106 results about "High-motion" patented technology

The invention discloses an event information guided image deblurring and high-frame-rate reconstruction method. The method comprises the following steps: step 1, obtaining a blurred image and an event stream corresponding to the blurred image to construct a training data set; 2, constructing a deblurring and frame insertion combined reconstruction network based on a dynamic cross-modal fusion module; step 3, training to obtain a trained joint reconstruction network based on the cross-modal attention mechanism and the UNet architecture; and step 4, inputting a to-be-reconstructed blurred image and a corresponding event stream into the trained deblurring and frame insertion combined reconstruction network based on the dynamic cross-modal fusion module to obtain a final multi-frame reconstruction image. According to the method, a higher weight dynamic state is given to an event mode in a high-speed motion scene, an image data weight is added in a static scene, and a scale feature fusion strategy is adopted for a seriously fuzzy scene, so that the problems of semantic difference and noise interference are reduced, and the image recovery quality of a fuzzy region is improved.

The invention discloses a badminton tracking method and system based on three-dimensional vision, and relates to computer vision. Badminton motion video data of a left view and a right view are synchronously collected through a binocular camera, a left view frame sequence and a right view frame sequence which are aligned in time are obtained, and the collected video data are preprocessed; obtaining standardized left and right view input frame data; according to input frame data, constructing a 2D key frame detection model based on an improved YOLOv8 network, and extracting the sum of 2D key frame coordinates of left and right views; according to the 2D key frame coordinate sum of the left view and the right view, 3D space positioning is carried out on the badminton through stereo matching and track prediction, 3D track data are obtained, according to the 3D track data, a broken track is repaired through a frame leakage compensation mechanism, and a final 3D track is obtained. In order to solve the problem that in the prior art, key frames are prone to being lost and track breakage is caused during high-speed movement such as smash, the breakage track of the shuttlecock is repaired.

The invention discloses a motion capture method based on sports equipment training, and relates to the technical field of intelligent motion capture, and the method comprises the steps: extracting a skeleton key point set of a detected object from a training ground image data stream through employing a human body key point detection algorithm, and extracting a two-dimensional contour region of sports equipment through employing a target segmentation algorithm, meanwhile, recording time index information of the corresponding image frames, performing synchronous comparison by utilizing timestamps of the training event data streams, establishing a time sequence mapping relation, and obtaining time sequence action data; taking the time sequence action data as a space anchor point, carrying out middle frame reconstruction on the high-speed motion stage based on a time sequence mapping relation, recovering an equipment motion track, and carrying out joint matching to generate a time sequence fusion sequence; establishing a multi-view geometric constraint through a time sequence fusion sequence and camera pose parameter information, and recovering a human body three-dimensional skeleton point cloud and an initial six-dimensional pose of the equipment; the space-time consistency and reconstruction precision of motion capture in a high-speed dynamic training scene are effectively improved.

The invention relates to the technical field of image communication, in particular to a video slow-action frame insertion playback system based on a generative adversarial network, which comprises a video signal acquisition module, a signal processing module, a frame rate conversion module and a playback code output module. The acquisition module outputs an original video frame sequence through an annular buffer; the processing module separates the denoised detail components and the edge gradient features in parallel; the frame rate conversion module uses a geometric structure as a boundary locking condition to guide detail components to execute nonlinear motion compensation and intermediate frame reconstruction; and the playback module executes time base remapping and distributed coding transmission. According to the invention, through a depth generation architecture of structural constraint textures, in combination with space-time consistency verification and a nearest neighbor pixel backfilling mechanism and a virtual time base rate decoupling technology, real-time slow-action video redisk with high signal-to-noise ratio and no artifacts for a high-speed moving target is realized.

The invention provides an automatic sorting and rechecking method and system for a whole pack of instant lottery tickets based on super-resolution vision, and relates to the technical field of machine vision. Details of motion blur loss are recovered through dynamic inter-frame alignment and multi-scale feature fusion, and a high-resolution image is generated. Static visual features are extracted, lottery ticket scrape-open layer film fluorescence spectrum response features of the first page of the lottery ticket bag are obtained, film material distribution characteristics are obtained through spectrum decomposition and fused into multi-modal features, the multi-modal features are matched with a standard library, and a preliminary sorting result is obtained. In the sorting process, the grabbing time sequence consistency of the mechanical arm is monitored, re-checking is started and abnormal time period characteristics are backtracked if the result reaches the threshold critical value or the time sequence is abnormal, and a re-checking report is formed if a plurality of judgment results are not consistent, so that the accuracy and reliability of automatic sorting of the whole lottery ticket can be guaranteed.

