WO2021199124A1 - 検出装置 - Google Patents

検出装置 Download PDF

Info

Publication number
WO2021199124A1
WO2021199124A1 PCT/JP2020/014484 JP2020014484W WO2021199124A1 WO 2021199124 A1 WO2021199124 A1 WO 2021199124A1 JP 2020014484 W JP2020014484 W JP 2020014484W WO 2021199124 A1 WO2021199124 A1 WO 2021199124A1
Authority
WO
WIPO (PCT)
Prior art keywords
detection
unit
image data
face
face area
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/014484
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
紫穂野 望月
陽平 伊藤
哲 寺澤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by NEC Corp filed Critical NEC Corp
Priority to US17/911,178 priority Critical patent/US20230147088A1/en
Priority to PCT/JP2020/014484 priority patent/WO2021199124A1/ja
Priority to JP2022512519A priority patent/JP7517412B2/ja
Publication of WO2021199124A1 publication Critical patent/WO2021199124A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—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
    • H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • 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
    • H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
    • 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
    • H04N23/69—Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/90—Arrangement of cameras or camera modules, e.g. multiple cameras in TV studios or sports stadiums
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G06V2201/033—Recognition of patterns in medical or anatomical images of skeletal patterns
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N5/00—Details of television systems
    • H04N5/222—Studio circuitry; Studio devices; Studio equipment
    • H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
    • H04N5/272—Means for inserting a foreground image in a background image, i.e. inlay, outlay
    • H04N2005/2726—Means for inserting a foreground image in a background image, i.e. inlay, outlay for simulating a person's appearance, e.g. hair style, glasses, clothes

