WO2011067906A1 - 認識用撮像装置及びその制御方法 - Google Patents
認識用撮像装置及びその制御方法 Download PDFInfo
- Publication number
- WO2011067906A1 WO2011067906A1 PCT/JP2010/006900 JP2010006900W WO2011067906A1 WO 2011067906 A1 WO2011067906 A1 WO 2011067906A1 JP 2010006900 W JP2010006900 W JP 2010006900W WO 2011067906 A1 WO2011067906 A1 WO 2011067906A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- area
- recognition
- unit
- face
- threshold
- Prior art date
Links
- 238000003384 imaging method Methods 0.000 title claims abstract description 185
- 238000000034 method Methods 0.000 title claims description 98
- 238000004364 calculation method Methods 0.000 claims abstract description 45
- 239000004065 semiconductor Substances 0.000 claims description 4
- 230000008569 process Effects 0.000 description 62
- 230000008859 change Effects 0.000 description 27
- 238000012545 processing Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 13
- 230000007423 decrease Effects 0.000 description 11
- 238000012937 correction Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 238000005286 illumination Methods 0.000 description 5
- 230000002411 adverse Effects 0.000 description 4
- 230000003247 decreasing effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 230000001815 facial effect Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 208000029152 Small face Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B7/00—Control of exposure by setting shutters, diaphragms or filters, separately or conjointly
- G03B7/08—Control effected solely on the basis of the response, to the intensity of the light received by the camera, of a built-in light-sensitive device
- G03B7/091—Digital circuits
- G03B7/093—Digital circuits for control of exposure time
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03B—APPARATUS OR ARRANGEMENTS FOR TAKING PHOTOGRAPHS OR FOR PROJECTING OR VIEWING THEM; APPARATUS OR ARRANGEMENTS EMPLOYING ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ACCESSORIES THEREFOR
- G03B15/00—Special procedures for taking photographs; Apparatus therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- 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
-
- 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
-
- 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
- H04N23/67—Focus control based on electronic image sensor signals
- H04N23/675—Focus control based on electronic image sensor signals comprising setting of focusing regions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/73—Circuitry for compensating brightness variation in the scene by influencing the exposure time
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/75—Circuitry for compensating brightness variation in the scene by influencing optical camera components
Definitions
- the present invention relates to an imaging device for recognition that recognizes an object in an image and a control method thereof.
- Patent Document 1 introduces a technique for performing camera focus adjustment, exposure adjustment, illumination adjustment, zoom adjustment, and the like using the result of determining the quality of captured image data.
- camera adjustment parameters are controlled based on a face recognition result.
- the aperture of the camera is controlled by the position, size, and orientation of the face. Specifically, this technique opens the throttle opening when the face is large, and vice versa.
- the illumination adjustment cannot always be operated as in Patent Document 1. For example, it is not possible to adjust the lighting in a place where flash is prohibited. There is also a problem that power consumption increases when the illumination adjustment is activated.
- the aperture opening is reduced for a small face, so that there is a problem that the amount of light hitting the face is insufficient and the recognition accuracy is lowered.
- an object of the present invention is to provide a recognition imaging apparatus capable of stably performing continuous recognition over time and a control method thereof.
- an imaging apparatus for recognition includes: an imaging unit that sequentially generates a plurality of images by imaging a target; and each of the plurality of images.
- An object recognition unit that recognizes an object region that is an area in which an object is imaged and a tracking unit that tracks the object region between the plurality of images.
- An area calculation unit for calculating an area of the object region; and, when the area is less than a first threshold value, an exposure time in the imaging unit is set to a first exposure time, and when the area is equal to or greater than the first threshold value,
- An exposure controller configured to set an exposure time to a second exposure time longer than the first exposure time.
- the imaging apparatus for recognition extends the exposure time when the area of the object region is sufficiently large.
- region can be increased.
- the exposure time is lengthened, blurring tends to occur in the object region.
- the area of the object area is sufficiently large, the resolution necessary for the object recognition process and the object tracking process can be ensured even if blurring increases, so that the object recognition process and the object tracking process are provided. There are few adverse effects.
- the S / N ratio of the object region increases as the incident light amount increases, the accuracy of the object recognition process and the object tracking process increases.
- the imaging apparatus for recognition can increase the incident light amount when the area of the object region is sufficiently large, so that the target object can be obtained even when the incident light amount is reduced over time. It is possible to easily secure the amount of incident light necessary for the recognition process.
- the recognition imaging apparatus shortens the exposure time when the area of the object region is small. As a result, blurring in the object region is reduced, so that the accuracy of the object recognition process and the object tracking process is improved.
- the recognition imaging apparatus does not have to perform illumination adjustment such as a flash, so that the amount of incident light can be increased and power consumption can be reduced even in places where flash is prohibited.
- the imaging device for recognition can stably perform continuous recognition in time.
- the recognition imaging apparatus further includes a movement speed calculation unit that calculates a movement speed of the object region, and the exposure control unit further includes the exposure time when the movement speed is less than a second threshold. May be set to a third exposure time, and when the moving speed is equal to or greater than the second threshold, the exposure time may be set to a fourth exposure time shorter than the third exposure time.
- the recognition imaging apparatus shortens the exposure time when the moving speed of the object region is high. As a result, blurring is less likely to occur in the object area, so that the resolution of the object area is increased. Therefore, the accuracy of the object recognition process and the object tracking process is improved.
- the recognition imaging apparatus increases the exposure time when the moving speed of the object region is slow.
- region can be increased.
- the resolution necessary for the object recognition process can be ensured even if the exposure time is lengthened, so that there is little adverse effect on the object recognition process and the object tracking process.
- the accuracy of the object recognition process and the object tracking process can be improved by increasing the incident light amount.
- the recognition imaging apparatus further includes an incident light amount calculation unit that calculates an incident light amount in the object area, and the exposure control unit is proportional to the area and is proportional to the incident light amount.
- the exposure time in the imaging unit is set to the fifth exposure time, and when the recognition incident light amount is less than the third threshold, the exposure time is longer than the fifth exposure time.
- the sixth exposure time may be set.
- the imaging device for recognition extends the exposure time when the amount of incoming light for recognition is small. Thereby, the incident light quantity of a target object area
- the recognition imaging apparatus shortens the exposure time when the amount of incident light for recognition is sufficiently large. As a result, blurring in the object region is reduced, so that the accuracy of the object recognition process and the object tracking process is improved.
- the exposure control unit sets the exposure time to the first exposure time when the recognition resolution that is proportional to the area and inversely proportional to the amount of blur in the object region is less than a fourth threshold; If the recognition resolution is equal to or greater than the fourth threshold, the exposure time may be set to the second exposure time.
- the recognition imaging apparatus can control the exposure time more accurately by using the recognition resolution in consideration of the blur amount.
- the recognition imaging apparatus includes an imaging unit that sequentially generates a plurality of images by imaging a target object, and the target object is captured in each of the plurality of images.
- a recognition imaging apparatus having a target recognition unit that recognizes a target region that is a target region and a tracking unit that tracks the target region between the plurality of images, wherein the area of the target region is If the area is less than the first threshold and the area is less than the first threshold, the in-focus position of the imaging device for recognition is set to the first position, and if the area is greater than or equal to the first threshold, the in-focus position is And an in-focus position control unit that sets the second position farther from the object than the first position.
- the recognition imaging apparatus can recognize an object that can be recognized by setting the in-focus position far from the object recognition distance when the area of the object region is sufficiently large.
- the depth of field can be expanded. In this way, when the area of the object area is sufficiently large, it is easy to ensure the resolution required for the object recognition process even if the object moves suddenly by widening the depth of field. it can.
- the recognition imaging apparatus sets the in-focus position close to the object recognition distance when the resolution of the object region is insufficient. Accordingly, the recognition imaging device according to one embodiment of the present invention can increase the resolution of the object region.
- the recognition imaging apparatus can perform continuous recognition in a stable manner by changing the focus position in accordance with the area of the object region.