For controlling reconstruction in emission tomography, the quality of data for detected emissions and / or the application controls the settings used in reconstruction. For example, a count density of the detected emissions is used to control the number of iterations in reconstruction to more likely avoid over and under fitting. The count density may be adaptively determined by re-binning through pixel size adjustment to find a smallest pixel size providing a sufficient count density. As another example, the detected data may have poor quality due to motion or high body mass index (BMI) of the patient, so the reconstruction is set to perform differently (e.g., less smoothing for high motion or a different number of iterations for high BMI). The quality of the data may be used in conjunction with the application or task for imaging the patient to control the reconstruction.

The invention relates to the technical field of computer vision and image processing, in particular to a foreground detection method fusing wavelet transform and a prompt mechanism, which is characterized in that in a dynamic background, high-speed motion and small target scene, F-measure is averagely improved by more than or equal to 0.30, and the detection precision is obviously superior to that of FFNet and ASCNet. The wavelet transform attention module suppresses background noise, highlights target edges and textures, and improves input feature purity. The CFF, MFR and PB of the decoder collaboratively fuse multi-scale features, redundant information is reduced, and target details and contour integrity are reserved. According to integral end-to-end training, single-frame reasoning only needs 28 ms, and real-time performance and accuracy are both considered. Therefore, the problems that in an existing neural network foreground target detection algorithm, input data are often influenced by noise and background interference, redundant information is easily introduced into a decoder in the multi-level feature fusion and transmission process, and consequently the detection result is inaccurate are solved.

The invention discloses an event camera image reconstruction method of a multi-frame fusion network based on optical flow guidance, and belongs to the technical field of computer vision and image processing. The method comprises the following steps of: 1, acquiring event data, and converting the event data into continuous and smooth space-time voxels by adopting a full-time interval voxel coding scheme based on Gaussian distribution; step 2, constructing an FMF-Net network guided by an optical flow; step 3, designing a comprehensive loss function used for training the FMF-Net network; 4, performing supervised training on the FMF-Net network by using the public event data set; and step 5, inputting space-time voxels by using the trained FMF-Net network, and outputting a high-fidelity reconstructed image. According to the method, long-time motion clues and time domain dynamic features can be fully utilized, high-fidelity image reconstruction is realized under high-speed motion and sparse event input, the problems of loss of reconstruction details and poor consistency of an existing method in a dynamic scene are solved, and the structural similarity and visual quality of a reconstructed image are remarkably improved.

The invention provides a camera-based AI visual recognition and prediction control method and related equipment, and the method comprises the steps: obtaining continuous image frames of a moving object, and recognizing the skeleton key point coordinates and appearance feature information of the moving object; inputting the skeleton key point coordinates and the appearance feature information into a preset time sequence neural network model to obtain a motion prediction track; performing space mapping on the centroid coordinates of the moving object according to the motion prediction trajectory, and determining focal length control parameters of the camera; meanwhile, angle mapping is carried out on the position offset of the moving object, and pan-tilt control parameters are determined; and tracking and shooting the moving object according to the focal length control parameter and the holder control parameter. Through the mode, the camera can complete the pre-adjustment of the focusing mechanism and the composition direction before the target motion trend occurs, thereby effectively reducing the delay error in the focal length switching process, and improving the clear imaging rate and composition stability of a high-speed motion main body.

The invention discloses an ultrahigh-speed imaging method, device and system of an event camera, and belongs to the technical field of image processing. The method comprises the following steps: acquiring a superpixel segmentation mask of a motion area according to an event trigger position and an image appearance-position feature, selecting event points in the superpixel segmentation area for continuous time point tracking, and calculating an optical flow field with continuous time and dense space by combining a point tracking time sequence track and the spatial superpixel mask. An imaging result of any to-be-imaged moment t between the two frames is calculated by using the optical flow field, and high-precision imaging of an ultra-high-speed motion scene can be realized.