Definitions

  • the present invention relates to a detection device, a detection method, and a recording medium.
  • Authentication technology such as face recognition that detects the face area and performs authentication based on the detected feature amount of the face area is known.
  • Patent Document 1 is one of the techniques used when detecting a face region.
  • Patent Document 1 describes an imaging device (imaging device) having a detection determination means, a correction means, a calculation means, and a release determination means.
  • the detection determination means determines whether or not the subject region can be detected based on a plurality of types of classifiers.
  • the correction means corrects the image data when it is determined that the subject area cannot be detected.
  • the release determining means compares the results calculated by the calculation means for calculating the similarity between the image data before and after the correction and the classifier, and determines whether or not to cancel the correction process based on the compared results.
  • Patent Document 1 there is a method of correcting image data when an area such as a face area cannot be detected by the detection means.
  • the target is in the camera for a short time, for example, even if you try to correct the image data by adjusting the parameters of the camera that acquires the image data, the target is out of the angle of view during the adjustment. There was a risk that it would appear in. As a result, detection omission may occur in the face area.
  • an object of the present invention is to provide a detection device, a detection method, and a recording medium that solve the problem that it is difficult to suppress detection omission in the face region.
  • the detection method which is one form of the present disclosure, in order to achieve such an object
  • the detector is The face area is detected based on the image data acquired by a predetermined photographing device, and the face area is detected. Based on the detected result, the setting for performing the face area detection process based on the image data acquired by another photographing device is changed.
  • the detection device which is another form of the present disclosure is A detection unit that detects the face area based on the image data acquired by a predetermined photographing device, and a detection unit. Based on the result detected by the detection unit, the setting change unit that changes the setting when performing the face area detection process based on the image data acquired by another photographing device, and the setting change unit. It has a structure of having.
  • the recording medium which is another form of the present disclosure is For the detector, A detection unit that detects the face area based on the image data acquired by a predetermined photographing device, and a detection unit. Based on the result detected by the detection unit, the setting change unit that changes the setting when performing the face area detection process based on the image data acquired by another photographing device, and the setting change unit. It is a computer-readable recording medium on which a program for realizing the above is recorded.
  • FIG. 1st Embodiment of this disclosure It is a figure which shows the configuration example of the face recognition system in 1st Embodiment of this disclosure. It is a block diagram which shows the configuration example of the face recognition apparatus shown in FIG. It is a figure which shows an example of the image information shown in FIG. It is a figure which shows an example of the posture information shown in FIG. It is a figure for demonstrating the processing of the face area estimation part. It is a block diagram which shows the structural example of the camera shown in FIG. It is a flowchart which shows the operation example of the face recognition apparatus in 1st Embodiment of this disclosure. It is a figure which shows the configuration example of the face recognition system in the 2nd Embodiment of this disclosure. It is a block diagram which shows the configuration example of the face recognition apparatus shown in FIG.
  • FIG. 1 It is a figure which shows the processing example of the moving destination estimation part shown in FIG. It is a flowchart which shows the operation example of the face recognition apparatus in the 2nd Embodiment of this disclosure. It is a block diagram which shows the other configuration example of the face recognition apparatus in the 2nd Embodiment of this disclosure. It is a figure which shows the configuration example of the face recognition system in 3rd Embodiment of this disclosure. It is a block diagram which shows the configuration example of the face recognition apparatus shown in FIG. It is a figure which shows an example of the authentication-related information shown in FIG. It is a block diagram which shows the structural example of the camera shown in FIG. It is a flowchart which shows the operation example of the face recognition apparatus in 3rd Embodiment of this disclosure. It is a figure which shows an example of the hardware configuration of the detection apparatus in 4th Embodiment of this disclosure. It is a block diagram which shows the structural example of the detection apparatus shown in FIG.
  • FIG. 1 is a diagram showing a configuration example of the face recognition system 100.
  • FIG. 2 is a block diagram showing a configuration example of the face recognition device 200.
  • FIG. 3 is a diagram showing an example of image information 234.
  • FIG. 4 is a diagram showing an example of posture information 235.
  • FIG. 5 is a diagram for explaining the processing of the face area estimation unit 244.
  • FIG. 6 is a block diagram showing a configuration example of the camera 300.
  • FIG. 7 is a flowchart showing an operation example of the face recognition device 200.
  • a face recognition system 100 that detects a face region and performs face recognition will be described.
  • the face recognition system 100 cannot detect the face area of the person to be authenticated based on the image data acquired by the camera 300-1, the area estimated based on the result of the posture detection, etc. Adjust the parameters and check again whether the face area is detected in the estimated area. If the face area is not detected by the reconfirmation, the face recognition system 100 instructs the camera 300-2, which is the destination camera, to adjust the parameters, or the face used when detecting the face area. Adjust the detection threshold. Then, the face recognition system 100 detects the face region using the adjusted face detection threshold value based on the image data acquired by the parameter-adjusted camera 300-2.
  • the camera 300-2 which is another photographing device may perform. Change the settings when performing face area detection processing using the acquired image data. Further, the setting to be changed includes, for example, at least one of a parameter used when the camera 300 acquires image data and a face detection threshold value.
  • FIG. 1 shows an overall configuration example of the face recognition system 100.
  • the face recognition system 100 includes, for example, a face recognition device 200 and two cameras 300 (camera 300-1, camera 300-2, hereinafter referred to as camera 300 unless otherwise specified). ,have.
  • the face recognition device 200 and the camera 300-1 are connected so as to be able to communicate with each other.
  • the face recognition device 200 and the camera 300-2 are connected so as to be able to communicate with each other.
  • the face recognition system 100 is installed in, for example, a shopping mall, an airport, a shopping district, etc., and searches for a suspicious person or a lost child by performing face recognition.
  • the place where the face recognition system 100 is deployed and the purpose for which the face recognition system 100 performs face recognition may be other than those illustrated above.
  • the face recognition device 200 is an information processing device that performs face recognition based on the image data acquired by the camera 300-1 and the camera 300-2. For example, when the face recognition device 200 cannot detect the face area based on the image data acquired by the camera 300-1, the face recognition device 200 detects the face area based on the image data acquired by the camera 300-2.
  • FIG. 2 shows a configuration example of the face recognition device 200. Referring to FIG. 2, the face recognition device 200 has, for example, a screen display unit 210, a communication I / F unit 220, a storage unit 230, and an arithmetic processing unit 240 as main components. ..
  • the screen display unit 210 is composed of a screen display device such as an LCD (Liquid Crystal Display).
  • the screen display unit 210 displays the information stored in the storage unit 230, such as the authentication result information 236, on the screen in response to an instruction from the arithmetic processing unit 240.
  • the communication I / F unit 220 includes a data communication circuit.
  • the communication I / F unit 220 performs data communication with the camera 300 and an external device connected via a communication line.
  • the storage unit 230 is a storage device such as a hard disk or a memory.
  • the storage unit 230 stores processing information and a program 237 required for various processes in the arithmetic processing unit 240.
  • the program 237 realizes various processing units by being read and executed by the arithmetic processing unit 240.
  • the program 237 is read in advance from an external device or a recording medium via a data input / output function such as the communication I / F unit 220, and is stored in the storage unit 230.
  • the main information stored in the storage unit 230 includes, for example, detection information 231, learned model 232, feature amount information 233, image information 234, posture information 235, and authentication result information 236.
  • the detection information 231 is information used when the face area detection unit 242 detects the face area. As will be described later, the face area detection unit 242 may perform face detection using a general face detection technique. Therefore, the information included in the detection information 231 may also correspond to the method in which the face area detection unit 242 performs face detection. For example, the detection information 231 may be a model learned based on the luminance gradient information or the like. The detection information 231 is acquired in advance from an external device or the like via, for example, the communication I / F unit 220 or the like, and is stored in the storage unit 230.