- the in-focus position control unit sets the in-focus position to the first position when a recognition resolution that is proportional to the area and inversely proportional to the amount of blur in the object region is less than a second threshold. If the recognition resolution is greater than or equal to the second threshold, the in-focus position may be set to the second position.
- the imaging apparatus for recognition can control the in-focus position with higher accuracy by using the resolution for recognition in consideration of the amount of blur.
- the recognition imaging apparatus includes an imaging unit that sequentially generates a plurality of images by imaging a target object, and the target object is captured in each of the plurality of images.
- a recognition imaging apparatus comprising: a target recognition unit that recognizes a target region that is a region that is a target; and a tracking unit that tracks and calculates the target region between the plurality of images, the area of the target region
- An aperture calculation unit that calculates the aperture value when the area is less than the first threshold value, and the aperture value is set to the first aperture value, and when the area is greater than or equal to the first threshold value, the aperture value is greater than the first aperture value. You may provide the aperture control part which sets to a big 2nd aperture value.
- the imaging device for recognition increases the aperture value when the area of the object region is sufficiently large.
- the area of the object region is sufficiently large, noise in each pixel is averaged, so that the influence of noise is reduced. Therefore, since the signal amount of each pixel in the object area is relatively large, the amount of light required for recognition can be secured even if the aperture value is increased.
- the recognition imaging apparatus can widen the recognition range while securing the light amount necessary for recognition. In addition, by increasing the depth of field, it is possible to easily ensure the resolution necessary for the object recognition process even when the object moves suddenly.
- the recognition imaging apparatus reduces the aperture value when the area of the object region is small.
- the imaging device for recognition according to an embodiment of the present invention can secure the light amount necessary for recognition by reducing the aperture value.
- the recognition imaging device does not need to perform illumination adjustment such as a flash, so that it is possible to secure a light amount even in a place where flash is prohibited and reduce power consumption.
- the recognition imaging apparatus further includes an incident light amount calculation unit that calculates an incident light amount in the object region, and the aperture controller further determines an aperture value when the incident light amount is less than a second threshold.
- the aperture value may be set to a third aperture value, and the aperture value may be set to a fourth aperture value that is greater than the third aperture value when the incident light amount is greater than or equal to the second threshold value.
- the imaging device for recognition increases the aperture value when the amount of incident light is sufficiently large.
- the signal amount of each pixel in the object area increases, so that the amount of light required for recognition can be secured even if the aperture value is increased.
- the recognition imaging apparatus can widen the recognition range while securing the light amount necessary for recognition. Further, when the amount of incident light is sufficiently large, the resolution required for the object recognition process can be easily ensured even if the object moves suddenly by widening the depth of field.
- the recognition imaging apparatus can secure the light amount required for recognition by reducing the aperture value when the incident light amount is small.
- the aperture control unit sets the aperture value to the first aperture value when the recognition incident light amount that is proportional to the area and proportional to the incident light amount is less than a third threshold value.
- the aperture value may be set to the second aperture value.
- the imaging device for recognition can control the aperture value with higher accuracy by using the incident light amount for recognition in consideration of the area.
- the present invention can be realized not only as such a recognition imaging apparatus, but also as a recognition imaging apparatus control method using a characteristic means included in the recognition imaging apparatus as a step, or such a characteristic. It can also be realized as a program that causes a computer to execute typical steps. Needless to say, such a program can be distributed via a non-transitory computer-readable recording medium such as a CD-ROM and a transmission medium such as the Internet.
- the present invention can be realized as a semiconductor integrated circuit (LSI) that realizes part or all of the functions of such a recognition imaging apparatus, or can be realized as a camera including such a recognition imaging apparatus.
- LSI semiconductor integrated circuit
- FIG. 1 is a block diagram of a recognition imaging apparatus according to Embodiment 1 of the present invention.
- FIG. 2 is a detailed block diagram of the recognition imaging apparatus according to Embodiment 1 of the present invention.
- FIG. 3 is a flowchart of face tracking processing according to Embodiment 1 of the present invention.
- FIG. 4 is a flowchart of a shutter speed control process corresponding to the area of the face area by the recognition imaging apparatus according to Embodiment 1 of the present invention.
- FIG. 5 is a flowchart of the shutter speed control process corresponding to the moving speed of the face area by the recognition imaging apparatus according to Embodiment 1 of the present invention.
- FIG. 1 is a block diagram of a recognition imaging apparatus according to Embodiment 1 of the present invention.
- FIG. 2 is a detailed block diagram of the recognition imaging apparatus according to Embodiment 1 of the present invention.
- FIG. 3 is a flowchart of face tracking processing according to Embodiment 1 of the present invention.
- FIG. 6 is a flowchart of the shutter speed control process according to the amount of incident light in the face area by the recognition imaging apparatus according to Embodiment 1 of the present invention.
- FIG. 7 is a flowchart of a shutter speed control process corresponding to the area of the face region and the amount of incident light by the recognition imaging apparatus according to Embodiment 1 of the present invention.
- FIG. 8 is a block diagram of a recognition imaging apparatus according to Embodiment 2 of the present invention.
- FIG. 9 is a detailed block diagram of a recognition imaging apparatus according to Embodiment 2 of the present invention.
- FIG. 10 is a flowchart of focus position control processing by the recognition imaging apparatus according to Embodiment 2 of the present invention.
- FIG. 11 is a diagram showing the relationship between the hyperfocal distance and the depth of field according to Embodiment 2 of the present invention.
- FIG. 12 is a block diagram of a recognition imaging apparatus according to Embodiment 3 of the present invention.
- FIG. 13 is a detailed block diagram of a recognition imaging apparatus according to Embodiment 3 of the present invention.
- FIG. 14 is a flowchart of aperture value control processing according to the area of the face region by the recognition imaging apparatus according to Embodiment 3 of the present invention.
- FIG. 15 is a flowchart of the aperture value control process according to the amount of incident light in the face area by the recognition imaging apparatus according to Embodiment 3 of the present invention.
- the imaging device for recognition according to Embodiment 1 of the present invention changes the shutter speed according to the area of the face region, the moving speed, and the incident light amount. Specifically, the recognition imaging apparatus according to Embodiment 1 of the present invention slows the shutter speed when the area of the face region is large.
- Embodiment 1 of the present invention can stably perform face recognition.
- Embodiment 1 of the present invention will be described with reference to the drawings.
- FIG. 1 is a block diagram of a recognition imaging apparatus 100 according to Embodiment 1 of the present invention.
- the recognition imaging apparatus 100 shown in FIG. 1 is, for example, a digital still camera, a digital video camera, a network camera, or a security camera.
- the recognition imaging apparatus 100 includes an imaging unit 101, an exposure control unit 102, a face recognition unit 105, a face tracking unit 106, and an area calculation unit 109.
- the imaging unit 101 receives a subject image from the imaging optical system and generates an electrical signal. In other words, the imaging unit 101 sequentially generates a plurality of images by imaging the target object.
- the face recognition unit 105 corresponds to the object recognition unit of the present invention.
- the face recognition unit 105 recognizes, for each of a plurality of images generated by the imaging unit 101, a target object region that is a region in which the target object is captured.
- the face tracking unit 106 corresponds to the tracking unit of the present invention.
- the face tracking unit 106 tracks a target area between a plurality of images generated by the imaging unit 101.
- the area calculation unit 109 calculates the area of the object region.
- the exposure control unit 102 sets the exposure time in the imaging unit 101 to the first exposure time, and when the area of the object region is equal to or larger than the area threshold, The exposure time in the imaging unit 101 is set to a second exposure time that is longer than the first exposure time.
- FIG. 2 is a block diagram showing a detailed configuration of the recognition imaging apparatus 100. As shown in FIG. 2, the recognition imaging apparatus 100 further includes a face recognition result storage unit 107, a moving speed calculation unit 108, and an incident light amount calculation unit 110.
- the imaging unit 101 includes a lens 112, a lens driving device 113 that changes the in-focus position of the lens 112, a diaphragm device 114 that adjusts the amount of light that passes through the lens 112, and a shutter device that adjusts the exposure time of the imaging element 116.
