1089 results about "Image sequence" patented technology

This application relates to the field of medical technology and provides a medical application scenario matching method, electronic device, and computer program product. The medical application scenario matching method includes: acquiring a medical image sequence; determining image information of the medical images in the medical image sequence, the image information including key information, which includes one or more of the following: imaging object information, phase information, lesion detection information, and image quality information of the corresponding medical image; and outputting at least one target application scenario adapted to the medical image sequence based on the key information. Embodiments of this application can prevent doctors from using unsuitable medical image sequences in specific application scenarios, thus helping to improve doctors' work efficiency.

This application relates to a method, apparatus, computer device, and storage medium for displaying medical images. In response to an instruction to acquire a first image sequence, a target type label for the first image sequence is determined. From a sequence of images to be identified containing various type labels, at least one second image sequence associated with the target type label is acquired. The first image sequence and at least one second image sequence are then displayed. Each type label is obtained based on a classification result determined according to each image sequence to be identified and a preset classification model. The embodiments of this application employ a preset classification model to automatically identify the image sequences to be identified, obtaining the classification results of each image sequence to be identified, thereby obtaining the type label for the image sequences to be identified. Compared to relying on manually entering tag information for medical images, the method proposed in this application can significantly reduce the error probability of acquiring the second image sequence based on the target type label, thereby greatly improving the accuracy of image sequence acquisition.

This application relates to the field of medical image processing technology, and provides a method, apparatus, device, and storage medium for reconstructing ECT images. This allows for more thorough capture of subtle changes in the concentration distribution of radioactive tracers at high temporal resolution, helping to reduce image noise levels and improve image quality. This application obtains a first ECT image sequence; the first ECT image sequence is obtained by scanning with an ECT scanning device; the first ECT image sequence is input into a pre-constructed intermediate frame prediction network to obtain an estimated second ECT image sequence; using the estimated second ECT image sequence as a priori image, a target second ECT image sequence is reconstructed; the estimated second ECT image sequence and the target second ECT image sequence belong to the second ECT image sequence; the temporal resolution of the second ECT image sequence is higher than that of the first ECT image sequence.

This application relates to the field of computer vision and image processing technology, and discloses a large-model pattern recognition method and system based on deep learning. The method includes: acquiring a temporal image sequence containing a target to be recognized; extracting the geometric topological features of the target in each frame of the image; tracking the target across frames to obtain a temporal numerical set of geometric topological features evolving over time; statistically analyzing the fluctuation parameters of the temporal numerical set within a preset temporal interval, and selecting geometric topological features that meet preset stability conditions from the fluctuation parameters as the essential features of the target; constructing a target pattern representation based on the essential features of the target, and matching the target pattern representation with a pre-stored pattern to determine the recognition result. This application significantly improves the robustness and generalization ability of the recognition model in complex dynamic scenarios such as material changes, illumination changes, pose changes, and even the emergence of new categories, effectively reducing the false positive rate and false negative rate.

The application relates to an adaptive control system for dynamic sensitivity adjustment of a photoelectric sensor, comprising: a photoelectric sensor, the sensitivity parameter of which can be adjusted online, used for collecting and outputting an image sequence; a target detection and feedback unit, used for carrying out target detection on the image sequence output by the photoelectric sensor, obtaining a boundary box of the target, a detection confidence and a local signal-to-noise ratio expectation value of the target area; an ambient light sensing unit, used for acquiring an ambient light intensity and generating a predicted ambient light intensity; a prediction model unit, used for predicting a scene displacement amplitude of a next frame based on a motion vector of a current image frame; and a parameter solving unit, which is internally provided with a sensor response model and a motion blur probability model, and is used for constructing a cost function with the sensitivity parameter as a variable; the application can realize better adaptive control.

The present application relates to the technical field of image recognition, and more particularly to a concrete prefabricated component surface defect detection method and system, which comprises the following steps: obtaining a shading vector of each pixel point based on a multi-angle image sequence; weighting and normalizing the shading vector by using a weight coefficient positively correlated with the zenith angle of a light source to obtain a light resistance amount; calculating the spatial gradient feature of the light resistance amount, and combining a geometric correction factor based on a local surface shape and an albedo correction factor to perform weighted fusion to obtain a steepness index; calculating the centripetal closeness of the light resistance amount gradient, fusing the same with the steepness index to generate a confidence index, and determining a defect region according to the confidence index. The present application can accurately distinguish between shallow pores, color spots and deep structural defects with steep and closed edges by constructing a light resistance amount and fusing multi-dimensional geometric features.

