53 results about "Defined Imaging" patented technology

Nonlinear peri-codec optimization for image and video coding includes obtaining a source image including pixel values expressed in a first defined image sample space, generating a neuralized image representing the source image, the neuralized image including pixel values that are expressed as neural latent space values, encoding the input image wherein the neural latent space values are used as pixel values in a second defined image sample space and the input image is in an operative image format of the encoder, such that a decoder decodes the encoded image to obtain a reconstructed image in the second defined image sample space, wherein the reconstructed image is a reconstructed neuralized image including reconstructed neural latent space values, such that a deneuralized reconstructed image corresponding to the source image is obtained by a nonlinear post-codec image processor in the first defined image sample space.

Intravascular imaging catheters and methods for making and using intravascular imaging catheters are disclosed. An example intravascular imaging catheter may include an elongate catheter shaft having a distal end region and a proximal region. A guidewire lumen may be defined in the elongate catheter shaft. The distal end region may include an imaging window defined by an open gap in the elongate catheter shaft. An imaging core may be disposed within the elongate catheter shaft. The imaging core may include an imaging device configured to be axially aligned with the imaging window.

The invention provides an image defogging enhancement and intelligent perception collaborative optimization method based on stream matching, and the method comprises the steps: obtaining a foggy input image, and constructing an ordinary differential equation for defining image transformation; the input image is input into a fog perception vector field, the fog perception vector field comprises an atmospheric scattering purifier and a defogging perception color lookup table, and the atmospheric scattering purifier is used for extracting multi-scale features from the foggy input image to generate clearer output; the defogging perception color lookup table adaptively adjusts the image color through a nonlinear color transformation mechanism; and solving the ordinary differential equation through an RK4 solver, iteratively updating the foggy input image at each time step, and ensuring that the input image can be stably converted into a clear image from an initial foggy state. The technical problems that in the prior art, the existing method is forced to reduce the model capacity due to the calculation efficiency constraint in the ultra-high-definition image defogging, so that the fog concentration estimation is incomplete, and the perception quality and the calculation efficiency cannot be considered at the same time are solved.

In an example, a method includes defining, for an interior portion of an object to be generated in additive manufacturing, an imaging characteristic in a radiation environment. In some examples the method further includes deriving object model data for generating the interior portion of the object by determining an amount of a first contrast agent and an amount of a second contrast agent to deposit such that the object generated according to the object model data comprises the defined imaging characteristic apparent in an image of at least a part of the object comprising the interior portion captured in the radiation environment. The first contrast agent and the second contrast agent may have different imaging characteristics in the radiation environment.

The invention discloses a vehicle pixel headlamp control method and a related device. The method comprises the following steps: acquiring a custom image and display mode indication information; and according to the display mode indication information, controlling a pixel headlamp to display image data after rendering of the custom image. By implementing the method, the controller indicates to render the display content of the pixel headlight of the vehicle according to the display mode indication information, so that the user-defined image is displayed according to the user demand, and the personalized demand of the user is met.

The invention discloses a high-performance video and UI (User Interface) display method based on a layered rendering architecture, which comprises the following steps of: defining image display layers and a priority sequence thereof, sequentially rendering each layer according to a sequence from low priority to high priority, and ensuring that the high priority layer can correctly cover the low priority layer; and controlling the display sequence of each layer by adopting a double-track system that a local display sequence is determined according to a z-index value in a lamination priority and the same priority, and synthesizing a final screen display image. The technical scheme of the invention has the main advantages that real-time rendering of a high-quality video stream is supported while UI responsiveness is kept, and the requirement of a high-performance scene is met; it is ensured that the UI layer is always kept above the video layer, or the stacking sequence is dynamically adjusted according to application requirements; and a hierarchical design principle is adopted, and loose coupling is realized among the modules, so that independent upgrading and maintenance are facilitated, and the expandability of the system is enhanced.

