[go: up one dir, main page]

WO2018154637A1 - Dispositif de détection de vibrations, procédé de détection de vibrations et programme de détection de vibrations - Google Patents

Dispositif de détection de vibrations, procédé de détection de vibrations et programme de détection de vibrations Download PDF

Info

Publication number
WO2018154637A1
WO2018154637A1 PCT/JP2017/006424 JP2017006424W WO2018154637A1 WO 2018154637 A1 WO2018154637 A1 WO 2018154637A1 JP 2017006424 W JP2017006424 W JP 2017006424W WO 2018154637 A1 WO2018154637 A1 WO 2018154637A1
Authority
WO
WIPO (PCT)
Prior art keywords
vibration
moving image
motion
normal
feature information
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/JP2017/006424
Other languages
English (en)
Japanese (ja)
Inventor
山本　英司
勝大 草野
尚吾 清水
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.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric 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 Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Priority to JP2018550857A priority Critical patent/JP6452923B1/ja
Priority to PCT/JP2017/006424 priority patent/WO2018154637A1/fr
Priority to TW106119956A priority patent/TW201832183A/zh
Publication of WO2018154637A1 publication Critical patent/WO2018154637A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H9/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by using radiation-sensitive means, e.g. optical means

Definitions

  • the present invention relates to a vibration detection device, a vibration detection method, and a vibration detection program.
  • the vibration detection method based on video disclosed in Patent Literature 1, in a captured image captured by an imaging unit, a moving component that moves up and down in the image due to vibration is specified, and the movement history of the specified moving component is determined. Frequency analysis is performed to calculate the vibration frequency intensity of the moving component. Next, the vibration detection method extracts a predetermined range of vibration frequencies from the calculated vibration frequency intensity of the moving component. Next, in the vibration detection method, based on the extracted frequency intensity within the predetermined frequency range, a captured image captured at a vibration equilibrium point within the predetermined frequency range is extracted as an equilibrium image. Next, in the vibration detection method, the image speed in the balanced image is calculated, and the image speed generated by the steady vibration is excluded from the captured image using the calculated image speed in the balanced image.
  • the center position of the displacement in the image displaced by the vibration is detected based on the captured image excluding the image speed generated by the steady vibration.
  • the center position of the detected displacement is monitored, and the displacement amount of the image due to the vibration in the image captured by the imaging unit is calculated.
  • Patent Document 1 Since the technique disclosed in Patent Document 1 is known to vibrate in the vertical direction of the screen in advance, a moving component having a concentration gradient in the vertical direction is specified, and the vibration occurs in any direction of the screen There was a problem that could not be applied. In addition, the technique disclosed in Patent Document 1 is intended only to detect vibrations, and there is a problem that abnormal vibrations cannot be detected by determining whether the vibrations are normal vibrations or abnormal vibrations. .
  • the present invention detects a vibration state from an image regardless of which direction the vibration detection target vibrates, and further detects abnormal vibration of the vibration detection target by determining whether the vibration detection target is normal vibration or abnormal vibration. For the purpose.
  • the vibration detection apparatus is A normal feature storage unit for storing normal feature information representing the characteristics of normal vibrations among the vibrations of the vibrating object, Moving image data representing a moving image obtained by photographing the vibrating object is acquired, a motion vector representing the movement of the vibrating object is extracted from the moving image data, and movement is performed for each movement direction range that is a range of the direction of the motion vector.
  • a histogram information generation unit that counts the number of vectors and generates a histogram for each frame of the moving image data as histogram information using the number of motion vectors for each of the motion direction ranges; Using the histogram information, a frequency analysis unit that calculates a frequency of a time-series change in the number of motion vectors for each motion direction range and a frequency component for each frequency as vibration feature information representing the vibration characteristics of the vibrating object.
  • a comparison unit that acquires the normal feature information from the normal feature storage unit, compares the vibration feature information with the normal feature information, and determines whether the vibration feature information has the normal feature information; It was.
  • the normal feature storage unit stores normal feature information representing normal vibration features among the vibrations of the vibrating object.
  • the histogram information generation unit acquires moving image data representing a moving image obtained by photographing the vibrating object, and extracts a motion vector representing the movement of the vibrating object from the moving image data.
  • the histogram generation unit counts the number of motion vectors for each motion direction range that is the range of motion vector directions, and uses the number of motion vectors for each motion direction range to generate a histogram for each frame of moving image data. Generated as histogram information.
  • the frequency analysis unit uses the histogram information to calculate the frequency of the time-series change in the number of motion vectors for each motion direction range and the frequency component for each frequency as vibration feature information representing the vibration characteristics of the vibrating object. To do. Then, the comparison unit compares the vibration feature information with the normal feature information, and determines whether or not the vibration feature information has normal feature information. Therefore, according to the vibration detection device according to the present invention, the vibration state is detected from the image regardless of the direction in which the vibration detection target vibrates, and further, it is determined whether the vibration state is normal vibration or abnormal vibration, Abnormal vibration of the vibration detection target can be detected.
