WO2016035282A1 - Dispositif de détection et système de détection - Google Patents

Dispositif de détection et système de détection Download PDF

Info

Publication number
WO2016035282A1
WO2016035282A1 PCT/JP2015/004265 JP2015004265W WO2016035282A1 WO 2016035282 A1 WO2016035282 A1 WO 2016035282A1 JP 2015004265 W JP2015004265 W JP 2015004265W WO 2016035282 A1 WO2016035282 A1 WO 2016035282A1
Authority
WO
WIPO (PCT)
Prior art keywords
unit
detection
person
predetermined period
abnormality
Prior art date
Application number
PCT/JP2015/004265
Other languages
English (en)
Japanese (ja)
Inventor
利春 竹ノ内
松田　啓史
康洋 森
杭　耕一郎
Original Assignee
パナソニックＩｐマネジメント株式会社
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 パナソニックＩｐマネジメント株式会社 filed Critical パナソニックＩｐマネジメント株式会社
Publication of WO2016035282A1 publication Critical patent/WO2016035282A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
    • 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

Definitions

  • the present invention relates to a detection device and a detection system.
  • the device described in Patent Document 1 needs to control the light emission timing and the light emission amount of the lighting device in order to suppress the occurrence of overexposure. That is, in the device described in Patent Document 1, the light emission of the lighting device is limited in order to suppress the occurrence of overexposure.
  • the present invention has been made in view of the above-described reason, and suppresses erroneous determination of the presence or absence of a person even if an overexposure occurs due to a severe light change in the area of an analysis image. It is an object of the present invention to provide a detection device and a detection system that can perform detection.
  • a detection device includes an imaging unit, a detection unit that detects presence or absence of a person in an analysis target region in an image captured by the imaging unit, and a detection result of the person based on the detection result of the detection unit.
  • a determination unit for determining presence / absence, a deriving unit for deriving a region where the amount of change in luminance in the first predetermined period is equal to or greater than a first threshold in the analysis target region, and a size of the region derived by the deriving unit A determination unit that determines that there is an abnormality if it is greater than or equal to the second threshold, and if the determination unit determines that there is an abnormality, (1) The detection operation is stopped, or (2) the determination unit does not employ the detection result of the presence or absence of a person in the detection unit.
  • a detection system includes an imaging unit, a detection unit that detects presence or absence of a person in an analysis target region in an image captured by the imaging unit, and a detection result of the person based on the detection result of the detection unit.
  • a determination unit for determining presence / absence, a deriving unit for deriving a region where the amount of change in luminance in the first predetermined period is equal to or greater than a first threshold in the analysis target region, and a size of the region derived by the deriving unit A determination unit that determines that there is an abnormality if it is greater than or equal to the second threshold, a transmission unit that transmits a control signal to the control target based on the determination result of the presence or absence of a person in the determination unit, and a load that is to be controlled
  • the determination unit determines that there is an abnormality, in the second predetermined period starting after the determination that there is an abnormality, (1) the detection unit stops the detection operation, or (2) the determination unit detects the detection unit. Do not use detection
  • the detection device and the detection system according to the present invention can suppress erroneous determination of the presence or absence of a person even if overexposure occurs due to a severe light change in the area of the analysis image.
  • FIG. 1 is a block diagram of a detection device and a detection system according to Embodiment 1 of the present invention.
  • FIG. 2 is a flowchart showing an example of the operation of the detection apparatus according to the first embodiment of the present invention.
  • FIG. 3 is a block diagram of a detection device and a detection system according to Embodiment 2 of the present invention.
  • FIG. 4 is a flowchart showing an example of the operation of the detection apparatus according to the second embodiment of the present invention.
  • FIG. 5 is a flowchart showing an example of the operation of the detection apparatus according to the third embodiment of the present invention.
  • FIG. 6 is a flowchart illustrating an example of the operation of the detection apparatus according to the fourth embodiment of the present invention.
  • Embodiment 1 the detection apparatus 100 and the detection system 120 according to Embodiment 1 of the present invention will be described with reference to FIGS. 1 and 2.
  • FIG. 1 is a block diagram of the detection device 100 and the detection system 120. As shown in FIG. 1, the detection device 100 includes an imaging unit 2 and a control unit 3.
  • the imaging unit 2 captures an image (specifically, a moving image) including an analysis target region in which the detection device 100 detects the presence or absence of a person.
  • the imaging unit 2 is a CCD camera or a CMOS camera.
  • the control unit 3 includes a detection unit 31, a determination unit 34, a derivation unit 33, and a determination unit 35.
  • the control unit 3 is realized by a processor, a microcomputer, a dedicated circuit, or the like.
  • the detection unit 31 detects the presence or absence of a person in the analysis target area in the image captured by the imaging unit 2.
  • the determination unit 34 determines the presence or absence of a person in the area of the analysis image based on the detection result of the detection unit 31.