1. Name of the product in this design: Camera (High-speed camera - SH3). 2. Purpose of this design: This design is used for photographing high-speed moving targets. 3. The key design features of this product are its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

This invention relates to the field of 3D geometric modeling engine technology, specifically to a method for rapidly displaying Points of Interest (POI) information from a 3D real-world model. The invention first monitors the motion state of a virtual camera, reusing historical states during high-speed movement to avoid image jumps caused by aliasing. Second, it calculates the original occlusion distance of the POI and quantifies the physical depth difference between it and the scene. Then, by analyzing the local window depth distribution, it obtains discrete suppression weights to correct the original distance, adaptively distinguishing between solid and discrete structures, suppressing vegetation noise while maintaining high sensitivity to building edges. Finally, it constructs a state update cost based on the corrected distance and introduces hysteresis decision logic, setting a potential energy threshold for state switching, effectively reducing flickering in critical areas. This significantly improves the accuracy and stability of POI information display.

1. The name of this design product: Online vertical high-speed motion machine. 2. Application of this product design: Positioning and dispensing of micro-precision products. Driven by a high-speed linear motor, it can achieve high-speed and precise positioning. A micro-injection system is used to apply adhesive to the narrow locations of tiny products, such as wafers, FPCBs, COMS and other high-requirement products. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

A virtual stereovision imaging array system and a moving target three-dimensional reconstruction method, the system comprises multiple cameras and multiple galvanometer mirrors, the galvanometer mirrors and the cameras are matched one by one, and a real-time controllable virtual camera array is formed; through synchronous control of the galvanometer mirrors, each virtual camera simultaneously tracks and locks the moving target; based on the real-time pose relationship between the virtual cameras and combined with the synchronously acquired image information, real-time three-dimensional reconstruction of the moving target is completed. The reconstruction method comprises joint calibration of the matched galvanometer mirrors and the cameras, determination of camera internal parameters and virtual camera external parameters; through real-time synchronous adjustment of the galvanometer mirrors, each virtual camera cooperatively tracks the moving target, acquires the moving target image, and updates the virtual camera external parameters in real time; in each frame of image, stereo matching is performed, and combined with the real-time updated virtual camera external parameters, the three-dimensional point cloud of the moving target is solved and obtained. The present application can complete high-efficiency and high-precision three-dimensional reconstruction of a high-speed moving target in a large field of view.

The invention relates to a ping-pong robot track recognition and ball hitting posture control system, which comprises a table surface environment sensing module, and is characterized in that the table surface environment sensing module is used for acquiring three-dimensional track data, table surface environment parameters and event signals of ping-pong balls in real time through a high-speed camera array unit and an environment state sensor unit; and a time label and a frame number are added to each frame of data, and the data are uniformly output to the multi-stage track processor module. A high-speed camera shooting array and a multi-source environment sensing technology are adopted, the three-dimensional space track of the table tennis ball can be captured in real time, dynamic adjustment is conducted according to table surface environment parameters, the multi-stage track processor can effectively remove noise and accurately extract track characteristics through a Kalman filtering self-adaptive algorithm, and therefore the table tennis ball track detection accuracy is improved. Compared with a traditional system, the system has the advantages that track recognition errors can be greatly reduced, and more accurate ball hitting angle and opportunity control can be provided.

The application discloses a kind of ultra-high speed imaging method, device and system of event camera, belong to image processing technical field;The present application obtains the superpixel segmentation mask of motion area according to event trigger position and image apparent-position feature, selects event point in superpixel segmentation area to carry out continuous time point tracking, combines point tracking time sequence track and space superpixel mask to calculate continuous time and space dense optical flow field, uses optical flow field to calculate the imaging result between two frames at any imaging time t, can realize the high-precision imaging of ultra-high speed motion scene.

The invention relates to the technical field of image processing and the technical field of automation, and particularly discloses a woodworking table saw safety detection method based on machine vision, compared with a traditional mechanical limit switch (the response time is greater than or equal to 500ms), the time difference from dangerous action to safety response is greatly shortened, and the safety of a woodworking table saw is improved. According to the method, cutting injury caused by misoperation and distraction is effectively avoided, the safety of hands and limbs of an operator is protected, non-contact detection is adopted, interference of wood dust is avoided, a high-speed movement scene can be responded in real time, and the safety and reliability of woodworking operation are effectively improved.

The application discloses a high-speed motion three-dimensional point tracking and trajectory reconstruction method and system, and relates to the technical field of three-dimensional point tracking. The method comprises the following steps: synchronously collecting an RGB image sequence and an event stream through a binocular multi-modal observation device; performing time alignment on the RGB image sequence and the event stream, extracting an RGB feature map based on the RGB image sequence, and extracting an event feature map based on the event stream; mapping the RGB feature map and the event feature map to a three-dimensional space; supplementing a three-dimensional feature point cloud through a linear interpolation algorithm; balancing the spatial distribution of the supplemented three-dimensional feature point cloud through an anchor point sampling algorithm to obtain a fused three-dimensional feature point cloud; and generating high-speed three-dimensional point trajectory data based on the fused three-dimensional feature point cloud through a time correlation transformer. The application effectively fuses the texture fidelity of the RGB image and the high time resolution of the event data, and can realize high-frame-rate and high-precision three-dimensional point trajectory reconstruction in a high-speed motion scene.