  • FIG. 1 is a configuration diagram of a vibration detection apparatus 100 according to Embodiment 1.
  • FIG. FIG. 6 is a diagram for explaining moving image compression data 11 according to the first embodiment.
  • the flowchart which shows the vibration detection process 610 and the vibration detection process S100 of the vibration detection program 620 which concern on Embodiment 1.
  • FIG. FIG. 3 is a flowchart showing normal vibration extraction processing S10 according to the first embodiment. Frequency components for each frequency obtained by frequency-analyzing the number of motion vectors in a specific motion direction range among motion vectors extracted from an image obtained by capturing a vibration object 502 that is performing normal vibration according to Embodiment 1. Example of arranging them in time series.
  • FIG. 6 is a flowchart showing a vibration feature comparison process S20 according to the first embodiment.
  • FIG. 6 is a configuration diagram of a vibration detection device 100 according to a modification of the first embodiment.
  • the block diagram of the vibration detection apparatus 100a which concerns on Embodiment 2.
  • FIG. 10 is a flowchart showing histogram information generation processing S110a according to the second embodiment.
  • Embodiment 1 FIG. *** Explanation of configuration *** The configuration of the vibration detection apparatus 100 according to the present embodiment will be described with reference to FIG.
  • the vibration detection apparatus 100 is a computer.
  • the vibration detection apparatus 100 includes hardware such as a processor 910, a storage device 920, an input interface 930, and an output interface 940.
  • the storage device 920 includes a memory 921 and an auxiliary storage device 922.
  • the vibration detection apparatus 100 includes a histogram information generation unit 110, a vibration analysis unit 120, and a storage unit 130 as functional configurations.
  • the histogram information generation unit 110 includes a compressed data reception unit 111, a motion vector extraction unit 112, a motion direction calculation unit 113, a motion quantity count unit 114, and a motion histogram generation unit 115.
  • the vibration analysis unit 120 includes a motion quantity extraction unit 121, a frequency analysis unit 122, a normal feature extraction unit 123, a comparison unit 124, and a notification unit 125.
  • the storage unit 130 includes a normal feature storage unit 131.
  • the normal feature storage unit 131 stores normal feature information 301 representing normal vibration features among the vibrations of the vibrating object that vibrates.
  • histogram information 21 is stored in the storage unit 130.
  • the motion quantity extraction unit 121 acquires the histogram information 21 and extracts the quantity of motion vectors for each motion direction range.
  • the functions of the extraction unit 123, the comparison unit 124, and the notification unit 125 are realized by software.
  • the compressed data receiving unit 111, the motion vector extracting unit 112, the motion direction calculating unit 113, the motion quantity counting unit 114, the motion histogram generating unit 115, the motion quantity extracting unit 121, and the frequency analyzing unit 122, the normal feature extraction unit 123, the comparison unit 124, and the notification unit 125 are referred to as the histogram information generation unit 110 and the vibration analysis unit 120, respectively.
  • the storage unit 130 is realized by the memory 921.
  • the storage unit 130 may be realized only by the auxiliary storage device 922 or by the memory 921 and the auxiliary storage device 922. A method for realizing the storage unit 130 is arbitrary.
  • the processor 910 is connected to other hardware via a signal line, and controls these other hardware.
  • the processor 910 is an IC (Integrated Circuit) that performs arithmetic processing.
  • Specific examples of the processor 910 are a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and a GPU (Graphics Processing Unit).
  • the memory 921 is a storage device that temporarily stores data. Specific examples of the memory 921 are SRAM (Static Random Access Memory) and DRAM (Dynamic Random Access Memory).
  • the auxiliary storage device 922 is a storage device that stores data.
  • a specific example of the auxiliary storage device 922 is an HDD (Hard Disk Drive).
  • the auxiliary storage device 922 includes an SD (registered trademark) (Secure Digital) memory card, a CF (Compact Flash), a NAND flash, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, a DVD (Digital Versatile Disk), and the like. It may be a portable storage medium.
  • the input interface 930 is a port connected to an imaging device such as the camera 504.
  • the input interface 930 acquires the moving image compressed data 11 representing the moving image captured by the camera 504 and outputs the acquired moving image compressed data 11 to the compressed data receiving unit 111.
  • the input interface 930 is a port connected to an input device such as a mouse, a keyboard, or a touch panel.
  • the input interface 930 is a USB (Universal Serial Bus) terminal.
  • the input interface 930 may be a port connected to a LAN (Local Area Network).
  • the output interface 940 is a port to which a cable of a display device such as a display is connected.
  • the output interface 940 is a USB terminal or an HDMI (registered trademark) (High Definition Multimedia interface) terminal.
  • the display is an LCD (Liquid Crystal Display).
  • the auxiliary storage device 922 stores programs for realizing the functions of the histogram information generation unit 110 and the vibration analysis unit 120.
  • a program that realizes the functions of the histogram information generation unit 110 and the vibration analysis unit 120 is also referred to as a vibration detection program 620.
  • This program is loaded into the memory 921, read into the processor 910, and executed by the processor 910.
  • the auxiliary storage device 922 stores an OS. At least a part of the OS stored in the auxiliary storage device 922 is loaded into the memory 921.
  • the processor 910 executes the vibration detection program 620 while executing the OS.
  • the vibration detection apparatus 100 may include only one processor 910, or may include a plurality of processors 910.