  • the deriving unit 33 derives an area (hereinafter referred to as “luminance change area”) in which the luminance change amount in the predetermined period T1 (first predetermined period) is equal to or greater than the first threshold S1 in the analysis target area.
  • the determining unit 35 determines that there is an abnormality if the size of the luminance change region derived by the deriving unit 33 is equal to or greater than the second threshold S2.
  • the analysis target area may be, for example, a partial area of the image captured by the imaging unit 2 or the entire area of the image captured by the imaging unit 2.
  • the control unit 3 further includes a storage unit 32 that stores the length of the predetermined period T1, the length of the predetermined period T2, the first threshold value S1, and the second threshold value S2.
  • the storage unit 32 is realized by a semiconductor memory or the like.
  • the determining unit 35 determines that there is an abnormality if the size of the luminance change region derived by the deriving unit 33 is equal to or greater than the second threshold S2.
  • the luminance change amount in the predetermined period T1 is greater than or equal to the first threshold value S1 due to a change in the operation mode of the control target to be described later or a severe light change caused by a disturbance in the analysis target area. If there is a region, the deriving unit 33 derives a luminance change region. And the determination part 35 will determine with abnormality, if the magnitude
  • the detection method in which the detection unit 31 detects the presence or absence of a person is not particularly limited.
  • the detection unit 31 may detect the presence / absence of a person based on the difference between the analysis image data and the background image data, or may detect the presence / absence of a person based on the difference between the analysis image data between frames. Also good.
  • the determination unit 34 determines the presence / absence of a person based on the detection result of detecting the presence / absence of a person in the detection unit 31.
  • the determination unit 35 determines that there is an abnormality, that is, when a severe light change occurs
  • the determination unit 34 starts a predetermined period T2 (second predetermined period) that starts after the determination unit 35 determines that there is an abnormality. Then, the judgment is stopped. That is, the determination unit 35 does not employ the detection result of the presence or absence of the person in the detection unit 31.
  • the predetermined period T1 is, for example, a fixed period (for example, 0.5 seconds) stored in advance in the storage unit 32, but may be a period between frames.
  • the period between frames is, for example, 0.033 seconds, but is not particularly limited.
  • the predetermined period T2 is, for example, a period corresponding to a period in which a severe light change occurs. That is, the predetermined period T2 corresponds to, for example, a period from when the determination unit 35 determines that there is an abnormality to when it recovers from the abnormality.
  • FIG. 2 is a flowchart showing an example of the operation of the detection apparatus 100.
  • step S21 the deriving unit 33 derives a luminance change region in which the luminance change amount in the predetermined period T1 is equal to or greater than the first threshold S1 in the analysis target region, and the process proceeds to step 22. Note that, in the analysis target region, when the amount of change in luminance during the predetermined period T1 is less than the first threshold value S1, the luminance change region is not derived.
  • step S22 the determination unit 35 determines that there is an abnormality when the size of the luminance change region is equal to or larger than the second threshold value S2 (YES in step S22), and the operation proceeds to step S23.
  • the size of the luminance change area is less than the second threshold value S2 (NO in step S22)
  • the operation returns to step S21, and the deriving unit 33 has the luminance change amount in the predetermined period T1 within the analysis target area. The presence / absence of a luminance change region that is equal to or greater than the threshold value S1 is confirmed.
  • the method for deriving the size of the luminance change region is not particularly limited.
  • the deriving unit 33 may derive the number of pixels constituting the luminance change region as the size of the luminance change region, or may set the total area of the pixels as the size of the luminance change region.
  • step S23 when the determination unit 35 determines that there is an abnormality, the determination unit 34 does not employ the detection result of the detection unit 31 until the predetermined period T2 has passed (step S23a).
  • step S23b when the predetermined period T2 has passed (YES in step S23b), the determination unit 34 continues to determine the presence / absence of a person based on the detection result of the presence / absence of the person in the detection unit 31 (step S24). ).
  • the detection unit 31 detects the presence or absence of a person in the analysis target area imaged by the imaging unit 2 in parallel with steps S21 to S24. Not limited to this, for example, the operations of steps S21 to S24 are not periodically performed, but when the detection unit 31 detects the presence of a person in the analysis target region imaged by the imaging unit 2. The operations of steps S21 to S24 may be performed. In this case, it is possible to save power in the detection device 100 as compared with the case where the operations of steps S21 to S24 are performed periodically. Further, when the determination unit 34 determines that there is a person based on the detection result of the detection unit 31, the operations in steps S21 to S24 may be performed.
  • the detection system 120 includes the detection device 100, a transmission unit 4 that transmits a control signal to a control target based on the determination result of the presence or absence of a person in the determination unit 34, and a load 5 that is a control target. .
  • the detection unit 31 may not be provided in the detection device 100.
