136 results about "Image motion" patented technology

The invention relates to the related technical field of computer vision, in particular to an event-guided image motion deblurring method in a real scene, which comprises the following steps of: 1, constructing an event-image two-branch fusion deblurring network, and obtaining effective information in a blurred image and an event stream to realize motion blurred image restoration; and 2, in the event branch, converting a spatially sparse event stream into a dense three-dimensional tensor form by using a voxel grid event representation method, and obtaining a spatio-temporal motion feature representation of the event through a spatio-temporal motion enhancement module. According to the event-guided image motion deblurring method in the real scene, an event stream in exposure time is divided into N time slices, the N time slices are respectively accumulated into 2xHxW event frames according to polarities, a 2NxHxW three-dimensional event tensor is constructed, time sequence dependency in 2N event channels is modeled by adopting a bidirectional channel scanning strategy based on a selection state space model, and the time sequence dependency in the 2N event channels is calculated. Information of motion over time over the exposure time is modeled.

The invention relates to the technical field of image motion analysis, in particular to a rectal cancer radiotherapy effect dynamic monitoring system combined with iconography analysis. Determining a reference recovery index representing the recovery effect from the dimensions of edge change and area change according to the characteristic that the lesion area becomes smaller and smaller along with the better and better treatment effect; then, based on the reference recovery index and in combination with the characteristic that rectum tissue circularity can cause gradual inward contraction of a lesion area and the edge is smoother and smoother, determining a more accurate shape recovery degree representing the reference recovery index; therefore, the corrected radiotherapy recovery curve is corrected more accurately according to the shape recovery degree, and dynamic monitoring of the rectal cancer radiotherapy effect is more visual and accurate.

The invention discloses a self-adaptive environment image processing method for industrial gas detection, which relates to the field of industrial gas detection and comprises the following steps: extracting feature points of a current frame by utilizing a feature point detection algorithm according to image frames of an industrial monitoring video stream, and acquiring coordinates of feature points between frames by combining an optical stream tracking technology; generating affine transformation parameters, performing transformation decomposition on the coordinates of the feature points by using the affine transformation parameters, and extracting pose change parameters to obtain an image motion track; predicting an image motion track by using an image track processing algorithm, and comparing the predicted image motion track with a real-time image motion track generated by the current frame; and optimizing the affine transformation parameters, and carrying out frame-by-frame processing on the video stream by using the optimized affine transformation parameters. Through feature point detection and an optical flow tracking algorithm, image motion information in an industrial monitoring video can be extracted, and industrial application requirements of high real-time performance and high stability are met.

The present invention relates to projectiles and munitions, and more specifically to such in flight. More particularly the present invention relates to projectiles and munitions in flight equipped with one or more image sensors adapted for acquiring image data of the environment surrounding the projection or munition in flight. The present invention further relates to systems and methods for correcting or stabilizing motion effects and artifacts present in the image data related to the movement or motion of the projectile or munition in flight, including spin or rotation of the projectile or munition.

The invention discloses a power line fog penetration monitoring method, system and device based on polarization-infrared multi-mode fusion and a medium. An atomic clock is tamed to trigger infrared pulse and polarization exposure, and pixel offset caused by jitter of an unmanned aerial vehicle is compensated through an image motion analysis method; constructing a polarization physical model, and establishing a relationship between the fogdrop particle size and the polarization degree; performing multi-modal feature fusion, constructing a double-branch deep learning network, and performing output judgment on the image according to a dynamic fusion strategy; and optimizing conductor features and insulator features in the power line through a special convolution kernel, and accurately extracting target features.

A video processing method includes obtaining a first initial motion vector (MV) and a second initial MV. The first initial MV points to a first reference image, and the second initial MV points to a second reference image. The method further includes, in response to the first reference image and the second reference image being both short-term reference images, calculating a motion offset of a current image block based on gradients at sampling points pointed to by the first initial MV and the second initial MV, and calculating a predicted image block of the current image block based on the motion offset of the current image block.

The invention relates to the technical field of LED control optimization, in particular to a power consumption monitoring and self-optimizing system of an energy-saving high-definition LED screen. The method comprises the following steps: monitoring various data in a monitoring module; further acquiring the power extended range of the target frame picture in the power consumption analysis module and acquiring the motion energy density of each type of picture element; further according to the distribution change of the lamp beads activated between the adjacent frames by each type of picture elements, in combination with the motion energy density, obtaining the picture motion intensity of the target frame picture; acquiring a real-time extra power consumption component in an adjusting module; constructing a database of impression coefficients; and finally, based on the real-time impression coefficient, in combination with the additional power consumption component and the distribution of the mass center of each lamp bead relative to the current thermodynamic diagram, the brightness of the lamp beads is adjusted, the problem that energy consumption redundancy and impression decline of the LED screen coexist is effectively solved, and the balance of energy conservation and visual experience is achieved.