  • the plurality of processors 910 may execute programs that realize the functions of the respective units of the histogram information generation unit 110 and the vibration analysis unit 120 in cooperation with each other.
  • Information, data, signal values, and variable values indicating the processing results of the respective sections of the histogram information generation unit 110 and the vibration analysis unit 120 are stored in the auxiliary storage device 922, the memory 921, or the processor 910 in the vibration detection device 100. Alternatively, it is stored in a cache memory.
  • the portable recording medium is a memory card such as a magnetic disk, a flexible disk, an optical disk, a compact disk, a Blu-ray (registered trademark) disk, a DVD (Digital Versatile Disc), or an SD (registered trademark) card.
  • the vibration detection program product is a storage medium and a storage device in which the vibration detection program 620 is recorded.
  • a vibration detection program product refers to a program loaded with a computer-readable program regardless of the appearance.
  • FIG. 2 illustrates an example of the vibrating object 502 in the moving image frame 501, a camera 504 that captures the vibrating object, and the moving image compressed data 11 output from the camera 504.
  • the compressed moving image data 11 is an example of moving image data 109 representing a moving image obtained by photographing the vibrating object 502.
  • a moving image frame 501 shown in FIG. 2 is a frame of an image obtained by photographing the vibrating object 502 with the camera 504.
  • the vibration 503 of the vibrating object 502 appears as a minute change in the position of the vibrating object 502 between the adjacent moving image frames 501.
  • the camera 504 has a moving image compression function that records a minute change in the position of the vibrating object 502 due to the vibration 503 in the moving image compression data 11 as a motion vector 506.
  • a motion vector 506 represents a minute change in the position of the vibrating object 502 between adjacent moving image frames 501 by a vector.
  • the vibration detection process S100 includes a normal vibration extraction process S10 and a vibration feature comparison process S20.
  • the normal vibration extraction process S10 is a process of extracting the vibration feature of the vibrating object 502 that is normally vibrating from the moving image compression data 11 as normal feature information 301 and storing it in the normal feature storage unit 131.
  • the normal feature extraction process S10 includes a histogram information generation process S110, a frequency analysis process S120, and a normal feature extraction process S130.
  • ⁇ Histogram information generation processing S110> the histogram information generation unit 110 acquires moving image data 109 representing a moving image obtained by photographing the vibrating object 502, and extracts a motion vector 506 representing the movement of the vibrating object 502 from the moving image data 109. . Then, the histogram information generation unit 110 counts the number of motion vectors for each motion direction range that is a range of motion vector directions. Then, the histogram information generation unit 110 generates a histogram for each frame of the moving image data 109 as the histogram information 21 using the number of motion vectors for each motion direction range.
  • the histogram information generation unit 110 acquires, as the moving image data 109, the moving image compressed data 11 including the motion vector 506, which is the moving image compressed data 11 obtained by compressing the moving image. Then, the histogram information generation unit 110 extracts the motion vector 506 from the moving image compressed data 11.
  • step S111 the vibrating object 502 is captured by the camera 504 having a moving image compression function.
  • step S ⁇ b> 112 the compressed data receiving unit 111 outputs the compressed moving image data 11 output from the camera 504.
  • the compressed data receiving unit 111 outputs moving image compressed data for one moving image frame.
  • the moving image compressed data 11 includes a motion vector 506 calculated in units of pixel blocks from information between adjacent moving image frames 501.
  • the motion vector 506 is an encoded motion vector defined by a compression method such as an MPEG (Moving Picture Expert Group) format. This encoded motion vector is calculated for each pixel block from information such as a luminance gradient between adjacent moving image frames 501.
  • MPEG Motion Picture Expert Group
  • step S ⁇ b> 113 the motion vector extraction unit 112 extracts all the motion vectors 506 included in each moving image frame 501 from the moving image compressed data 11 received by the compressed data receiving unit 111.
  • step S ⁇ b> 114 the motion direction calculation unit 113 acquires the motion vector 506 from the motion vector extraction unit 112.
  • the motion direction calculation unit 113 calculates the motion direction of the motion vector by calculating the arc tangent of the X component and the Y component for each motion vector. Further, the motion direction calculation unit 113 calculates the square root of the sum of the square of the X component and the square of the Y component for each motion vector to obtain the magnitude of the motion vector.
  • step S115 the motion quantity counting unit 114 acquires the motion direction and magnitude for each motion vector obtained by the motion direction calculation unit 113.
  • the motion quantity counting unit 114 determines whether the motion direction of the motion vector falls within a motion direction range that is a range of the motion vector direction, and classifies the motion vector for each motion direction range.
  • the movement direction range is each angle range obtained by equally dividing 360 ° into m.
  • the motion quantity counting unit 114 converts the motion vector into a motion direction range 1, a motion direction range 2,..., A motion direction depending on which motion direction range each of the motion vectors extracted by the motion vector extraction unit 112 enters. Classify into range m.
  • the motion quantity counting unit 114 counts the number of motion vectors classified into the motion direction range for each motion direction range.
  • the motion quantity counting unit 114 may count only the quantity regardless of the magnitude of the motion vector, or may count the quantity by weighting according to the magnitude of the motion vector.