  • the detection unit 31 may be externally attached to the detection device 100 as a device different from the detection device 100.
  • the load 5 is a lighting device having at least two operation modes of “light-off” and “light-on”, but is not limited thereto.
  • the load 5 may be an electric device having at least two operation modes such as an air conditioner (an air conditioner that adjusts indoor temperature and humidity) and a cooking device.
  • the transmission unit 4 transmits a control signal instructing “lighting” to the load 5.
  • the transmission unit 4 transmits a control signal that instructs the load 5 to “turn off”.
  • the transmission method of the control signal from the transmission part 4 to the load 5 is not specifically limited.
  • the transmission unit 4 may transmit the control signal directly to the load 5 or may indirectly transmit it via a repeater (not shown).
  • the load 5 When the load 5 receives a control signal instructing “lighting” from the transmission unit 4, the load 5 switches from the “lighting off” operation mode to the “lighting” operation mode. At that time, a severe light change occurs in the image captured by the imaging unit 2. Therefore, the detection unit 31 may not be able to detect a person due to such a light change, or may be erroneously detected.
  • the determination unit 34 when the determination unit 35 determines that there is an abnormality, the determination unit 34 does not adopt the detection result of the detection unit 31 in the predetermined period T2. Accordingly, even if an error occurs in detection of the detection target by the detection unit 31 due to a change in the operation mode of the load 5 or an intense light change in the image due to a disturbance, the error hardly occurs.
  • the detection device 100 and the detection system 120 can determine the presence or absence of a person with high accuracy.
  • the detection apparatus 100 and the detection system 120 can suppress erroneous determination of the presence or absence of a person when an overexposure occurs due to a severe light change in the analysis target region.
  • the determination unit 34 does not employ the detection result of the presence / absence of a person in the predetermined period T2 corresponding to the period in which the above-described intense light change occurs. Thereby, the determination part 34 can determine the presence or absence of a person continuously based on the detection result of the detection part 31, if the abnormality by the above-mentioned intense light change is lost. Therefore, the detection device 100 and the detection system 120 can determine the presence or absence of a person with higher accuracy.
  • the control unit 3 includes a detection unit 31, a storage unit 32, a derivation unit 33, a determination unit 34, and a determination unit 35, and the transmission unit 4 is externally attached to the control unit 3.
  • the distribution of the constituent elements is not particularly limited.
  • the control unit 3 may include the transmission unit 4, and the storage unit 32 may be externally attached as a separate device from the control unit 3.
  • the detection part 31 may stop the detection operation. In this case, since the detection unit 31 stops the detection operation, it is possible to suppress erroneous determination of the presence / absence of a person even if an overexposure occurs due to a severe light change in the analysis target region.
  • the imaging unit 2 may increase the frame rate.
  • the imaging unit 2 can shorten the feedback period by increasing the frame rate. That is, the imaging unit 2 can shorten the period from when a severe light change occurs until the severe light change settles (recovers to a normal light change).
  • the predetermined period T2 may be shorter than a period in which a severe light change occurs (a period until the severe light change settles), depending on the use environment and purpose of use of the detection device 100 and the detection system 120. You may make it a period longer than the period when the intense light change has generate
  • the determination unit 34 immediately detects the presence or absence of the person in the detection unit 31 even after the intense light change has ended. The result will not be adopted. In this manner, the determination unit 34 determines the presence / absence of the person with higher accuracy by determining the presence / absence of the person based on the detection result of the presence / absence of the person in the detection unit 31 over a period of time. can do.
  • the length of the predetermined period T2 is stored in the storage unit 32 in advance, the length is not limited thereto.
  • the determination unit 35 determines the end of the presence of abnormality, and the period from when the determination unit 35 determines that there is an abnormality to when it is determined that the presence of abnormality ends is the predetermined period T2. May be.
  • the detection apparatus 100 can adjust the length of the predetermined period T2 according to a change in the surrounding environment.
  • the means for determining that the above-described abnormality is finished is not particularly limited.
  • the deriving unit 33 derives an area in the analysis target area in which the luminance change amount in the predetermined period T1 is equal to or smaller than the third threshold S3 in the predetermined period T2, and the determination unit 35 is an area derived by the deriving unit 33. If the magnitude of is greater than or equal to the second threshold value, it may be determined that the presence of abnormality ends. Further, the determination unit 35 may determine that the presence of abnormality ends based on the gain recovery state of the imaging unit 2, the exposure period of the imaging unit 2, and the luminance value in the analysis target area.
  • the detection device 200 and the detection system 220 include the detection device 100 and the detection system 120, and a creation unit 36 that creates a presence region that surrounds the detected person when the control unit 3 further detects that the detection unit 31 has a person. And the operation of the determination unit 34 differ from the detection device 100 and the detection system 120.