The invention provides an event-driven image motion deblurring method. The event-driven image motion deblurring method comprises the following steps: S1, acquiring a deblurring data set comprising a blurred image, a clear image and an event stream within exposure time; s2, performing preprocessing by adopting a cyclic event representation method, and converting an event stream into an event frame similar to a potential real image; and S3, constructing a deblurring network by adopting linear deformable convolution and a multi-branch feature extraction attention mechanism. And S4, inputting the fuzzy data set into the trained deblurring network to obtain a clear image after deblurring. According to the method, the high time resolution characteristic of the event stream data is utilized, and an advanced convolution and attention mechanism is combined, so that a clear image can be effectively recovered from a motion blurred image.

The invention discloses a dynamic image motion correction method based on a graph neural network, and the method comprises the following steps: a), constructing a target region trajectory tracking model based on the graph neural network, and achieving the high-precision motion trajectory modeling; b) analyzing an image displacement mode in real time through a dynamic discrimination algorithm; and c) realizing adaptive image motion correction based on the target area track features. According to the method, the problem of complex motion trail modeling limitation caused by dependence on fixed template matching in a traditional method is innovatively solved, and the problem of spatial-temporal characteristic aliasing caused by unsteady state deformation of nervous tissues is effectively solved. According to the technical scheme, the dependence on a hardware synchronization signal acquisition module is eliminated, the resource configuration requirement of the edge computing equipment is remarkably reduced, and meanwhile, the multi-scale time sequence integration efficiency is improved. According to the method, dynamic imaging reconstruction of subcellular neural activities can be realized, and dynamic change details in a target neuron issuing process can be accurately restored.

The invention discloses an optical satellite drift angle accurate calculation and attitude correction method and system, and relates to the technical field of satellite attitude control, and the method comprises the steps: calculating a prime unitary circle curvature radius according to a WGS84 ellipsoid parameter, and converting the geodetic coordinate of a ground target point into an ECEF rectangular coordinate; calculating Julian days based on UTC time, determining an age difference angle and a nutation angle, and converting an ECEF coordinate into a J2000 coordinate; calculating the projection of the earth rotation angular velocity in a J2000 coordinate system, and determining a relative velocity vector; determining an orthogonalized body coordinate system in combination with a unit vector from the target satellite to the ground target point; and projecting the relative velocity vector to a body coordinate system, calculating a drift angle and a double-rotation-sequence Euler angle, and correcting a real-time execution attitude by rotating a matrix around a Z axis. According to the method, high-precision image motion compensation can be realized, the imaging quality of a high-resolution optical satellite in a complex task scene is improved, and a technical foundation is laid for wide application of sub-meter remote sensing images.

The invention relates to the technical field of face recognition, in particular to a face recognition type endemic area access control system, which comprises a face image acquisition module for starting an image sensor for endemic area access control to capture a face image sequence based on personnel in a visual field, carrying out image motion ambiguity value evaluation and screening a single-frame image to obtain a qualified face image. According to the method, the face image sequence is collected in real time, the motion ambiguity value is dynamically evaluated, low-quality images caused by personnel movement or environment interference are effectively eliminated through a single-frame screening mechanism, and the accuracy of subsequent feature extraction is improved. According to the method, double judgment logic of a full face feature vector and an unauthorized feature space boundary distance is adopted, and orthogonal projection and standardization processing of a multi-dimensional feature space are combined, so that the recognition precision of abnormal access behaviors such as disguise and forgery is enhanced, and the misjudgment rate is reduced.

This invention discloses a license plate recognition method and system for a parking lot patrol robot based on dynamic visual compensation, belonging to the field of data processing technology. The method includes: predicting the transient stationary point of chassis vibration based on motion posture data sequence to trigger license plate image acquisition; calculating motion blur vectors by combining angular velocity data and imaging intrinsic parameters to generate a spatial variation degradation kernel; using this kernel to perform non-uniform deblurring on the license plate candidate region, extracting and fusing the restored texture features and original topological features, and outputting the license plate recognition result and confidence level; calculating visual degradation parameters based on the blur vector length and confidence level, triggering deceleration and initiating hysteresis hold-up period control when the parameter exceeds a threshold. This invention solves the technical problems of non-uniform image motion blur caused by vibration and rotation in dynamic inspection and frequent control oscillations caused by single feedback, effectively improving the accuracy and operational stability of the robot's license plate recognition.