  • the trained model 232 is a trained model used by the posture detection unit 243 when detecting the posture.
  • the trained model 232 is generated in advance by learning using teacher data such as image data containing skeleton coordinates in an external device or the like, and is acquired from the external device or the like via the communication I / F unit 220 or the like. It is stored in the storage unit 230.
  • the feature amount information 233 includes information indicating the face feature amount used when the face recognition unit 246 performs face recognition.
  • information indicating the face feature amount used when the face recognition unit 246 performs face recognition for example, identification information for identifying a person and information indicating a facial feature amount are associated with each other.
  • the feature amount information 233 is acquired in advance from an external device or the like via, for example, the communication I / F unit 220 or the like, and is stored in the storage unit 230.
  • the image information 234 includes image data acquired by the camera 300.
  • the image data and the information indicating the date and time when the camera 300 acquired the image data are associated with each other.
  • FIG. 3 shows an example of image information 234.
  • the image information 234 includes image data acquired from the camera 300-1 and image data acquired from the camera 300-2.
  • the posture information 235 includes information indicating the posture of the person detected by the posture detection unit 243.
  • the posture information 235 includes information indicating the coordinates of each part of the person.
  • FIG. 4 shows an example of posture information 235. With reference to FIG. 4, in the posture information 235, the identification information and the site coordinates are associated with each other.
  • the part included in the part coordinates corresponds to the trained model 232.
  • the upper part of the spine, the right shoulder, the left shoulder, ..., are illustrated.
  • the site coordinates can include, for example, about 30 sites (other than those illustrated).
  • the part included in the part coordinates may be other than those illustrated in FIG. 4 and the like.
  • the authentication result information 236 includes information indicating the result of authentication by the face recognition unit 246. Details of the processing by the face recognition unit 246 will be described later.
  • the arithmetic processing unit 240 has a microprocessor such as an MPU and its peripheral circuits, and by reading and executing the program 237 from the storage unit 230, the hardware and the program 237 are made to cooperate to realize various processing units. do.
  • the main processing units realized by the arithmetic processing unit 240 include, for example, an image acquisition unit 241, a face area detection unit 242, a posture detection unit 243, a face area estimation unit 244, a parameter adjustment unit 245, a face authentication unit 246, and an output. There is a part 247 and the like.
  • the image acquisition unit 241 acquires the image data acquired by the camera 300 from the camera 300 via the communication I / F unit 220. Then, the image acquisition unit 241 stores the acquired image data in the storage unit 230 as image information 234 in association with, for example, the acquisition date and time of the image data.
  • the image acquisition unit 241 acquires the image data from the camera 300-1 and the image data from the camera 300-2.
  • the image acquisition unit 241 may always acquire image data from the camera 300-1 and the camera 300-2, and for example, the image acquisition unit 241 does not have to acquire the image data from the camera 300-2 until a predetermined condition is satisfied. I do not care.
  • the image acquisition unit 241 may be configured to acquire image data from the camera 300-2 when the face region cannot be detected based on the image data acquired by the camera 300-1. No.
  • the face area detection unit 242 detects the face area of a person based on the image data included in the image information 234. As described above, the face area detection unit 242 can detect the face area by using a known technique. For example, the face area detection unit 242 detects the face area using the detection information 231 and the face detection threshold value. In other words, the face region detection unit 242 can detect a region whose similarity with the detection information 231 is equal to or higher than the face detection threshold value as the face region.
  • the face area detection unit 242 detects the face area based on the image data acquired from the camera 300-1 among the image data included in the image information 234.
  • the parameter adjustment unit 245 adjusts the parameters of the area estimated based on the result of the posture detection.
  • the face area detection unit 242 can confirm whether or not there is a face area in the area estimated by the face area estimation unit 244 based on the result of the posture detection. In other words, the face area detection unit 242 detects the face area for the area estimated by the face area estimation unit 244 in a state where the parameter adjustment unit 245 adjusts the parameters of the area estimated by the face area estimation unit 244. Can be done.
  • the parameter adjustment unit 245 instructs the camera 300-2 to adjust the parameters. Is performed, and the face detection threshold is adjusted. For example, the parameter adjustment unit 245 lowers the face detection threshold.
  • the face area detection unit 242 can detect the face area using the adjusted face detection threshold value based on the image data acquired by the parameter-adjusted camera 300-2. By performing face detection with the face detection threshold lowered, the probability that face detection can be performed increases.
  • the face area detection unit 242 detects the face area based on the image data acquired from the camera 300-1, and is based on the image data acquired from the parameter-adjusted camera 300-1 and the camera 300-2.
  • the face area can be detected by various methods such as detection of the face area.
  • the posture detection unit 243 detects the posture of the person by recognizing the skeleton of the person to be authenticated in the image data using the trained model 232. For example, the posture detection unit 243 recognizes each part such as the upper part of the spine, the right shoulder, the left shoulder, ..., As shown in FIG. In addition, the posture detection unit 243 calculates the coordinates in the screen data of each recognized portion. Then, the posture detection unit 243 associates the recognition / calculation result with the identification information and stores the posture information 235 in the storage unit 230.
  • the portion recognized by the posture detection unit 243 corresponds to the trained model 232 (teacher data used when learning the trained model 232). Therefore, the posture detection unit 243 may recognize a part other than those illustrated above according to the trained model 232.
  • the face area estimation unit 244 estimates the area where the face area is estimated to exist based on the result detected by the posture detection unit 243. For example, the face area estimation unit 244 estimates the area when the posture detection unit 243 detects the posture but the face area detection unit 242 cannot detect the face area. The face area estimation unit 244 may estimate the area at a timing other than those illustrated above.
  • FIG. 5 is a diagram for explaining an example of estimation by the face area estimation unit 244. As shown in FIG. 5, it can be estimated that the face region is located in the vicinity of the shoulders, neck, etc. on the side opposite to the side where the hips, legs, etc. are located, when viewed from the shoulders and the like. Therefore, the face area estimation unit 244 can estimate the area where the face area will exist by confirming the coordinates of each part with reference to the posture information 235.
  • the parameter adjustment unit 245 adjusts the parameters used in the face authentication process, such as the parameters used when the camera 300 acquires the image data and the face detection threshold value.
  • the parameter adjustment unit 245 determines the parameters for the area estimated by the face area estimation unit 244. Make adjustments. Specifically, for example, the parameter adjusting unit 245 causes the camera 300-1 to adjust the parameters used when the camera 300-1 acquires the image data for the area estimated by the face area estimation unit 244. To instruct. As a result, the camera 300-1 corrects the parameters and acquires image data using the corrected parameters.
  • the parameter adjustment unit 245 may instruct the camera 300-1 to correct the parameters for the entire image data. Further, the parameter adjusting unit 245 may adjust the parameters used when the face area detecting unit 242 detects the face area, such as lowering the face detection threshold value, in addition to the above-mentioned instruction to the camera 300-1.
  • the parameter adjusting unit 245 instructs the camera 300-2 to adjust the parameters used when acquiring the image data when the face area detecting unit 242 cannot detect the face area even by the reconfirmation. do.
  • the parameter adjustment unit 245 adjusts the parameters used when performing face authentication based on the detection result of the face area detection unit 242.
  • the parameters for which the parameter adjustment unit 245 instructs the camera 300 to make adjustments include, for example, brightness, sharpness, contrast, and a frame rate indicating the number of image data acquisitions per unit time. For example, when it is assumed that the face detection fails because the brightness value is too high due to the backlight, the parameter adjusting unit 245 instructs to lower the brightness.
  • the parameters adjusted by the parameter adjusting unit 245 may be at least a part of the above-exemplified parameters, or may be other than the above-exemplified parameters.
  • the parameter adjustment unit 245 can instruct the camera 300-1 and the camera 300-2 to adjust the parameters and also instruct the time for adjusting the parameters.