  • symbol is attached
  • FIG. 3 is a block diagram of the detection device 200 and the detection system 220. As shown in FIG. 3, the control unit 3 further includes a creation unit 36.
  • the creation unit 36 When the detection unit 31 detects the presence of a person, the creation unit 36 creates a rectangular existence area so as to surround the person based on the width and height of the person in the analysis target area. To do.
  • the creation unit 36 may create an existence area for each frame, or create an existence area for each predetermined number of frames.
  • the creation unit 36 starts at the same time as the second predetermined period based on the existence area created by the creation unit 36 immediately before the determination unit 35 determines that there is an abnormality. Then, a virtual existence area that is assumed to exist when a person exists in a predetermined period T3 (third predetermined period) having a length equal to or longer than the predetermined period T2 is created in the analysis target area.
  • the shapes of the existence area and the virtual existence area are not limited to rectangular shapes.
  • the shape of the existence area and the virtual existence area may be, for example, a rhombus.
  • the creation unit 36 will be described assuming that the existence region created immediately before the determination unit 35 determines that there is an abnormality is a virtual existence region in the predetermined period T2, but the creation method of the virtual existence region is not particularly limited.
  • the creation unit 36 may create a virtual existence area based on the existence area created before the determination unit 35 immediately before determining that there is an abnormality.
  • the determination unit 34 determines whether or not there is a person based on the creation result of the creation unit 36. That is, the determination unit 34 determines that there is a person if at least one of the existence area and the virtual existence area exists, and if both the existence area and the virtual existence area do not exist, there is no person. to decide.
  • FIG. 4 is a flowchart showing an example of the operation of the detection apparatus 200. Steps S41 and S45 are the same as steps S21 and S24 in FIG.
  • step S42 when the size of the luminance change region derived by the deriving unit 33 in step S41 is greater than or equal to S2 (YES in step S42), the determination unit 35 determines that there is an abnormality, and the operation of the detection device 200 is performed in step S44. Proceed to. When the size of the brightness change area is less than the second threshold S2 (NO in step S42), the operation of the detection device 200 returns to step S41, and the deriving unit 33 continues to derive the brightness change area.
  • step S44 the determination unit 34 does not adopt the detection result of the detection unit 31 in the predetermined period T2 (step S44a). Then, the creation unit 36 creates the person's presence area detected by the detection unit 31 created immediately before the determination unit 35 determines that there is an abnormality as the virtual existence area of the person (step S44b).
  • step S44b may be performed simultaneously with step S44a.
  • step S44c when the predetermined period T2 has passed (YES in step S44c), the determination unit 34 adopts the detection result of the presence / absence of the person in the detection unit 31, and based on the adopted detection result, the presence of the person is detected. The presence or absence is determined (step S45).
  • step S46 If it is less than the predetermined period T3 having a length equal to or longer than the predetermined period T2 in step S46 (NO in step S46), the process returns to step S45.
  • step S46 when the predetermined period T3 has passed (YES in step S46), the creation unit 36 releases the virtual existence area created in step S44b (step S48) and returns to step S41.
  • the predetermined period T2 and the predetermined period T3 may be counted simultaneously, or for example, the predetermined period T3 ′ may begin to be counted after the predetermined period T2 ends.
  • the length of the predetermined period T3 ′ may be a length obtained by subtracting the length of the predetermined period T2 from the length of the predetermined period T3.
  • the length of the predetermined period T3 is stored in the storage unit 32.
  • the predetermined period T3 is longer than the predetermined period T2. For this reason, the creation unit 36 does not immediately release the virtual existence area after the predetermined period T2 ends, that is, after the abnormality due to the occurrence of a severe light change, but does not cancel the virtual existence area after a certain period. In other words, after the predetermined period T2 ends, even if the detection unit 31 detects that there is no person, the determination unit 34 does not immediately determine that there is no person, but only after the virtual existence area is released. Judge that there is no person.
  • the detection unit 31 detects the presence of a person when the person stays within the region of the analysis image after the abnormality due to the occurrence of a severe light change or when the person's movement is small. There are cases where it is not possible. In such a case, the determination unit 34 does not immediately determine that there is no person, but when the detection unit 31 continuously detects that there is no person until the virtual existence area is released, Judge that there is no person. Therefore, the detection device 200 and the detection system 220 can determine the presence or absence of a person with higher accuracy.
  • the creation unit 36 creates (displays) the presence area of the person.
  • the determination unit 35 determines that there is an abnormality
  • the creation unit 36 creates a virtual existence region based on the existence region created by the creation unit 36 immediately before the determination unit 35 determines that there is an abnormality in a predetermined period T3.
