151 results about "Image estimation" patented technology

A computer-implemented method for determining an estimation of a two-dimensional scattered radiation distribution in a two-dimensional X-ray image that is based on an imaging procedure performed by an X-ray detector is provided. The method includes receiving the X-ray image, applying an estimation algorithm to the X-ray image or to a two-dimensional intermediate image determined from the X-ray image. The estimation algorithm determines a respective two-dimensional partial scattered radiation image for a plurality of physical scatter processes such that image values of pixels of the respective partial scattered radiation image in each case describe an estimated value for a respective scattered radiation dose that was applied to a respective detector region of the X-ray detector assigned to the respective pixel during acquisition of the X-ray image by the respective physical scatter process. The estimation of the scattered radiation distribution is determined based on the plurality of partial scattered radiation images.

This invention discloses a quantum entangled light spatial correlation imaging method based on iterative deconvolution, belonging to the field of quantum information. The method includes the following steps: illuminating the target sample with a position-momentum entangled light source, and acquiring multiple frames of entangled light carrying sample information using a single-photon camera; performing statistical operations on the acquired multi-frame images to remove irrelevant background noise and obtain a joint probability distribution image of the sample; extracting the correlation width using the spatial distribution image of the joint probability distribution through differential coordinate projection to construct the point spread function of the optical system; using the point spread function for forward convolution projection and backward error projection, updating the image estimate through iterative calculation until the convergence condition is met to obtain the target sample image. This invention utilizes a camera to image with a position-momentum entangled light source under low illumination conditions, which can obtain high-contrast target imaging and has potential advantages in imaging light-sensitive samples.

Provided is an information processing device comprising: an acquiring unit that acquires an image of the ground around a moving body and information indicating the behavior of the moving body when the moving body moves; an estimating unit that estimates the type of the ground on the basis of the image; and a predicting unit that predicts the behavior of the moving body when the moving body moves on the ground of the type estimated by the estimating unit on the basis of a regression model for the type of the ground, and updates the regression model for the type of the ground on the basis of the predicted behavior of the moving body and the behavior of the moving body acquired by the acquiring unit. This allows the behavior of the moving body to be estimated more appropriately.

This invention discloses a low-light image quality enhancement system and method based on enhanced night scene modeling. The system includes: a sample data construction module, which generates enhanced low-light scene images based on an initial image dataset using a dual-channel hybrid generative network architecture and constructs an optimized training sample library; and a hybrid enhancement model, constructed based on an attention module and a probabilistic graphical model module. During the training phase, the hybrid enhancement model uses the optimized training sample library as input and employs a region-adaptive weighted loss function for parameter optimization. During the application phase, the optimized model receives the low-light image to be processed, estimates the illumination and noise distribution of the low-light image, and generates the enhanced image. This invention significantly improves the coverage of night scene training data and achieves adaptive enhancement of image features under low-light conditions, significantly improving the noise suppression effect in dark areas and the ability to restore image details.

A method for detecting the position of a hand belonging to a vehicle occupant comprises at least one iteration including the following steps: - acquisition of an image (IMG) including the occupant by means of an image sensor (5); - estimation, by processing the acquired image (IMG), of the respective three-dimensional coordinates (Xi, Yi, Zi) of a plurality of points on a part of the occupant's body including said hand; - determination, based on the respective three-dimensional coordinates (Xi, Yi, Zi) of the plurality of points on said body part, of a plurality of probabilities of presence (Pj) of the hand relative respectively to a plurality of predetermined areas of the vehicle's interior. A detection device and an associated system are also described. Figure for the abstract: Figure 1

The invention discloses a phase difference wavefront-image estimation method based on depth image prior. The method comprises the following steps: firstly, constructing a forward physical model of an incoherent imaging system, and generating an observation image with out-of-focus aberration by introducing phase difference; and then using a depth image prior network to jointly optimize image domain loss and wavefront domain loss under the condition of no external training data by taking the consistency of an observation image and a model generation image as a constraint so as to simultaneously obtain a high-quality recovered image and accurate wavefront estimation. The method provided by the invention can realize accurate wavefront estimation and high-quality image recovery under the condition of large aberration under the condition of only needing a small number of acquired images, and has the advantages of strong anti-noise capability, no need of an additional wavefront sensor and low system complexity. The method can be widely applied to fluorescence microscopic imaging and other high-resolution microscopic imaging technologies, and the imaging resolution and the image quality are improved.

