206 results about "Image motion" patented technology

The invention provides a liquid crystal display drive control method and system, and the method comprises the steps: obtaining a page loaded in a memory of a liquid crystal computer, calculating the maximum image motion degree of the page loaded in the memory of the liquid crystal computer through the difference between continuous frames, and adjusting the refresh rate of a liquid crystal display screen; acquiring a fixation point position and fixation time of the user through an eye movement tracking technology, and adjusting the brightness of the liquid crystal display screen according to the fixation point position and the fixation time of the user; predicting future display contents and user behaviors by using a machine learning algorithm in combination with the use habits of the user and historical data of the display, and adjusting the brightness and refresh rate of the display based on a prediction result; the energy consumption data of the display are recorded in real time, the actual energy consumption and the expected energy consumption are compared and analyzed, and abnormity is found in time and feedback adjustment is carried out. Through the method and the corresponding system, the use energy consumption of the liquid crystal screen can be saved under the condition that the user experience is not influenced.

The invention provides an image motion estimation method and a related device, and an electronic device can intercept a rendering instruction for an image frame, obtains the related resources of the image frame based on the rendering instruction, carries out the motion estimation of two adjacent image frames through the fusion of an optical flow motion estimation method and a 3D motion field motion estimation method, and achieves the motion estimation of the two adjacent image frames. And determining motion vector information between two adjacent image frames. In this way, the motion estimation effect between two adjacent image frames can be improved.

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 relates to the technical field of computer vision, and discloses a multi-sensor fusion feature-based video image stabilization method, which comprises the following steps of: estimating relative motion among feature points in a video stream extraction image by using an optical flow model, and fusing image motion features and gyroscope motion features to estimate a camera motion track; smoothing the moving track of the jittering camera to obtain a stable moving track of the camera; and finally, changing the stable camera motion path through a warp grid to obtain a stable image sequence, and finally synthesizing a stable video.

The invention discloses an SAR image fine focusing method based on fractional Fourier transform. Relates to the field of radar remote sensing technology application, in particular to the technical field of SAR image focusing processing. The technical problem that a motion compensation method based on inertial navigation data and a self-focusing method based on phase errors, which are commonly used in SAR image motion compensation methods, cannot meet the requirements of fine and rapid focusing is solved. The method comprises the following steps: S1, carrying out distance direction partitioning on a defocused SAR image to obtain a plurality of distance blocks; s2, calculating fractional Fourier transform of a strong point target in each distance block; s3, calculating a kurtosis characteristic of a fractional order Fourier transform result; s4, the maximum value of the kurtosis features is searched in a one-dimensional mode, and the optimal rotation order of each distance block is obtained; and S5, performing fractional Fourier transform on the SAR image based on the optimal rotation order of each distance block to obtain a focused SAR image.

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 relates to the cross technical field of aeronautical optical imaging and motion control, in particular to a quantitative calculation method and evaluation index for an image motion compensation effect, which comprises the following steps of: S1, acquiring an image representation of an image without an image motion target, and calculating the modulation contrast # imgabs0 # of the image without the image motion target; s2, introducing a motion function, and obtaining image representation of an image motion target picture coupled with the motion function; s3, according to the optical imaging principle, the image motion target picture modulation contrast # imgabs1 # after the image motion effect is generated within the imaging system integration time is calculated; s4, an image motion quantitative evaluation transfer function # imgabs2 is calculated, the index is a number with the value ranging from 0 to 1, the image motion compensation capacity capable of being achieved in the integral time of the system can be expressed through the ratio of the two modulation contrast ratios, and due to the normalization effect, the index can also transversely compare the capacities of different image motion compensation systems.