  • the creation unit 36 releases the created virtual existence area after a predetermined period T3.
  • the determination unit 34 determines that there is a person if the virtual existence area exists.
  • the detection device 200 and the detection system 220 may be erroneous even if an error occurs in detection of the detection target by the detection unit 31 when a severe light change occurs in the analysis image due to switching of the operation mode of the load 5 or due to disturbance. Therefore, it can be determined that there is no person.
  • the detection unit 31 within the region of the analysis image within the existence region.
  • the presence or absence of a person may be detected with higher accuracy than other areas, for example, in units of images.
  • the detection device 200 and the detection system 220 can detect the presence or absence of a person with higher accuracy.
  • the creation unit 36 may create a region larger than the existence region as a virtual existence region based on the existence region created immediately before the determination unit 35 determines that there is an abnormality. Further, the creation unit 36 may create an area that is shifted from the position of the existence area by a predetermined distance (for example, 10 pixels) in the movement direction of the person as a virtual existence area. It can also be assumed that the person detected by the detection unit 31 moves in the predetermined period T2. Accordingly, the creation unit 36 creates an area larger than the existence area or an area that is shifted from the position of the existence area by a predetermined distance in the direction of movement of the person as a virtual existence area, so that the detection unit 31 is highly accurate with high accuracy. It is possible to detect the presence or absence of.
  • step 44a the determination unit 34 has been described that, when the determination unit 35 determines that there is an abnormality, the detection result of the presence or absence of the person in the detection unit 31 is not adopted in the predetermined period T2. Similarly to the above, in the predetermined period T2, the detection unit 31 may stop the detection operation.
  • the detection device 300 and the detection system 320 mainly detect that the detection unit 31 is present between the detection device 200 and the detection system 220 and the predetermined period T3 until the predetermined period T3 ends.
  • the derivation unit 33 differs from the detection device 200 and the detection system 220 in that the derivation unit 33 derives the virtual movement distance of the person detected by the detection unit 31 and the operation of the creation unit 36.
  • symbol is attached
  • the derivation unit 33 detects the presence or absence of a person by the detection unit 31 and based on the movement status of the person detected by the detection unit 31 in a predetermined period T4 (fourth predetermined period).
  • the moving speed of is derived.
  • the deriving unit 33 derives the distance between the center of the existing area in a certain frame and the center of the existing area in the frame in which a predetermined period T4 has elapsed from the frame as the movement distance of the person.
  • the value obtained by dividing by the predetermined period T4 is defined as the movement speed of the person.
  • the deriving unit 33 sets a value obtained by multiplying the derived movement speed of the person by the predetermined period T2 as a virtual movement distance.
  • the length of the predetermined period T4 may be a predetermined period (for example, 0.2 seconds) stored in the storage unit 32 in advance, or may be an interval between two consecutive frames (for example, 0.033 seconds).
  • the deriving unit 33 may periodically update the movement speed of the person detected by the detection unit 31 until the determination unit 35 determines that there is an abnormality. For example, when the predetermined period T4 is set to an interval of two consecutive frames, the deriving unit 33 derives the movement speed of the person for each frame and stores it in the storage unit 32, and immediately before the determination unit 35 determines that there is an abnormality.
  • the virtual moving distance is derived based on the moving speed of the person stored in the.
  • the creating unit 36 creates a presence area again. Then, the creation unit 36 compares the distance between the existence area created after the predetermined period T2 ends and the virtual existence area with the virtual movement distance, and cancels the virtual existence area if the distance is less than the virtual movement distance, Leave.
  • the method of deriving the distance between the existence area and the virtual existence area is not particularly limited.
  • the deriving unit 33 may derive the distance between the center of the existence area and the center of the virtual existence area as the distance between the existence area and the virtual existence area, or the maximum distance between the virtual existence area and the existence area.
  • the distance between two points close to each other may be derived as the distance between the existence area and the virtual existence area.
  • FIG. 5 is a flowchart showing an example of the operation of the detection apparatus 300.
  • Step S51 is the same as step S45 of the second embodiment. That is, the flowchart of the operation of the detection apparatus 300 illustrated in FIG. 5 is a continuation of step S45 of the second embodiment.
  • step S52 when the detection unit 31 detects the presence of a person (YES in step S52), the creation unit 36 creates a presence area of the detected person (step S53), and the operation of the detection apparatus 300 is step. Proceed to 54. Otherwise (NO in step S52), the operation of detection device 300 proceeds to step S56.
  • step S54 if the distance between the existence area and the virtual existence area is less than the virtual movement distance (YES in step S54), the creation unit 36 releases the virtual existence area (step S55), and the operation of the detection device 300 is performed. Advances to step S56. Otherwise (YES in step S54), the operation of the detection device 300 proceeds to step S56.