The invention relates to the technical field of video image processing, in particular to a fire source point rapid positioning device and method for a long and narrow tunnel, and solves the technical problem that accurate positioning of a fire source point is difficult to realize in the prior art. The device comprises an image acquisition unit used for acquiring tunnel video data in a long and narrow tunnel; the tunnel video data comprises tunnel images collected according to a time sequence; the fire source identification unit is used for carrying out image motion feature and image texture feature analysis based on the tunnel image and identifying fire source pixel points from the tunnel image; the fire source pixel points are corresponding pixel points of the fire source points in the long and narrow tunnel in the tunnel image; and the positioning unit is used for carrying out space coordinate conversion based on the identified fire source pixel points to obtain three-dimensional coordinates of the fire source points corresponding to the fire source pixel points.

The invention relates to a rapid scanning type laser active detection system based on laser angle on-line control, and the system comprises an adjustable beam expanding optical unit which can continuously adjust the beam expanding multiplying power on line through position closed-loop control; the scanning detection execution unit can perform large-range search and can compensate image motion caused by carrier motion and continuous scanning, and a variable-speed spiral scanning mode with high probability of finding a target is adopted as a scanning mode; the off-axis beam expanding unit is used for further compressing a laser divergence angle; the photoelectric imaging system can splice scanned images on line, so that the scanning process is clearer and more visual; and the time sequence control unit assists in image motion compensation control. The scanning process can be rapidly completed, imaging is clear in the scanning process, and the scanning result can be directly presented.

The application discloses a two-axis two-frame roll-pitch configuration photoelectric detection equipment control system and method, and belongs to the field of photoelectric detection equipment. The system comprises a power supply, an image controller, a servo controller, an outer frame, an outer frame roll motor, a first code disc, an outer frame slip ring, an inner frame, an inner frame pitch motor, a second code disc, a first gyroscope, a second gyroscope and a camera. An angle instruction is sent from a display control console to the servo controller and the image controller. The servo controller performs angle conversion, position loop control, roll rotation direction judgment and speed loop control, and outputs a signal to drive the motor. The code disc measures real-time angle information of the motor and sends the information to the servo controller. The gyroscope measures real-time angular velocity information of the camera and sends the information to the servo controller. The image controller receives a roll angle to perform electronic image stabilization, outputs an image to the display control console, and sends an image deviation to the servo controller when tracking a target. The image motion direction is consistent with the azimuth and pitch direction in the base coordinate system, and the human-computer interaction comfort is improved.

The invention discloses an RFID multi-label image motion deblurring method in a dynamic scene. The method comprises the following steps: 1, acquiring an RFID multi-label image in the dynamic scene and preprocessing the RFID multi-label image; 2, decomposing into a plurality of frequency band sub-bands through two-dimensional discrete wavelet transform, and calibrating structural consistency and suppressing noise through a structural consistency module; 3, extracting multi-level features by using an encoder containing an LPFBlock multi-layer structure, and integrating cross-scale features through a feature fusion block to obtain multi-scale deep coding features; 4, after coding features are weighted and enhanced by an RSAM residual space attention module, up-sampling and texture reconstruction are performed by a decoder, high-frequency details are recovered in combination with jump connection, and reconstructed sub-bands are output; and 5, performing inverse wavelet transform on the reconstructed sub-band, and outputting a clear RFID tag image. According to the method, through wavelet transform decomposition, multi-scale feature coding and attention enhancement mechanisms, detail features of the motion blur RFID tag image can be efficiently recovered, and the image quality is remarkably improved.

The present application relates to the cross field of aerial remote sensing imaging and motion control, and specifically provides a multi-mode pod cooperative imaging control method and system, the method steps comprising: integrating a multi-mode photoelectric sensor in a pod to obtain load parameters of the multi-mode photoelectric sensor to calculate various indicators of remote sensing imaging; generating a swing-scan instruction and a push-scan instruction for the pod based on the various indicators; wherein the swing-scan instruction is used for load swing-scan, and the push-scan instruction is used for image motion compensation; the swing-scan instruction and the push-scan instruction are used to cooperatively execute the tasks of swing-scan imaging and image motion compensation based on the same control cycle; under the condition of low-altitude high-speed flight, the present application cooperatively plans the motion of a multi-mode pod and remote sensing imaging, ensures the stable imaging quality of the multi-mode sensor, guarantees the accuracy and reliability of remote sensing data, and improves the remote sensing operation ability and efficiency.

Motion correction in ultrasound imaging uses a suitably trained machine learning algorithm or model to correct for tissue motion in ultrasound images. A reference frame is selected from the input image data to use as a ground truth input to the machine learning model.