- an image sensor 116 that converts an image formed by the lens 112 into an electric signal
- an AD converter 117 that converts an electric signal (analog signal) generated by the image sensor 116 into a digital signal.
- the recognition imaging apparatus 100 performs signal processing such as gain correction, gamma correction, color conversion, and enlargement / reduction on the digital signal generated by the AD converter 117, thereby the face recognition unit 105 described later.
- An input image 120 to be used is created for each frame.
- the exposure control unit 102 controls the shutter speed in the shutter device 115 of the imaging unit 101.
- the shutter speed is decreased, the exposure time during which light strikes the image sensor 116 becomes longer.
- many electric signals of the subject can be obtained, so that the amount of incident light of the input image increases.
- the shutter speed is increased, the exposure time during which the image sensor 116 is exposed to light is shortened. Thereby, since the electrical signal of the subject is reduced, the incident light amount of the input image is reduced.
- the face recognition unit 105 recognizes a face area on the input image 120 using the input image 120 generated by the imaging unit 101.
- the face recognition unit 105 stores the generated face recognition result 121 in the face recognition result storage unit 107 for each frame.
- a recognition target a face area of an unspecified person or a face area of a specific person is assumed.
- the recognition of the face area of an unspecified person recognizes an image area including general facial features.
- a detailed recognition algorithm is realized by using the AdaBoost algorithm disclosed in Patent Document 3 and the like, and configuring a discriminator that detects a dedicated face orientation for each face orientation.
- the method for recognizing the face area of an unspecified person is not limited to this algorithm.
- the recognition of the face area of the specific person is performed by determining the consistency between the detailed face feature information in the face area of the unspecified person and the face feature information 123 of the specific person registered in the face recognition result storage unit 107. Identify individuals with
- recognition is performed on a recognition image obtained by resizing the input image 120 to a certain size.
- a face is recognized using a recognition image obtained by reducing an input image.
- eye recognition is performed on a recognized face area of an unspecified person and the face area of the specified person is recognized using a recognition image resized so that the distance between both eyes becomes a predetermined value. Is going.
- the recognition of the face area of a specific person uses more detailed feature information than the recognition of the face area of an unspecified person, so a higher resolution is required than the recognition of the face area of an unspecified person.
- the face tracking unit 106 tracks a face between successive input images 120 (frames) based on the past face recognition result 121 held by the face recognition result storage unit 107.
- the face recognition result 121 used for face tracking is the center coordinates of the face area on the input image 120.
- the face once recognized is recognized in the vicinity of the position recognized in the previous frame in the next frame.
- the face tracking unit 106 implements the face tracking process using the continuity of the recognition positions.
- FIG. 3 is a flowchart of face tracking processing by the face tracking unit 106.
- the face tracking unit 106 determines whether or not there is a face area to which a label is attached one frame before in the vicinity of the center coordinates of the face area recognized in the current frame ( S101).
- the face tracking unit 106 has been assigned to the face area one frame before the face area recognized in the current frame.
- the same label as the label is assigned (S102).
- the face tracking unit 106 recognizes a unique label different from the face recognized so far in the current frame. (S103).
- the face tracking unit 106 selects a face label for controlling the camera adjustment parameters. As a selection method, if a specific person registered in the face recognition unit 105 is recognized, a label of the face is selected. In addition, the face to be controlled may be selected according to the size and position of the recognized face as disclosed in Patent Document 2 and the like. In addition, the face tracking unit 106 stores the generated face tracking result 122 in the face recognition result storage unit 107 for each frame.
- the face recognition result storage unit 107 holds the face recognition result 121 generated by the face recognition unit 105 and the face tracking result 122 generated by the face tracking unit 106 for each frame.
- the face recognition result 121 includes the coordinates of the face area on the input image, the number of vertical and horizontal pixels of the face area, the recognition status of the registered specific person, and the like.
- the face tracking result 122 includes a label for distinguishing a face area, a label for a camera control target, and the like.
- the face recognition result storage unit 107 holds face feature information 123 that is detailed information of the face of the specific person used in the recognition of the specific person by the face recognition unit 105.
- the recognition imaging apparatus 100 always refers to the latest history by deleting from the oldest data when the memory capacity reaches the limit as a result of data being stored in the face recognition result storage unit 107 for each frame. can do.
- the moving speed calculation unit 108 uses the face recognition result 121 and the face tracking result 122 held in the face recognition result storage unit 107 to calculate the moving speed of the face of the label to be controlled by the camera. Specifically, the moving speed calculation unit 108 calculates the number of moving pixels from the center coordinate of the face area of the previous frame to the center coordinate of the face area of the current frame in the face having the same label in the current frame and the previous frame. calculate. Then, the moving speed calculation unit 108 calculates the moving speed in the plane direction based on the calculated number of moving pixels.
- the moving speed calculation unit 108 calculates, for a face having the same label in the current frame and the previous frame, the number of vertical and horizontal pixels in the face area of the previous frame and the vertical and horizontal number of pixels in the face area of the current frame. Calculate the difference. Then, the moving speed calculation unit 108 calculates the moving speed in the depth direction based on the calculated difference.
- the method for obtaining the moving speed is not limited to these methods.
- the area calculation unit 109 obtains the area of the face area in the face of the label to be controlled by the camera based on the face recognition result 121 and the face tracking result 122 held in the face recognition result storage unit 107.
- the resolution of the face of the image for recognition hereinafter, the resolution for recognition
- the recognition resolution is the density of pixels in an image, and the larger the value, the clearer the facial features.
- the resolution for recognition is a value that is proportional to the area (number of pixels) of the face region and inversely proportional to the amount of blur (or amount of blur) in the face region.
- an AF evaluation value (a value corresponding to the contrast amount) of the recognition image area
- the recognition resolution may be a value obtained by normalizing the AF evaluation value of the face area on the input image 120 by the area of the recognition image.
- the method of obtaining the area in the face region is not limited to this method.
- the incident light amount calculation unit 110 calculates the incident light amount in the face area of the camera control target label based on the face recognition result 121 and the face tracking result 122 held in the face recognition result storage unit 107. Specifically, the incident light amount calculation unit 110 calculates the average value of the luminance values of a plurality of pixels included in the face area of the recognition image or the average of the luminance values of a plurality of pixels included in the face area on the input image 120. A value is calculated, and an incident light amount is calculated using the calculated average value. Further, when luminance correction such as gain or gamma correction is applied to the input image 120, the incident light amount calculation unit 110 performs reverse correction of those corrections on the input image 120, and the image after the reverse correction is performed. Is used to calculate the incident light amount. However, the method of obtaining the incident light amount in the face area is not limited to this method.
- the exposure control unit 102 determines the shutter speed using the area of the face area, the moving speed, and the incident light amount calculated by the moving speed calculating unit 108, the area calculating unit 109, and the incident light amount calculating unit 110.
- the exposure control unit 102 calculates the shutter speed using information generated by the moving speed calculation unit 108, the area calculation unit 109, and the incident light amount calculation unit 110 will be described. Further, as a precondition, the face to be processed is a face to be controlled by the camera whose face is tracked (the face history is one frame before).
- FIG. 4 is a flowchart of a shutter speed control process based on the area of the face area.
- a series of processing shown in each of FIGS. 4 to 7 is performed for each frame.
- the series of processes shown in each of FIGS. 4 to 7 may be performed for each of a plurality of predetermined frames.
- the area calculation unit 109 calculates the area of the face area to be processed.
- the area is the AF evaluation value in the recognition image (S201).
- the exposure control unit 102 determines whether or not the area of the face region has reached the area threshold (area sufficient for recognition) (S202).
- the area threshold varies depending on the recognition method. For example, the area threshold value for the face recognition of a specific person is higher than the area threshold value for the face recognition of an unspecified person.
- the exposure control unit 102 sets the shutter speed of the imaging unit 101 to a shutter speed slower than the current shutter speed (S203). In other words, the exposure control unit 102 sets the exposure time of the imaging unit 101 to an exposure time longer than the current exposure time.
