WO2021036661A1 - Procédé et appareil de filtrage, et produit associé - Google Patents

Procédé et appareil de filtrage, et produit associé Download PDF

Info

Publication number
WO2021036661A1
WO2021036661A1 PCT/CN2020/105583 CN2020105583W WO2021036661A1 WO 2021036661 A1 WO2021036661 A1 WO 2021036661A1 CN 2020105583 W CN2020105583 W CN 2020105583W WO 2021036661 A1 WO2021036661 A1 WO 2021036661A1
Authority
WO
WIPO (PCT)
Prior art keywords
correlation peak
filtering
correlation
peak
frequency band
Prior art date
Application number
PCT/CN2020/105583
Other languages
English (en)
Chinese (zh)
Inventor
高风波
Original Assignee
深圳市豪视智能科技有限公司
深圳市广宁股份有限公司
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 深圳市豪视智能科技有限公司, 深圳市广宁股份有限公司 filed Critical 深圳市豪视智能科技有限公司
Publication of WO2021036661A1 publication Critical patent/WO2021036661A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/02—Preprocessing
    • G06F2218/04—Denoising
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks

Definitions

  • This application relates to the field of detection technology, and in particular to a filtering method, device and related products.
  • vibration can reflect the operating conditions of certain mechanical structures. You can take a video of the vibration device when it is running, and then extract the vibration signal from the video, and then obtain the operating status of the device based on the vibration signal. A variety of noise information will be introduced due to environmental influences, and the vibration signal extracted from the video also contains a large amount of noise signals, which makes it impossible to accurately obtain the operating status of the device.
  • the embodiments of the present application provide a filtering method, device, and related products.
  • an embodiment of the present application provides a filtering method, including:
  • the filtering strategy includes a filtering bandwidth
  • determining the filtering strategy corresponding to each correlation peak according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak includes:
  • the product of the initial filter bandwidth corresponding to each correlation peak and the bandwidth adjustment coefficient is used as the filter bandwidth corresponding to each correlation peak.
  • the determining the bandwidth adjustment coefficient corresponding to the correlation peak according to the corresponding position of each correlation peak in the detection video includes:
  • the filtering method before determining the filtering strategy corresponding to each correlation peak according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak, the filtering method further includes:
  • the determining the filtering strategy corresponding to each correlation peak according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak includes:
  • the filtering strategy corresponding to each correlation peak is determined according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak after the dimensionality reduction process.
  • the filtering method before the use of the principal component decomposition method to perform dimensionality reduction processing on each correlation peak, the filtering method further includes:
  • the use of the principal component decomposition method to perform dimensionality reduction processing on each correlation peak includes:
  • the filtering each correlation peak according to the filtering strategy corresponding to each correlation peak includes:
  • filter processing is performed on each correlation peak through interpolation filtering.
  • the present application also provides a filtering device, including:
  • the first acquisition module is configured to acquire one or more correlation peaks obtained by performing phase correlation calculation on the frame sequence corresponding to the detected video, where the correlation peaks are frequency domain signals;
  • a filtering strategy determination module configured to determine a filtering strategy corresponding to each correlation peak according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak;
  • the filtering module is used for filtering each correlation peak according to the filtering strategy corresponding to each correlation peak.
  • an embodiment of the present application also provides an electronic device, including a processor, a memory, and an information recommendation program stored on the memory and executable by the processor, wherein the information recommendation program is When executed by the processor, instructions for implementing the steps in the filtering method described in any one of the foregoing embodiments.
  • the present application also provides a computer-readable storage medium with a filtering program stored on the computer-readable storage medium, wherein the filtering program is executed by a processor to implement the filtering method described in any one of the above items.
  • the present application also provides a detection device for detecting the operating status of the device to be detected.
  • the detection device includes the filtering device of the foregoing embodiment or the electronic device of the foregoing embodiment.