  • the camera 300-2 acquires the person to be authenticated after the person to be authenticated is reflected in the image data acquired by the camera 300-1 from the information indicating the installation position of the camera 300-1 or the camera 300-2 or the information indicating the walking speed. It is possible to calculate in advance the time until the person to be authenticated appears in the image data to be authenticated. Therefore, the parameter adjustment unit 245 may instruct the camera 300-2 to adjust the parameters during the time when it is estimated that the person to be authenticated is displayed on the camera 300-2.
  • the time for instructing the camera 300-2 to adjust the parameters may be estimated in advance using, for example, a general walking speed, or the image data acquired by the camera 300-1 may be used. It may be calculated based on the walking speed of the person calculated based on the above.
  • the face recognition unit 246 performs face recognition using the detection result of the face area detection unit 242. Then, the face recognition unit 246 stores the face recognition result as the authentication result information 236 in the storage unit 230.
  • the face recognition unit 246 extracts feature points such as eyes, nose, and mouth of a person in the face area detected by the face area detection unit 242, and calculates a feature amount based on the extracted result. Then, the face recognition unit 246 sets the calculated feature amount by examining whether or not the similarity between the calculated feature amount and the face feature amount included in the feature amount information 233 exceeds the face comparison threshold. The feature amount stored in the storage unit 230 is collated, and authentication is performed based on the collation result. By performing face recognition in this way, the face recognition unit 246 can identify a specific target person such as a lost child.
  • the output unit 247 outputs the authentication result information 236 indicating the result of the authentication process by the face recognition unit 246.
  • the output by the output unit 247 is performed, for example, by displaying the screen on the screen display unit 210 or transmitting the output to the external device via the communication I / F unit 220.
  • the above is a configuration example of the face recognition device 200.
  • the camera 300 is a photographing device that acquires image data, and is, for example, a surveillance camera.
  • FIG. 6 shows a configuration example of the camera 300. Referring to FIG. 6, the camera 300 has, for example, a transmission / reception unit 310, a setting unit 320, and a photographing unit 330.
  • the camera 300 has an arithmetic unit such as a CPU and a storage device.
  • the camera 300 can realize each of the above processing units by executing the program stored in the storage device by the arithmetic unit.
  • the transmission / reception unit 310 transmits / receives data to / from the face recognition device 200 or the like. For example, the transmission / reception unit 310 transmits the image data acquired by the photographing unit 330 to the face recognition device 200. Further, the transmission / reception unit 310 receives a parameter adjustment instruction or the like from the face recognition device 200.
  • the setting unit 320 adjusts the parameters used when the photographing unit 330 acquires the image data based on the parameter adjustment instruction received from the face recognition device 200. For example, the setting unit 320 adjusts brightness, sharpness, contrast, frame rate, etc. based on the instruction received from the face recognition device 200. The setting unit 320 can adjust the parameters for the instructed area in response to the instruction.
  • the photographing unit 330 acquires image data using the parameters set by the setting unit 320.
  • the image data acquired by the photographing unit 330 can be transmitted to the face recognition device 200 via the transmitting / receiving unit 310 in association with the date and time when the photographing unit 330 acquired the image data.
  • the face area detection unit 242 detects the face area based on the image data acquired from the camera 300-1 among the image data included in the image information 234 (step S101).
  • the face region estimation unit 244 estimates that the face region exists based on the result detected by the posture detection unit 243.
  • the region is estimated (step S103).
  • the parameter adjusting unit 245 instructs the camera 300-1 to adjust the parameters used when the camera 300-1 acquires the image data for the area estimated by the face area estimation unit 244 (step). S104). As a result, the camera 300-1 corrects the parameters.
  • the face area detection unit 242 detects the face area for the area estimated by the face area estimation unit 244 (step S105).
  • the parameter adjusting unit 245 adjusts the parameters used when acquiring the image data for the camera 300-2. Instruct. Further, the parameter adjusting unit 245 adjusts the parameters used when the face area detecting unit 242 detects the face area, such as lowering the face detection threshold value (step S107).
  • the face area detection unit 242 detects the face area using the adjusted face detection threshold value based on the image data acquired by the parameter-adjusted camera 300-2 (step S108).
  • the face authentication unit 246 performs face authentication using the detection result of the face area detection unit 242 (step S109).
  • the above is an operation example of the face recognition device 200.
  • the face recognition device 200 has a face area detection unit 242 and a parameter adjustment unit 245.
  • the parameter adjusting unit 245 can instruct the camera 300-2 to adjust the parameters based on the detection result of the face area based on the image data acquired by the camera 300-1. ..
  • the parameter adjustment unit 245 can lower the face detection threshold value in advance.
  • the face area detection unit 242 can detect the face area based on the image data acquired in the state where the parameters are adjusted in advance. As a result, it is possible to appropriately adjust the parameters and suppress the omission of detection of the face region.
  • the face recognition device 200 has a posture detection unit 243 and a face area estimation unit 244.
  • the face region estimation unit 244 can estimate the region where the face region is presumed to exist based on the detection result by the posture detection unit 243.
  • the range of parameter adjustment by the parameter adjustment unit 245 and the range of detection of the face area by the face area detection unit 242 can be narrowed down, and efficient parameter adjustment and face area detection can be realized.
  • the parameter adjusting unit 245 is used to acquire image data for the camera 300-2 when the face area detecting unit 242 cannot detect the face area even by reconfirmation. I was instructed to make adjustments.
  • the parameter adjusting unit 245 is configured to instruct the camera 300-2 to correct the parameters without performing the confirmation again. It doesn't matter. In this case, for example, the processes from step S103 to step S105 described with reference to FIG. 7 may not be performed. Further, when the processes from step S103 to step S105 are not performed, the face recognition device 200 may not have the posture detection unit 243 and the face area estimation unit 244. For example, as described above, the face recognition device 200 may have only a part of the configuration illustrated in FIG.
  • FIG. 2 illustrates a case where the function as the face recognition device 200 is realized by using one information processing device.
  • the function as the face recognition device 200 may be realized by, for example, a plurality of information processing devices connected via a network.
  • FIG. 8 is a diagram showing a configuration example of the face recognition system 400.
  • FIG. 9 is a block diagram showing a configuration example of the face recognition device 500.
  • FIG. 10 is a diagram for explaining a processing example of the movement destination estimation unit 548.
  • FIG. 11 is a flowchart showing an operation example of the face recognition device 500.
  • FIG. 12 is a block diagram showing another configuration example of the face recognition device 500.
  • the face recognition system 400 which is a modification of the face recognition system 100 described in the first embodiment, will be described.
  • the face recognition system 100 having two cameras 300, a camera 300-1 and a camera 300-2, has been described.
  • the face recognition system 400 having three or more cameras 300 will be described.
  • the face recognition system 400 estimates the camera to be moved based on the result of the posture detection. .. Then, the face recognition system 400 instructs the estimated camera 300 to adjust the parameters.
  • FIG. 8 shows an overall configuration example of the face recognition system 400.
  • the face recognition system 400 includes, for example, a face recognition device 500 and three cameras 300 (camera 300-1, camera 300-2, camera 300-3). As shown in FIG. 1, the face recognition device 500 and the camera 300-1 are connected so as to be able to communicate with each other. Further, the face recognition device 500 and the camera 300-2 are connected so as to be able to communicate with each other. Further, the face recognition device 500 and the camera 300-3 are connected so as to be able to communicate with each other.
  • FIG. 8 illustrates a case where the face recognition system 400 has three cameras 300.
  • the number of cameras 300 included in the face recognition system 400 is not limited to three.
  • the face recognition system 400 may have four or more cameras 300.
  • the face recognition device 500 is an information processing device that performs face recognition in the same manner as the face recognition device 200 described in the first embodiment.
  • FIG. 9 shows a configuration example of the face recognition device 500.
  • the face recognition device 500 has, for example, a screen display unit 210, a communication I / F unit 220, a storage unit 230, and an arithmetic processing unit 540 as main components. ..
  • a configuration characteristic of the present embodiment will be described.
  • the arithmetic processing unit 540 has a microprocessor such as an MPU and its peripheral circuits, and by reading and executing the program 237 from the storage unit 230, the hardware and the program 237 are made to cooperate to realize various processing units. do.
  • the main processing units realized by the arithmetic processing unit 540 include, for example, an image acquisition unit 241, a face area detection unit 242, a posture detection unit 243, a face area estimation unit 244, a parameter adjustment unit 545, a face authentication unit 246, and an output. There are a unit 547, a movement destination estimation unit 548, and the like.