- the exposure control unit 102 calculates the upper limit value of the shutter speed at which the recognition resolution does not fall below the resolution threshold, based on the relationship between the current face area area and the current shutter speed. Then, the exposure control unit 102 sets the shutter speed to a value equal to or less than the calculated upper limit value.
- the exposure control unit 102 lengthens the exposure time of the imaging unit 101. Thereby, the amount of incident light in the face area can be increased.
- the exposure time is lengthened, blurring tends to occur in the face area.
- the area of the face area is sufficiently large, the resolution necessary for the face recognition process can be ensured even if the blurring increases, so that there is little adverse effect on the face recognition process and the face tracking process.
- the S / N ratio of the face area increases as the incident light amount increases, the accuracy of the face recognition process and the face tracking process increases.
- the exposure control unit 102 sets the shutter speed of the imaging unit 101 to a shutter speed faster than the current shutter speed (S204). In other words, the exposure control unit 102 sets the exposure time of the imaging unit 101 to an exposure time longer than the current exposure time.
- the exposure control unit 102 shortens the exposure time of the imaging unit 101. As a result, blurring in the face area is reduced, and the accuracy of the face recognition process and the face tracking process is improved.
- the exposure control unit 102 may increase or decrease the shutter speed by a predetermined fixed value, or change the amount of change in the shutter speed according to the area of the face area. May be. For example, in step S203, the exposure control unit 102 may set a slower shutter speed as the face area is larger. Similarly, in step S204, the exposure control unit 102 may set a faster shutter speed as the face area is smaller.
- the exposure control unit 102 may set a shutter speed that is faster than at least the shutter speed set in step S203 in step S204. In other words, the exposure control unit 102 may set the exposure time of the imaging unit 101 to an exposure time longer than the exposure time set in step S203 in step S204.
- the exposure control unit 102 slows the shutter speed when the area of the face region is equal to or larger than the first area threshold, and reduces the shutter speed when the area of the face region is smaller than the second area threshold smaller than the first area threshold. It is not necessary to change the shutter speed when the face area is between the first area threshold and the second area threshold. Further, the exposure control unit 102 may change the amount of change in the shutter speed according to the size of the area of the face region and the plurality of area threshold values.
- FIG. 5 is a flowchart of a shutter speed control process based on the moving speed of the face area.
- similar processing may be denoted by the same reference numeral, and description thereof may be omitted.
- the moving speed calculation unit 108 calculates the moving speed in the plane direction of the face to be processed (S211).
- the exposure control unit 102 determines whether or not the moving speed of the face area is equal to or higher than the speed threshold (S212).
- the exposure control unit 102 sets the shutter speed of the imaging unit 101 to a shutter speed slower than the current shutter speed (S203).
- the resolution necessary for the face recognition process can be ensured even if the exposure time is lengthened, so that the adverse effect on the face recognition process and the face tracking process is small.
- the accuracy of face recognition processing and face tracking processing can be improved by increasing the amount of incident light.
- the exposure control unit 102 sets the shutter speed of the imaging unit 101 to a shutter speed faster than the current shutter speed (S204).
- the exposure control unit 102 shortens the exposure time of the imaging unit 101.
- the shutter speed By increasing the shutter speed, blurring hardly occurs in the face area, so the resolution of the face area increases. Thereby, the precision of face recognition processing and face tracking processing is improved.
- the exposure control unit 102 may increase or decrease the shutter speed by a predetermined fixed value, or change the amount of change in the shutter speed according to the moving speed of the face area. May be. For example, in step S203, the exposure control unit 102 may set a slower shutter speed as the moving speed of the face area is slower. Similarly, in step S204, the exposure control unit 102 may set a faster shutter speed as the moving speed of the face area increases.
- the exposure control unit 102 may set a shutter speed that is faster than at least the shutter speed set in step S203 in step S204. In other words, the exposure control unit 102 may set the exposure time of the imaging unit 101 to an exposure time longer than the exposure time set in step S203 in step S204.
- the exposure control unit 102 increases the shutter speed when the moving speed of the face area is equal to or higher than the first speed threshold, and releases the shutter when the moving speed of the face area is lower than the second speed threshold smaller than the first speed threshold.
- the shutter speed may not be changed when the speed is decreased and the moving speed of the face area is between the first speed threshold and the second speed threshold.
- the exposure control unit 102 may change the amount of change in the shutter speed in accordance with the size of the moving speed of the face area and the plurality of speed thresholds.
- FIG. 6 is a flowchart of the shutter speed control process based on the incident light amount of the face area.
- the incident light amount calculation unit 110 calculates the incident light amount of the face area to be processed (S221).
- the incident light amount is an average value of luminance values of a plurality of pixels included in the face area of the recognition image.
- the exposure control unit 102 determines whether or not the incident light amount of the face area has reached the incident light amount threshold value (incident light amount sufficient for recognition) (S222).
- the threshold for the amount of incident light varies depending on the recognition method. For example, the incident light amount threshold value for face recognition of a specific person is higher than the incident light amount threshold value for face recognition of an unspecified person.
- the exposure control unit 102 may use the incident light amount itself calculated by the incident light amount calculation unit 110 as the incident light amount used for this determination, is proportional to the area calculated by the area calculation unit 109, and The recognition incident light quantity proportional to the incident light quantity calculated by the incident light quantity calculation unit 110 may be calculated, and the recognition incident light quantity may be compared with the incident light intensity threshold value.
- the exposure control unit 102 sets the shutter speed of the imaging unit 101 to a shutter speed slower than the current shutter speed (S203).
- the exposure control unit 102 can increase the incident light amount by delaying the exposure time of the imaging unit 101. As a result, the SN ratio of the face area is increased, and the accuracy of the face recognition process and the face tracking process is improved.
- the exposure control unit 102 sets the shutter speed of the imaging unit 101 to a shutter speed faster than the current shutter speed (S204).
- the exposure control unit 102 calculates the lower limit value of the shutter speed that does not fall below the threshold value of the incident light amount from the relationship between the incident light amount of the current face and the current shutter speed. Then, the exposure control unit 102 sets the shutter speed to a value equal to or greater than the calculated lower limit value.
- the exposure control unit 102 shortens the exposure time of the imaging unit 101. As a result, it is possible to reduce the blurring of the face area while ensuring the amount of incident light necessary for the face recognition process.
- the shutter speed can be increased so that blurring can be suppressed even when the moving speed of the object suddenly increases. It is easy to secure the necessary resolution.
- the exposure control unit 102 may increase or decrease the shutter speed by a predetermined fixed value, or change the amount of change in the shutter speed according to the amount of incident light in the face area. May be. For example, in step S203, the exposure control unit 102 may set a slower shutter speed as the amount of incident light in the face area is smaller. Similarly, in step S204, the exposure control unit 102 may set a faster shutter speed as the amount of incident light in the face area increases.
- the exposure control unit 102 may set a shutter speed that is faster than at least the shutter speed set in step S203 in step S204. In other words, the exposure control unit 102 may set the exposure time of the imaging unit 101 to an exposure time longer than the exposure time set in step S203 in step S204.
- the exposure control unit 102 increases the shutter speed when the incident light amount of the face area is equal to or greater than the first incident light intensity threshold value, and the incident light amount of the face area is less than the second incident light intensity value smaller than the first incident light intensity threshold value. In this case, the shutter speed is slowed down, and the shutter speed may not be changed when the incident light amount of the face region is between the first incident light amount threshold value and the second incident light amount threshold value. Further, the exposure control unit 102 may change the amount of change in the shutter speed according to the magnitude of the incident light amount of the face area and the plurality of incident light amount threshold values.
- the exposure control unit 102 may change the shutter speed according to at least one of the area of the face area, the moving speed, and the incident light amount.
- FIG. 7 is a flowchart of a modification of the shutter speed control process performed by the exposure control unit 102.
- the exposure control unit 102 may be set to a shutter speed slower than the current shutter speed (S203).