  • the filtering method of the embodiment of the present application obtains one or more correlation peaks obtained by performing phase correlation calculation on the frame sequence corresponding to the detection video; each correlation peak is determined according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak Corresponding filtering strategy; filtering each correlation peak according to the filtering strategy corresponding to each correlation peak.
  • FIG. 1 is a schematic structural diagram of an electronic device according to an embodiment of the application.
  • FIG. 2 is a schematic flowchart of a filtering method according to an embodiment of the application
  • FIG. 3 is a schematic diagram of a process of amplifying a detection video involved when the filtering method of an embodiment of the application is used to detect the operating status of the device to be detected;
  • FIG. 4 is a schematic diagram of another flow of the filtering method according to an embodiment of the application.
  • FIG. 5 is a schematic diagram of another flow of the filtering method according to an embodiment of the application.
  • FIG. 6 is a schematic diagram of still another process of the filtering method according to an embodiment of the application.
  • FIG. 1 is a schematic diagram of the hardware structure of an electronic device 100 provided by an embodiment of the present application.
  • the electronic device 100 includes a processor 101, a memory 102, an input/output interface 103, and one or more programs.
  • One or more programs are stored in the memory 102 and configured to be executed by the processor 101.
  • the programs include any of the following Instructions for the steps of the filtering method of the embodiment.
  • the electronic device 100 may be a server device or a terminal device.
  • the memory 102 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as a disk memory.
  • the memory 102 may optionally be a storage device independent of the aforementioned processor 101.
  • the input and output interface 103 may optionally include a USB interface, a standard wired interface, a wireless interface (such as a WI-FI interface), and the like.
  • FIG. 2 is a schematic flowchart of a filtering method provided by an embodiment of the present application. This method may include but is not limited to the following steps:
  • the filtering method of the embodiment of the present application can be used but not limited to detecting the vibration of the device to be detected.
  • the vibration of the device to be tested can reflect the operating conditions of the device to be tested.
  • the detection video may be a video obtained by shooting the device to be detected by the imaging module.
  • the detection video can be analyzed to extract the vibration information of the device to be tested from the detection video, and then the vibration information can be analyzed to obtain the operating status of the device to be tested.
  • the detection video is a vibration magnified video obtained by using the Euler algorithm to amplify the vibration in the video obtained by shooting the imaging module with the device to be detected.
  • Devices to be tested include, but are not limited to, various mechanical equipment, building structures, etc.
  • the phase correlation calculation is performed on the frame sequence corresponding to the detection video to obtain the cross cross power spectrum, and the cross cross power spectrum includes one or more correlation peaks.
  • the correlation peak is a frequency domain signal, and each correlation peak can reflect the severity of the state change of a certain frequency band at a certain position in the detection video.
  • the phase correlation calculation of the frame sequence corresponding to the detection video can obtain the cross-power spectrum.
  • the state change information in the video picture is extracted from the detected video.
  • the status change information includes vibration information and other noise information, and the vibration information can reflect the operating conditions of the device to be tested.
  • the filtering method of the embodiment of the present application can be used to filter each correlation peak in the cross cross power spectrum to reduce the noise information in each correlation peak, so that the operating status of the device to be detected obtained from the detection video is more accurate.
  • Each correlation peak can be analyzed to obtain the corresponding position of each correlation peak in the detection video, and the corresponding position of the correlation peak in the detection video can be understood as the position in the detection video corresponding to the state change reflected by the correlation peak.
  • the brightness of a location in the detection video changes periodically with time, and one or more correlation peaks obtained by phase correlation calculation on the corresponding frame sequence of the detection video include at least one correlation peak to reflect the location. The brightness changes.
  • each correlation peak in the detection video can be used as a basis.