  • the movement destination estimation unit 548 estimates the camera 300 located at the movement destination of the person who could not detect the face area based on the result detected by the posture detection unit 243. For example, when the face area detection unit 242 cannot detect the face area even by reconfirmation, the movement destination estimation unit 548 refers to the posture information 235 and acquires information indicating the installation position of the camera 300. Then, the movement destination estimation unit 548 estimates the camera 300 located at the movement destination of the person based on the posture information 235 and the information indicating the installation position of the camera 300.
  • FIG. 10 is a diagram for explaining an example of estimation by the movement destination estimation unit 548.
  • the body of a person is generally oriented in the moving direction. Therefore, it can be estimated that the direction in which the body of the person is facing, which is determined based on the posture information 235, is the moving direction of the person.
  • the movement destination estimation unit 548 is a camera 300 in which the camera 300 located ahead of the estimated movement direction of the person is located at the movement destination of the person based on the posture information 235 and the information indicating the installation position of the camera 300. Presumed to be.
  • the movement destination estimation unit 548 may be configured to extract a movement locus of a person or the like based on image data of a plurality of frames and estimate whether the camera 300 is located at the movement destination based on the extracted movement locus. No. The movement destination estimation unit 548 may perform estimation by combining estimation based on the result detected by the posture detection unit 243 and estimation based on the movement locus.
  • the parameter adjustment unit 545 adjusts the parameters used in the face authentication process such as the parameters used when the camera 300 acquires the image data and the face detection threshold value.
  • the parameter adjustment unit 545 determines the parameters for the area estimated by the face area estimation unit 244. Make adjustments. Specifically, for example, the parameter adjusting unit 245 causes the camera 300-1 to adjust the parameters used when the camera 300-1 acquires the image data for the area estimated by the face area estimation unit 244. To instruct. As a result, the camera 300-1 corrects the parameters and acquires image data using the corrected parameters.
  • the parameter adjustment unit 545 is a parameter used when acquiring image data for the camera 300 estimated by the movement destination estimation unit 548. Instruct to make adjustments. Further, the parameter adjusting unit 545 can adjust the parameters used when the face area detecting unit 242 detects the face area, such as lowering the face detection threshold value.
  • the parameter adjusting unit 545 when the parameter adjustment unit 545 adjusts the parameters of the moving destination camera 300, the parameter adjusting unit 545 instructs the camera 300 estimated by the moving destination estimation unit 548 to adjust the parameters.
  • the output unit 547 outputs the authentication result information 236 indicating the result of the authentication process by the face recognition unit 246.
  • the output by the output unit 547 is performed, for example, by displaying the screen on the screen display unit 210 or transmitting the output to the external device via the communication I / F unit 220.
  • the output unit 547 can output information such as a specific target person specified by authentication by the face recognition unit 246, and can also output information indicating the movement direction of the person estimated by the movement destination estimation unit 548. ..
  • information indicating the moving direction By outputting information indicating the moving direction together with information such as the specified target person, the person who received the output from the output unit 547 can know the moving direction of the specific target, and the specific target person can be known more quickly. Will be able to be found.
  • step S105 is the same as the operation of the face recognition device 200 described in the first embodiment. If the face area cannot be detected for a predetermined time after the process of step S105 (step S106, No), the movement destination estimation unit 548 estimates the camera 300 located at the movement destination of the person (step S106). S201).
  • the parameter adjustment unit 545 instructs the camera 300 estimated by the movement destination estimation unit 548 to adjust the parameters used when acquiring the image data. Further, the parameter adjusting unit 245 adjusts the parameters used when the face area detecting unit 242 detects the face area, such as lowering the face detection threshold value (step S107). Subsequent processing is the same as the operation of the face recognition device 200 described in the first embodiment.
  • the face recognition device 500 has a movement destination estimation unit 548 and a parameter adjustment unit 245.
  • the parameter adjusting unit 245 can instruct the camera 300 estimated by the moving destination estimation unit 548 to adjust the parameters used when acquiring the image data.
  • the parameter adjusting unit 245 can instruct the camera 300 estimated by the moving destination estimation unit 548 to adjust the parameters used when acquiring the image data.
  • it is possible to suppress an increase in the frame rate of the camera 300, which is not the destination it is possible to suppress a situation in which the amount of data communication is unnecessarily increased.
  • the movement destination estimation unit 548 may utilize the movement destination estimation information 238 stored in the storage unit 230 as shown in FIG. 12 when estimating the camera 300 located at the movement destination.
  • the movement destination estimation information 238 includes information indicating the position of the camera 300, information indicating the movement tendency of a person in each time zone, such as many people heading in this direction in the morning time zone, clothes, and belongings. , Gender, age, and other information indicating the movement tendency of each person's attributes can be included.
  • the destination estimation information 238 may include information other than the above-exemplified information used when estimating the destination.
  • the face recognition system 400 and the face recognition device 500 can take various modified examples as in the case described in the first embodiment.
  • FIG. 13 is a diagram showing a configuration example of the face recognition system 600.
  • FIG. 14 is a block diagram showing a configuration example of the face recognition device 700.
  • FIG. 15 is a diagram showing an example of authentication-related information 732.
  • FIG. 16 is a block diagram showing a configuration example of the camera 800.
  • FIG. 17 is a flowchart showing an operation example of the face recognition device 700.
  • the face recognition system 600 that detects the face area and performs face recognition will be described.
  • the face recognition system 600 manages person-related information such as the color of clothes and belongings of a person whose face has been authenticated. Further, when it is determined that a person having an unauthenticated feature is reflected in the image data based on the person-related information, the face recognition system 600 enlarges the face of the person by optical zoom, digital zoom, or the like. Instruct the camera 800.
  • FIG. 13 shows an overall configuration example of the face recognition system 600.
  • the face recognition system 600 includes a face recognition device 700 and a camera 800. As shown in FIG. 13, the face recognition device 700 and the camera 800 are connected so as to be able to communicate with each other.
  • FIG. 13 illustrates a case where the face recognition system 600 has one camera 800.
  • the number of cameras 800 included in the face recognition system 600 is not limited to one.
  • the face recognition system 600 may have a plurality of cameras 800 of two or more.
  • the face recognition device 700 functions as the face recognition device 200 and the face recognition device 500 described in the first embodiment and the second embodiment. You may have it.
  • the face recognition device 700 is an information processing device that performs face recognition based on the image data acquired by the camera 800. For example, when it is determined that a person having an unauthenticated feature is reflected in the image data based on the person-related information to be managed by the face recognition device 700, the person or the person may be subjected to optical zoom, digital zoom, or the like. Instruct the camera 800 to magnify the face. Then, the face recognition device 700 detects the face region and performs face recognition based on the enlarged image data of the person.
  • FIG. 14 shows a configuration example of the face recognition device 700. Referring to FIG. 14, the face recognition device 700 has, for example, a screen display unit 710, a communication I / F unit 720, a storage unit 730, and an arithmetic processing unit 740 as main components. ..
  • the configuration of the screen display unit 710 and the communication I / F unit 720 may be the same as the screen display unit 210 and the communication I / F unit 220 described in the first embodiment and the second embodiment. Therefore, the description thereof will be omitted.
  • the storage unit 730 is a storage device such as a hard disk or a memory.
  • the storage unit 730 stores processing information and a program 734 required for various processes in the arithmetic processing unit 740.
  • the program 734 realizes various processing units by being read and executed by the arithmetic processing unit 740.
  • the program 734 is read in advance from an external device or a recording medium via a data input / output function such as the communication I / F unit 720, and is stored in the storage unit 730.
  • the main information stored in the storage unit 730 includes, for example, detection information 731, authentication-related information 732, and image information 733.