The invention relates to a scene surface reconstruction method and device based on image motion blur removal and two-dimensional Gaussian point shading, equipment and a medium. The method comprises the following steps: carrying out gradient back propagation according to luminosity loss, smoothness loss, normal consistency loss and depth consistency loss so as to adjust a camera pose and Gaussian point cloud parameters of a real motion blurred image; based on ray tracing, transparency accumulation and depth regularization constraint, carrying out surface estimation on a clear image corresponding to the real motion blurred image to restore a two-dimensional Gaussian point-share scene of the clear image corresponding to the real motion blurred image, the two-dimensional Gaussian point-share scene comprising an object surface depth and an object surface shape; and performing scene surface reconstruction on a clear image corresponding to the real motion blurred image by adopting a preset truncated signed distance function according to the object surface depth and the object surface shape. According to the method, the authenticity of scene reconstruction can be enhanced, and accurate two-dimensional Gaussian point-share scene reconstruction is realized.

The embodiment of the invention discloses a candidate list sorting method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: receiving a preset video frame; encoding the preset video frame to obtain an image encoding unit information set corresponding to the preset video frame; obtaining a reference video frame corresponding to the preset video frame; determining the image predictive coding unit information as current image coding information; determining each piece of image prediction coding unit information meeting a preset adjacent condition in the image coding unit information set as each piece of adjacent image coding information; generating each adjacent image motion vector corresponding to each adjacent image coding information; constructing a motion vector candidate list; and performing reordering processing on the motion vector candidate list so as to update the motion vector candidate list. According to the embodiment, bits consumed by writing the motion vector into the code stream in the video transmission process are reduced, and the video compression efficiency is improved.

An event-guided lightweight attention network for efficiently removing image motion blur belongs to the technical field of image processing and comprises an image feature extraction module, an event feature extraction module, a cross-modal attention feature fusion module and an image reconstruction module. Firstly, image coding features and event coding features are extracted from a motion blurred image and an event voxel grid through an image feature extraction module and an event feature extraction module respectively, then, the image coding features and the event coding features are fused through a cross-modal attention feature fusion module to obtain fusion features, and finally, the motion blurred image and the event voxel grid are subjected to cross-modal attention feature fusion. The fused features are processed by an image reconstruction module to obtain a clear image. According to the invention, the motion blur removal of the image is realized, the obtained image is higher in definition, the image processing time is saved, and the image processing efficiency is higher; the attention network is a single-stage network and has the characteristic of light weight.

The invention relates to an installation structure and a precision adjustment method of a long-distance laser target tracking and ranging light path, which are used for high-precision adjustment of a laser emission direction of a space target tracking and ranging light path. And the deviation between the emergent direction of the laser reflected by the three reflectors and the swing angle of the rotary table is minimum. The method comprises the following steps: firstly, leading a pitch axis and an azimuth axis to a plane mirror by using an autocollimator; secondly, a second reflecting mirror and a first reflecting mirror are installed and adjusted through the installation mode of a cushion column and a fastening screw, the grinding amount of the cushion column is calculated according to the back image motion track of an autocollimator or the motion track of a laser imaging point in a measurement camera, the cushion column is ground on the basis, and the purpose of high-precision installation and adjustment is achieved; thirdly, through zero calibration of a visible light camera, a measurement camera and a corner reflector, an adjustment system of a third reflector is built, and adjustment of the third reflector is achieved; finally, the cushion columns and the fastening screws are reinforced through epoxy glue, and the mechanical resistance of the light path is guaranteed.

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.

The invention relates to the technical field of image processing, and discloses an image motion error processing method, system and device and a medium, and the method comprises the steps: determining a real position and an expected position through the position, corresponding to a selected region in wide-angle imaging, of a long-focus picture in the wide-angle imaging, thereby determining the image motion error of all long-focus regions in the wide-angle imaging; the image motion error is converted into the azimuth angle and the pitch angle of the visual axis under the coordinate system of the two-dimensional pointing mirror, so that the rotation degree required for adjusting the image motion error currently is determined, the image motion error is effectively reduced, image distortion is avoided, complex calculation is not needed, the problem of difficulty in accurate positioning of a visual field expansion system is effectively solved, and the visual field effect is also improved. And fatigue and easy damage are caused by frequent use.