The application discloses a motion training evaluation system and method based on cooperation of an event camera and a visual camera, and is applied to the field of computer vision, and aims at the problems that an existing training evaluation system based on an optical camera cannot capture fast motion trajectories and limb shapes, cannot effectively evaluate action quality, and cannot provide effective training guidance; the application provides continuous human motion events in the form of event streams, can achieve millisecond-level motion response, is not affected by motion blur effects of high-speed moving objects, and can provide a higher dynamic range, and can provide more effective motion training evaluation in scenes with strong light, backlight, and sharp changes in brightness. Through cooperation of the visual camera and the event camera, not only the accuracy of fast actions can be evaluated, but also standard action teaching and training in the form of visual scene interaction can be performed.

This invention discloses a precision detection method and system for surface defects in metal strips, relating to the interdisciplinary fields of mechanical engineering and machine vision. The method includes: synchronously acquiring multi-band images using a multispectral light source and an industrial camera array; establishing a spatiotemporal synchronization model based on encoder speed signals and performing sub-pixel-level image registration to correct motion distortion; adaptively fusing multispectral images based on a material-spectral response database to enhance the signal-to-noise ratio of micro-defects; employing a lightweight deep learning model to achieve pixel-level defect segmentation and classification; and extracting defect geometric parameters and automatically classifying them using a process tolerance library. This invention aims to solve the problems of narrow material applicability, severe image distortion under high-speed motion, low micro-defect detection rate, and complex system deployment in existing technologies. It achieves high-precision, high-speed online detection of non-ferromagnetic metal strips, significantly improving the sensitivity to micron-level defects, system robustness, and ease of deployment.

The invention discloses a projection screen image quality optimization processing method and terminal based on an intelligent agent identification video source, and relates to the technical field of video processing, and the method comprises the steps: selecting a projected screen device through a voice projection screen instruction to complete projection screen connection; the voice control instruction is converted into a control signal for current projection screen connection, and the control signal is sent to the projection screen end through a reverse channel, so that the projection screen content of the projection screen end is directly controlled, or the projection screen equipment is directly controlled according to the voice control instruction; identifying the signal source type of the current input video source; analyzing the inherent frame rate and the resolution of the input video source, and when the screen projection device detects that the video source is a predetermined low-frame-rate content or a predetermined high-speed motion content, determining that the video source is a high frame compensation income scene; and a motion estimation and motion compensation frame compensation function is automatically started to insert a calculation frame between original frames for frame compensation. According to the invention, the video content can be automatically identified, optimization functions such as frame compensation can be intelligently started, and meanwhile, the screen projection experience of voice interaction can be realized in the whole process, so that the use convenience and immersion of a user are greatly improved.

The embodiment of the invention provides a time sequence controllable non-contact deformation measuring method and device, computer equipment and a medium, and relates to the technical field of optical measurement experiment mechanics, and the method comprises the following steps: determining time sequence control parameters, internal and external parameters and a coordinate system transformation matrix of an industrial camera; collecting a sequence diagram of the surface of the measured object based on the trigger signal, triggering the light source to provide illumination to generate a first data stream, and controlling the event camera to output a second data stream of pixel brightness change of the surface of the measured object; analyzing the second data stream, and dynamically controlling image acquisition of the industrial camera according to the instantaneous motion state parameters; and carrying out digital image correlation matching and three-dimensional reconstruction to obtain a high spatial resolution deformation field of the measured object at the sampling moment, and carrying out event-driven three-dimensional reconstruction to generate a three-dimensional deformation measurement result. According to the scheme, the contradiction between clear imaging and long-time continuous acquisition of the high-speed moving object is solved through sequential control parameters combining short exposure and long interval.