  • the detection information 731 may be the same as the detection information 231 described in the first embodiment or the second embodiment. Therefore, the description thereof will be omitted.
  • the authentication-related information 732 includes information indicating the amount of facial features used when the face authentication unit 745 performs face authentication. In addition, the authentication-related information 732 includes information indicating whether or not the user has been authenticated, and person-related information such as the color of a person's clothes and belongings.
  • FIG. 15 shows an example of authentication-related information 732.
  • the authentication-related information 732 for example, information indicating the feature amount of a person, identification information such as a name, presence / absence of detection indicating whether or not authentication has been performed, the color of clothes, and belongings. And are associated with each other.
  • the authentication-related information 732 may include person-related information other than the color of clothes and belongings.
  • the image information 733 includes the image data acquired by the camera 800.
  • the image information 733 for example, the image data and the information indicating the date and time when the camera 800 acquired the image data are associated with each other.
  • the camera 800 may acquire image data obtained by enlarging a person or a face in response to an instruction from the face recognition device 700. Therefore, the image information 733 includes image data obtained by enlarging a person or a face.
  • the arithmetic processing unit 740 has a microprocessor such as an MPU and its peripheral circuits, and by reading and executing the program 734 from the storage unit 730, the hardware and the program 734 are linked to realize various processing units. do.
  • the main processing units realized by the arithmetic processing unit 740 include, for example, an image acquisition unit 741, a feature detection unit 742, an enlargement instruction unit 743, a face area detection unit 744, and a face recognition unit 745.
  • the image acquisition unit 741 acquires the image data acquired by the camera 800 from the camera 800 via the communication I / F unit 720. Then, the image acquisition unit 741 stores the acquired image data in the storage unit 730 as image information 733 in association with, for example, the acquisition date and time of the image data.
  • the feature detection unit 742 Based on the image data included in the image information 733, the feature detection unit 742 detects the person-related information which is the characteristic information of the person such as the color of the clothes worn by the person and the belongings of the person.
  • the feature detection unit 742 may use a known technique to detect the color of a person's clothes, belongings, and the like.
  • the face recognition device 700 has a function such as a posture detection unit (posture detection unit 243 described in the first embodiment)
  • the result detected by the posture detection unit is used to determine the color of a person's clothes, belongings, and the like. May be detected.
  • the expansion instruction unit 743 confirms whether or not the person-related information detected by the feature detection unit 742 is stored in the authentication-related information 732 as authenticated. Then, when the person-related information detected by the feature detection unit 742 is not stored in the authentication-related information 732 as authenticated, the enlargement instruction unit 743 asks the camera 800 to enlarge the person having the unstored feature. Instruct. For example, the enlargement instruction unit 743 may instruct to enlarge the periphery of the person, or may instruct to enlarge the periphery of the face of the person.
  • the face area detection unit 744 detects the face area of a person based on the image data included in the image information 733. Similar to the face area detection unit 242, the face area detection unit 744 can detect the face area using a known technique.
  • the image information 733 includes image data obtained by enlarging a person or a face. Therefore, the face area detection unit 744 can detect the face area of the person or the face based on the enlarged image data of the person or the face.
  • the face recognition unit 745 performs face recognition using the detection result of the face area detection unit 744. Then, the face recognition unit 745 associates the result of face recognition with the person-related information of the authenticated person and stores it in the storage unit 730 as the authentication-related information 732.
  • the process when the face authentication unit 745 performs face authentication may be the same as the face authentication unit 246 described in the first embodiment and the second embodiment. Therefore, the description thereof will be omitted.
  • the above is a configuration example of the face recognition device 700.
  • the camera 800 is a photographing device that acquires image data.
  • FIG. 16 shows a configuration example of the camera 800. Referring to FIG. 16, the camera 800 has, for example, a transmission / reception unit 810, a zoom setting unit 820, and a photographing unit 830.
  • the camera 800 has an arithmetic unit such as a CPU and a storage device.
  • the camera 800 can realize each of the above processing units by executing the program stored in the storage device by the arithmetic unit.
  • the transmission / reception unit 810 transmits / receives data to / from the face recognition device 700 or the like. For example, the transmission / reception unit 810 transmits the image data acquired by the photographing unit 830 to the face recognition device 700. Further, the transmission / reception unit 810 receives a zoom instruction or the like from the face recognition device 700.
  • the zoom setting unit 820 enlarges the instructed person or face based on the zoom instruction received from the face recognition device 700.
  • the zoom setting unit 820 may perform optical zoom or digital zoom based on the zoom instruction.
  • the shooting unit 830 acquires image data.
  • the photographing unit 830 acquires image data obtained by enlarging a person or a face.
  • the image data acquired by the photographing unit 830 can be transmitted to the face recognition device 700 via the transmission / reception unit 810 in association with the date and time when the photographing unit 830 acquired the image data.
  • the above is a configuration example of the camera 800. Subsequently, an operation example of the face recognition device 700 will be described with reference to FIG.
  • the feature detection unit 742 obtains person-related information, which is characteristic information of the person, such as the color of clothes worn by the person and the belongings of the person, based on the image data included in the image information 733. Detect (step S301).
  • the expansion instruction unit 743 confirms whether or not the person-related information detected by the feature detection unit 742 is stored in the authentication-related information 732 as authenticated (step S302).
  • the enlargement instruction unit 743 causes the camera 800 to enlarge the person having the unstored feature.
  • the enlargement instruction unit 743 may instruct to enlarge the periphery of the person, or may instruct to enlarge the periphery of the face of the person.
  • the face area detection unit 744 detects a person's face area based on the image data included in the image information 733 (step S304). Since the zoom is instructed by the process of step S303, the face area detection unit 744 can detect the face area of the person or face based on the enlarged image data of the person or face.
  • the face recognition unit 745 performs face recognition using the detection result of the face area detection unit 744 (step S305). Then, the face recognition unit 745 associates the result of face recognition with the person-related information of the authenticated person and stores it in the storage unit 730 as the authentication-related information 732.
  • the above is an operation example of the face recognition device 700.
  • the face recognition device 700 has a feature detection unit 742, an enlargement instruction unit 743, and a face area detection unit 744.
  • the enlargement instruction unit 743 can instruct the camera 800 to enlarge the person or face based on the result detected by the feature detection unit 742.
  • the face area detection unit 744 can detect the face area by using the image data in which the person or the face is enlarged. This makes it possible to detect the face region with higher accuracy.
  • the face recognition system 600 can have a plurality of cameras 800. Further, the face recognition device 700 can have the functions of the face recognition device 200 and the face recognition device 500 described in the first embodiment and the second embodiment. The face recognition system 600 and the face recognition device 700 may be modified in the same manner as in the first embodiment and the second embodiment.
  • FIGS. 18 and 19 show a configuration example of the detection device 900.
  • the detection device 900 detects a person's face region based on the image data.
  • FIG. 18 shows a hardware configuration example of the detection device 900.
  • the detection device 900 has the following hardware configuration as an example.
  • -CPU Central Processing Unit
  • 901 Arimetic unit
  • ROM Read Only Memory
  • RAM Random Access Memory
  • 903 storage device
  • -Program group 904 loaded in RAM 903
  • a storage device 905 that stores the program group 904.
  • -Drive device 906 that reads and writes the recording medium 910 outside the information processing device.
  • -Communication interface 907 that connects to the communication network 911 outside the information processing device -I / O interface 908 for inputting / outputting data -Bus 909 connecting each component
  • the detection device 900 can realize the functions as the detection unit 921 and the setting change unit 922 shown in FIG. 30 by the CPU 901 acquiring the program group 904 and executing the program group 901.
  • the program group 904 is stored in the storage device 905 or the ROM 902 in advance, for example, and the CPU 901 loads the program group 904 into the RAM 903 or the like and executes the program group 904 as needed.
  • the program group 904 may be supplied to the CPU 901 via the communication network 911, or may be stored in the recording medium 910 in advance, and the drive device 906 may read the program and supply the program to the CPU 901.