- the exposure control unit 102 sets the shutter speed of the imaging unit 101 to the current shutter speed.
- a shutter speed faster than the shutter speed may be set (S204).
- the exposure control unit 102 does not change the shutter speed.
- the exposure control unit 102 changes the change amount of the shutter speed according to at least one of the area of the face area, the moving speed, and the incident light amount. May be.
- a specific method for controlling the change amount may be the same as described above.
- the recognition imaging apparatus 100 increases or decreases the shutter speed in accordance with the area of the face region, the moving speed, and the incident light amount, thereby resolving the facial resolution necessary for the face recognition process. And the SN ratio can be improved. As a result, the recognition imaging apparatus 100 can stably perform continuous temporal recognition.
- the exposure control unit 102 changes the exposure time by changing the shutter speed.
- the exposure time may be changed by other methods.
- the recognition imaging apparatus according to Embodiment 2 of the present invention changes the focus position of the recognition imaging apparatus according to the area of the face region. Specifically, the recognition imaging apparatus according to Embodiment 2 of the present invention sets the in-focus position far from the face when the area of the face region is large.
- the recognition imaging apparatus can stably perform face recognition.
- FIG. 8 is a block diagram of a recognition imaging apparatus 100A according to Embodiment 2 of the present invention.
- 8A and 8B includes a focusing position control unit 103 instead of the exposure control unit 102 in contrast to the configuration of the recognition imaging device 100 according to the first embodiment.
- FIG. 9 is a block diagram showing a detailed configuration of the recognition imaging apparatus 100A.
- the focus position control unit 103 controls the focus position in the lens driving device 113 of the imaging unit 101. If the in-focus position is close to the object, the object is in focus and the resolution of the object in the input image is increased. On the other hand, if the in-focus position is far from the object, the object is not in focus, so the resolution of the object in the input image decreases.
- the focus position control unit 103 sets the focus position to the first position when the area of the face region is less than the area threshold, and sets the focus position when the area of the face region is equal to or larger than the area threshold.
- the second position is set farther from the object than the first position.
- FIG. 10 is a flowchart of the focus position control process performed by the recognition imaging apparatus 100A.
- the face to be processed is the face to be controlled by the camera.
- a series of processing shown in FIG. 10 is performed for each frame. Note that the series of processes shown in FIG. 10 may be performed for each of a plurality of predetermined frames.
- the area calculation unit 109 calculates the area of the face area to be processed (S201).
- the area is an AF evaluation value in the recognition image.
- the focus position control unit 103 determines whether the area of the face region has reached the area threshold (S202).
- the focus position control unit 103 sets the focus position so that the focus position is farther from the face position than the current focus position. Set (S303).
- the focus position control unit 103 makes the focus position closer to the face position than the current focus position.
- An in-focus position is set (S304).
- the focus position control unit 103 may set the focus position closer to the face than at least the position set in step S303 in step S304.
- the in-focus position control unit 103 separates the in-focus position from the face when the area of the face area is equal to or greater than the first area threshold, and the area of the face area is less than the second area value smaller than the first area threshold.
- the focus position may not be changed.
- the focus position control unit 103 may change the amount of change in the focus position according to the size of the area of the face region and the plurality of area threshold values.
- step S303 and step S304 will be described in detail with reference to FIG. First, a general focus position control method that does not consider the face area will be described with reference to FIG.
- the depth of field is obtained by the following (Expression 1), (Expression 2), and (Expression 3).
- DN is the front end of the depth of field
- DF is the rear end of the depth of field.
- the total depth of field is the sum of DF and DN.
- s is a focus position
- H is a hyperfocal distance (a focus position where infinity enters the back end of the depth of field)
- N is an aperture value
- c is an allowable circle of confusion. (The allowable blur diameter)
- f is the focal length of the lens.
- the diameter of the permissible circle of confusion within which the blur amount is within 1 pixel is set as c
- the depth of field when the focus position is controlled at the distance S where the face is recognized is set as W0.
- the in-focus position control unit 103 determines the depth of field W1 that can ensure the resolution with which the face can be recognized when the in-focus position is S in consideration of the area of the face region. As an example, it is assumed that the face area to be recognized is twice as long as the area necessary for recognition. In such a case, the resolution required for recognition can be satisfied even if the diameter of the permissible circle of confusion required for recognition is increased to 2c.
- the focus position control unit 103 sets the focus position at the position of the hyperfocal distance H1 as shown in FIG. Thereby, the recognizable depth of field W2 can be further increased. As described above, the focus position control unit 103 can widen the recognizable depth of field by appropriately controlling the focus position according to the area of the face region.
- the focus position control unit 103 widens the recognizable depth of field by setting the focus position far from the face recognition distance in step S303. As described above, when the area of the face region is sufficiently large, the resolution necessary for the face recognition process can be easily ensured even if the object moves suddenly by increasing the depth of field.
- the focus position control unit 103 sets the focus position near the face recognition distance in step S304. Thereby, the focus position control unit 103 can increase the resolution of the face area.
- the recognition imaging apparatus 100A according to Embodiment 2 of the present invention can stably perform continuous temporal recognition by changing the focus position according to the area of the face region.
- the recognition imaging apparatus changes the aperture value according to the area of the face region and the amount of incident light. Specifically, the recognition imaging apparatus according to Embodiment 3 of the present invention increases the aperture value when the area of the face region is large.
- the recognition imaging apparatus can stably perform face recognition.
- FIG. 12 is a block diagram of a recognition imaging apparatus 100B according to Embodiment 3 of the present invention.
- the recognition imaging apparatus 100B shown in FIG. 12 includes an aperture control unit 104 instead of the exposure control unit 102 with respect to the configuration of the recognition imaging apparatus 100 according to the first embodiment.
- FIG. 13 is a block diagram showing a detailed configuration of the recognition imaging apparatus 100B.
- the aperture control unit 104 controls the aperture value in the aperture device 114 of the imaging unit 101. If the aperture value is decreased, the amount of light passing through the lens 112 increases, so that many electrical signals of the object can be obtained. Thereby, the incident light amount of the input image increases. In addition, the depth of field is shallow (the focused area is narrow). On the other hand, when the aperture value is increased, the amount of light passing through the lens is reduced, so that the electrical signal of the subject is reduced. Thereby, the incident light amount of the input image is reduced. Also, the depth of field is deep (the in-focus area is wide).
- the aperture control unit 104 sets the aperture value to the first aperture value when the area of the face region is less than the area threshold value, and sets the aperture value to the first aperture value when the area of the face region is equal to or greater than the area threshold value.
- the second aperture value is set larger than the value.
- the aperture control unit 104 calculates the aperture value using information generated by the area calculation unit 109 and the incident light amount calculation unit 110 will be described.
- the face to be processed is the face to be controlled by the camera.
- FIG. 14 is a flowchart of aperture value control processing based on the area of the face region.
- FIGS. 14 and 15 are performed for each frame. Note that the series of processes shown in each of FIGS. 14 and 15 may be performed for a plurality of predetermined frames.
- the area calculating unit 109 calculates the area of the face area to be processed (S201).
- the area is the number of pixels in the face area in the input image.
- the aperture control unit 104 determines whether the area of the face area has reached the area threshold (S202).
- the aperture control unit 104 sets an aperture value larger than the current aperture value (S403).
- the larger the aperture value the deeper the depth of field, so that the recognition range can be expanded.
- the aperture control unit 104 can widen the recognition range while ensuring the amount of light necessary for recognition.
- the depth of field it is possible to easily ensure the resolution necessary for the face recognition process even when the object moves suddenly.
- the aperture control unit 104 increases the aperture value until it is close to the incident light intensity threshold value. That is, the aperture control unit 104 increases the aperture value as the area increases.
- the aperture control unit 104 sets an aperture value smaller than the current aperture value (S404). In addition, the aperture control unit 104 decreases the aperture value as the face area is smaller.
- the aperture control unit 104 can secure the amount of light required for recognition by reducing the aperture value.