Disclosed are an image labeling method and device, a storage medium and equipment, wherein the method comprises: obtaining a three-dimensional point cloud of a target scene and at least one to-be-labeled image sequence, labeling static elements in the three-dimensional point cloud of the target scene to obtain labeling information of the static elements in the three-dimensional point cloud, and then projecting the labeling information of each static element in the three-dimensional point cloud to at least one to-be-labeled image set corresponding to the target scene, thereby realizing labeling of static elements in the at least one to-be-labeled image set corresponding to the target scene. Based on the embodiments of the present disclosure, labeling of static elements in all to-be-labeled images in the at least one to-be-labeled image set corresponding to the target scene can be realized at one time, and compared with labeling of to-be-labeled images corresponding to different orientations of the target scene one by one, the image labeling efficiency can be effectively improved.

The application discloses a multi-point focusing fitting microscopic imaging plane leveling method, system and device, which is used for high-precision automatic leveling of an imaging plane. The method comprises the following steps: establishing a two-dimensional sampling grid based on a measured plane, and determining grid node coordinates; establishing a space coordinate system, and calling calibration data to obtain a calibration image plane; continuously collecting an image sequence covering the two-dimensional sampling grid; dividing the image sequence according to the grid node coordinates to obtain a grid image sequence; calculating the definition of the grid image sequence by using a no-reference definition evaluation method to obtain a definition sequence; establishing an index relationship between the grid node coordinates and the maximum definition in the corresponding definition sequence to obtain a definition point set; performing plane fitting based on the definition point set to obtain a global focal plane model; calculating parallel parameters of the global focal plane relative to the calibration image plane according to the global focal plane model; and adjusting the posture of a placement platform of the measured plane through the parallel parameters.

This invention discloses a method, device, and medium for correcting human motion posture based on AI vision, relating to the field of AI vision technology. The method includes: acquiring multi-channel image sequences of human posture using multiple cameras; performing temporal alignment and normalization on the multi-channel image sequences; obtaining a human probability map using a pre-trained human semantic segmentation network; performing morphological cleanup to obtain a human silhouette sequence; performing back-projection according to camera intrinsic and extrinsic parameters to obtain a 3D joint sequence from a 3D AI visual volume; extracting the human motion manifold to perform contact-sensing neural motion priors and outputting prior signals; and using posture feasibility scores and joint importance weights to weightedly fuse the geometric difference vector and the center of gravity correction component to obtain a comprehensive joint correction vector. This invention generates a 3D AI visual volume through back-projection and extracts the central skeleton, using constant bone segment lengths for constraint and correction, thus enhancing the reliability of posture stability analysis and alignment with standard action templates.

The application discloses a road centerline determination method and system based on a deep neural network satellite map, and relates to the technical field of satellite image processing; the method comprises the following steps: preprocessing time-phase satellite images of a collected to-be-processed region, vehicle GPS track data and street view image sequences to obtain a dynamic region in the to-be-processed region, a track density map and a street view feature mapping table; inputting the time-phase satellite images into a pre-trained road segmentation model to obtain multiple road probability maps; based on the multiple road probability maps, performing dynamic region weighted fusion, non-dynamic region logical or operation and threshold determination to obtain an initial road mask; vectorizing the initial road mask into a centerline network and extracting cross nodes to obtain an initial road network topology; and the application has the advantages of improving the accuracy of the road network topology and guaranteeing the rationality of path planning.

The application discloses a control method and device of an access gate, a storage medium and an electronic device. The method comprises: acquiring a time sequence image sequence corresponding to a passing area, wherein the passing area comprises an access gate, and the time sequence image sequence comprises a plurality of continuous image frames; performing an object detection operation on each image frame in the time sequence image sequence to determine object information of a target object; in the case that the object information meets object recognition conditions, performing a state prediction operation on the target object to generate a gate control signal matched with a passing action of the target object; and adjusting a motion trajectory parameter of the access gate according to the gate control signal, wherein the motion trajectory parameter comprises at least one of an opening angle and a rotating speed. The application solves the technical problem of low passing efficiency caused by the rigid opening and closing actions of the gate and the response lag of the gate when the passing speed of the user is inconsistent and the body size difference is large.