  • FIG. 18 shows an example of the hardware configuration of the detection device 900.
  • the hardware configuration of the detection device 900 is not limited to the above case.
  • the detection device 900 may be composed of a part of the above-described configuration, such as not having the drive device 906.
  • the detection unit 921 detects the face area based on the image data acquired by the predetermined photographing device.
  • the setting change unit 922 changes the setting when performing the face area detection process based on the image data acquired by another photographing device based on the result detected by the detection unit 921.
  • the detection device 900 has a detection unit 921 and a setting change unit 922.
  • the setting change unit 922 can change the setting when performing the face area detection process using the image data acquired by another photographing device based on the result detected by the detection unit 921. As a result, it is possible to appropriately adjust the parameters and suppress the omission of detection of the face region.
  • the above-mentioned detection device 900 can be realized by incorporating a predetermined program into the detection device 900.
  • the detection device 900 that detects the face area based on the image data detects the face area based on the image data acquired by a predetermined photographing device.
  • the detection device 900 that detects the face area based on the image data detects the face area based on the image data acquired by the predetermined photographing device. Based on the detected result, the setting for performing the face area detection process based on the image data acquired by another photographing device is changed.
  • the above-mentioned object of the present invention is to have the same operation and effect as the above-mentioned detection device 900. Can be achieved.
  • the detector is The face area is detected based on the image data acquired by a predetermined photographing device, and the face area is detected.
  • a detection method that changes the settings for performing face area detection processing using image data acquired by other imaging devices based on the detected results.
  • (Appendix 2) The detection method described in Appendix 1.
  • a detection method that instructs the other imaging device to adjust the parameters used when the other imaging device acquires the image data based on the detected result.
  • Appendix 3) The detection method according to Appendix 1 or Appendix 2.
  • Appendix 4 The detection method according to any one of Supplementary note 1 to Supplementary note 3.
  • the setting for performing the face area detection process based on the image data acquired by another photographing device is changed.
  • Detection method .. (Appendix 5) The detection method according to any one of Supplementary note 1 to Supplementary note 4. If the face area cannot be detected based on the image data acquired by the predetermined photographing device, the setting for performing the face area detection process based on the image data acquired by the predetermined photographing device is changed to change the face area.
  • a detection method that changes the settings when performing face area detection processing using image data acquired by another imaging device after detecting. (Appendix 6) The detection method according to Appendix 5.
  • a detection method that detects a face area for an area estimated based on the detection result (Appendix 7) The detection method according to any one of Supplementary note 1 to Supplementary note 6.
  • the shooting device in the traveling direction of the person is estimated based on the result of detecting the posture of the person, and the setting for performing the face area detection process based on the image data acquired by the estimated shooting device.
  • the detection method to change (Appendix 8) The detection method according to any one of Supplementary note 1 to Supplementary note 7.
  • a detection method that detects the characteristics of a person and instructs the photographing device to acquire image data in a magnified state based on the detected result (Appendix 9) The detection method according to Appendix 8. A detection method that instructs the photographing device to acquire image data in a magnified state when a feature of an undetected person is detected. (Appendix 10) The detection method according to any one of Supplementary note 1 to Supplementary note 9. Face recognition is performed based on the result of detecting the face area, and A detection method that outputs the result of face recognition and information indicating the direction of travel estimated based on the result of detecting the posture of the person specified as a result of face recognition.
  • a detection unit that detects the face area based on the image data acquired by a predetermined photographing device, and a detection unit. Based on the result detected by the detection unit, the setting change unit that changes the setting when performing the face area detection process based on the image data acquired by another photographing device, and the setting change unit. Detection device with.
  • the detection device according to Appendix 11, The setting change unit is a detection device that instructs the other imaging device to adjust parameters used when the other imaging device acquires image data based on the result detected by the detection unit.
  • the detection device according to Appendix 12 The detection device according to Appendix 12, The setting changing unit is a detection device that adjusts a face detection threshold value used when performing a face area detection process using image data acquired by another photographing device based on the result detected by the detection unit.
  • the setting changing unit performs the face area detection process based on the image data acquired by another photographing device.
  • a detector that changes the settings when performing.
  • the setting changing unit When the detection unit cannot detect the face area based on the image data acquired by the predetermined photographing device, the setting changing unit performs the face area detection process based on the image data acquired by the predetermined photographing device.
  • a detection device that changes the setting when performing face area detection processing using image data acquired by another photographing device after the detection unit detects the face area by changing the setting at the time of performing. (Appendix 16)
  • the detection device according to Appendix 15, The setting changing unit is an area estimated based on the result of detecting the posture of a person when the detecting unit cannot detect the face area based on the image data acquired by the predetermined photographing device.
  • the detection unit is a detection device that detects a face region with respect to an region estimated based on the result of detecting the posture of a person.
  • the detection device according to any one of Supplementary note 11 to Supplementary note 16. It has a movement destination estimation unit that estimates the imaging device in the direction of travel of the person based on the result of detecting the posture of the person.
  • the setting changing unit is a detection device that changes settings when performing face area detection processing based on image data acquired by the photographing device estimated by the moving destination estimation unit.
  • Appendix 18 The detection device according to any one of Supplementary note 11 to Supplementary note 17.
  • a feature detector that detects the characteristics of a person, Based on the result detected by the feature detection unit, an enlargement instruction unit that instructs the photographing apparatus to acquire image data in an enlarged state of the person, and an enlargement instruction unit.
  • Detection device with. The detection device according to Appendix 18, The enlargement instruction unit is a detection device that instructs a photographing device to acquire image data in an enlarged state when the detection unit detects a feature of an undetected person.
  • the detection device according to any one of Supplementary note 11 to Supplementary note 19.
  • a face recognition unit that performs face recognition based on the result of detecting the face area
  • An output unit that outputs a result of face authentication by the face authentication unit and information indicating a traveling direction estimated based on the result of detecting the posture of a person specified as a result of the face authentication by the face authentication unit.
  • Detection device with. (Appendix 21)
  • a detection unit that detects the face area based on the image data acquired by a predetermined photographing device, and a detection unit.
  • the setting change unit that changes the setting when performing the face area detection process based on the image data acquired by another photographing device, and the setting change unit.
  • a computer-readable recording medium that records programs to achieve this.
  • the programs described in each of the above embodiments and appendices may be stored in a storage device or recorded in a computer-readable recording medium.
  • the recording medium is a portable medium such as a flexible disk, an optical disk, a magneto-optical disk, and a semiconductor memory.
  • Face recognition system 100 Face recognition system 200 Face recognition device 210 Screen display unit 220 Communication I / F unit 230 Storage unit 231 Detection information 232 Learned model 233 Feature information 234 Image information 235 Attitude information 236 Authentication result information 237 Program 238 For destination estimation Information 240 Calculation processing unit 241 Image acquisition unit 242 Face area detection unit 243 Posture detection unit 244 Face area estimation unit 245 Parameter adjustment unit 246 Face recognition unit 247 Output unit 300 Camera 310 Transmission / reception unit 320 Setting unit 330 Imaging unit 400 Face recognition system 500 Face recognition device 540 Calculation processing unit 545 Parameter adjustment unit 547 Output unit 548 Movement destination estimation unit 600 Face recognition system 700 Face recognition device 710 Screen display unit 720 Communication I / F unit 730 Storage unit 731 Detection information 732 Authentication-related information 733 Image Information 734 Program 740 Arithmetic processing unit 741 Image acquisition unit 742 Feature detection unit 743 Enlargement instruction unit 744 Face area detection unit 745 Face recognition unit 800 Camera 810 Transmission /