The invention belongs to the technical field of industrial camera anti-blurring, and discloses an industrial camera system for resisting high-speed motion blurring, which forms a complete closed loop from physical compensation to software repair through coupling of hardware active anti-shake and software deconvolution, and can effectively solve the problem of mixed blurring in an industrial scene. The hardware end is driven by piezoelectric ceramics and flexible damping in a combined manner, and is matched with real-time data of a six-axis IMU, so that low-frequency uniform-speed vibration and high-frequency instantaneous impact can be quickly counteracted; a software end deduces a fuzzy kernel based on an IMU track, residual fuzzy is restored through Fourier domain deconvolution, and fuzzy elimination is more thorough than that of a traditional single hardware or software scheme; when the device is actually used for metal part detection, tiny cracks which cannot be seen clearly due to fuzziness can be clearly presented now, so that the reliability of defect identification is improved, and the 0.1 mm level detection precision requirement in industrial production is met; and the imaging frame rate is stabilized to be more than 100fps while the precision is ensured, and the method can cope with scenes with high real-time requirements.

This invention discloses an anti-blurring dual-stream surface defect detection method and apparatus for industrial vision, relating to the fields of image processing and computer vision. The method acquires surface images of metal parts under high-speed motion environments; inputs a pre-constructed anti-blurring dual-stream feature enhancement network, which includes an adversarial detail recovery subnetwork and an inter-layer feature reshaping subnetwork set in parallel with a shared backbone; the backbone network includes a multi-scale guidance module, fusing residual dense connections, spatial-channel attention, and multi-scale convolution to enhance feature representation; outputs high-frequency detail images through the adversarial detail recovery subnetwork and pixel-level defect segmentation images through the inter-layer feature reshaping subnetwork; locates defect regions based on the segmented images and extracts image patches from the high-frequency images; finally, inputs the defect recognition subnetwork to output classification results; this invention improves the accuracy and robustness of defect detection in high-speed environments by collaboratively optimizing detail reconstruction and segmentation through a dual-stream network.

This invention discloses a motion blur compensation image enhancement method for high-speed cameras, relating to the field of computer vision technology. The method includes acquiring raw sequence data recorded by a high-speed imaging device, analyzing overlapping regions of adjacent frames in the sequence using a temporal convolutional network to determine the temporal continuity features corresponding to highly overlapping frames, obtaining a separated frame sequence, and using an optical flow estimation algorithm to track the object's movement trajectory based on the separated frame sequence. If the optical flow vector exceeds a preset threshold, it is judged as an interference factor in a dynamic scene, resulting in a motion-compensated frame sequence. This motion blur compensation image enhancement method for high-speed cameras not only improves the accuracy of image enhancement but also enables real-time and accurate extraction of key information frames in complex dynamic environments, optimizing the defect detection process. It has broad application prospects, particularly in high-speed motion analysis and industrial inspection, significantly improving detection efficiency and accuracy.

The invention belongs to the technical field of image processing, and particularly relates to an image recognition system and an image recognition sensor applied to a camera, and the system comprises an image recognition module, a preprocessing module, a texture recognition module, an optical flow track module and a camera tracking module which are in communication connection in sequence. FPGA hardware acceleration is combined with redundancy reduction of particle screening, so that an image recognition system can stably perform full-link processing on a high-speed camera, and the non-delay tracking requirement of a high-speed moving target is met; through a texture channel fused by multiple edge channels, the edge integrity rate in a high-speed motion fuzzy scene is improved, and the tracking loss rate of light field particles is reduced; through a designed double-constraint optical flow mechanism, the optical flow estimation error of a high-speed moving target is reduced, the inter-frame position deviation of camera tracking is reduced, and accurate positioning of the high-speed target is realized, so that the problems of image precision reduction and tracking breakage caused by high-speed movement of the target in high-speed camera image recognition are solved.

The application provides a stage light tracking control method and system based on target positioning, the method comprises collecting a video stream and obtaining a candidate box through target detection, and determining a main feature area of a human body through pose estimation; the input length of three-dimensional convolution is adjusted based on a time sequence light fluctuation index, global features are extracted, and attention weights are assigned to local texture features of the main feature area; a motion pattern signature is constructed using sparse optical flow of skeletal key points, a target re-identification vector is generated by fusing the global features and weighted local features, and a historical feature library is matched; the fusion weight of position prediction and feature measurement in a cost matrix is adjusted according to the amplitude of the motion pattern signature, and target matching is completed; a virtual aiming point is calculated based on the key point confidence of the matched target, a position compensation amount is generated by combining a light mapping model and sparse optical flow, and a control instruction is output to drive the light to continuously track stage characters, thereby improving the tracking stability and alignment accuracy under complex lighting and high-speed motion scenes.