  • Determine the filtering strategy for each correlation peak The frequency range (ie, frequency band) corresponding to each correlation peak is different, and the filtering strategy of each correlation peak is determined according to the frequency band corresponding to the correlation peak, so that the filtering strategy is more adapted to each correlation peak, thereby helping to determine the filtering strategy from each correlation peak.
  • the filtering strategy may include, but is not limited to, the bandwidth of the filter, the type of the filter, and the like, for example.
  • each correlation peak After obtaining the filtering strategy of each correlation peak, filter processing is performed on each correlation peak according to the corresponding filtering strategy, so that the signal-to-noise ratio of the signal obtained from the detection video is higher.
  • each correlation peak can be filtered by interpolation filtering according to the filtering strategy corresponding to each correlation peak, so that the filtering effect is better.
  • the filtering method of the embodiment of the present application obtains one or more correlation peaks obtained by performing phase correlation calculation on the frame sequence corresponding to the detection video; each correlation peak is determined according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak Corresponding filtering strategy; filtering each correlation peak according to the filtering strategy corresponding to each correlation peak.
  • the frame sequence in the detection video can be first converted from the RGB color space to the YIQ color space, and the brightness information and chroma information of the video frames can be separated.
  • the conversion relationship between RGB and YIQ is:
  • the Euler motion amplification algorithm includes: decomposing the Y-channel image after FFT transformation into the complex and manipulable gold tower spatial domain to obtain a pyramidal structure composed of multiple sub-images with different spatial resolutions; for each sub-image in the multiple sub-images in the pyramid-shaped structure Perform time-domain band-pass filtering to obtain the transformed signal corresponding to the target frequency band.
  • the vibration can be reflected by the brightness of the video frame sequence, then the vibration information in the detection video can be obtained by analyzing the Y channel in the detection video.
  • phase correlation algorithm is used to calculate the cross power spectrum between the frame sequences on the frame sequence after the video motion amplification processing.
  • the phase correlation algorithm uses the following formula to calculate the cross cross power spectrum.
  • Fa is the Fourier transform of a frame image
  • the lower side of the division formula is the modulus of the correlation product of the two Fourier transformed signals.
  • R crosses the cross power spectrum (including frequency domain noise) of the calculation result of this step.
  • the correlation peaks in the cross cross power spectrum are filtered, which improves the signal-to-noise ratio of the useful signal, so that the detection video that contains the image of the detection device when the detection device is running is extracted Information, useful signals have a higher signal-to-noise ratio.
  • a pyramid structure is obtained.
  • the pyramid structure includes multiple layers of sub-images, and the image resolution from top to bottom is sequentially reduced, and the spatial frequency is sequentially reduced.
  • the time-domain band-pass filtering of each layer of image is to obtain the target frequency band, so that the sub-image resolution of the target frequency band can clearly express the motion characteristics of the image, and at the same time, the high resolution will not cause excessive calculation. Therefore, according to the pyramid structure, the frequency bands of each sub-image at different spatial frequencies are obtained from bottom to top, and the acquisition sequence is compared with the standard frequency band.
  • the frequency band acquisition and matching of the spatial frequency of one or more sub-images above the sub-images of this layer improves the efficiency of time-domain band-pass filtering.
  • the maximum number of pyramid decomposition levels is determined: log2(min(xres,yres)), where xres is the width pixel value of the image, and yres is the height pixel value of the image.
  • first group includes sub-images corresponding to 2n+1 layers
  • second group includes sub-images corresponding to 2(n+1) layers, where n is an integer greater than or equal to 0 , N ⁇ max(2(n+1),2n+1);
  • the first group of sub-images are processed by the first processor to perform temporal band-pass filtering according to the number of layers from small to large
  • the second group of sub-images are processed by the second processor to perform temporal band-pass filtering according to the number of layers from small to large.
  • the time-domain band-pass filtering process is to match the frequency bands of different spatial frequencies corresponding to the sub-images with the standard frequency band, and the first processor and the second processor are independently operating processors;