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Collating Specific Patterns (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Image Analysis (AREA)
PCT/JP2020/014484 2020-03-30 2020-03-30 検出装置 Ceased WO2021199124A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/911,178 US20230147088A1 (en) 2020-03-30 2020-03-30 Detection apparatus
PCT/JP2020/014484 WO2021199124A1 (ja) 2020-03-30 2020-03-30 検出装置
JP2022512519A JP7517412B2 (ja) 2020-03-30 2020-03-30 検出装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/014484 WO2021199124A1 (ja) 2020-03-30 2020-03-30 検出装置

Publications (1)

Publication Number Publication Date
WO2021199124A1 true WO2021199124A1 (ja) 2021-10-07

Family

ID=77928479

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/014484 Ceased WO2021199124A1 (ja) 2020-03-30 2020-03-30 検出装置

Country Status (3)

Country Link
US (1) US20230147088A1 (https=)
JP (1) JP7517412B2 (https=)
WO (1) WO2021199124A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024236933A1 (ja) * 2023-05-16 2024-11-21 コニカミノルタ株式会社 管理装置

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022103285A1 (en) * 2020-11-10 2022-05-19 Motorola Solutions, Inc System and method for improving admissibility of electronic evidence
US12356076B2 (en) * 2022-05-24 2025-07-08 Canon Kabushiki Kaisha Image capture control device, image capture device, image capture control method, and non-transitory computer-readable storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006165822A (ja) * 2004-12-03 2006-06-22 Nikon Corp 電子カメラおよびプログラム
JP2008199514A (ja) * 2007-02-15 2008-08-28 Fujifilm Corp 画像表示装置
JP2011066828A (ja) * 2009-09-18 2011-03-31 Canon Inc 撮像装置、撮像方法及びプログラム
JP2014204375A (ja) * 2013-04-08 2014-10-27 キヤノン株式会社 画像処理システム、画像処理装置、それらの制御方法、及びプログラム
JP2016143157A (ja) * 2015-01-30 2016-08-08 キヤノン株式会社 画像処理装置、画像処理方法、及び画像処理システム

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6003133B2 (ja) * 2012-03-21 2016-10-05 カシオ計算機株式会社 撮像装置、撮像制御方法及びプログラム
JP6922821B2 (ja) * 2018-04-13 2021-08-18 オムロン株式会社 画像解析装置、方法およびプログラム

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006165822A (ja) * 2004-12-03 2006-06-22 Nikon Corp 電子カメラおよびプログラム
JP2008199514A (ja) * 2007-02-15 2008-08-28 Fujifilm Corp 画像表示装置
JP2011066828A (ja) * 2009-09-18 2011-03-31 Canon Inc 撮像装置、撮像方法及びプログラム
JP2014204375A (ja) * 2013-04-08 2014-10-27 キヤノン株式会社 画像処理システム、画像処理装置、それらの制御方法、及びプログラム
JP2016143157A (ja) * 2015-01-30 2016-08-08 キヤノン株式会社 画像処理装置、画像処理方法、及び画像処理システム

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024236933A1 (ja) * 2023-05-16 2024-11-21 コニカミノルタ株式会社 管理装置

Also Published As

Publication number Publication date
JPWO2021199124A1 (https=) 2021-10-07
JP7517412B2 (ja) 2024-07-17
US20230147088A1 (en) 2023-05-11

Similar Documents

Publication Publication Date Title
KR102299847B1 (ko) 얼굴 인증 방법 및 장치
CN108629168B (zh) 脸部验证方法、设备以及计算设备
US7127086B2 (en) Image processing apparatus and method
US10872268B2 (en) Information processing device, information processing program, and information processing method
US9959454B2 (en) Face recognition device, face recognition method, and computer-readable recording medium
US8073206B2 (en) Face feature collator, face feature collating method, and program
US7995807B2 (en) Automatic trimming method, apparatus and program
US8907985B2 (en) Image display device and image display method
US8824739B2 (en) Eyelid-detection device, eyelid-detection method, and recording medium
US20100253495A1 (en) In-vehicle image processing device, image processing method and memory medium
WO2021199124A1 (ja) 検出装置
US11176356B2 (en) Face authentication device having database with small storage capacity
JP2005149144A (ja) 物体検出装置、物体検出方法、および記録媒体
CN103493100B (zh) 眼睑检测装置、眼睑检测方法
US10496874B2 (en) Facial detection device, facial detection system provided with same, and facial detection method
US11367308B2 (en) Comparison device and comparison method
KR102194511B1 (ko) 대표 영상프레임 결정시스템 및 이를 이용한 방법
JP6098133B2 (ja) 顔構成部抽出装置、顔構成部抽出方法及びプログラム
JP6798609B2 (ja) 映像解析装置、映像解析方法およびプログラム
KR20200049936A (ko) 생체 인식 장치 및 방법
JP2014096057A (ja) 画像処理装置
JP2005149145A (ja) 物体検出装置、物体検出方法、およびコンピュータプログラム
US11763596B2 (en) Image capturing support apparatus, image capturing support method, and computer-readable recording medium
KR20210050649A (ko) 모바일 기기의 페이스 인증 방법
CN113191197B (zh) 一种图像还原方法及装置

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: 20928905

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022512519

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 202217055761

Country of ref document: IN

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20928905

Country of ref document: EP

Kind code of ref document: A1