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 an image motion detection method and device and electronic equipment, and the method comprises the steps: obtaining a long-term reference frame image and a current frame image, and enabling the long-term reference frame image to be updated through the multi-frame fusion of a historical frame image; obtaining a self-adaptive threshold value, wherein the self-adaptive threshold value is associated with the ISO of the current frame image; according to the long-term reference frame image, the current frame image, a self-adaptive threshold value and a plurality of preset window areas, obtaining the number of first motion areas; according to the first motion area number and a preset motion area number threshold value, an image motion detection result associated with the current frame image is obtained, and the image motion detection result is used for representing whether a moving shooting object appears in the video image at the moment when the current frame image is located. According to the method and the device, the detection accuracy and the wake-up rate can be ensured on the basis of low computing resources and storage resources, false alarms are reduced to the greatest extent, and the requirements of users are met in actual use.

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 present invention proposes a liquid crystal display drive control method and system, the method comprising: obtaining a page loaded in the memory of a liquid crystal computer, calculating the maximum image motion degree of the page loaded in the memory of the liquid crystal computer by the difference between consecutive frames, and then adjusting the refresh rate of the liquid crystal display screen; obtaining the user's gaze point position and gaze time by eye tracking technology, and adjusting the brightness of the liquid crystal display screen according to the user's gaze point position and gaze time; combining the user's usage habits and the historical data of the display, using a machine learning algorithm to predict future display content and user behavior, and adjusting the brightness and refresh rate of the display based on the prediction results; recording the energy consumption data of the display in real time, comparing and analyzing the actual energy consumption with the expected energy consumption, and timely discovering abnormalities and making feedback adjustments. Through this method and the corresponding system, the energy consumption of the liquid crystal screen can be saved without affecting the user experience.

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.

The invention discloses a water surface motion blurred image enhancement method for intelligent navigation of a ship. The method comprises the following steps: 1) obtaining a water surface motion blurred image training set for intelligent navigation of the ship; 2) constructing an image motion blur removing model based on the generative adversarial network, wherein the image motion blur removing model comprises a generator and a discriminator; 3) training the model; and 4) using a generator of the trained model to realize motion blur removal of the water surface image. The method can eliminate the adverse effect of motion blur on visual perception, and guarantees the intelligent navigation safety of the ship.

The invention discloses a multi-path atmospheric coherence length measurement method and system for satellite-ground laser communication. The system is composed of a binocular image acquisition module, a control module, a data processing module and a storage module. The binocular image acquisition module is used for acquiring paired star light spot images, the control module is used for controlling the binocular image acquisition module to effectively acquire, and the data processing module is used for extracting mass centers of star light spots from two frames of synchronously acquired images and calculating atmospheric optical turbulence intensity on a path where the light spots are located by using a differential image motion method; the storage module stores the data result. In the specific measurement method, the detection capability of the measurement system is calculated by adopting a photon flow density method; determining the number of detectable fixed star light spots and the probability thereof according to the size of the field of view of the equipment; realizing estimation of pixel motion and tracking of a star point trajectory by using an optical flow method; the atmospheric coherence length and seeing are calculated according to the mass center motion variance of the fixed star light spot, and the intensity of atmospheric optical turbulence at different positions is revealed.

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 relates to an image pre-division method based on a multi-layer multi-motion search result, and belongs to the technical field of video coding. The method comprises the steps that an original image and a prediction search image are acquired, and according to the original image and the prediction search image, motion information of the original image is obtained through multi-layer multi-time motion search; obtaining a video sequence and extracting to obtain an image frame set, coding and extracting features of the image frame set to obtain an image pre-division data set; training and testing according to the image pre-division data set through a decision tree algorithm to obtain an image pre-division decision tree; and obtaining a current image frame, extracting current image motion information through the multi-layer multi-time motion search, and obtaining a current image pre-division state through the image pre-division decision tree according to the current image motion information, thereby assisting an encoder in encoding, accelerating the process of determining the encoding block division form, and improving the encoding efficiency. The calculation consumption of the encoder is reduced, and efficient and accurate image pre-division is realized.