The present application relates to the field of optical remote sensing, and more particularly to a space camera off-track image motion test and compensation ground test device and test method thereof, the method comprising: fixing a TDICMOS camera on a three-dimensional turntable and pointing its optical axis to a drum target; determining a push-scan direction image motion speed according to the line frequency and pixel size of the TDICMOS camera; determining an image motion speed perpendicular to the push-scan direction based on a preset angle between the push-scan direction image motion speed and the push-scan direction of the detector; using the object-image relationship to inverse the target motion speed of the drum target; controlling the rotation of the drum target and driving the three-dimensional turntable to perform a pitch compensation motion to eliminate image motion mismatch; and acquiring off-track scanning images in a dynamic process. The present application uses a drum rotation to simulate the motion of a target, is not limited by the refresh frequency of a display screen, can effectively match the test requirements of a high line frequency TDICMOS camera, and realizes ground verification of the off-track scanning image motion compensation effect.

The invention discloses an image motion compensation method based on a grooved cam, and the method comprises the steps: firstly, determining the target angular velocity of a plane mirror based on the input angular velocity, carrying out the interval division of a compensation period, setting an extension path, a far stop, a return path and a near stop, and carrying out the image motion compensation of an imaging system during the exposure integration period, an equal-acceleration section, a constant-speed section and an equal-deceleration section are arranged in the extending stroke section; then, obtaining a matching relation between the exposure integral time of the camera and a constant-speed extending stroke section according to different internal and external trigger modes; secondly, constructing a lift function to determine a cam profile, generating a cam theoretical pitch curve, and performing normal equidistant correction to obtain an actual groove profile; and finally, obtaining a direct mapping relation between the rotating speed of the plane mirror and the rotating speed of the groove cam through a mechanism motion transmission relation, so that a visual axis which is output in an exposure period and is opposite to an image motion direction is slightly deflected to restrain the image motion. The method is high in real-time performance, does not need complex control, and is good in compensation synchronism and repeatability.

This specification discloses a method and system for correcting scanned data. The method includes: acquiring multiple motion vector fields corresponding to multiple motion time points of a target object based on reference time points; acquiring image motion deviations corresponding to each motion time point based on the motion vector fields corresponding to each motion time point and the motion reconstruction images corresponding to each motion time point; acquiring raw data deviations corresponding to each motion time point based on each image motion deviation; and correcting the scanned data based on the raw data deviations corresponding to at least one of the motion time points to obtain corrected data.

The present invention discloses a frequency stepped signal radar imaging method based on phase cancellation to improve the high-resolution imaging effect of high-speed moving targets. The frequency stepped signal radar imaging method of the present invention includes the following steps: (10) Transmitting frequency stepped signals: Alternately transmitting two sets of frequency stepped signals, where the pulse repetition period of one set of frequency stepped signals is twice that of the other frequency stepped signal; (20) Obtaining echo signals: Obtaining echo data reflected by target scattering points; (30) Range image motion compensation: Using an improved phase cancellation algorithm to perform range image velocity phase compensation on the echo data; (40) Frequency stepped signal range imaging: Performing an inverse Fourier transform on the echo sampling sequence and then performing oversampling stitching to obtain a high-resolution stationary range image of the moving target.

The present application relates to the technical field of artificial intelligence, and more particularly to an AI interaction system for ornithological scientific research, which comprises a collection unit, a trigger determination unit, a path determination unit, a dominant determination unit, a prompt generation unit and an adjustment unit. The present application constructs a multi-level behavior determination process through joint analysis of bird song spectrum, image motion characteristics, flight trajectory and environmental factors, and through statistical analysis of the time distribution and spatial distribution of these behavior indicators within a preset period, and correlation analysis with environmental factors such as temperature, humidity, wind speed and illumination, the influence of environmental changes on bird activity frequency and spatial aggregation degree can be identified, so that the acoustic trigger threshold can be dynamically adjusted, so that the system can continuously maintain the sensitive recognition ability of bird activity with the change of the habitat environment, and then realize high-reliable behavior recognition and interaction prompt for ornithological scientific research.

The application relates to the technical field of image acquisition and processing, in particular to a skin fine texture acquisition method and system, wherein four light sources L1 to L4 are uniformly and sequentially arranged around the center line of a camera lens, each light source has at least three channels C1 to C3 and emits light rays to the same skin area to be acquired; a positive direction image and a negative direction image are acquired; images in the same coordinate axis direction are subjected to difference value operation to obtain gradient images in three directions; the gradient image gray values in the three directions are normalized to obtain normal line values in three channels; the normal line values in the three channels are converted to be respectively loaded into a normal line map three channel and output the normal line map; the positive direction image light source lighting mode comprises L1 and L2 lighting C1 and C2, the negative direction image light source lighting mode comprises L3 and L4 lighting C1 and C2, and C3 of the four light sources is all lighted in the positive direction image or the negative direction image, so that the image motion blur probability is reduced.