  • the motion quantity counting unit 114 may count only when the magnitude of the motion vector is a certain value or more. At this time, a threshold value for determining whether or not the magnitude of the motion vector is a certain value or more may be provided.
  • the motion histogram generation unit 115 acquires the number of motion vectors counted for each motion direction range from the motion quantity counting unit 114.
  • the motion histogram generation unit 115 generates a histogram for each frame of the moving image data 109 using the number of motion vectors for each motion direction range. Specifically, the motion histogram generation unit 115 generates a histogram for one moving image frame with the horizontal axis as the number 1 to m of the motion direction range and the vertical axis as the number of motion vectors.
  • the motion histogram generation unit 115 accumulates the generated histogram for one moving image frame as the histogram information 21 in the storage unit 130. In the histogram information 21 of the storage unit 130, histograms generated for each moving image frame constituting the moving image are accumulated in time series.
  • the frequency analysis unit 122 uses the histogram information 21 to calculate the frequency of the time series change in the number of motion vectors for each motion direction range and the frequency component for each frequency, and the vibration characteristics of the vibrating object 502. Is calculated as vibration feature information 302 representing Specifically, the frequency analysis unit 122 performs the Fourier transform on the time-series change of the motion vector quantity for each motion direction range, thereby performing the time-series change frequency and the frequency of the motion vector quantity for each motion direction range.
  • the number of motion vectors for n consecutive frames is extracted every (1 to m).
  • step S122 the frequency analysis unit 122 acquires the number of motion vectors for n consecutive frames for each motion direction range from the motion quantity extraction unit 121.
  • the frequency analysis unit 122 performs a Fourier transform on the time series change of the motion vector quantity in each motion direction range, and obtains a frequency component for each frequency. Then, the frequency analysis unit 122 outputs the frequency with respect to the time-series change of the motion vector quantity and the frequency component for each frequency as the vibration feature information 302 in each motion direction range.
  • the normal feature extraction unit 123 extracts information representing normal vibration features as normal feature information 301 from the vibration feature information 302 calculated by the frequency analysis unit 122. Specifically, first, in step S123, the normal feature extraction unit 123 acquires, from the frequency analysis unit 122, the frequency of the time-series change of the quantity of motion vectors for each motion direction range and the frequency component for each frequency. That is, the normal feature extraction unit 123 acquires the vibration feature information 302 calculated by the frequency analysis unit 122. The normal feature extraction unit 123 accumulates frequency components for each frequency of the time-series change in the number of motion vectors for each motion direction range in time series.
  • the normal feature extraction unit 123 obtains the vibration characteristics of the vibrating object 502 that normally vibrates from the frequency components for each frequency of the time-series change in the number of motion vectors for each motion direction range accumulated in time series. Extract as In step S123, the normal feature extraction unit 123 stores the normal feature information 301 in the normal feature storage unit 131 of the storage unit 130.
  • FIG. 5 shows the frequency obtained by frequency analysis of the number of motion vectors in a specific motion direction range among the motion vectors extracted from the video obtained by photographing the vibrating object 502 that is normally oscillating according to the present embodiment.
  • the example which arranged the frequency component for every in time series is shown.
  • FIG. 5 shows that, in a specific motion direction range, the state where the frequency component of a specific frequency in the time-series change of the quantity of motion vectors is larger than the frequency components of other frequencies is maintained even when the time changes.
  • the example of the characteristic of the normal vibration which is leaning is shown.
  • the characteristic of normal vibration may appear in a plurality of combinations of the frequency components for each frequency of the time-series change in the number of motion vectors for each motion direction range of the motion vectors extracted from the moving image compression data. .
  • a time-series change pattern specifically, a pattern in which the frequency component of a specific frequency periodically increases or decreases, or a pattern in which a frequency component whose frequency component is larger than other frequencies periodically changes. good.
  • the vibration feature comparison process S20 is a process of determining whether the vibration of the vibrating object 502 obtained from the moving image compression data 11 is normal vibration or abnormal vibration and notifying the determination result.
  • the vibration feature comparison process S20 includes a histogram information generation process S110 and an abnormality determination process S220.
  • the histogram information generation process S110 is the same process as the histogram information generation process S110 described in the normal vibration extraction process S10.
  • Steps S111 to S116 in FIG. 6 are the same as steps S111 to S116 in FIG.
  • Steps S121 to S122 in FIG. 6 are the same as steps S121 to S122 in FIG.
  • the comparison unit 124 acquires the normal feature information 301 from the normal feature storage unit 131, compares the vibration feature information 302 with the normal feature information 301, and determines whether or not the vibration feature information 302 has the normal feature information 301. .
  • the notification unit 125 outputs an abnormal vibration notification that notifies the vibration abnormality.
  • the comparison unit 124 determines that the vibration feature information 302 includes the normal feature information 301
  • the notification unit 125 outputs a normal vibration notification that notifies the normality of vibration.
