23 results about "Motion magnification" patented technology

The invention relates to a bridge structure modal parameter identification method, which is based on a bridge structure tiny vibration video acquired by a camera. VMD (variational mode decomposition), PBVM (phase-based video motion amplification), Gabor filtering-based phase extraction method GBP (Gabor filtering), an improved clustering algorithm ICA (independent clustering algorithm) and an integrated covariance-driven random subspace recognition (SSI-Cov) and FDD (frequency domain decomposition) algorithm are fused to construct a set of complete non-contact structural modal parameter recognition system. According to the method, effective decoupling of multiple vibration modes of a bridge structure, frequency domain feature extraction of small-amplitude vibration and intelligent and automatic modal parameter extraction are achieved under the conditions that the target frequency bandwidth does not need to be known in advance, environmental noise interference exists and no obvious feature target exists, and the method belongs to the technical field of bridge structure health monitoring.

The invention relates to the technical field of computer vision and video processing, in particular to a video motion amplification method based on a cyclic generative adversarial network, which comprises the following steps: inputting a reference frame, a query frame and a motion amplification factor into a trained video motion amplification model for motion amplification; during training, an amplification frame is constructed and generated through the motion amplification module; constructing and generating a reference frame through a motion reduction module; discriminating the difference between the generated amplified frame and the corresponding real amplified frame through a first discriminator; discriminating the difference between the generated reference frame and the corresponding reference frame through a second discriminator; and a fusion loss calculation module calculates fusion loss and optimizes network parameters by combining the difference between the generated amplified frame and the corresponding real amplified frame and the difference between the generated reference frame and the corresponding reference frame according to the discrimination results of the first discriminator and the second discriminator. According to the method, high fidelity and high robustness can be realized in various complex scenes, and video motion amplification of artifacts can be effectively inhibited.

This invention relates to the field of defect detection technology in image recognition, specifically disclosing a method and system for detecting defects in mobile phone SIM card tray manufacturing based on image recognition. By acquiring multiple frames of time-series images and performing sub-pixel-level spatiotemporal registration, the influence of mechanical vibration and displacement deviation is eliminated. The optical flow field is calculated, and local strain tensors, optical flow vorticity, and motion consistency entropy are extracted to construct a time-varying feature matrix. Frequency domain decomposition and motion amplification are performed on the feature matrix to enhance the signal response of minute defects. Dynamic time-domain features and static image features are fused to establish a deep learning-based defect detection model. Finally, a defect probability cloud map is generated, and the defect type and location are output using a dynamic threshold mechanism. This invention achieves high-precision and high-efficiency automatic detection of minute defects in mobile phone SIM card trays, exhibiting good stability and adaptability.

The invention relates to the technical field of micro-expression recognition, in particular to a micro-expression recognition method based on motion amplification and hierarchical Transform. According to the technical scheme, the method comprises the following steps: performing motion amplification processing on a start frame and a peak value frame in a micro-expression video sequence to obtain an amplified peak value frame; calculating an optical flow graph between the start frame and the amplified peak frame based on an RAFT optical flow estimation method; and inputting the optical flow diagram into a hierarchical Transform network, and extracting motion relation characteristics among all the parts of the face. According to the method, a weak motion signal of a micro expression is enhanced through a motion amplification technology, key face areas such as eye peripheries and mouth corners are accurately focused by using a local attention mechanism in a hierarchical Transform, multi-scale feature fusion is realized in combination with block aggregation, and finally higher recognition accuracy and stronger generalization ability are verified in a plurality of data sets.

The application relates to the technical field of motion regulation and driving, in particular to a reciprocating motion amplification device and method of a flexible structure of a swing bridge. The reciprocating motion amplification device comprises a loading unit, an excitation execution unit, a self-adaptive identification unit and an energy supply unit. The excitation execution unit and the self-adaptive identification unit are both installed in the loading unit. The self-adaptive identification unit collects vibration response signals of the flexible target structure in real time and identifies the real-time natural frequency, controls the excitation execution unit to adjust the excitation frequency, so that the excitation frequency is automatically matched with the real-time natural frequency, resonance effect is excited, and reciprocating motion amplification is realized. Through closed-loop self-adaptive control, frequency drift is automatically tracked without manual intervention, excitation power consumption is reduced while the significant amplification effect is maintained, and the system adaptability and intelligent level are improved.

The application discloses a power transmission line power warning safety monitoring method and system based on image recognition, and belongs to the field of power transmission line monitoring. The method comprises the following steps: acquiring a video image sequence containing a power transmission conductor to be monitored, segmenting a conductor area, selectively amplifying vibration motion, and obtaining a motion amplified video; extracting a sub-pixel level vibration displacement time domain signal from the video, performing a running modal analysis, identifying structural modal parameters of the conductor, and constructing a modal fingerprint feature according to the parameters and comparing the modal fingerprint feature with a normal state benchmark to generate an abnormality saliency map and perform abnormality judgment. When an abnormality exists, warning information containing an abnormal position is output. The application solves the technical problem that the existing image monitoring technology has low high-order modal parameter identification precision, and it is difficult to early warn and position local minor damage.