  • the first processor or the second processor determines that the frequency band matches the standard frequency band successfully, determining that the frequency band is the target frequency band;
  • the first target sub-image and the second target sub-image are transformed signals corresponding to the target frequency band.
  • the base array uses the first processor to perform time-domain band-pass filtering in the order of 1,3,5...2n+1, and the even array uses the second processor. Perform the time-domain band-pass filter processing in the order of 2,4,6,...2(n+1).
  • the two processors can start running at the same time or have a certain processing time interval.
  • the obtaining method may be to match the frequency bands of different spatial frequencies corresponding to the sub-images with the standard frequency bands.
  • the first processor or the second processor determines that the frequency band is successfully matched with the standard frequency band, it is determined that the frequency band is the target frequency band.
  • the target frequency band represents the spatial frequency of the lowest resolution sub-image that can reflect the vibration information of the image
  • the sub-image corresponding to the target frequency band is determined as the first target sub-image, and then the sub-image corresponding to the target frequency band in the upper layer of the sub-image is obtained as the second
  • the target sub-image, the first target sub-image and the second target sub-image are transformed signals corresponding to the target frequency band, and subsequent amplification and transformation are performed.
  • the frame image corresponding to the target vibration video can be enlarged more accurately, and more accurate motion information can be obtained, and at the same time, the amount of calculation that needs to be increased for amplifying a higher resolution image is avoided.
  • the sub-images corresponding to the pyramid structure are grouped, and then the sub-images of different groups are subjected to time-domain band-pass filtering through two independently operating processors, which can improve the efficiency of filtering processing, and at the same time obtain
  • the sub-image of the layer corresponding to the target frequency band is used as the first target sub-image
  • the sub-image of the upper layer is obtained as the second target sub-image
  • the first target sub-image and the second target sub-image are transformed signals corresponding to the target frequency band
  • the filtering strategy includes filtering bandwidth, and the filtering strategy corresponding to each correlation peak is determined according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak including but Not limited to the following steps:
  • the correlation peaks obtained by performing phase correlation calculation on the frame sequence corresponding to the detection video include multiple similar state change information of multiple pixels in similar positions in the screen corresponding to the detection video, so that multiple pixels can be reflected. The status of the location changes. Then, in the screen corresponding to the detection video, the state changes at different positions are different, and the frequency distribution of the corresponding correlation peaks is also different. If the same filter bandwidth is used for filtering, then in order to avoid useful signals being filtered, the filter bandwidth needs to be set to a larger value, but this will cause the noise signal to be unable to be filtered.
  • the initial filter bandwidth corresponding to each correlation peak is determined according to the frequency band corresponding to each correlation peak, and the frequency band corresponding to the correlation peak is positively correlated with the initial filter bandwidth.
  • the larger the frequency band corresponding to the correlation peak, the corresponding initial filter bandwidth The wider it is, the better the filter bandwidth can be adapted to the correlation peaks, which can effectively filter noise signals and also help prevent useful signals from being filtered, thereby making the filtering effect better.
  • B*(1-a) can be used as the initial filter bandwidth
  • B is the frequency band corresponding to each correlation peak
  • a can be determined according to actual needs.
  • a can be set to be larger
  • more useful signals need to be obtained a can be set to a smaller value.
  • the setting method of the initial filter bandwidth is not limited to the above example, and is not limited here.
  • Vibration at different locations in the detection video has different effects on detecting the operating status of the device to be detected. Then the bandwidth adjustment coefficient corresponding to the correlation peak can be determined according to the corresponding position of each correlation peak in the detection video. The bandwidth adjustment coefficient is used to adjust the initial filter bandwidth to make the filter bandwidth more reasonable.
  • the screen corresponding to the detection video can be divided into multiple areas according to the impact of the vibration of the corresponding position of the correlation peak in the detection video on the operating status of the device to be detected, and a preset bandwidth adjustment can be set for each area