  • the comparison unit 124 acquires, from the frequency analysis unit 122, a frequency component for each frequency of a time-series change in the number of motion vectors for each motion direction range. That is, the comparison unit 124 acquires the vibration feature information 302 calculated by the frequency analysis unit 122. The comparison unit 124 compares the vibration feature information 302 with the normal feature information 301 stored in the normal feature storage unit 131. The comparison unit 124 compares whether or not there is a feature that matches the normal feature information 301 in the frequency component for each frequency of the time-series change in the number of motion vectors for each motion direction range accumulated in time series.
  • the comparison unit 124 may correct the movement direction range in consideration of the possibility that the tilt of the vibrating object during photographing is different from the tilt of the vibrating object during normal vibration extraction.
  • the comparison unit 124 outputs a comparison result comparing the vibration characteristics of the vibrating object 502 being photographed with the characteristics of normal vibration.
  • FIG. 7 shows the frequency obtained by frequency-analyzing the quantity of motion vectors in a specific motion direction range among the motion vectors extracted from the video obtained by photographing the vibrating object 502 that is abnormally vibrating according to the present embodiment. It is a figure which shows the example which arranged the frequency component for every in time series.
  • FIG. 7 is an example of the time series change frequency and the frequency component change of the number of motion vectors in the same motion direction range as the example shown in FIG.
  • the characteristic of normal vibration shown in FIG. 5 there are more frequency components at a specific frequency than other frequencies, and the frequency is maintained even when the time changes.
  • the time series change of the frequency and frequency component shown in FIG. 7 does not have such a characteristic of normal vibration. Therefore, the comparison unit 124 determines that the vibration has characteristics different from the normal vibration.
  • the comparison unit 124 When the frequency component for each frequency of the time-series change in the number of motion vectors for each motion direction range accumulated in time series has a feature that matches the normal feature information 301, the comparison unit 124 performs normal vibration as the comparison result 303. Set detection. In addition, the comparison unit 124, as the comparison result 303, when there is no feature that matches the normal feature information 301 in the frequency component for each frequency of the time series change in the number of motion vectors for each motion direction range accumulated in time series. Set abnormal vibration detection.
  • step S224 the notification unit 125 determines whether the comparison result 303 is normal vibration detection or abnormal vibration detection. In the case of normal vibration detection, the process proceeds to step S243. If abnormal vibration is detected, the process proceeds to step S244. In step S225, the notification unit 125 notifies normal vibration detection. In step S226, the notification unit 125 notifies abnormal vibration detection.
  • the vibration detection device 100 may include a communication device that communicates with other devices via a network.
  • the communication device has a receiver and a transmitter.
  • the communication device is wired or wirelessly connected to a communication network such as a LAN, the Internet, or a telephone line.
  • the communication device is a communication chip or a NIC (Network Interface Card).
  • the communication device is a communication unit that communicates data.
  • the receiver is a receiving unit that receives data.
  • the transmitter is a transmission unit that transmits data.
  • the vibration detection device 100 according to the present embodiment may acquire the operation description and the non-functional requirements via the communication device.
  • the vibration detection apparatus 100 according to the present embodiment may transmit the conversion operation description to another apparatus via the communication apparatus.
  • the functions of the histogram information generation unit 110 and the vibration analysis unit 120 are implemented by software. However, as a modification, the functions of the respective parts of the histogram information generation unit 110 and the vibration analysis unit 120 may be realized by hardware.
  • the vibration detection apparatus 100 includes hardware such as a processing circuit 909, an input interface 930, and an output interface 940.
  • the processing circuit 909 is a dedicated electronic circuit that realizes the functions of the respective units of the histogram information generation unit 110 and the vibration analysis unit 120 and the storage unit 130 described above.
  • the processing circuit 909 is a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, a logic IC, a GA, an ASIC, or an FPGA.
  • GA is an abbreviation for Gate Array.
  • ASIC is an abbreviation for Application Specific Integrated Circuit.
  • FPGA is an abbreviation for Field-Programmable Gate Array.
  • each unit of the histogram information generation unit 110 and the vibration analysis unit 120 may be realized by one processing circuit 909 or may be realized by being distributed to a plurality of processing circuits 909.
  • the functions of the histogram information generation unit 110 and the vibration analysis unit 120 may be realized by a combination of software and hardware. That is, some functions of the vibration detection device 100 may be realized by dedicated hardware, and the remaining functions may be realized by software.
  • the processor 910, the storage device 920, and the processing circuit 909 of the vibration detection device 100 are collectively referred to as “processing circuit”. That is, regardless of the configuration of the vibration detection device 100 shown in FIGS. 1 and 8, the functions of the histogram information generation unit 110 and the vibration analysis unit 120 and the storage unit 130 are realized by processing circuitry. Is done.
  • Part may be read as “Process” or “Procedure” or “Process”. Further, the function of “unit” may be realized by firmware.
  • the vibration detection apparatus 100 extracts a vibration motion vector from a video image of a vibrating object, and performs frequency analysis for each movement direction range.
  • vibration detection apparatus 100 according to the present embodiment extracts normal feature information that is a feature of normal vibration in advance based on a time-series change in the result of frequency analysis.