This invention discloses a method for magnifying minute motion in reconstructed image sequences based on event streams, solving the problem of blurred minute motion details in poorly reconstructed images, belonging to the field of computer vision. The method includes: converting the original event stream data of the target in the task into a grayscale image sequence; performing a Fourier transform to obtain a frequency domain sub-band set; introducing a complex controllable pyramid algorithm to obtain a feature sub-band set with multi-scale and multi-directional joint characteristics, separating phase component sets and amplitude component sets; performing S-transform time-frequency filtering on the separated phase component set to obtain a phase component set in the time-frequency domain, and obtaining an enhanced phase component set based on a linear amplification factor; fusing the enhanced phase component set and the separated amplitude component set sub-band by sub-band to obtain a reconstructed frequency domain sub-band set, and outputting a magnified minute motion image sequence after Fourier inverse transformation to the time domain. This invention achieves accurate extraction of motion information from poorly reconstructed images.

The invention discloses a mobile vibration inspection system and method carried on a mechanical dog, and relates to intelligent detection. The method comprises the following steps: preprocessing video data to obtain preprocessed video data; performing complex controllable pyramid decomposition on the preprocessed video data to obtain multi-scale and multi-direction amplitudes and phase differences of each frame of video; according to the phase difference, adopting a phase optical flow method to extract vibration displacement; performing Fourier transform frequency analysis on the vibration displacement to obtain vibration frequency characteristics; and according to the obtained amplitude and phase difference and the obtained vibration frequency characteristics, amplifying and reconstructing the original video to obtain a reconstructed video after motion amplification. Aiming at the poor reconstruction stability of the motion video, the method achieves the video stabilization processing through an ORB algorithm and affine transformation, carries out the multi-scale decomposition through a complex controllable pyramid, employs a phase optical flow method to extract the tiny vibration, achieves the amplification of the tiny vibration while maintaining the quality of the video, and improves the reconstruction quality of the video.

The invention discloses a fixed asset change state acquisition method and device, which are applied to the field of financial science and technology, and the method comprises the steps: carrying out the motion amplification of a collected fixed asset video, which comprises a starting frame, to obtain a reconstruction frame; according to the starting frame and the reconstruction frame, an optical flow feature map is obtained, and the optical flow feature map comprises optical flow features representing dynamic changes of the fixed assets; and inputting the optical flow feature map into a pre-constructed fixed asset identification model to obtain a target fixed asset change state. According to the method, the optical flow feature map is obtained through the collected asset video, the optical flow feature map is input into the fixed asset identification model, and the change state of the fixed assets is accurately identified through the model, so that the change state of the fixed assets is accurately and efficiently obtained, and the safety of credit assets is improved.

Embodiments of the present application provide a fault detection method and device based on motion amplification, and relate to the field of fault detection. The fault detection method comprises: acquiring a video signal and obtaining continuous multiple frames of original image signals containing a fault detection object and corresponding digital image signals from the video signal; obtaining full-field vibration displacement information of the fault detection object after image multi-scale analysis; extracting phase information from the full-field vibration displacement information based on a preset amplification multiple and a preset modal order, replacing local phase information of the corresponding digital image signals, and obtaining image information of each frame of digital image signals; and synthesizing each frame of digital image signals with corresponding image information to obtain continuous multiple frames of digital image signals that are motion amplified. The present application performs conversion, analysis, amplification, synthesis and other processing means on the original image signals after the video signal is acquired, and obtains motion amplified images in which the fault of a component can be identified by the naked eye, so that fault detection is convenient and automated.

The application discloses a kind of multi-modal perception methods based on armored vehicle shooting simulation evaluation, comprising, obtaining the physical perception data of visual image sequence and vibration signal sequence and the digital simulation data of shooting data sequence;Visual image sequence is processed with motion amplification, and vibration signal sequence is processed with time-frequency conversion;The processed physical data and digital data are input into double-flow neural network model, and the measured and theoretical feature coding of binary is output;The hamming distance of feature coding is calculated, when the distance is greater than threshold value, the physical compensation parameter is calculated according to the coding difference using decoder network, and is written into fire control system error compensation unit.The application realizes the quantization comparison of physical world response and digital world instruction in unified space by cross-modal feature fusion and hash mapping, and constructs the correction link from deviation evaluation to parameter inversion, improves the accuracy of shooting simulation evaluation and the intelligent level of fire control system error correction.