The invention discloses an image reconstruction method and system and a storage medium, and the method comprises the steps: carrying out the random cutting of a low-resolution image in an image data set, and obtaining an image block; extracting shallow layer features of the low-resolution image; taking a certain image block as a query sample, defining other image blocks from the same low-resolution image as the query sample as positive samples, and defining image blocks from low-resolution images different from the query sample as negative samples; respectively extracting feature vectors of the query sample, the positive sample and the negative sample; extracting the shallow features and deep features of the feature vectors, and enhancing the deep features to obtain enhanced features; and converting the enhanced features into a high-resolution image. According to the method, the utilization efficiency of image structure information is improved, and the problem of task imbalance is solved.

Surface determination systems, threat detection systems and medical treatment systems are described. According to one aspect, a surface determination system includes processing circuitry configured to access a three-dimensional complex-valued image volume of a target, define image locations of the image volume using first and second dimensions of the image volume, for each of the first locations, identify voxels along a third dimension of the image volume that correspond to the respective first location, for each of the first locations, select one voxel that corresponds to the first location as having an increased amplitude compared with other voxels that correspond to the first location, and for each selected voxel, use phase information to identify a second location in the third dimension for the selected voxel that corresponds to a location of a surface of the target and that is different than a third location of the respective voxel.

This invention discloses a navigation-following unmanned surface vessel (USV) formation control method based on active vision, comprising the following steps: constructing a kinematic model of the USV based on a geodetic coordinate system; establishing a gimbal monocular camera model for the gimbal camera mounted on the USV; defining servo tracking errors for the navigation-following USV formation system by combining the USV kinematic model and the gimbal monocular camera model; defining image coordinate errors based on the viewing angle constraints of the gimbal monocular camera; designing a motion controller and adaptive parameter update law for the USV using the Lyapunov synthesis method; and designing a gimbal camera steering controller and adaptive parameter update law using the Lyapunov synthesis method. This method ensures the smooth implementation of visual servo control of the USV by defining servo tracking errors and image coordinate errors, and then incorporating these two errors into the Lyapunov synthesis method to design the USV motion controller, the gimbal camera steering controller, and the adaptive parameter update law.

The present application discloses a method for evaluating image clarity, and the application scenarios include at least various types of terminals, such as mobile phones, computers, and vehicle-mounted terminals. It includes: obtaining a first image group from an image sequence, and each frame of the image sequence includes an image corresponding to a target object; extracting feature points from the first image group to obtain a first feature point set corresponding to the first image and a second feature point set corresponding to the second image, and the first feature point and the second feature point have a one-to-one correspondence; determining a first motion speed of the target object according to the first feature point set and the second feature point set; determining a clarity evaluation result of the second image according to the size relationship between the first motion speed and the blur speed threshold. The present application also provides an apparatus, a device, and a storage medium. The present application can effectively define image clarity, thereby helping to screen out images with higher clarity for subsequent processing.

This invention discloses an image data filtering method and system based on an object detection learning algorithm, relating to the field of intelligent parking management. The method includes: using a modified object detection model training method and an initially labeled image dataset to obtain a basic object detection model; and on this basis, using a partitioned test set to define image-level uncertainty based on image content recognition accuracy information to obtain preliminary image filtering indicators; further, when the amount of image data filtered in one step is much greater than the expected amount of labeled data, a second image filtering is performed through image feature clustering to ensure that the filtered image content has a diverse distribution under the same data volume conditions; through several iterative model updates, the energy efficiency ratio of newly added labeled data to model accuracy can be ultimately improved.

The invention provides a method for determining the organic matter surface porosity of the total area occupied by organic matter pores, which comprises the following steps: carrying out an electron microscope scanning experiment on a shale sample to obtain a first scanning electron microscope image of the shale sample; extracting all organic matter regions in the first scanning electron microscope image of the shale sample by using preset image processing software to obtain the total area fraction of organic matters on the surface of the shale sample; obtaining the average surface porosity of organic matter pores from the first scanning electron microscope image of the shale sample according to a preset fifth rule; and according to the total area fraction of the organic matters on the surface of the shale sample and the average surface porosity of the organic matter pores, obtaining the organic matter surface porosity of the organic matter pores in the total area according to a preset formula. The organic matter surface porosity of the organic matter pores in the total area can characterize the characteristics of the shale surrounding pore structure, reflect the shale organic matter thermal evolution process, and provide a basis for evaluating shale gas reservoir and dessert section optimization.