  • the vibration detection apparatus 100 which concerns on this Embodiment compares the vibration feature information of the image
  • the vibration detection device it is possible to determine whether the vibration is a normal vibration or an abnormal vibration from the difference in vibration state, and to detect the abnormal vibration of the vibration detection target. Further, according to the vibration detection device according to the present embodiment, it is possible to determine whether the vibration is a normal vibration or an abnormal vibration from the difference in vibration state, and to detect the abnormal vibration of the vibration detection target. Furthermore, according to the vibration detection apparatus according to the present embodiment, it is possible to determine whether the vibration is normal vibration or abnormal vibration without being affected by camera vibration and positional deviation, and vibration object position and inclination deviation.
  • Embodiment 2 differences from the first embodiment will be mainly described.
  • the mode of extracting the motion vector of the moving image compressed data 11 has been described.
  • a mode will be described in which it is determined whether the vibration of the vibrating object 502 is normal or abnormal when the movement vector is extracted by detecting the movement of the vibrating object 502 between adjacent moving image frames 31.
  • FIG. 9 The configuration of the vibration detection apparatus 100a according to the present embodiment will be described with reference to FIG. 9, the same components as those described in the first embodiment are denoted by the same reference numerals, and the description thereof is omitted.
  • the vibration detection apparatus 100a includes a histogram information generation unit 110a instead of the histogram information generation unit 110 of FIG.
  • the histogram information generation unit 110a acquires the moving image frame 31 constituting the moving image as the moving image data 109, and extracts the motion vector 506 by detecting the movement of the vibrating object between the adjacent moving image frames 31.
  • the histogram information generation unit 110a may extract the motion vector 506 by detecting the movement of the vibrating object between the adjacent moving image frames 31.
  • the adjacent moving image frames 31 are concepts included in the adjacent moving image frames 31.
  • the histogram information generation unit 110a includes a frame reception unit 311 that receives a moving image frame 31, a moving object extraction unit 312 and a moving object motion vector extraction unit instead of the compressed data reception unit 111 and the motion vector extraction unit 112 illustrated in FIG. 313.
  • the frame receiving unit 311 receives the moving image frame 31 output from the camera 505 having no moving image compression function via the input interface 930.
  • Other configurations of the vibration detection apparatus 100a according to the present embodiment are the same as those of the first embodiment.
  • the histogram information generation process S110a will be described with reference to FIG. 10 differs from FIG. 4 and FIG. 6 described in the first embodiment in the processing from step S111 to step S113.
  • step S111a the vibrating object 502 is photographed by the camera 505 having no moving image compression function.
  • step S112a the frame reception unit 311 outputs the moving image frame 31 output from the camera 505.
  • step S113a the moving object extracting unit 312 sequentially receives moving image frames from the frame receiving unit 311 and extracts moving object information in the screen from the difference between adjacent moving image frames.
  • the moving body motion vector extraction unit 313 receives the moving body information from the moving body extraction unit 312 and generates a motion vector from the direction of motion and the magnitude of the motion. Subsequent operations are the same as those in the first embodiment.
  • the vibration detection apparatus 100 it is determined whether the vibration of the vibrating object is normal vibration or abnormal vibration using a moving image frame output from a camera that does not have a moving image compression function. be able to.
  • each part of the vibration detection device 100 constitutes the vibration detection device 100 as an independent functional block.
  • the configuration of the vibration detection apparatus 100 is not limited to the configuration described in the above embodiment.
  • the functional blocks of the vibration detection device 100 are arbitrary as long as the functions described in the above-described embodiments can be realized.
  • the vibration detection device 100 may be configured by any other combination of these functional blocks or an arbitrary block configuration.
  • the vibration detection device 100 may be a system including a plurality of devices instead of a single device.
  • Embodiments 1 and 2 have been described, a combination of a plurality of portions may be implemented among these embodiments. Or you may implement one part among these embodiments. In addition, these embodiments may be implemented in any combination as a whole or in part.
  • the above-described embodiments are essentially preferable examples, and are not intended to limit the scope of the present invention, its application, and uses, and various modifications can be made as necessary. .
  • 11 moving image compressed data 21 histogram information, 31 moving image frame, 109 moving image data, 100, 100a vibration detection device, 110, 110a histogram information generating unit, 111 compressed data receiving unit, 112 motion vector extracting unit, 113 motion direction Calculation unit, 114 motion quantity count unit, 115 motion histogram generation unit, 120 vibration analysis unit, 121 motion quantity extraction unit, 122 frequency analysis unit, 123 normal feature extraction unit, 124 comparison unit, 125 notification unit, 130 storage unit, 131 Normal feature storage unit, 301 normal feature information, 302 vibration feature information, 303 comparison result, 311 frame receiving unit, 312 moving object extraction unit, 313 moving object motion vector extraction unit, 501 frame, 502 vibrating object, 503 vibration, 504, 50 Camera, 506 motion vector, 610 vibration detection method, 620 vibration detection program, 909 processing circuit, 910 processor, 920 storage device, 921 memory, 922 auxiliary storage device, 930 input interface, 940 output interface, S100 vibration detection processing, S10 normal Vibration extraction processing, S20