The optical information reading method can appropriately adjust imaging conditions when analyzing captured images and reading the optical information contained in the images, without considering the environment in which the information to be read is placed. In the case of illuminating a aiming light that serves as a reference for pointing the imaging unit at the optical information to be read, and simultaneously periodically capturing images and analyzing the images to read the optical information contained in the images, the amount of movement of the imaging unit within a certain time range is estimated based on the images captured within that time range, and the imaging conditions are adjusted based on the pixel values ​​of the pixels in the captured images through imaging adjustment processing (212). When it is determined that the target has been determined based on the estimated amount of movement ("Yes" in S101), the imaging conditions are adjusted based on the pixel values ​​of pixels within a predetermined range near the position of the aiming light in the captured images (S102~S106, S113).

[Problem] To make it possible to increase accuracy of three-dimensional reconstruction. [Solution] An information processing system comprising a control unit that: estimates, for each captured image of a first captured image group of an object captured by a first imaging device and a second captured image group of the object captured by a second imaging device, the position and orientation of imaging on the basis of a common reference; generates, on the basis of a ranging data group of the object measured by a ranging device attached to the second imaging device, an integrated point cloud obtained by integrating each piece of ranging data so as to be consistent with the positions and orientations estimated from each captured images of the second captured image group; and performs three-dimensional reconstruction of the object on the basis of the integrated point cloud and the first captured image group.

A robot system includes circuitry configured to: acquire a workpiece image showing a workpiece present in real space; estimate skeleton information indicating a skeleton of the workpiece based on the workpiece image; acquire constraint information representing a constraint regarding a task to be performed on the workpiece; determine a completion state of the task based on the acquired constraint information and the estimated skeleton information; and cause a robot placed in the real space to perform the task in accordance with the determined completion state.

A road surface detection system and a vehicle control unit are provided, capable of implementing suitable driving operation according to the waviness of a road surface in a vehicle's direction of travel. For this purpose, the road surface detection system 300, which detects a property of a road surface on which the vehicle 100 is traveling, includes the imaging unit 301, which captures an image of the road surface; the waviness estimation unit 303, which estimates the waviness of the road surface from the image; the front-to-back waviness cycle estimation unit 304, which estimates a waviness cycle in the front-to-back direction of the vehicle 100 from the image; and the road surface shape determination unit 306, which determines a shape of the road surface based on the waviness and the front-to-back waviness cycle.

The present application relates to a kind of asteroid global terrain three-dimensional reconstruction method for illumination change, comprising the following steps: input asteroid optical image, estimate camera pose and generate sparse point cloud, initialize Gaussian radiation field;Using image segmentation large model outputs the segmentation mask of asteroid optical image, prunes Gaussian radiation field;In combination with the mixed mask output by Gaussian radiation field, identify the shadow area of asteroid surface;The camera position, spherical harmonic coefficient and hash coding are combined into incident light angle, input into neural network, and the color value of Gaussian cell of illumination and shadow area is regressed;Add depth normal consistency loss and rotation variance and scale constraint loss, combine photometric loss to jointly supervise the optimization of Gaussian radiation field, calculate Gaussian opacity field, extract the three-dimensional model of asteroid global terrain.The present application can identify the shadow area on asteroid, improve the three-dimensional reconstruction precision of asteroid with surface illumination change.