The application discloses an image classification method and device, a storage medium and a computer device. The method is applied to the computer device and comprises the following steps: in a self-defined image classification mode of an electronic album, in response to a triggering operation of a user on an update control of an image corresponding to a to-be-managed image category, updating the image in the to-be-managed image category, calling a training interface, obtaining a first image classification model corresponding to the self-defined image mode through the training interface, the model being pre-trained, and performing transfer training on all images of the to-be-managed image category according to the first image classification model, so as to obtain a first image classification model after transfer training. The classification of the updated image can be matched by using the first image classification model after transfer training, the classification accuracy is improved, finally, the to-be-classified images of the electronic album are classified by using the trained first image classification model, the image classification efficiency and accuracy are improved, and the image searching efficiency is further improved.

The present invention discloses an image reconstruction method, system and storage medium, which randomly crops low-resolution images in an image dataset to obtain image patches; extracts shallow features of the low-resolution images; takes a certain image patch as a query sample, defines other image patches from the same low-resolution image as the query sample as positive samples, and defines image patches from low-resolution images different from the query sample as negative samples; respectively extracts feature vectors of the query sample, positive samples and negative samples; extracts deep features of the shallow features and the feature vectors, enhances the deep features to obtain enhanced features; and converts the enhanced features into high-resolution images. The present invention improves the utilization efficiency of image structure information and solves the problem of task imbalance.

A head-mounted display system includes an emissive micro-display including an array of light emitters corresponding to pixels, where the array of light emitters is configured to output image light that defines images. The system also includes an aspheric lens configured to receive the image light from the emissive micro-display and correct the image light. The system also includes a first surface mirror configured to redirect the image light from the aspheric lens from a first direction to a second direction substantially orthogonal to the first direction. Moreover, the system includes a collimating optic configured to receive the image light from the first surface mirror and collimate the image light. In addition, the system includes an eyepiece configured to receive the image light from the collimating optic and to direct the image light to an eye of a user.

The decoding device includes circuitry and a memory connected to the circuitry. The circuitry acquires an image from a bitstream and a first parameter associated with the image. The first parameter includes modal information representing the image category, which indicates that the image category is at least one of the following: a visible light image, an infrared image, an ultraviolet image, an undefined image, or a pre-defined image category for extension.

A system (100), and method (200) thereof, is provided for identifying and forecasting animal activity. The method (200) may comprise receiving (202) the images (112) from the camera (110) to define image specific raw data (114); assimilating (204) the image specific raw data (114) with contemporaneous weather data (140); determining (206) a mean rate of animal sightings for each of a plurality of prior time intervals associated with the assimilated image specific raw data using a first analytics model; minimizing (208) a difference between observed sightings and predicted sightings based at least in part on outputs from the first analytics model using a second analytics model; and determining (212) an amount of likely animal sightings for each of a plurality of future time intervals based at least in part on the outputs from the first analytics model and outputs from the second analytics model using a third analytics model.

This invention discloses a method for inspecting the quality of bed making in hotels using a bed-making service robot. The method is integrated into the robot's control system and includes the following steps: determining the bed-making quality inspection target, defining image range information, range type, and inspection dimension; generating control commands for the robot's sensors based on the image range information; acquiring image group information returned by the robot sensors; loading an image recognition model, including a standard definition unit, a feature extraction unit, and a feature comparison unit; inputting the image group information into the image recognition model to obtain inspection results and correction strategies. According to this technical solution, when inspecting the quality of bed making services provided by the robot, clear inspection standards can be established, reducing reliance on manual labor, saving labor costs, improving the efficiency of hotel room preparation and control, ensuring greater accuracy and consistency in inspection, and providing readable evaluation results.