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)

Abstract

La présente invention concerne une unité de mémorisation de caractéristiques normales (131) mémorisant des informations de caractéristiques normales (301) représentant une caractéristique de vibration normale. Une unité de génération d'informations d'histogramme (110) acquiert des données d'image animée (109) et extrait, à partir des données d'image animée, un vecteur de mouvement représentant le mouvement d'un objet vibrant. De plus, l'unité de génération d'informations d'histogramme (110) compte la quantité de vecteurs de mouvement de chaque plage de direction de mouvement et utilise la quantité de vecteur de mouvement de chaque plage de direction de mouvement afin de générer des informations d'histogramme (21) de chaque trame des données d'image animée (109). De plus, une unité d'analyse de fréquence (122) utilise les informations d'histogramme (21) afin de calculer, en tant qu'informations de caractéristique de vibration (302), les fréquences de changements de série chronologique dans la quantité de vecteur de mouvement de chaque plage de direction de mouvement et les composantes de fréquence de chaque fréquence. Un comparateur compare les informations de caractéristique de vibration (302) et les informations de caractéristique normale (301).
PCT/JP2017/006424 2017-02-21 2017-02-21 Dispositif de détection de vibrations, procédé de détection de vibrations et programme de détection de vibrations Ceased WO2018154637A1 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2018550857A JP6452923B1 (ja) 2017-02-21 2017-02-21 振動検知装置、振動検知方法および振動検知プログラム
PCT/JP2017/006424 WO2018154637A1 (fr) 2017-02-21 2017-02-21 Dispositif de détection de vibrations, procédé de détection de vibrations et programme de détection de vibrations
TW106119956A TW201832183A (zh) 2017-02-21 2017-06-15 振動檢測裝置、振動檢測方法以及振動檢測程式產品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2017/006424 WO2018154637A1 (fr) 2017-02-21 2017-02-21 Dispositif de détection de vibrations, procédé de détection de vibrations et programme de détection de vibrations

Publications (1)

Publication Number Publication Date
WO2018154637A1 true WO2018154637A1 (fr) 2018-08-30