Even when repeatedly placing and removing the same type of product from a weighing pan, the goal is to avoid a deterioration in work efficiency. [Solution] The product processing device 1 according to one embodiment includes a camera 11 that captures images of products 100 placed on a product placement unit 10 and generates captured images, a display unit 12 that displays various information, a control unit 13 that estimates product candidates C based on the captured images and displays the product candidates C on the display unit 12, and a label printer 14 that prints product information related to product 100 on a label. The control unit 13, based on the product candidates C displayed on the display unit 12, causes the label printer 14 to print product information related to the identified product when a product is identified by the operator's operation, and after a product has been identified, if it is determined that a product candidate C estimated based on a captured image of another product is the same as the first product, it uses the product information related to the first product to print product information related to the other product on the label printer 14.

An information processing device and an information processing method capable of appropriately handling a shielding region of a road are provided.The information processing device includes a first information conversion unit 15 that estimates a first road region from an image obtained by imaging the road, a second information conversion unit 17 that estimates a second road region from map information stored in a map information storage unit 11, and a difference extraction unit 16 that extracts difference information representing a difference between the first road region and the second road region. Further, in the information processing method, a computer estimates the first road region from the image obtained by imaging the road, estimates the second road region from the map information, and extracts the difference information indicating the difference between the first road region and the second road region.

The invention relates to the technical field of image processing, in particular to a retinopathy recognition method, system and device based on artificial intelligence and a medium, and the method comprises the steps: taking the eye of a detected pregnant woman as a target object, setting a preset position, scanning in the depth direction, obtaining point fault information, carrying out three-dimensional reconstruction, and generating a second image. Generating a third image, performing correction processing, presetting a straight line in the corrected image, obtaining pixel values corresponding to the positions where the first pixel and the second pixel are located, and obtaining the thickness data of each layer; taking the thickness data as a pixel value; setting the value of each layer of pixel to be equal to the thickness data of the layer; generating a fourth image; and establishing an image database, adding a disease marker to the reference image, training the image estimation model by using the reference image added with the disease marker, and outputting a disease corresponding to the fourth image. The method improves the prediction efficiency and accuracy of the eye fundus image.

This invention discloses a terahertz SAR imaging method based on total variational and Cauchy combined regularization: The data obtained after range compression and azimuth deskewing of the echo data received by terahertz SAR is used as the observation matrix, the Fourier transform matrix is ​​the coefficient matrix, and the image is the matrix to be recovered. Image recovery is modeled as an inverse problem, introducing Cauchy regularization to represent sparse features and total variational regularization to recover target structural features. An alternating minimization framework is used to solve the problem, obtaining an image estimate. The image estimate is combined with the original echo data to solve for the platform phase error estimate, which is then compensated into the observation matrix. The above steps are repeated to iteratively estimate the desired image and phase error to obtain a high-precision imaging result. This invention also provides a terahertz SAR imaging device based on total variational and Cauchy combined regularization. This invention can obtain high-quality focused images and has good compensation effects for both low-frequency motion errors and high-frequency vibration errors.

The invention provides a multi-view three-dimensional reconstruction method based on image segmentation, which comprises the following steps: estimating a depth map of each image based on a plurality of acquired images of different views of the same scene, and the estimation mode comprises the following steps: down-sampling all the images for multiple times to obtain a plurality of feature maps of different hierarchies corresponding to each image; iteratively processing each image for multiple times, obtaining a depth map of each level of the image each time, and determining reliable pixels and unreliable pixels at the time; according to the feature maps of all the images at the corresponding levels, the depth estimation values of the reliable pixels are updated, the depth estimation values of the unreliable pixels are reconstructed through a preset deformation algorithm, and the algorithm comprises the steps that different objects of the images are segmented into different areas, and the depth estimation values of the unreliable pixels are obtained for the unreliable pixels; only selecting a plurality of anchor points from reliable pixels in the same area as the pixel to perform patch deformation so as to reconstruct and obtain a depth estimation value; and fusing the depth maps obtained at the last time of all the images to obtain three-dimensional point cloud data.