A machine characteristic acquisition unit (22) acquires a machine characteristic that specifies computational information with a computational formula by taking information about image data of a processing target as an input, with respect to each of one or more types of machines that can be used in a target image processing, among machines corresponding to each of a plurality of processor types. A device characteristic acquisition unit (23) acquires a device characteristic indicating a correction content for the computational formula specified by the machine characteristic with respect to one or more types of processors contained in a target device, among the plurality of processor types.In a case where a defined process, which is a defined image process, is carried out by a defined device, which is a defined device, a computation unit (21) computation information based on a machine characteristic and a device characteristic with respect to a machine which is a computation target, by considering one or more machines that can be used in the defined process and that are contained in the defined device as the machine which is the computation target.

The present invention discloses a method for enhancing image watermarks based on a neural network structure. A neural network model for image watermark enhancement is constructed based on the neural network model ViT and pre-trained on an image dataset. The pre-trained model is then used to perform image watermark enhancement processing through a multi-step iterative method, generating deceptive adversarial noise on the image. This is used to enable the model to learn a pre-defined image watermark pattern, thereby making it difficult for the ViT network trained on the image after generating the adversarial noise to forget the pre-defined watermark pattern. The masked noise is then added to the image pixels, thereby obtaining an enhanced watermarked image. The technical solution provided by the present invention significantly improves the difficulty of removing watermarks using existing watermark removal technologies by reducing the difference in activation values ​​between clean samples and watermarked samples, and can be widely promoted and applied.

The invention discloses a zero-sample custom image generation method, a control device, a storage medium and a system, and belongs to the technical field of image generation. The method comprises the steps of obtaining an input text sample set used for customizing images, generating at least one image consistent with an identity described by the input text sample for each input text sample in the input text sample set, constructing a training data set based on the generated images, and adopting a parallel processing architecture to process the input text sample set and the training data set. And training a preset text-to-image diffusion model, and deploying the trained text-to-image diffusion model so as to obtain a corresponding self-defined image according to the text input by the user. Through the parallel processing architecture, the preset text-to-image diffusion model is trained, so that the trained model can accurately output the image consistent with the input text information.

This application discloses an image retrieval method and apparatus, relating to the field of knowledge distillation technology. The method includes: using user-input query text as the retrieval source, and employing text semantic understanding and image feature matching algorithms to filter and output target images from a pre-defined image library that match the text content description, thereby completing cross-modal text-image retrieval. This solves the technical problems in related technologies, such as the difficulty in deeply mining core knowledge like fine-grained probability distribution and coarse-grained structural features of the attention mechanism during image retrieval, and the inability of the distillation process to cover all dimensions of knowledge at the attention level, resulting in insufficient integrity of knowledge transfer. The method achieves the technical effect of helping users quickly locate target images with concise text descriptions through deep correlation matching between text and images, effectively simplifying the image search operation process, and providing users with an efficient and convenient image retrieval and browsing experience.

Adaptive acquisition control timing control for image and video acquisition and processing includes obtaining, by an auto-exposure compensation component of an image processing pipeline of an image capture apparatus, during a current sensor readout window corresponding to obtaining current input image data from an image sensor of the image capture apparatus, in accordance with defined image acquisition and processing timing data, current auto-exposure compensation data for processing subsequent input image data obtained from the image sensor during a subsequent sensor readout window sequentially immediately subsequent to the current sensor readout window, and outputting, to a second data storage unit instance of the image processing pipeline, by the auto-exposure compensation component, during the current sensor readout window, the current auto-exposure compensation data.

The present application relates to a kind of training method, equipment and medium for the multi-task prediction model of medical image, the method includes the following steps: obtaining multi-center, multiple devices, multiple tracer initial medical image and clinical risk factor feature, the initial medical image includes PET image and CT image;First equalization processing is carried out to initial medical image corresponding lesion segmentation gold standard, obtain equalized 3D image sequence;Resampling is carried out to the 3D image sequence, extract deep learning feature and pre-defined image group feature;Second equalization processing is carried out to the deep learning feature, and feature post-processing is carried out to the equalized feature;The deep learning feature, pre-defined image group feature and clinical risk factor feature obtained are spliced, and final feature is obtained;With final feature as input, multi-task prediction model is trained and obtained.Compared with prior art, the present application has the advantages of high medical image processing accuracy, suitable for multi-modal image and the like.