  • the bandwidth adjustment coefficient is determined in step 022
  • the preset bandwidth adjustment coefficient corresponding to the area where the corresponding position of each correlation peak is located in the detection video can be directly obtained, and the preset bandwidth adjustment coefficient is used as the bandwidth corresponding to the correlation peak Adjustment coefficient.
  • the bandwidth adjustment coefficient can be obtained quickly and accurately.
  • the user can set bandwidth weighting coefficients for each area in the screen corresponding to the detection video according to the structure of the device to be detected, and then use the product of the preset bandwidth adjustment coefficient and the bandwidth weighting coefficient as the relevant bandwidth adjustment of the corresponding area Coefficient, which makes the filtering bandwidth of each correlation peak more reasonable. For example, if the vibration of some key parts of the device to be tested is more able to reflect the operating conditions of the device to be tested than other parts, then the bandwidth weighting coefficient of the corresponding area of the key part in the detection video screen can be set to a larger value. , Making the filtering bandwidth larger, so that more useful information can be extracted.
  • the filter bandwidth obtained in this way comprehensively considers the corresponding position of the correlation peak in the detection video and the frequency band corresponding to the correlation peak, so that the filter bandwidth is more adapted to each correlation peak, thereby helping to extract useful information from each correlation peak. State change signal.
  • the calculation method of the filter bandwidth is not limited to the above method. In other embodiments, a suitable calculation method may be selected according to the frequency band corresponding to each correlation peak and the corresponding position of each correlation peak in the detection video to determine the filter bandwidth.
  • the filtering method further includes the steps:
  • Step 04 is executed after step 01 and before step 02.
  • Principal component decomposition (PCA) is used to reduce the dimensionality of the correlation peak data in the two main directions of vibration detection. It can be understood that when the vibration information is obtained from the correlation peaks, in the process of filtering the correlation peaks, each correlation peak needs to be calculated, and the correlation peaks extracted from the detection video include multiple dimensions of the screen corresponding to the detection video. State change status information, which will lead to cumbersome calculations and low efficiency in the filtering process. After the principal component decomposition method is used to reduce the dimensionality of the correlation peaks, and then perform other calculations about the filtering process, the calculation amount of the filtering process can be greatly reduced.
  • Step 02 includes:
  • the correlation peaks after the dimensionality reduction process are calculated to obtain the filtering strategy corresponding to each correlation peak, which can reduce the calculation amount of the filtering process and improve the filtering efficiency.
  • the filtering method further includes:
  • Step 05 is executed after step 01 and before step 04.
  • the imaging module shoots the detection video of the device to be detected
  • small changes in some pixels can also form a correlation peak, but the degree of frequency change is not large enough, and the peak value of the correlation peak is small.
  • These signals are useful for analyzing the operating status of the device to be tested.
  • the effect of is small or even no effect, which can be understood as a noise signal.
  • a preset peak range can be preset, and the peak value of each correlation peak can be compared with the preset peak range during filtering to filter out some common noise signals.
  • Step 04 includes:
  • the vibration of the device to be detected is a periodic reciprocating motion, and the state change caused by the vibration is also periodic.
  • the state change caused by the noise is often not periodic, for example, in an outdoor scene, the state change caused by the light and dark changes of the outdoor optical fiber.
  • periodic vibrations can be used to reflect the operating conditions of the device to be tested, because non-periodic vibrations are often caused by the external environment, rather than by the external environment.
  • the non-periodic signal caused by the detection device itself cannot be used to analyze the operating status of the device to be detected.
  • the inverse Fourier transform can be performed on the correlation peak to convert the frequency domain signal into the time domain signal to obtain multiple state change signals, and then The non-periodic signal in the state change signal is removed to further remove the noise, so that the operating status of the device to be detected obtained from the detection video is more accurate.
  • An embodiment of the present application also provides a filtering device, including:
  • the first acquisition module is configured to acquire one or more correlation peaks obtained by performing phase correlation calculation on the frame sequence corresponding to the detected video, where the correlation peaks are frequency domain signals;
  • the filtering strategy determination module is used to determine the filtering strategy corresponding to each correlation peak according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak;
  • the filtering module is used for filtering each correlation peak according to the filtering strategy corresponding to each correlation peak.
  • the filter device of the embodiment of the present application obtains one or more correlation peaks obtained by performing phase correlation calculation on the frame sequence corresponding to the detection video, the correlation peak is a frequency domain signal; according to the corresponding position and correlation peak of each correlation peak in the detection video
  • the corresponding frequency band determines the filtering strategy corresponding to each correlation peak; filtering processing is performed on each correlation peak according to the filtering strategy corresponding to each correlation peak.
  • the filtering strategy includes filtering bandwidth.
  • the filtering strategy determination module includes:
  • the initial filter bandwidth determining unit is configured to determine the initial filter bandwidth corresponding to each correlation peak according to the frequency band corresponding to each correlation peak;
  • the bandwidth adjustment coefficient determining unit is configured to determine the bandwidth adjustment coefficient corresponding to the correlation peak according to the corresponding position of each correlation peak in the detection video;
  • the filter bandwidth determining unit is configured to use the product of the initial filter bandwidth corresponding to each correlation peak and the bandwidth adjustment coefficient as the filter bandwidth corresponding to each correlation peak.
  • the bandwidth adjustment coefficient determining unit is configured to obtain a preset bandwidth adjustment coefficient corresponding to the area where the corresponding position of each correlation peak in the detection video is located, and use the preset bandwidth adjustment coefficient as the bandwidth adjustment corresponding to the correlation peak coefficient.
  • the filtering device further includes:
  • the dimensionality reduction module is used to reduce the dimensionality of each correlation peak by using the principal component decomposition method
  • the filtering strategy determination module is used to determine the filtering strategy corresponding to each correlation peak according to the corresponding position of each correlation peak in the detection video after the dimensionality reduction processing and the frequency band corresponding to the correlation peak.
  • the filtering device further includes:
  • the judgment module is used to compare the peak value of each correlation peak with the preset peak range, and respectively determine whether the peak value of each correlation peak is within the preset peak range;
  • the dimensionality reduction module is used to perform dimensionality reduction processing on correlation peaks whose peaks are within a preset peak range.
  • the filtering module is configured to perform filtering processing on each correlation peak by interpolation filtering according to a filtering strategy corresponding to each correlation peak.
  • each module in the above-mentioned filtering device corresponds to the steps in the above-mentioned filtering method embodiment, and their functions and realization processes are not repeated here.
  • the present application also provides a computer-readable storage medium with a filter program stored on the computer-readable storage medium, where the filter program is executed by a processor to implement the steps of the filter method in any of the above-mentioned embodiments.
  • the embodiment of the present application also provides a detection device for detecting the operating status of the device to be detected.
  • the detection device includes the filtering device of the above-mentioned embodiment or the electronic device of the above-mentioned embodiment.
  • the detection device of the embodiment of the present application obtains one or more correlation peaks obtained by performing phase correlation calculation on the frame sequence corresponding to the detection video; each correlation peak is determined according to the corresponding position of each correlation peak in the detection video and the frequency band corresponding to the correlation peak Corresponding filtering strategy; filtering each correlation peak according to the filtering strategy corresponding to each correlation peak.
  • the noise information in each correlation peak can be reduced, so that the signal-to-noise ratio of the state change signal obtained from the detection video is higher, so that the The operating status of the device to be tested obtained from the detection video is more accurate.