  • step S56 the determination unit 34 determines the presence or absence of a person based on the existence area or the virtual existence area created by the creation unit 36. That is, the determination unit 34 determines that there is a person if there is at least one of the existence area or the virtual existence area. If both the existence area and the virtual existence area do not exist, the existence of the person is determined. Judge that there is no.
  • the detection device 300 continues to detect the presence / absence of a person by the detection unit 31.
  • the determination unit 34 determines that there is no person because there is no existence area. At this time, if the predetermined period T3 is set to be longer than the predetermined period T2, even if the detection unit 31 detects that there is no person after the predetermined period T2, that is, after the period of intense light change ends, it is determined. The unit 34 does not immediately determine that there is no person. The determination unit 34 determines that there is no person when it is detected that there is no person continuously after a certain period of time.
  • the creation unit 36 releases the virtual existence region if the distance between the existence region created after the end of the second predetermined period and the virtual existence region is less than the virtual movement distance based on the detection result of the detection unit 31.
  • the detection device 300 and the detection system 320 can determine whether the person detected after the intense light change occurs and the person detected before the intense light change are the same person. That is, the detection apparatus 300 and the detection system 320 are more accurate than the detection apparatus 200 and the detection system 220 when a plurality of persons exist in the region of the analysis image after a severe light change occurs. The presence or absence can be detected.
  • the detection apparatus 400 and the detection system 420 are mainly detected in that the creation unit 36 expands the virtual existence area based on the virtual movement distance between the end of the predetermined period T2 and the end of the predetermined period T3. Different from the device 300 and the detection system 320.
  • symbol is attached
  • the deriving unit 33 derives the virtual movement distance by the same procedure as that of the third embodiment. Then, when the predetermined period T2 ends, the creation unit 36 expands the virtual existence area in the moving direction of the virtual moving distance to a portion corresponding to the virtual moving distance.
  • the direction of the movement speed of the person may be the movement direction, and a movement direction range that can be estimated from the direction of the movement speed of the person, for example, a range of 0 ° to ⁇ 90 ° from the direction of the movement speed of the person.
  • the moving direction may be set. In that case, the virtual existence area is expanded to a range corresponding to the virtual movement distance in the range of 0 ° to ⁇ 90 ° from the direction of the movement speed of the person.
  • the creation unit 36 creates a presence area again. Then, the creation unit 36 compares the distance between the existence area created after the predetermined period T2 ends and the virtual existence area after the area is expanded with the virtual movement distance. Release the area.
  • FIG. 6 is a flowchart showing an example of the operation of the detection device 400. Steps S61 and S63 to S67 are the same as steps S51 to S56 of FIG.
  • step S62 the creation unit 36 expands the virtual existence area based on the virtual movement distance derived by the deriving unit 33.
  • step S62 is not limited.
  • step S62 may be inserted between step S63 and step S64. That is, the creation unit 36 may expand the virtual existence area based on the virtual movement distance after the detection unit 31 detects the presence or absence of a person. Further, step S62 may be inserted between step S64 and step S65.
  • step S65 if the distance between the existence region created by the creation unit 36 in step S64 and the virtual existence region expanded in step S62 is less than the virtual movement distance (YES in step S65), the creation unit 36 The virtual existence area is canceled (step S66).
  • the deriving unit 33 derives the virtual movement distance in the predetermined period T2 of the person detected by the detection unit 31 before the determination unit 35 determines that there is an abnormality.
  • the creation unit 36 creates a virtual existence area based on the virtual movement distance in the direction of the movement speed of the person detected by the detection unit 31. To spread. Thereby, the presence area of the person can be specified. Therefore, the detection device 400 and the detection system 420 can detect the presence or absence of a person with higher accuracy than the detection device 300 and the detection system 320.
  • Embodiments 1 to 4 have been described as examples of the technology disclosed in the present application. However, the technology in the present disclosure is not limited to this, and can also be applied to embodiments in which changes, replacements, additions, omissions, and the like have been made as appropriate. In addition, it is possible to combine the components described in the first to fourth embodiments to form a new embodiment.
  • each component may be configured by dedicated hardware, or may be realized by executing a software program suitable for each component.
  • Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.
  • the comprehensive or specific aspect of the present invention may be realized by a system, method, integrated circuit, computer program, or non-transitory recording medium such as a computer-readable CD-ROM. You may implement
  • the present invention may be realized as a human detection method.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Geophysics And Detection Of Objects (AREA)
  • Alarm Systems (AREA)
  • Image Analysis (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