The invention discloses a deep learning-based method for identifying infinitesimal displacement of a structure in a video, which belongs to the technical field of structure health monitoring and comprises the following steps of: 1, acquiring original video data of the displacement of the structure; 2, inputting the original video into a pre-trained motion amplification network model, and carrying out motion amplification processing to generate a motion amplification video; 3, inputting the motion amplification video into a pre-trained video super-resolution network model, wherein the video super-resolution network model performs super-resolution reconstruction on the motion amplification video through a bidirectional propagation mechanism, a second-order connection mechanism and an optical flow guide deformable alignment strategy; according to the method, the STB-VMM network model and the Basic VSR + + network model are combined, joint optimization of motion amplification and super-resolution is achieved, artifacts generated when the motion amplification factor is large are reduced, and the problem that the video image quality is low after motion amplification is solved.

The application discloses a video motion amplification method, system, device and storage medium, and relates to the technical field of computer vision and image processing, and comprises the following steps: converting a video sequence to be amplified into a continuous frame sequence; inputting a current frame and a reference frame in the frame sequence into a video motion amplification model to obtain a motion amplified image; wherein the video motion amplification model comprises a shallow feature extraction module and a motion feature extraction module, the motion feature extraction module comprises a down-sampling module, a deep feature extraction module, a controller, a decoder and an up-sampling module. By adopting a state space model as the core architecture of the deep feature extraction module and the decoder, the model can realize long-distance dependence modeling on an image feature sequence with linear calculation complexity, and the processing efficiency of video motion amplification is significantly improved.

The invention discloses a multi-modal sensing method based on armored vehicle shooting simulation evaluation. The method comprises the steps that physical sensing data of a visual image sequence and a vibration signal sequence and digital simulation data of a shooting data parameter sequence are obtained; performing motion amplification processing on the visual image sequence, and performing time-frequency transformation processing on the vibration signal sequence; inputting the processed physical data and digital data into a double-flow neural network model, and outputting binary actual measurement and theoretical feature codes; and calculating the Hamming distance of the feature codes, and when the distance is greater than a threshold value, calculating a physical compensation parameter according to the coding difference by using a decoder network, and writing the physical compensation parameter into a fire control system error compensation unit. Through cross-modal feature fusion and Hash mapping, quantitative comparison of physical world responses and digital world instructions in a unified space is achieved, a correction link from deviation evaluation to parameter inversion is constructed, and the accuracy of shooting simulation evaluation and the intelligent level of error correction of a fire control system are improved.

The invention discloses a three-dimensional micro-motion amplification method based on 3D Gaussian, and relates to the technical field of three-dimensional motion amplification, and the method comprises the steps: constructing a static space learning network, extracting the spatial features of a 3D point cloud of a static space image, calculating a 3D scene structure of the static space image, and carrying out the rasterization imaging; constructing a micro-motion learning network, sharing parameters of the static space learning network to the micro-motion learning network, extracting spatial features and micro-motion features of the 3D point cloud of the micro-motion image, adding the spatial features and the micro-motion features to obtain complete micro-motion information, calculating a 3D scene structure of the micro-motion image according to the amplified micro-motion information, and performing rasterization imaging. And a micro-motion magnified image is obtained. According to the invention, the limitation that a traditional two-dimensional motion amplification method can only process the motion information of a plane image is overcome, and effective amplification of micro-motion with a three-dimensional structure is realized.

The application relates to a bridge structure modal parameter identification method, which is based on a bridge structure micro-vibration video collected by a camera, fuses a variational mode decomposition (VMD), a phase-based video motion magnification (PBVM), a Gabor filter-based phase extraction method (GBP), an improved clustering algorithm (ICA) and an integrated covariance-driven stochastic subspace identification (SSI-Cov) and frequency domain decomposition (FDD) algorithm, and constructs a complete non-contact structure modal parameter identification system. In the absence of prior knowledge of the target frequency bandwidth, environmental noise interference and without obvious characteristic targets, the effective decoupling of multiple vibration modes of the bridge structure, the frequency domain feature extraction of small-amplitude vibration and the intelligent and automatic modal parameter extraction are realized, and the application belongs to the technical field of bridge structure health monitoring.

The application discloses a motion magnification adjustment method and device, a robot and a storage medium. The method comprises the following steps: calculating a real-time joint torque of the robot in a motion process; calculating a motion planning magnification based on the real-time joint torque and a reducer torque limit value; and adjusting an original motion magnification of the robot by using the motion planning magnification, so that the real-time joint torque does not exceed the reducer torque limit value. The application can avoid that the real-time joint torque exceeds the reducer torque limit value, and improve the service life of the reducer.