- the aperture control unit 104 may set an aperture value smaller than at least the aperture value set in step S403 in step S404.
- the aperture control unit 104 increases the aperture value when the area of the face region is equal to or larger than the first area threshold, and sets the aperture value when the area of the face region is smaller than the second area value smaller than the first area threshold.
- the aperture value may not be changed when the area of the face region is between the first area threshold and the second area threshold.
- the aperture control unit 104 may change the amount of change in the aperture value according to the size of the area of the face region and the plurality of area threshold values.
- FIG. 15 is a flowchart of the aperture value control process based on the incident light amount of the face area.
- the incident light amount calculation unit 110 calculates the incident light amount of the face area to be processed (S221).
- the incident light amount is an average value of luminance values of a plurality of pixels included in the face area of the input image.
- the aperture controller 104 determines whether or not the incident light amount in the face area has reached the incident light amount threshold value (S222).
- the aperture control unit 104 sets an aperture value larger than the current aperture value (S403).
- the aperture control unit 104 increases the aperture value until it is close to the incident light intensity threshold value. That is, the aperture control unit 104 increases the aperture value as the incident light amount increases.
- the aperture control unit 104 can widen the recognition range while ensuring the amount of light necessary for recognition. As described above, by expanding the depth of field, it is possible to easily ensure the resolution necessary for the face recognition process even when the object moves suddenly.
- the aperture control unit 104 sets an aperture value smaller than the current aperture value (S404). The smaller the aperture value, the narrower the recognition range, so it is desirable to increase the aperture value until it is close to the incident light intensity threshold. That is, the aperture control unit 104 decreases the aperture value as the incident light amount decreases.
- the aperture control unit 104 can secure the amount of light required for recognition by reducing the aperture value.
- the aperture control unit 104 may set an aperture value smaller than at least the aperture value set in step S403 in step S404.
- the aperture control unit 104 increases the aperture value when the incident light amount of the face area is equal to or greater than the first incident light amount threshold value, and the incident light amount of the face area is less than the second incident light amount value smaller than the first incident light amount threshold value.
- the aperture value may be decreased, and the aperture value may not be changed when the incident light amount of the face region is between the first incident light amount threshold value and the second incident light amount threshold value.
- the aperture control unit 104 may change the amount of change in the aperture value according to the magnitude of the incident light amount of the face area and the plurality of incident light amount threshold values.
- the recognition imaging apparatus 100B recognizes the light amount necessary for recognition by controlling the aperture value according to the area of the face region and the incident light amount. Can be made as deep as possible. Accordingly, the recognition imaging apparatus 100B can perform more stable recognition.
- the aperture control unit 104 may change the aperture value according to at least one of the area of the face area and the incident light amount.
- the aperture controller 104 may change the aperture value change amount according to at least one of the area of the face area and the amount of incident light. Good.
- a specific method for controlling the change amount may be the same as described above.
- the present invention can also be applied to the case of recognizing an arbitrary object in an image.
- the recognition imaging apparatus may include two or more of the exposure control unit 102, the focus position control unit 103, and the aperture control unit 104 described above.
- the focus position or the aperture value may be changed.
- the area threshold value used for the exposure time, the focus position, and the aperture value may be different.
- the speed threshold values used for the exposure time, the focus position, and the aperture value may be different, and the incident light intensity threshold values used for the exposure time, the focus position, and the aperture value may be different.
- Each processing unit included in the recognition imaging apparatus according to the above embodiment is typically realized as an LSI that is an integrated circuit. These may be individually made into one chip, or may be made into one chip so as to include a part or all of them.
- circuits are not limited to LSI, and may be realized by a dedicated circuit or a general-purpose processor.
- An FPGA Field Programmable Gate Array
- reconfigurable processor that can reconfigure the connection and setting of circuit cells inside the LSI may be used.
- part or all of the functions of the recognition imaging apparatus according to the embodiment of the present invention may be realized by a processor such as a CPU executing a program.
- functions other than the imaging unit 101 can be realized by a processor such as a CPU executing a program.
- the present invention may be the above program or a non-transitory computer-readable recording medium on which the above program is recorded.
- the program can be distributed via a transmission medium such as the Internet.
- steps S201 and S221 may be any order.
- the order of steps S231 and S232 may be any order.