The application provides a large attitude angle dynamic push-broom line frequency calculation and matching method of a spaceborne TDI detector, and is used for solving the technical problems that the existing image motion velocity vector calculation model does not consider the actual ellipsoid earth shape, calculation errors are introduced in the satellite attitude transformation process, or the actual ellipsoid earth shape is considered, but a large number of matrices, differentials and partial derivatives make the calculation result complex, the calculation speed is slow, and the calculation amount is large. The large attitude angle dynamic push-broom line frequency calculation and matching method of the spaceborne TDI detector considers the ellipsoid earth model and satellite attitude change and the like, combines the vector relationship method and the coordinate transformation method, can accurately calculate the object distance and the downward angle corresponding to each detector center point in the dynamic push-broom process of the camera, and further obtains the image motion velocity on the image plane corresponding to each detector center point; so as to calculate the image motion velocity, the line frequency and the deflection angle corresponding to each detector center point, and complete the line frequency matching.

The present invention discloses a method and device for judging image motion and stillness. The method includes the following steps: filtering the current frame image and the reference frame image respectively using a first filtering window, and performing differencing on the filtered current frame image and reference frame image to obtain a first difference image; filtering the current frame image and the reference frame image respectively using a second filtering window, and performing differencing on the filtered current frame image and reference frame image to obtain a second difference image, where the second filtering window is larger than the first filtering window; calculating a fusion weight according to the second difference image to obtain a fusion weight, and fusing the first difference image and the second difference image according to the fusion weight to obtain a fused difference image; performing binarization processing on the fused difference image to judge the motion area and the stillness area. Thereby, the accuracy of judging the motion area and the stillness area in a scene with a high noise level is improved.

A video processing method includes obtaining a first initial motion vector (MV) and a second initial MV. The first initial MV points to a first reference image that is a forward frame of a current image block, and the second initial MV points to a second reference image that is a backward frame of the current image block. The method further includes, in response to the first reference image and the second reference image being both short-term reference images, calculating a motion offset of the current image block based on gradients at sampling points pointed to by the first initial MV and the second initial MV, and calculating a predicted image block of the current image block based on the motion offset of the current image block.

The present invention is developed in view of the problems of the prior art, and one of the purposes thereof is to provide a flame detection device capable of reducing erroneous determination of flame detection. This flame detection device (1) is a flame detection device for an iron-making-related facility, and is provided with: an image acquisition unit (10) that acquires an image of a region to be detected; a partial image detection unit (32) that detects a partial image having a predetermined feature from within a frame of the acquired image; a motion vector detection unit (33) that detects a motion vector of a partial video between frames of the video; and a flame state determination unit (36) that determines the state of the flame in the region to be detected using the detected motion vector.

The present invention discloses a multi-path atmospheric coherence length measurement method and system for satellite-to-ground laser communication. The system consists of a binocular image acquisition module, a control module, a data processing module, and a storage module. The binocular image acquisition module is used to acquire paired star spot images, the control module is used to control the binocular image acquisition module to effectively acquire images, the data processing module is used to extract the centroid of the star spot from the two frames of synchronously acquired images, and use the differential image motion method to calculate the atmospheric optical turbulence intensity on the path where the spot is located; the storage module saves the data results. In the specific measurement method, the photon flux density method is used to calculate the detection capability of the measurement system; the number of detectable star spots and their probability are determined based on the field of view of the equipment; the optical flow method is used to realize the estimation of pixel motion and the tracking of star point trajectories; the atmospheric coherence length and seeing are calculated based on the variance of the centroid motion of the star spot, revealing the intensity of atmospheric optical turbulence at different positions.

The application relates to a method and device for correcting image motion artifacts, an electronic device and a storage medium, wherein the method for correcting image motion artifacts comprises the following steps: acquiring an initial image to be processed, wherein the initial image is generated based on initial raw data; performing threshold segmentation processing on the initial image to generate a plurality of isosurface parts, and the plurality of isosurface parts constitute a first image; generating first raw data based on the first image, and generating second raw data based on the first raw data and the initial raw data; and generating a second image based on the second raw data, wherein the second image is an image after motion artifact correction. Through the application, the problem that image motion artifacts cannot be safely and stably corrected in the related art is solved, and the technical effect of safely and stably correcting image motion artifacts is achieved.