  • the imaging module can be used to shoot the testing video of the device to be tested when it is running, and then the status change information can be extracted from the testing video containing the screen when the testing device is running, and the status change information can be reflected
  • the vibration information of the device to be tested can be used to obtain the operating status of the device to be tested based on the vibration information of the device to be tested.
  • the frame sequence in the detection video can be converted from the RGB color space to the YIQ color space, and the brightness information and chroma information of the video frames can be separated.
  • the conversion relationship between RGB and YIQ is:
  • the Euler motion amplification algorithm to amplify the video data line. Specifically, it includes: decomposing the Y-channel image after FFT transformation into complex and manipulable gold tower spatial domain. The images of different scales decomposed in the Y-channel spatial domain are subjected to time-domain band-pass filtering. It can be understood that in the video picture, the vibration can be reflected by the brightness of the video frame sequence, then the Y channel in the detection video can be analyzed to obtain the detection video Vibration information.
  • phase correlation algorithm is used to calculate the cross power spectrum between the frame sequences on the frame sequence after the video motion amplification processing.
  • the phase correlation algorithm uses the following formula to calculate the cross cross power spectrum.
  • Fa is the Fourier transform of a frame image
  • the lower side of the division formula is the modulus of the correlation product of the two Fourier transformed signals.
  • R crosses the cross power spectrum (including frequency domain noise) of the calculation result of this step.
  • the cross cross power spectrum includes one or more correlation peaks, and the correlation peaks are frequency domain signals. It can be understood that each correlation peak can reflect the state change of a certain position in the detection video, and the phase correlation calculation of the true sequence corresponding to the detection video can be understood as the cross-power spectrum can be understood as extracting the video image from the detection video.
  • Status change information includes vibration information and other noise information.
  • the filtering method of the embodiment of the present application can be used to filter the correlation peaks in the cross cross power spectrum to reduce the noise information in the correlation peaks, so that the detection video containing the image of the detection device during operation can be extracted Among the information, the signal-to-noise ratio of the useful signal is higher.
  • the computer program product includes one or more computer instructions.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (such as a floppy disk, a hard disk, and a magnetic tape), an optical medium (such as an optical disk), or a semiconductor medium (such as a solid-state hard disk).
  • the disclosed device may also be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or integrated. To another system, or some features can be ignored or not implemented.
  • the displayed or discussed indirect coupling or direct coupling or communication connection between each other may be through some interfaces, indirect coupling or communication connection between devices or units, and may be in electrical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. . Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • the functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of this application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium
  • a number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium may include, for example: U disk, mobile hard disk, Read-Only Memory (ROM), Random Access Memory (RAM, Random Access Memory), magnetic disks or optical disks and other storable program codes. Medium.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Optimization (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Multimedia (AREA)
  • Algebra (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé et appareil de filtrage, et un produit associé. Le procédé de filtrage comporte les étapes consistant à: acquérir un ou plusieurs pics de corrélation obtenus en effectuant un calcul de corrélation de phase sur une séquence de trames correspondant à une vidéo de détection, le ou les pics de corrélation étant un ou des signaux dans le domaine fréquentiel; déterminer une politique de filtrage correspondant à chaque pic de corrélation en fonction d'une position correspondante de chaque pic de corrélation dans la vidéo de détection et d'une bande de fréquences correspondant au pic de corrélation; et effectuer un traitement de filtrage sur chaque pic de corrélation selon la politique de filtrage correspondant à chaque pic de corrélation.
PCT/CN2020/105583 2019-04-26 2020-07-29 Procédé et appareil de filtrage, et produit associé WO2021036661A1 (fr)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN201910346014 2019-04-26
CN201910815821.3A CN110674697B (zh) 2019-04-26 2019-08-30 滤波方法、装置及相关产品
CN201910815821.3 2019-08-30