　L'invention concerne un système de détection (120) qui comporte une unité de capture d'image (2) ; une unité de détection (31) pour détecter si une personne existe ou non ; une unité d'évaluation (34) pour évaluer, sur la base du résultat de détection de l'unité de détection (31), si une personne existe ou non dans la zone d'une image d'analyse ; une unité de calcul (33) pour calculer une zone dans laquelle l'amplitude d'un changement de luminance pendant une période prescrite (T1) dans l'image d'analyse est supérieure ou égale à un premier seuil (S1) ; et une unité de détermination (35) pour déterminer qu'il existe une anomalie lorsque la taille de la zone calculée par l'unité de calcul (33) est supérieure ou égale à un second seuil (S2). L'unité d'évaluation (34) comprend un dispositif de détection (100) qui, lorsque l'unité de détermination (35) détermine qu'il existe une anomalie, n'adopte pas le résultat de détection de l'unité de détection (31) pendant une période prescrite (T2), une unité d'émission (4) pour émettre, sur la base du résultat d'évaluation de l'unité d'évaluation (34) déterminant si une personne existe ou non, un signal de commande à un objet à commander, et une charge (5) qui est l'objet à commander.
PCT/JP2015/004265 2014-09-03 2015-08-25 Dispositif de détection et système de détection WO2016035282A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2014-179335 2014-09-03
JP2014179335 2014-09-03