The application discloses a video motion magnification method based on a Transformer network, and steps of the method comprise the following steps: 1, extracting motion representation by using a proposed motion representation encoder; 2, calculating the difference of the motion representation to obtain motion changes; 3, performing nonlinear magnification by using a proposed motion magnification conversion module to obtain magnified motion representation; 4, fusing the magnified motion representation with the features of the motion representation of a query frame; 5, obtaining fine magnified fusion features by using a proposed multi-refinement decoder; and 6, reconstructing a high-quality motion magnification image. The application can quickly and accurately magnify and visualize the micro motion in a video which is difficult for the human eye to observe, and the proposed Transformer network can effectively suppress problems such as ringing artifacts, noise and motion blur existing in the motion magnification video, so that a high-quality motion magnification video can be generated.

The invention discloses an inhaul cable force identification method, device and equipment based on a high-order vibration mode. The method comprises the following steps: acquiring a vibration video of a stay cable, amplifying the vibration video by using a phase-based motion amplification algorithm to obtain an amplified vibration video, acquiring vibration displacement of the stay cable in the amplified vibration video by using a center line detection algorithm, and acquiring a high-order vibration mode of the stay cable by using a preset subspace recognition method according to the vibration displacement. And calculating the middle half-wavelength of any two-order high-order vibration mode, and determining the cable force of the inhaul cable according to the middle half-wavelength. According to the scheme, when the cable force of the inhaul cable is calculated, the effective length of the inhaul cable is replaced with the middle half-wavelength of the high-order vibration mode, the influence of complex boundary conditions on calculation of the effective length of the inhaul cable can be eliminated, and therefore the recognition precision of the cable force of the bridge inhaul cable is improved.

The invention discloses a rotating body three-dimensional vibration displacement measurement method based on deep learning and motion amplification by using a binocular camera, and the method comprises the steps: collecting a calibration image in a static state of a rotating body; constructing a first data set in the motion state of the rotating body; performing vibration feature enhancement on the rotating body vibration image in the first data set according to a phase-based motion amplification algorithm to obtain a second data set; constructing a third data set according to the second data set; training and verifying the improved YOLOv11 deep learning detection model by using a training set and a verification set in the third data set to obtain a frozen model; performing rectangular frame detection on a test set in the third data set according to the frozen model to obtain a fourth data set; taking a vibration image of the test set and a rectangular detection frame in the fourth data set as input of a target tracking network, and taking a result obtained through the target tracking network as a fifth data set; and obtaining the three-dimensional vibration displacement data of the rotating body according to the calibration image and the fifth data set. According to the three-dimensional vibration measurement method, sub-pixel-level center point matching is achieved through the improved YOLOv11 network, motion amplification is combined to enhance tiny vibration signal feature target tracking, target tracking is introduced to optimize time sequence data relevance, and the accuracy and robustness of the three-dimensional vibration measurement method are effectively improved.

A kind of video motion amplification software system for inspection, it is characterized in that, it includes following calculation steps, (1) read in a short video data, (2) to each frame image is carried out spatial low-pass filtering and is reduced sampling, record result as b, (3) select the attention area of b, record as b1, (4) to b1, select the average value of the feature of each frame image the color or color combination of pixel, waveform and frequency spectrum analysis are carried out to time sequence of feature value average value, combine priori knowledge, try and finally determine the type, cut-off frequency and order parameter of time band-pass filter, (5) according to the determined parameter, time band-pass filtering is carried out to video b pixel by pixel, the result is recorded as video c, (6) video c is enlarged according to the configured amplification parameter G, and add original video b, then constitute the final enlarged video, record as d, there is d=G*c+b;Each step involves process parameter supports man-machine interaction mode setting and adjustment.

The application relates to the technical field of pain classification, in particular to a facial pain expression grading evaluation method and device based on visual learning, which comprises the following steps: acquiring an RGB-D video stream of a target patient's facial pain expression, acquiring an RGB video frame sequence and a depth video frame sequence according to the RGB-D video stream; performing 3D key point detection on the RGB video frame sequence according to the depth video frame sequence to obtain a 3D key point sequence of the RGB video frame; and performing micro-motion amplification on the RGB video frame sequence to obtain an enhanced RGB video frame sequence. Through micro-motion amplification on the RGB video frame sequence, the facial expression can be enhanced, and some subtle muscle movements and expression changes can be captured, which is crucial for accurate identification of pain expressions; and through construction of a muscle movement vector field and combination of an anatomic related action graph, the coordinated movement of facial muscles can be modeled more finely, so that the recognition accuracy of facial actions is improved.

Provided is a non-invasive vital sign monitoring method, electronic device, and storage medium. The method comprises: acquiring real-time infrared video images in a sleep monitoring environment; performing sleep state monitoring on a subject in the real-time infrared video image to obtain a first target image indicating that the subject has entered a sleep state; performing motion magnification on the first target image according to preset vital sign information to obtain a second target image; performing target region extraction on the second target image to obtain a region associated with the preset vital sign information; and extracting vital signs from the target region to obtain the subject's vital sign information. The invention achieves accurate, non-invasive monitoring of vital signs during sleep.