The embodiment of the application provides a kind of unmanned plane hovering method and related equipment, belong to unmanned plane technical field.In the application scheme, the movement information of unmanned plane can be detected from ground image sequence in high frequency and real time using optical flow algorithm, and the pose of unmanned plane is quickly adjusted according to the movement information of unmanned plane in time, when the disturbance of unmanned plane appears, it is quickly corrected, so that unmanned plane can be stably hovered above ground marker.

This disclosure provides embodiments of a method, apparatus, electronic device, and readable medium for generating motion trajectory information. One specific implementation of the method includes: acquiring a target image sequence; generating a sequence of adjacent target image groups; acquiring an inertial information sequence; inputting the adjacent target image group sequence into an image feature extraction layer to obtain an image feature tensor sequence; inputting the inertial information sequence into an inertial feature extraction layer to obtain an inertial feature vector sequence; inputting the image feature tensor sequence and the inertial feature vector sequence into an image inertial feature fusion layer to obtain an image inertial fusion feature tensor sequence; inputting the image inertial fusion feature tensor sequence into a pose network layer to obtain a pose information sequence; inputting the target image sequence into a depth network layer to obtain a depth map sequence; and generating motion trajectory information based on the pose information sequence and the depth map sequence. This implementation improves the accuracy of the estimated pose and the correctness of the generated motion trajectory.

A biological sample analysis system and a biological sample analysis method. The biological sample analysis system includes a plurality of imaging devices, a plurality of local computing devices, and a cloud computing device. Each imaging device captures a series of images from a biological sample. Actions performed by each local computing device include: receiving the series of images from a corresponding one of the imaging devices; and processing the series of images using a local machine learning model to generate an analysis result. The cloud computing device performs actions including: training a cloud machine learning model based on the series of images and the analysis result from the local computing devices to generate an optimized machine learning model; and transmitting the optimized machine learning model to each local computing device to replace or update the local machine learning model.

The application relates to the technical field of optical three-dimensional measurement and machine vision, and discloses a coating thickness detection method and system based on visual monitoring, which comprises the following steps: controlling a test environment to induce transient evaporation of a liquid phase on a coating surface, and collecting an image sequence under structured light projection; calculating an evaporation gradient index field of the image, extracting a time stamp corresponding to a time sequence maximum value to construct an extreme value time field; performing a spatial gradient operation on the extreme value time field to generate an evaporation dynamics scalar field; fusing the scalar field with a structured light fringe modulation degree matrix to construct a quality map function; guiding a spatial phase unwrapping path by the quality map function, obtaining a full field of view absolute phase, and calculating coating thickness. The application uses phase transition space-time evolution rules to guide phase unwrapping, so that the algorithm path actively avoids a phase abnormal area caused by water droplet refraction, error global diffusion is inhibited, and the accuracy of coating thickness measurement under a dynamic alternating environment is improved.

Methods encode or decode a picture sequence, some having different resolutions, and transmit a bitstream of encoded video data. The decoding method includes decoding a first syntax element for specifying a reference size of pictures referring to a high-level syntax structure and a second syntax element for specifying a picture size scaled from the reference size of the pictures referring to the high-level syntax structure. The method includes deriving at least one offset factor and at least one scale factor representing a scale difference between a current picture including a current block to be decoded and a reference picture referred to by the current block. The method includes generating a prediction block of the current block from the reference picture by using the motion vector of the current block, the at least one scale factor, and the at least one offset factor. The method includes reconstructing transform coefficients from the bitstream, generating a residual block of the current block by inversely transforming the transform coefficients, and reconstructing the current block based on adding the prediction block and the residual block.