Family

ID=63253566

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2017/006424 Ceased WO2018154637A1 (fr) 2017-02-21 2017-02-21 Dispositif de détection de vibrations, procédé de détection de vibrations et programme de détection de vibrations

Country Status (3)

Country Link
JP (1) JP6452923B1 (fr)
TW (1) TW201832183A (fr)
WO (1) WO2018154637A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07181075A (ja) * 1993-12-22 1995-07-18 Hitachi Zosen Corp 物体の変位状態計測方法および変位状態計測装置
JP2003156389A (ja) * 2001-11-21 2003-05-30 Toshiba Corp 振動計測装置及び記憶媒体
WO2007049693A1 (fr) * 2005-10-27 2007-05-03 The Tokyo Electric Power Company, Incorporated Systeme et procede de mesure de vibration, et programme informatique
US20110134329A1 (en) * 2009-12-04 2011-06-09 Chao-Ho Chen Stabilization method for vibrating video frames
JP2014179061A (ja) * 2013-02-14 2014-09-25 Sony Corp 分析システム、分析プログラム及び分析方法
JP2015175827A (ja) * 2014-03-18 2015-10-05 日本電気株式会社 振動計測装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07181075A (ja) * 1993-12-22 1995-07-18 Hitachi Zosen Corp 物体の変位状態計測方法および変位状態計測装置
JP2003156389A (ja) * 2001-11-21 2003-05-30 Toshiba Corp 振動計測装置及び記憶媒体
WO2007049693A1 (fr) * 2005-10-27 2007-05-03 The Tokyo Electric Power Company, Incorporated Systeme et procede de mesure de vibration, et programme informatique
US20110134329A1 (en) * 2009-12-04 2011-06-09 Chao-Ho Chen Stabilization method for vibrating video frames
JP2014179061A (ja) * 2013-02-14 2014-09-25 Sony Corp 分析システム、分析プログラム及び分析方法
JP2015175827A (ja) * 2014-03-18 2015-10-05 日本電気株式会社 振動計測装置

Also Published As

Publication number Publication date
TW201832183A (zh) 2018-09-01
JP6452923B1 (ja) 2019-01-16
JPWO2018154637A1 (ja) 2019-02-28

Similar Documents

Publication Publication Date Title
US9852511B2 (en) Systems and methods for tracking and detecting a target object
US8472669B2 (en) Object localization using tracked object trajectories
US9367733B2 (en) Method and apparatus for detecting people by a surveillance system
KR102399017B1 (ko) 이미지 생성 방법 및 장치
US20190230269A1 (en) Monitoring camera, method of controlling monitoring camera, and non-transitory computer-readable storage medium
JP6863383B2 (ja) 欠陥検出装置、欠陥検出方法、及びコンピュータ読み取り可能記録媒体
US20170104979A1 (en) Method and Apparatus for Depth Algorithm Adjustment to Images based on Predictive Analytics and Sensor Feedback in an Information Handling System
JP2010258710A5 (fr)
US20150146006A1 (en) Display control apparatus and display control method
US10185886B2 (en) Image processing method and image processing apparatus
US10063779B2 (en) Image processing apparatus, image capturing apparatus, image processing method, and storage medium
US9613429B2 (en) Image reading out control apparatus, image reading out control method thereof, and storage medium
US11036974B2 (en) Image processing apparatus, image processing method, and storage medium
KR20140045897A (ko) 시각적 이미지 매칭을 기반으로 한 미디어 스트림 식별 장치 및 방법
US20150154455A1 (en) Face recognition with parallel detection and tracking, and/or grouped feature motion shift tracking
CN108010059B (zh) 电子防抖算法的性能分析方法及装置
US20190197695A1 (en) Image processing apparatus, image processing method, and storage medium
US20200334481A1 (en) Image processing apparatus, method for detecting event from image, and storage medium
US20180330170A1 (en) Information processing apparatus, information processing system, information processing method, and storage medium
US20180314893A1 (en) Information processing device, video image monitoring system, information processing method, and recording medium
JP4513034B2 (ja) 画像信号処理装置、画像信号処理方法、およびプログラム
JPWO2003088648A1 (ja) 動き検出装置、画像処理システム、動き検出方法、プログラム、および記録媒体
KR101214858B1 (ko) 클러스터링 기법을 이용한 이동물체 검출장치 및 방법
US11341773B2 (en) Detection device and control method of the same
JP6452923B1 (ja) 振動検知装置、振動検知方法および振動検知プログラム

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2018550857

Country of ref document: JP

Kind code of ref document: A

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

Ref document number: 17897745

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: 17897745

Country of ref document: EP

Kind code of ref document: A1