Publications (1)

Publication Number Publication Date
WO2021036661A1 true WO2021036661A1 (fr) 2021-03-04

Family

ID=69075853

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/105583 WO2021036661A1 (fr) 2019-04-26 2020-07-29 Procédé et appareil de filtrage, et produit associé

Country Status (2)

Country Link
CN (1) CN110674697B (fr)
WO (1) WO2021036661A1 (fr)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110674697B (zh) * 2019-04-26 2023-04-25 深圳市豪视智能科技有限公司 滤波方法、装置及相关产品
CN114504327B (zh) * 2021-12-28 2024-05-17 深圳大学 一种脑电噪声的处理方法、装置及计算机设备
CN117576091B (zh) * 2024-01-15 2024-04-09 深圳昱拓智能有限公司 一种基于视频检测的冷却塔风机振动检测方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2187059A (en) * 1986-02-20 1987-08-26 British Broadcasting Corp Motion detector for video signal prediction systems
CN103024248A (zh) * 2013-01-05 2013-04-03 上海富瀚微电子有限公司 运动自适应的视频图像降噪方法及其装置
CN103714522A (zh) * 2014-01-06 2014-04-09 海信集团有限公司 图像降噪方法和图像降噪系统
CN110659583A (zh) * 2019-04-26 2020-01-07 深圳市豪视智能科技有限公司 信号处理方法、装置及相关产品
CN110674697A (zh) * 2019-04-26 2020-01-10 深圳市豪视智能科技有限公司 滤波方法、装置及相关产品

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2958010C (fr) * 2016-02-19 2021-09-07 Covidien Lp Systeme et methode de surveillance des signes vitaux fondee sur la video
CN107844779B (zh) * 2017-11-21 2021-03-23 重庆邮电大学 一种视频关键帧提取方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2187059A (en) * 1986-02-20 1987-08-26 British Broadcasting Corp Motion detector for video signal prediction systems
CN103024248A (zh) * 2013-01-05 2013-04-03 上海富瀚微电子有限公司 运动自适应的视频图像降噪方法及其装置
CN103714522A (zh) * 2014-01-06 2014-04-09 海信集团有限公司 图像降噪方法和图像降噪系统
CN110659583A (zh) * 2019-04-26 2020-01-07 深圳市豪视智能科技有限公司 信号处理方法、装置及相关产品
CN110674697A (zh) * 2019-04-26 2020-01-10 深圳市豪视智能科技有限公司 滤波方法、装置及相关产品

Also Published As

Publication number Publication date
CN110674697B (zh) 2023-04-25
CN110674697A (zh) 2020-01-10

Similar Documents

Publication Publication Date Title
WO2021036661A1 (fr) Procédé et appareil de filtrage, et produit associé
WO2021036662A1 (fr) Procédé et dispositif de traitement de signal, et produit associé
CN110595745B (zh) 针对设备的固定螺丝异常的检测方法及相关产品
JP6107537B2 (ja) 撮像システムおよびその画像処理方法、画像処理装置およびその画像処理方法、並びに、プログラム
JP4453648B2 (ja) 画像処理装置および撮像装置
US11272146B1 (en) Content adaptive lens shading correction method and apparatus
KR20050013245A (ko) 감지된 이미지 및 비디오의 선명도를 추정하는 방법 및시스템
US10217193B2 (en) Image processing apparatus, image capturing apparatus, and storage medium that stores image processing program
JP5765893B2 (ja) 画像処理装置、撮像装置および画像処理プログラム
JP2015122634A (ja) 画像処理装置、撮像装置、プログラム及び画像処理方法
JP2021043874A (ja) 画像処理装置、画像処理方法、およびプログラム
KR101035365B1 (ko) Ｃｓ를 이용한 화질 평가 장치 및 방법
TW200910261A (en) Image processing methods and image processing apparatuses utilizing the same
JP2012090146A (ja) 画像処理装置、および画像処理方法、並びにプログラム
JP2014146872A5 (fr)
US20130108163A1 (en) Image evaluation apparatus, image evaluation method, and program
CN112950592B (zh) 基于高维离散余弦变换的无参考光场图像质量评价方法
Bonanomi et al. I3D: a new dataset for testing denoising and demosaicing algorithms
JP5227906B2 (ja) 映像記録システム
Van Houten et al. Using sensor noise to identify low resolution compressed videos from youtube
CN110020999B (zh) 一种基于同态滤波的非制冷红外热像自适应映射方法
JP5810778B2 (ja) 画像処理装置および画像処理方法
JP2010063169A (ja) 画像処理装置および撮像装置
JP7197210B2 (ja) 画像補正システム、画像補正方法、及びプログラム
JP5539561B2 (ja) 画像処理装置およびその方法

Legal Events

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

Ref document number: 20859430

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: 20859430

Country of ref document: EP

Kind code of ref document: A1