The application discloses a kind of multi-camera-based animal vital sign monitoring method, medium, equipment, it is related to animal vital sign monitoring technical field, method includes: using DLC posture estimation network to train animal multi-view video, obtain key point information;According to the key point information of main visual angle, the centroid motion of animal is analyzed and compared with motion threshold, determine animal state, in the continuous image sequence of relative static state time period, according to key point information, obtain region of interest;Corner point is detected in region of interest, and corresponding motion signal is acquired by tracking corner point;Correlation analysis is carried out to motion signal, and sorting is carried out based on information gain, and vital sign signal is obtained by fusing motion signal higher than set threshold;Power spectrum is used to analyze vital sign signal, obtain the energy distribution of vital sign signal, and the value of respiratory rate and heart rate is calculated.The application can effectively reduce artificial intervention, and has the role of promoting to animal experiment method innovation and data analysis.

The application provides a building facade modeling method and device based on semantic decoupling, equipment and medium, relating to the technical field of image processing. The method comprises: acquiring an image sequence and point cloud data of the building facade of a target building; based on depth distribution prediction, the two-dimensional image features of the image sequence are promoted to three-dimensional view cone features; through a cross-attention mechanism, the three-dimensional view cone features are fused with the geometric features of the point cloud data to obtain multi-modal fusion features; based on the multi-modal fusion features, the point cloud data is subjected to semantic segmentation and accessory stripping, and based on the point cloud data after accessory stripping, a building facade model of the target building is constructed. The application can accurately remove interference objects such as air conditioners, burglar nets and cables, while retaining the complete building body point cloud, thereby providing a high-quality data basis for subsequent engineering calculation, style management and control and BIM modeling, and greatly reducing the workload of manual accessory cleaning.

The application provides a PVC film preparation system and method based on industrial intelligent vision. In a stable production process of an extruder, an extruder screw torque signal and a melt temperature signal are collected, and a PVC film surface image sequence is obtained in real time. A black point density change rate per unit area in the PVC film surface image sequence is counted, and an area distribution feature of the black points in the PVC film surface image is extracted. A torque fluctuation amplitude in the screw torque signal and an over-threshold integral quantity of the melt temperature signal are calculated. The area distribution feature, the torque fluctuation amplitude and the over-threshold integral quantity are used to determine the causes of the black points in the PVC film preparation, and a determination result of the causes of the black points is obtained. Based on the black point density change rate and the cause category of the determination result, a parameter adjustment amount is calculated, and a speed adjustment amount and a maintenance time required to reduce the black point density to a target value are output. Based on the above scheme, cause category quantitative determination based on multi-source signal fusion can be realized.

The application discloses a ship engine room infrared thermal image and vibration combined diagnosis method based on a multi-mode, relates to the technical field of mechanical equipment state monitoring, and synchronously collects infrared thermal image data and vibration data of a contact area between a bearing seat and a mounting base structure in an engine room operation process, forms an infrared thermal imaging frame sequence and a vibration signal data sequence through data processing; constructs a contact area thermal image sequence and a radial vibration attenuation sequence according to the infrared thermal imaging frame sequence and the vibration signal data sequence, and maps to a unified time axis for consistency determination; aggregates time sub-sections with inconsistent evolution rhythms to form a thermal-vibration response deviation trend, judges the thermal-vibration response deviation trend, and outputs thermal-vibration response deviation results of the contact area. The method is suitable for positioning and discriminating abnormal contact between a bearing seat and a mounting base of a ship engine room through time sequence correlation analysis of thermal image information and vibration information for combined identification of the structure contact state.

The application discloses a scene-based non-uniformity correction method, and relates to the technical field of image processing.The application extracts a difference area by analyzing the difference degree of a night vision system continuous image sequence, combines the information entropy of the image to evaluate the importance score of the frame, thereby identifying key frames and non-key frames; for the key frames, full-frame storage is adopted and online average calculation is performed to generate initial non-uniformity correction parameters; the non-key frames only retain difference area data, and the difference area data is locally updated based on the correction parameters of the key frames, and the correction effect is further optimized through the statistical characteristics of the difference area; the standard deviation convergence condition is dynamically adjusted to optimize the non-uniformity correction precision, and the newly-added key frames are automatically processed in the real-time image sequence, and redundant data is deleted.The application significantly improves the image processing efficiency and correction precision, reduces the redundant calculation and storage overhead, is high in adaptability, can optimize the correction parameters in real time, and is particularly suitable for efficient and accurate night vision system image processing.

