び方法、機器制御装置及び方法、並びにプログラム |
Non-Patent Citations (1)
Title |
---|
AKIRA SAITO: "Tanpatsuon o Riyo shita Hand Gesture Interaction", IPSJ SIG NOTES 2012 (HEISEI 24) NENDO 6, 15 April 2013 (2013-04-15) * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160328873A1 (en) * | 2013-04-24 | 2016-11-10 | Morpho, Inc. | Image compositing device and image compositing method |
US9959649B2 (en) * | 2013-04-24 | 2018-05-01 | Morpho, Inc. | Image compositing device and image compositing method |
CN106454071A (zh) * | 2016-09-09 | 2017-02-22 | 捷开通讯(深圳)有限公司 | 终端及其基于手势进行自动拍摄的方法 |
Also Published As
Publication number | Publication date |
---|---|
US20160300104A1 (en) | 2016-10-13 |
US9996740B2 (en) | 2018-06-12 |
JPWO2015046500A1 (ja) | 2017-03-09 |
JP6132925B2 (ja) | 2017-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102469722B1 (ko) | 디스플레이 장치 및 그 제어 방법 | |
JP6042434B2 (ja) | 立体画像ペアを獲得するためのシステムおよび方法 | |
WO2017032086A1 (zh) | 一种拍照控制方法及终端 | |
JP5619775B2 (ja) | マルチメディアの表示から情報を制御及び要求する方法 | |
KR101929077B1 (ko) | 이미지 식별 방법 및 이미지 식별 장치 | |
GB2500416A (en) | Repositioning a virtual object by gesture in an augmented reality environment | |
JP2013250882A5 (ja) | ||
CN101931753A (zh) | 目标跟踪和图像跟踪设备、操作控制方法及数字摄像机 | |
JP5769277B2 (ja) | 入力装置、入力方法及びプログラム | |
CN104469119A (zh) | 一种信息处理方法及电子设备 | |
US10291843B2 (en) | Information processing apparatus having camera function and producing guide display to capture character recognizable image, control method thereof, and storage medium | |
WO2014054249A1 (en) | Information processing apparatus, information processing method, and program | |
KR101821692B1 (ko) | 이미지 수집 방법 및 장치 | |
JP6132925B2 (ja) | 情報処理装置、情報処理方法、プログラム及び情報記憶媒体 | |
CN110297545B (zh) | 手势控制方法、手势控制装置和系统、以及存储介质 | |
JP2008287691A5 (ja) | ||
KR20150085289A (ko) | 촬영 조건을 설정하는 방법 및 이를 수행하는 전자 장치 | |
WO2015131590A1 (zh) | 一种控制黑屏手势处理的方法及终端 | |
JP6170241B2 (ja) | 文字特定装置、および制御プログラム | |
CN107003730B (zh) | 一种电子设备、拍照方法及拍照装置 | |
JP7117872B2 (ja) | 画像処理装置、撮像装置、画像処理方法、及びプログラム | |
CN111986229A (zh) | 视频目标检测方法、装置及计算机系统 | |
WO2018054097A1 (zh) | 一种自拍校准视线的方法、装置及终端 | |
US10880457B2 (en) | Image processing apparatus, image capturing apparatus, image processing method, and storage medium | |
CN104427244B (zh) | 摄像设备和摄像方法 |
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: 14847336 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015539419 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15022342 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: 14847336 Country of ref document: EP Kind code of ref document: A1 |