According to an embodiment of the present disclosure, an image generation device providing a motion artifact correction function is disclosed. The device comprises a light generation unit configured to emit light irradiated onto a target object, a light receiving unit configured to receive optical signals reflected from the target object, a driving unit configured to control a light propagation path, and at least one processor. The processor is configured to irradiate light onto the target object to generate at least one scanning image, estimate a motion speed, generate a corrected scanning image by correcting the at least one scanning image based on the estimated motion speed, and generate a final corrected image based on the at least one corrected scanning image.Also disclosed is a method for operating the image generation device.

A system for tissue suturing guidance in a surgical site includes an imaging device configured to capture an image of a surgical needle within the surgical site and an imaging device control unit configured to control the imaging device. The imaging device control unit includes a processor and a memory. The memory stores instructions which, when executed by the processor, cause the system to capture an image of a surgical needle and a surgical tool within the surgical site via the imaging device, estimate a pose of the surgical needle based on the captured image, generate an augmented image based on the estimated pose of the surgical needle, and display on a display, the augmented image of the surgical needle.

The invention relates to a method for detecting the position of a hand of an occupant of a vehicle, the method comprising at least one iteration comprising the following steps: - acquiring an image (IMG) including the occupant by means of an image sensor (5); - estimating, by processing the acquired image (IMG), the respective three-dimensional coordinates (Xi, Yi, Zi) of a plurality of points of a portion of the body of the occupant comprising the hand; - determining, as a function of the respective three-dimensional coordinates (Xi, Yi, Zi) of the plurality of points on the portion of the body, a plurality of probabilities (Pi) of the presence of the hand, the probabilities respectively being associated with a plurality of predetermined zones of the passenger compartment of the vehicle. The invention also relates to a detection device and an associated system.

Systems, methods, and apparatuses for image reconstruction. One computer-implemented method includes receiving measurement data representing a subject and generating an image estimate of the subject based on the measurement data. The method also includes refining the image estimate by performing an iterative reconstruction process comprising a plurality of iteration steps, each iteration step comprising (i) computing a data consistency term based on the image estimate and the measurement data, (ii) generating a correction term using a machine learning model based on the image estimate, the data consistency term, the measurement data, and cross-iteration information, and (iii) updating the image estimate based on the correction term, the data consistency term, and a global learning rate corresponding to the iteration step.

This invention provides an ultrasound diagnostic system and a control method for the ultrasound diagnostic system that can estimate the position and orientation of an ultrasound probe even when the ultrasound probe is in a blind spot in the field of view of an optical camera. [Solution] The ultrasound diagnostic system comprises an ultrasound probe (1) having a reference figure projection light source (11) that projects a reference figure, a projection member (4) onto which an image of the reference figure is projected from the reference figure projection light source (11), a diagnostic device (2) connected to the ultrasound probe (1), and an optical camera (3) connected to the diagnostic device (2) that acquires an optical image of the projection member (4). The diagnostic device (2) has a probe position estimation unit (24) that estimates the position and orientation of the ultrasound probe (1) based on the image of the reference figure projected onto the projection member (4) that is captured in the optical image.

The invention discloses a TLH-Net-based image enhancement method in a low-illumination and fog superposition scene. The method comprises the following steps: 1) data set construction: constructing a low-illumination superposition fog image data set; 2) low-illumination defogging network design: designing a three-branch low-illumination defogging network; decomposing the input image into a fog image, a reflection image and an illumination image; 3) designing a fog image estimation network: designing a fog layer decomposition network; 4) a reflectogram estimation network: designing a reflectogram estimation network, decomposing the reflectogram based on the Retinex theory and performing denoising; according to the method, the Retinex theory, the atmospheric scattering model and semantic guidance are fused, the problem of target information fuzziness caused by low illumination and fog superposition is effectively solved, and the adaptability and generalization ability of the model in different scenes are improved.