The invention relates to the technical field of transcranial magnetic stimulation medical image processing, and discloses a transcranial magnetic stimulation medical image processing system and method.The system comprises an image obtaining module used for collecting multi-modal medical image data and defining image partitions according to clinical diagnosis requirements; the feature analysis module is used for extracting stimulation associated features and constructing a feature mapping relation between the image subareas and the image positioning stimulation areas; the region fusion module is used for screening a core region and analyzing a parameter fusion matching degree to obtain parameter focusing fusion information; the mapping relation updating module is used for updating the feature mapping relation based on the parameter focusing fusion information; and the processing execution module is used for determining a processing target and a process according to the updated mapping relation and generating a processing execution library. The method corresponds to module steps of the system. According to the scheme, the precision and efficiency of transcranial magnetic stimulation medical image processing can be improved, and clinical diagnosis requirements are met.

The application provides a flow matching-based image defogging enhancement and intelligent perception collaborative optimization method, including the steps of: acquiring a foggy input image, constructing a common differential equation defining image transformation; inputting the input image into a fog perception vector field, the fog perception vector field including: an atmospheric scattering purifier and a defogging perception color lookup table, the atmospheric scattering purifier being used to extract multi-scale features from the foggy input image to generate a clearer output, and the defogging perception color lookup table being used to adaptively adjust the image color through a nonlinear color transformation mechanism; solving the common differential equation through an RK4 solver, and iteratively updating the foggy input image at each time step to ensure that the input image can be smoothly and stably transformed from the initial foggy state to a clear image. The application solves the technical problem that the existing method in the prior art is forced to reduce the model capacity due to the calculation efficiency constraint in the ultra-high-definition image defogging, resulting in incomplete fog concentration estimation and inability to balance the perception quality and calculation efficiency.

A method for comparing the utilization rate of UAV flight path images belongs to the field of remote sensing data processing technology. The method involves: labeling images acquired by the UAV to select target areas; classifying images based on these target areas; after filtering, images are divided into three categories: irrelevant images without target information, valid images containing target information, and invalid images where target information is occluded; defining image utilization evaluation indicators, including total utilization (TU), effective utilization (EU), and occlusion rate (OR); TU represents the image utilization rate without considering occlusion, and EU represents the image utilization rate considering occlusion; and calculating the image utilization rate. This invention can effectively quantify the utilization rate of images captured by UAVs, providing technical support for further flight path planning, improving modeling accuracy, and reducing operational costs.

Techniques are described for computer-aided diagnostic evaluation of liver exams. A method embodiment comprises rendering, by a system operatively coupled to a processor, medical images of a liver of a patient in a graphical user interface (GUI) of a medical imaging application that facilitates evaluating liver imaging exams. The method further comprises identifying, by the system, an observation on the liver as depicted in one or more of the medical images and evaluating defined imaging features associated with the observation as depicted in the one or more medical images. The method further comprises providing, by the system, feature information regarding the defined imaging features via the GUI.

A surgical system includes a handheld cable housing with a user input device positioned thereon. The surgical system includes an endoscope shaft with a distal end and a proximal end. The proximal end of the endoscope shaft is coupled to the handheld cable housing, where the distal end of the endoscope shaft comprises an image sensor. The endoscope shaft is rotatable relative to the handheld cable housing. One or more angular position sensors configured to measure an angular offset relative to a defined image horizon. Upon receiving angular offset data indicative of an angular offset relative to the defined image horizon, an image processor generates rotated image data based on the angular offset data and causes display of the rotated image data.

The present invention relates to an image generating device (161, 162, 163) of or for a vehicle (10), comprising an input device (20) for inputting data defining an image (17), a digital projector (26) for projecting the defined image (17) onto a surface (18) of or near the vehicle (10), and an interface (30) for establishing a communication between the input device (20) and the digital projector (26). The present invention is further drawn to a vehicle (12) comprising such an image generating device (161, 162, 163) and to a method for generating an image using such an image generating device (161, 162, 163).