Publications (1)

Publication Number Publication Date
WO2016035282A1 true WO2016035282A1 (fr) 2016-03-10

Family

ID=55439370

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2015/004265 WO2016035282A1 (fr) 2014-09-03 2015-08-25 Dispositif de détection et système de détection

Country Status (2)

Country Link
TW (1) TW201614602A (fr)
WO (1) WO2016035282A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62250783A (ja) * 1986-04-24 1987-10-31 Matsushita Electric Works Ltd 画像監視方式
JP2001008189A (ja) * 1999-04-23 2001-01-12 Hitachi Ltd 移動物体監視装置
JP2009169717A (ja) * 2008-01-17 2009-07-30 Meidensha Corp 画像処理による侵入者検知装置
WO2013187047A1 (fr) * 2012-06-13 2013-12-19 パナソニック株式会社 Dispositif de détection d'objet

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62250783A (ja) * 1986-04-24 1987-10-31 Matsushita Electric Works Ltd 画像監視方式
JP2001008189A (ja) * 1999-04-23 2001-01-12 Hitachi Ltd 移動物体監視装置
JP2009169717A (ja) * 2008-01-17 2009-07-30 Meidensha Corp 画像処理による侵入者検知装置
WO2013187047A1 (fr) * 2012-06-13 2013-12-19 パナソニック株式会社 Dispositif de détection d'objet

Also Published As

Publication number Publication date
TW201614602A (en) 2016-04-16

Similar Documents

Publication Publication Date Title
EP2273450B1 (fr) Suivi et détection de cible dans des images
US10521673B2 (en) Counting persons in queue system, apparatus, method, and storage medium
US9418278B2 (en) Image analysis method, camera apparatus, control apparatus, control method and storage medium
US10863090B2 (en) Control apparatus, image capturing apparatus, control method, and computer-readable storage medium
US8311280B2 (en) Image processing apparatus and image processing method
US10769800B2 (en) Moving object detection apparatus, control method for moving object detection apparatus, and non-transitory computer-readable storage medium
JP2011234226A5 (fr)
US10484591B2 (en) Focus adjusting apparatus, focus adjusting method, and image capturing apparatus
WO2015029588A1 (fr) Système de traitement d'image, procédé de traitement d'image et programme
US20170094237A1 (en) Image processing apparatus, image processing method, and computer-readable storage medium
US20180220113A1 (en) Projection display system, information processing apparatus, information processing method, and storage medium therefor
US11343434B2 (en) Image processing apparatus and control method for same
JP6099023B2 (ja) プロジェクタシステム
JP6664106B2 (ja) 検知装置、検知システム、およびプログラム
US20210056826A1 (en) Information processing apparatus, information processing method, and medium
US11321390B2 (en) Video data generation apparatus, video data generation method, and program
JP2011188332A5 (ja) 画像揺れ補正装置および画像揺れ補正方法
US11172138B2 (en) Image capture apparatus capable of performing HDR combination, method of controlling same, and storage medium
WO2016035282A1 (fr) Dispositif de détection et système de détection
JP6387877B2 (ja) 着席判定装置、着席判定方法、及びプログラム
JP5118590B2 (ja) 被写体追尾方法及び撮像装置
US9215365B2 (en) Imaging apparatus and imaging method
JP6230980B2 (ja) 物体監視装置
JP6766009B2 (ja) 監視装置、監視方法、コンピュータプログラム、及び記憶媒体
JP2015064714A (ja) 遠隔操作装置、遠隔操作方法、および遠隔操作プログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15838535

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15838535

Country of ref document: EP

Kind code of ref document: A1