The invention relates to a 3D occupancy grid sensing method and device, a vehicle and a readable storage medium. The method comprises the following steps: acquiring space image features and image estimation depth of a space image acquired from a target space; generating a preset number of anchor frames for the target space, and fusing the initialized anchor frame information and the image estimation depth of each anchor frame to obtain anchor frame preprocessing features of each anchor frame; obtaining first spatial information and first occupation category information of each anchor frame according to the spatial image features, the pre-processing features of each anchor frame and the anchor frame embedding features; according to second space information of effective grids in a plurality of grids generated for the target space and each piece of first space information, obtaining an occupation probability that each effective grid is occupied by each anchor frame; and obtaining second occupation type information of each occupied grid in each effective grid according to each occupation probability, each piece of first space information and each piece of first occupation type information. By adopting the method, the calculation efficiency of sensing the 3D occupied grids can be improved.

A moving body control device according to the present invention includes an acquisition unit that acquires an image obtained by imaging situations in a vicinity of a moving body, a recognition unit that recognizes an object that is present in the vicinity of the moving body on the basis of the image, an own position estimation unit that estimates the own position of the moving body on the basis of the image, and a movement control unit that performs movement control of the moving body on the basis of an estimation result of the own position. The recognition unit recognizes at least a first object that is present in the vicinity of the moving body and that is moving, as an object. The own position estimation unit sets regions of objects to be excluded from a region in the image when estimating the own position, on the basis of type of each object and reliability representing likelihood, and estimates the own position on the basis of information regarding a region in the image that is not excluded.

Provided are systems and methods of inverting a trained NeRF model, where the NeRF model stores the structure of a scene or object to estimate 6D poses from images taken at new viewpoints. 6D pose estimation has a wide range of applications, including visual localization and object pose estimation for robotic manipulation.

A method for estimating a pose of a user by a head-mounted display (HMD) device is provided. The method includes obtaining at least two images from at least two cameras of the HMD device, each of the at least two obtained images including a view of at least a portion of a body of the user wearing the HMD device, estimating a pose of the body of the user based on the view of the at least portion of the body of the user included in each of the at least two obtained images, estimating a pose of a head of the user based on the at least two obtained images, and estimating the pose of the user based on the estimated pose of the body of the user and the estimated pose of the head of the user.

More appropriately update the map information for mobile body to estimate the position of the mobile body control device and method, mobile body control system, storage medium. The control device of the mobile body has: a part of getting, taking the image of the surrounding situation of the mobile body; recognition part, based on the image recognition existing in the mobile body surrounding object; self position estimation part, based on the image estimation of the mobile body own position; mobile control part, based on the estimation result of the self position of the mobile body movement control; information processing part, extract the first image in the image which satisfies the prescribed condition of updating the map information, make the first image store in the storage part, the prescribed condition is at least the condition of extracting the image including the first category object which is shown in the map information in advance, the information processing part determines the first category object from the recognized object existing in the mobile body surrounding, extracts the first image which reflects the determined first category object.

In a case where an image is periodically captured in each frame by an imager (110) and optical information contained in the image is read by analyzing (S81 to S87) the image, an amount of movement of the imager (110) per frame is estimated (S31 to S42) based on images captured in a certain time range (T), and an imaging condition including at least one of an exposure time and an illumination lighting time is adjusted (S113 or S115) by an imaging adjustment process (212). In this case, an upper limit of a value of the at least one to be set by the imaging adjustment process is determined (S112 or S114) based on the estimated amount of movement of the imager (110) per frame.

This invention discloses a depth image estimation method, apparatus, electrical device, and storage medium. The depth image estimation method is applied to an embedded neural network processor. The method includes: acquiring a first image and a second image captured by a binocular camera; cropping the effective regions of the first and second images respectively to obtain a first effective image and a second effective image; using a pre-trained lightweight image correction network model to align and correct the rows of the first and second effective images to obtain a first corrected image and a second corrected image; and using a pre-trained lightweight depth estimation network model to estimate the depth of the first corrected image and the second corrected image to obtain a depth image. This method reduces computational complexity, computational load, and computation time, while ensuring the real-time performance of the depth estimation method.