The present application relates to teaching robot practice evaluation related technology, provide a kind of teaching robot operation trajectory three-dimensional evaluation method, system, equipment and storage medium.The method obtains the image sequence of teaching robot in the process of executing practice task collected by fixed external camera, identifies and continuously tracks end effector, tool center point or preset key position, obtains two-dimensional operation trajectory information;According to the camera internal parameter and external parameter, the two-dimensional trajectory point is mapped into space ray, and the three-dimensional operation trajectory under world coordinate system is solved in combination with constraint optimization model;Again, according to key event, key action node or preset space region, action stage is divided and time sequence is aligned, and matching score is generated for each action stage and output trajectory score result.The scheme is suitable for practice task process evaluation in teaching robot platform.

Method and device for encoding and decoding images with an attention mechanism The invention relates to a method and a device for decoding a current image (Iv) in a sequence of images (Si). The method comprises the following steps: - obtaining (E31) a set of correction information (IC, FMC) for said at least one current image; - obtaining (E32) a set of prediction information (IP, FMP) for said at least one current image; - decoding (E34) a set of parameters (WMX) representative of at least one reconstruction neural network (MIX); - processing (E35) said correction information and said prediction information by said at least one reconstruction neural network to produce a representation (FMREC, Ivd) of a decoded current image.

This invention relates to a remote sensing interpretation method and system that integrates multi-source spatiotemporal spectral features and a visual model. First, optical imagery, harmonic data, and synthetic aperture radar (SAR) data of the target area are acquired and preprocessed. Next, spatiotemporal features of the optical imagery and harmonic data are extracted separately and fused using a cross-attention mechanism to generate fused features. Then, the fused features and SAR data are subjected to image serialization, temporal encoding, and spatial encoding processing, and spatiotemporal features are extracted using a self-attention mechanism. Finally, the spatiotemporal features are decoded and the multi-source feature convolution results are fused to generate pixel-level land cover classification results. This invention introduces harmonic data to capture the temporal variation trend of ground features, utilizes the visual Transformer self-attention mechanism to capture spatiotemporal interdependencies, and combines multi-source data to capture multi-dimensional features of ground features, avoiding the limitations of a single data source. Furthermore, the fusion of multi-source temporal features allows the model to adapt to different geographical environments, improving generalization performance.

The present application relates to the technical field of medical data processing, and provides a medical image data processing method based on deep learning, which comprises the following steps: collecting data according to a collection template, extracting pulse timing by adaptive threshold peak detection, calculating instantaneous phase by linear interpolation, comparing quantitative indicators with preset threshold values, judging steady state by combining peak loss rate and mutation detection rules, and verifying by calculating inter-channel phase consistency; splitting the collected data according to concept entities to form a data relationship model, implementing fast global rigidity estimation, applying affine transformation, estimating pixel-level displacement field by using a pyramid dense optical flow network, applying the displacement field to original pixels, and performing time domain fusion by taking optical flow confidence and registration residual as weights; cropping the short-time steady image sequence after registration compensation, taking a mixed network of a convolution front end and a space-time Transformer backbone as a prediction model, and outputting a pixel-level risk heat map, a candidate lesion list and confidence intervals of each output.

This application provides a method for image fingerprint recognition of small unmanned aerial vehicles (UAVs) based on heterogeneous information fusion, belonging to the field of UAV detection and recognition technology. The method includes: acquiring visible light image sequences and infrared image sequences of the target UAV, performing time synchronization, spatial registration, and scale normalization; extracting structural texture features, dynamic differential features, and infrared energy criterion feature vectors; inputting these into a cross-scene decoupled hypergraph fingerprint network for fusion encoding to obtain a low-dimensional unique image fingerprint vector; training the network using cross-scene consistency constraints and scene identity orthogonality constraints to establish a UAV image fingerprint database; matching the fingerprint vector of the target to be identified with the fingerprint database, using an open set unknown individual recognition mechanism to determine the matching result, and outputting the recognition result or the result for an unknown target. This application relies solely on image information to achieve fine-grained recognition at the model and individual levels, and has the advantages of low deployment cost, strong cross-scene stability, and high reliability of open set recognition.