- the present invention can be applied to a recognition imaging apparatus and its control method.
- the present invention can be applied to cameras such as a digital still camera, a digital video camera, a network camera, and a security camera provided with a recognition imaging device.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Studio Devices (AREA)
- Exposure Control For Cameras (AREA)
- Focusing (AREA)
- Automatic Focus Adjustment (AREA)
Abstract
Description
本発明の実施の形態1に係る認識用撮像装置は、顔領域の面積、移動速度及び入光量に応じて、シャッタースピードを変更する。具体的には、本発明の実施の形態1に係る認識用撮像装置は、顔領域の面積が大きい場合、シャッタースピードを遅くする。
本発明の実施の形態2に係る認識用撮像装置は、顔領域の面積に応じて、当該認識用撮像装置の合焦位置を変更する。具体的には、本発明の実施の形態2に係る認識用撮像装置は、顔領域の面積が大きい場合、合焦位置を顔から遠くに設定する。
DN={s×(H-f)}/(H+s-2f)・・・(式2)
DF={s×(H-f)}/(H-s)・・・(式3)
本発明の実施の形態3に係る認識用撮像装置は、顔領域の面積及び入光量に応じて、絞り値を変更する。具体的には、本発明の実施の形態3に係る認識用撮像装置は、顔領域の面積が大きい場合、絞り値を大きくする。
101 撮像部
102 露出制御部
103 合焦位置制御部
104 絞り制御部
105 顔認識部
106 顔追跡部
107 顔認識結果記憶部
108 移動速度算出部
109 面積算出部
110 入光量算出部
112 レンズ
113 レンズ駆動装置
114 絞り装置
115 シャッター装置
116 撮像素子
117 AD変換器
120 入力画像
121 顔認識結果
122 顔追跡結果
123 顔特徴情報
Claims (18)
- 対象物を撮像することにより順次複数の画像を生成する撮像部と、
前記複数の画像の各々において、当該画像内で対象物が撮像されている領域である対象物領域を認識する対象物認識部と、
前記複数の画像間において前記対象物領域を追跡する追跡部とを有する認識用撮像装置であって、
前記対象物領域の面積を算出する面積算出部と、
前記面積が第1閾値未満の場合、前記撮像部における露出時間を第1露出時間に設定し、前記面積が前記第1閾値以上の場合、前記露出時間を前記第1露出時間より長い第2露出時間に設定する露出制御部とを備える
認識用撮像装置。 - 前記認識用撮像装置は、さらに、
前記対象物領域の移動速度を算出する移動速度算出部を備え、
前記露出制御部は、さらに、前記移動速度が第2閾値未満の場合、前記露出時間を第3露出時間に設定し、前記移動速度が前記第2閾値以上の場合、前記露出時間を前記第3露出時間より短い第4露出時間に設定する
請求項1に記載の認識用撮像装置。 - 前記認識用撮像装置は、さらに、
前記対象物領域における入光量を算出する入光量算出部を備え、
前記露出制御部は、前記面積に比例し、かつ、前記入光量に比例する認識用入光量が第3閾値以上の場合、前記撮像部における露出時間を第5露出時間に設定し、前記認識用入光量が前記第3閾値未満の場合、前記露出時間を前記第5露出時間より長い第6露出時間に設定する
請求項1に記載の認識用撮像装置。 - 前記露出制御部は、前記面積に比例し、かつ、前記対象物領域におけるブレ量に反比例する認識用解像度が第4閾値未満の場合、前記露出時間を前記第1露出時間に設定し、前記認識用解像度が前記第4閾値以上の場合、前記露出時間を前記第2露出時間に設定する
請求項1に記載の認識用撮像装置。 - 対象物を撮像することにより順次複数の画像を生成する撮像部と、
前記複数の画像の各々において、当該画像内で対象物が撮像されている領域である対象物領域を認識する対象物認識部と、
前記複数の画像間において前記対象物領域を追跡する追跡部とを有する認識用撮像装置であって、
前記対象物領域の面積を算出する面積算出部と、
前記面積が第1閾値未満の場合、当該認識用撮像装置の合焦位置を第1位置に設定し、前記面積が前記第1閾値以上の場合、前記合焦位置を、前記第1位置より前記対象物から離れた第2位置に設定する合焦位置制御部とを備える
認識用撮像装置。 - 前記合焦位置制御部は、前記面積に比例し、かつ、前記対象物領域におけるボケ量に反比例する認識用解像度が第2閾値未満の場合、前記合焦位置を前記第1位置に設定し、前記認識用解像度が前記第2閾値以上の場合、前記合焦位置を前記第2位置に設定する
請求項5に記載の認識用撮像装置。 - 対象物を撮像することにより順次複数の画像を生成する撮像部と、
前記複数の画像の各々において、当該画像内で対象物が撮像されている領域である対象物領域を認識する対象物認識部と、
前記複数の画像間において前記対象物領域を追跡算出する追跡部とを有する認識用撮像装置であって、
前記対象物領域の面積を算出する面積算出部と、
前記面積が第1閾値未満の場合、絞り値を第1絞り値に設定し、前記面積が前記第1閾値以上の場合、前記絞り値を前記第1絞り値より大きい第2絞り値に設定する絞り制御部とを備える
認識用撮像装置。 - 前記認識用撮像装置は、さらに、
前記対象物領域における入光量を算出する入光量算出部を備え、
前記絞り制御部は、さらに、前記入光量が第2閾値未満の場合、絞り値を第3絞り値に設定し、前記入光量が前記第2閾値以上の場合、前記絞り値を前記第3絞り値より大きい第4絞り値に設定する
請求項7に記載の認識用撮像装置。 - 前記絞り制御部は、前記面積に比例し、かつ、前記入光量に比例する認識用入光量が第3閾値未満の場合、前記絞り値を前記第1絞り値に設定し、前記認識用入光量が前記第2閾値以上の場合、前記絞り値を前記第2絞り値に設定する
請求項8に記載の認識用撮像装置。 - 対象物を撮像することにより順次複数の画像を生成する撮像部を備える認識用撮像装置の制御方法であって、
前記複数の画像の各々において、当該画像内で対象物が撮像されている領域である対象物領域を認識する対象物認識ステップと、
前記複数の画像間において前記対象物領域を追跡する追跡ステップと、
前記対象物領域の面積を算出する面積算出ステップと、
前記面積が第1閾値未満の場合、前記撮像部における露出時間を第1露出時間に設定し、前記面積が前記第1閾値以上の場合、前記露出時間を前記第1露出時間より長い第2露出時間に設定する露出制御ステップとを含む
認識用撮像装置の制御方法。 - 対象物を撮像することにより順次複数の画像を生成する撮像部を備える認識用撮像装置の制御方法であって、
前記複数の画像の各々において、当該画像内で対象物が撮像されている領域である対象物領域を認識する対象物認識ステップと、
前記複数の画像間において前記対象物領域を追跡する追跡ステップと、
前記対象物領域の面積を算出する面積算出ステップと、
前記面積が第1閾値未満の場合、前記認識用撮像装置の合焦位置を第1位置に設定し、前記面積が前記第1閾値以上の場合、前記合焦位置を、前記第1位置より前記対象物から離れた第2位置に設定する合焦位置制御ステップとを含む
認識用撮像装置の制御方法。 - 対象物を撮像することにより順次複数の画像を生成する撮像部を備える認識用撮像装置の制御方法であって、
前記複数の画像の各々において、当該画像内で対象物が撮像されている領域である対象物領域を認識する対象物認識ステップと、
前記複数の画像間において前記対象物領域を追跡する追跡ステップと、
前記対象物領域の面積を算出する面積算出ステップと、
前記面積が第1閾値未満の場合、絞り値を第1絞り値に設定し、前記面積が前記第1閾値以上の場合、前記絞り値を前記第1絞り値より大きい第2絞り値に設定する絞り制御ステップとを含む
認識用撮像装置の制御方法。 - 請求項10記載の認識用撮像装置の制御方法をコンピュータに実行させるための
プログラム。 - 請求項11記載の認識用撮像装置の制御方法をコンピュータに実行させるための
プログラム。 - 請求項12記載の認識用撮像装置の制御方法をコンピュータに実行させるための
プログラム。 - 請求項1記載の前記撮像部と、前記対象物認識部と、前記追跡部と、前記面積算出部と、前記露出制御部とを備える
半導体集積回路。 - 請求項5記載の前記撮像部と、前記対象物認識部と、前記追跡部と、前記面積算出部と、前記合焦位置制御部とを備える
半導体集積回路。 - 請求項7記載の前記撮像部と、前記対象物認識部と、前記追跡部と、前記面積算出部と、前記絞り制御部とを備える
半導体集積回路。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011544185A JP5400171B2 (ja) | 2009-12-01 | 2010-11-26 | 認識用撮像装置及びその制御方法 |
CN201080006206.5A CN102301693B (zh) | 2009-12-01 | 2010-11-26 | 识别用摄像装置以及其控制方法 |
US13/147,207 US8860875B2 (en) | 2009-12-01 | 2010-11-26 | Imaging device for recognition and method of controlling the same |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2009-273070 | 2009-12-01 | ||
JP2009273070 | 2009-12-01 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011067906A1 true WO2011067906A1 (ja) | 2011-06-09 |
Family
ID=44114769
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2010/006900 WO2011067906A1 (ja) | 2009-12-01 | 2010-11-26 | 認識用撮像装置及びその制御方法 |
Country Status (4)
Country | Link |
---|---|
US (1) | US8860875B2 (ja) |
JP (1) | JP5400171B2 (ja) |
CN (1) | CN102301693B (ja) |
WO (1) | WO2011067906A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20170131657A (ko) * | 2015-08-19 | 2017-11-29 | 구글 엘엘씨 | 통합 메모리 및 프로세서를 갖는 스마트 이미지 센서 |
JP2019102847A (ja) * | 2017-11-28 | 2019-06-24 | 株式会社ザクティ | 画像処理装置 |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5412953B2 (ja) * | 2009-05-20 | 2014-02-12 | リコーイメージング株式会社 | 撮像装置 |
US8854397B2 (en) * | 2011-12-13 | 2014-10-07 | Facebook, Inc. | Photo selection for mobile devices |
US9724597B2 (en) * | 2012-06-04 | 2017-08-08 | Sony Interactive Entertainment Inc. | Multi-image interactive gaming device |
CN103024165B (zh) * | 2012-12-04 | 2015-01-28 | 华为终端有限公司 | 一种自动设置拍摄模式的方法和装置 |
US10306125B2 (en) | 2014-10-09 | 2019-05-28 | Belkin International, Inc. | Video camera with privacy |
US9179105B1 (en) | 2014-09-15 | 2015-11-03 | Belkin International, Inc. | Control of video camera with privacy feedback |
US9628720B2 (en) * | 2015-08-12 | 2017-04-18 | Qualcomm Incorporated | System and method to control an imaging process |
US10713501B2 (en) * | 2015-08-13 | 2020-07-14 | Ford Global Technologies, Llc | Focus system to enhance vehicle vision performance |
JP6800871B2 (ja) * | 2015-10-16 | 2020-12-16 | オリンパス株式会社 | 内視鏡装置、内視鏡装置の作動方法、および記録媒体 |
JP6839089B2 (ja) * | 2015-10-16 | 2021-03-03 | オリンパス株式会社 | 内視鏡装置、内視鏡装置の作動方法、および記録媒体 |
CN106131518A (zh) * | 2016-06-30 | 2016-11-16 | 东莞市中控电子技术有限公司 | 一种图像处理的方法以及图像处理装置 |
JP6364698B2 (ja) * | 2016-09-30 | 2018-08-01 | 三菱重工機械システム株式会社 | 合焦位置調整装置、合焦位置調整システム、プログラム、および合焦位置調整方法 |
WO2019069905A1 (ja) * | 2017-10-04 | 2019-04-11 | Necソリューションイノベータ株式会社 | 情報処理装置、制御方法、及びプログラム |
CN110786001B (zh) * | 2018-11-28 | 2022-06-10 | 深圳市大疆创新科技有限公司 | 拍摄方法和拍摄系统 |
JP7331483B2 (ja) * | 2019-06-18 | 2023-08-23 | 株式会社アイシン | 撮像制御装置 |
CN117544851A (zh) * | 2021-07-31 | 2024-02-09 | 华为技术有限公司 | 拍摄方法及相关装置 |
CN114596597A (zh) * | 2022-04-12 | 2022-06-07 | 深圳市汇顶科技股份有限公司 | 指纹识别的方法、装置和电子设备 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004320287A (ja) * | 2003-04-15 | 2004-11-11 | Nikon Gijutsu Kobo:Kk | デジタルカメラ |
JP2006208626A (ja) * | 2005-01-27 | 2006-08-10 | Sony Corp | オートフォーカス制御装置、オートフォーカス制御方法および撮像装置 |
JP2008233470A (ja) * | 2007-03-20 | 2008-10-02 | Sanyo Electric Co Ltd | 絞り制御装置及び画像処理装置 |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040207743A1 (en) * | 2003-04-15 | 2004-10-21 | Nikon Corporation | Digital camera system |
WO2005006072A1 (ja) * | 2003-07-15 | 2005-01-20 | Omron Corporation | 対象決定装置及び撮像装置 |
JP4434939B2 (ja) * | 2004-12-27 | 2010-03-17 | キヤノン株式会社 | 撮像装置及びその制御方法 |
JP4767595B2 (ja) | 2005-06-15 | 2011-09-07 | パナソニック株式会社 | 対象物検出装置及びその学習装置 |
JP2007094535A (ja) | 2005-09-27 | 2007-04-12 | Konica Minolta Photo Imaging Inc | 認証システム及び認証方法 |
JP4172507B2 (ja) * | 2006-07-13 | 2008-10-29 | ソニー株式会社 | 撮像装置、および撮像装置制御方法、並びにコンピュータ・プログラム |
US20080136958A1 (en) * | 2006-12-11 | 2008-06-12 | Pentax Corporation | Camera having a focus adjusting system and a face recognition function |
JP5053731B2 (ja) * | 2007-07-03 | 2012-10-17 | キヤノン株式会社 | 画像表示制御装置及び画像表示制御方法及びプログラム及び記録媒体 |
JP4518157B2 (ja) * | 2008-01-31 | 2010-08-04 | カシオ計算機株式会社 | 撮像装置及びそのプログラム |
JP4539729B2 (ja) * | 2008-02-15 | 2010-09-08 | ソニー株式会社 | 画像処理装置、カメラ装置、画像処理方法、およびプログラム |
US8300117B2 (en) * | 2008-03-28 | 2012-10-30 | Fuji Xerox Co., Ltd. | System and method for exposing video-taking heuristics at point of capture |
JP4582212B2 (ja) * | 2008-06-24 | 2010-11-17 | カシオ計算機株式会社 | 撮像装置及びプログラム |
KR101539043B1 (ko) * | 2008-10-31 | 2015-07-24 | 삼성전자주식회사 | 인물 구도 제안 영상 촬영 장치 및 방법 |
-
2010
- 2010-11-26 US US13/147,207 patent/US8860875B2/en active Active
- 2010-11-26 CN CN201080006206.5A patent/CN102301693B/zh active Active
- 2010-11-26 WO PCT/JP2010/006900 patent/WO2011067906A1/ja active Application Filing
- 2010-11-26 JP JP2011544185A patent/JP5400171B2/ja active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004320287A (ja) * | 2003-04-15 | 2004-11-11 | Nikon Gijutsu Kobo:Kk | デジタルカメラ |
JP2006208626A (ja) * | 2005-01-27 | 2006-08-10 | Sony Corp | オートフォーカス制御装置、オートフォーカス制御方法および撮像装置 |
JP2008233470A (ja) * | 2007-03-20 | 2008-10-02 | Sanyo Electric Co Ltd | 絞り制御装置及び画像処理装置 |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20170131657A (ko) * | 2015-08-19 | 2017-11-29 | 구글 엘엘씨 | 통합 메모리 및 프로세서를 갖는 스마트 이미지 센서 |
JP2018525853A (ja) * | 2015-08-19 | 2018-09-06 | グーグル エルエルシー | 一体化されたメモリおよびプロセッサを有するスマートイメージセンサ |
US10129477B2 (en) | 2015-08-19 | 2018-11-13 | Google Llc | Smart image sensor having integrated memory and processor |
KR101953813B1 (ko) * | 2015-08-19 | 2019-03-04 | 구글 엘엘씨 | 통합 메모리 및 프로세서를 갖는 스마트 이미지 센서 |
US10547779B2 (en) | 2015-08-19 | 2020-01-28 | Google Llc | Smart image sensor having integrated memory and processor |
JP2019102847A (ja) * | 2017-11-28 | 2019-06-24 | 株式会社ザクティ | 画像処理装置 |
JP6992947B2 (ja) | 2017-11-28 | 2022-01-13 | 株式会社ザクティ | 画像処理装置 |
Also Published As
Publication number | Publication date |
---|---|
CN102301693A (zh) | 2011-12-28 |
JP5400171B2 (ja) | 2014-01-29 |
US20110285897A1 (en) | 2011-11-24 |
US8860875B2 (en) | 2014-10-14 |
JPWO2011067906A1 (ja) | 2013-04-18 |
CN102301693B (zh) | 2014-09-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5400171B2 (ja) | 認識用撮像装置及びその制御方法 | |
JP5335302B2 (ja) | 焦点検出装置及びその制御方法 | |
US10650526B2 (en) | Image processing apparatus, image capturing apparatus, image processing method, and storage medium | |
US9131145B2 (en) | Image pickup apparatus and control method therefor | |
US10511781B2 (en) | Image pickup apparatus, control method for image pickup apparatus | |
JP5446076B2 (ja) | デジタルカメラ | |
JP6202860B2 (ja) | 撮像装置及び撮像方法 | |
US11159711B2 (en) | Image-capturing apparatus | |
JP2010122301A (ja) | フォーカス制御装置、およびフォーカス制御方法 | |
US11277554B2 (en) | Control apparatus, imaging apparatus, control method, and storage medium | |
US20100171836A1 (en) | Image capturing apparatus, control method thereof, and program | |
JP6139960B2 (ja) | 撮像装置およびその制御方法 | |
JP5873336B2 (ja) | 焦点調節装置 | |
US10747089B2 (en) | Imaging apparatus and control method of the same | |
JP5698499B2 (ja) | フォーカス調整装置及び撮像装置 | |
JP4981758B2 (ja) | 焦点調節装置及び方法 | |
JP2013160925A (ja) | 撮像装置およびフォーカス制御方法 | |
WO2014189047A1 (ja) | 撮像装置およびオートフォーカス制御方法 | |
CN114762313B (zh) | 图像处理方法、装置、存储介质及电子设备 | |
US11012609B2 (en) | Image pickup apparatus and its control method, and storage medium | |
US12063437B2 (en) | Control apparatus, image capturing apparatus, control method, and memory medium | |
JP2013142728A (ja) | 焦点調節装置 | |
US11595562B2 (en) | Image processing apparatus, control method thereof, and storage medium | |
US20240070877A1 (en) | Image processing apparatus, method for controlling the same, imaging apparatus, and storage medium | |
US20240098366A1 (en) | Focus control apparatus, image pickup apparatus, and focus control method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 201080006206.5 Country of ref document: CN |
|
ENP | Entry into the national phase |
Ref document number: 2011544185 Country of ref document: JP Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 10834362 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13147207 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: 10834362 Country of ref document: EP Kind code of ref document: A1 |