175 results about "Fluoroscopic image" patented technology

Disclosed are approaches that may provide image-guidance to interventionalists by providing true 3D visualization and quantitative feedback in real-time. A guidance system may allow a physician to manipulate a medical device and see a 3D rendering with quantitative feedback floating in mixed reality, next to standard monitors. Image tracking may detect and co-register the medical device's 3D position using, for example, bi-plane C-arm X-ray fluoroscopy and provide a 3D trajectory as quantitative feedback. Patterns in a fluoroscopic image may be used to accurately determine an object's z-position from a single angle projection.

Systems and methods for view-conditioned diffusion for real-world vehicle gaussian splatting. A single perspective image can be transformed using image transformation techniques to generate a training dataset that addresses a domain gap between synthetic data and real-world data in a traffic scene. A pre-trained diffusion model can be finetuned with the training dataset to obtain a fine-tuned diffusion model. Perspective-aware images having different perspective views of an entity from the single perspective image can be generated using the fine-tuned diffusion model. A large generative model (LGM) can be trained using the perspective-aware images to generate a gaussian splatting model for the entity. View-conditioned simulations from the single perspective image can be generated by using the gaussian splatting model for downstream tasks.

Methods and systems for x-ray and fluoroscopic image capture and, in particular, to a versatile, multimode imaging system incorporating a hand-held x-ray emitter operative to capture digital or thermal images of a target; a stage operative to capture static x-ray and dynamic fluoroscopic images of the target; a system for the tracking and positioning of the x-ray emission; a device to automatically limit the field of the x-ray emission; and methods of use and use of such systems to register a virtual model of an anatomic structure to the corresponding anatomic structure.

Methods and systems for X-ray and fluoroscopic image capture and, in particular, to a versatile, multimode imaging system incorporating a handheld X-ray emitter operative to capture non-invasive images of a target; a stage operative to capture static X-ray and dynamic fluoroscopic images of the target; a system for the tracking and positioning of the X-ray emission to improve safety of obtaining X-ray images as well as improve the quality of X-ray images. Where the devices can automatically limit the field of the X-ray emission.

A method includes obtaining multiple see-through image frames of an environment around an augmented reality (AR) device using multiple imaging sensors of the AR device. The method also includes generating a depth map based on the see-through image frames and generating a three-dimensional (3D) representation of the environment based on the depth map. The method further includes projecting the 3D representation onto a curved surface, mapping points of the projected 3D representation to multiple virtual view images, and presenting the virtual view images on one or more displays of the AR device. Generating the depth map may include generating an initial depth map using a trained machine learning model and modifying the initial depth map to provide both spatial consistency and temporal consistency in order to generate a refined depth map. The curved surface may include a portion of a cylindrical, spherical, or conical surface.

The gas-phase welding equipment comprises a liquid storage tank, a preheating device, a heating cavity and a perspective imaging system, the liquid storage tank is used for storing gas-phase liquid, the preheating device is connected to the liquid storage tank and heats the gas-phase liquid to a first temperature, and the heating cavity is connected to the preheating device and heats the gas-phase liquid to a second temperature. The perspective imaging system is used for heating the gas-phase liquid until the gas-phase liquid is evaporated so as to heat a workpiece, the perspective imaging system comprises a ray imaging assembly, a servo driving mechanism and a digital imaging device, the ray imaging assembly is arranged above the heating cavity through the servo driving mechanism, and the ray imaging assembly can be located in the heating cavity through the servo driving mechanism to carry out horizontal moving scanning; the digital imaging device is arranged below the heating cavity and used for receiving rays of the ray imaging assembly to form a perspective image, and specific defect factors can be analyzed according to the perspective image of a workpiece welding spot, so that the specific defect factors are fed back to gas-phase welding equipment to adjust corresponding working parameters such as pressure, temperature, constant-temperature time and cooling slope.

The invention relates to the technical field of industrial vision, in particular to an intelligent fruit quality grading method and system based on computer vision. According to the method, a fruit digital twinborn tensor is constructed by aligning visible light and perspective images, and semantic association and weighted fusion of internal and external features are realized by using a cross-dimensional semantic bridging matrix. Furthermore, heterogeneity-quality feature decoupling flow is adopted, the feature space is forcibly split into safety and quality feature vectors under the orthogonal loss constraint, and a safety and taste double-effect atlas is generated based on the safety and quality feature vectors so as to output a grading instruction. The method effectively solves the problems that the moldy core and the physical damage are difficult to distinguish and the sugar degree prediction is interfered by rotting fermentation, and realizes the accurate elimination of the pathological defects of the fruits and the lossless grading of the flavor quality.

The invention provides a multi-level domain adaptive pedestrian detection method and system based on a teacher model, and the method comprises the steps: training a target detector through employing source domain perspective image data with a pedestrian label, and obtaining an initial target detector; constructing a target domain teacher model and a cross-domain student model; and performing multi-level domain adaptive adversarial training by using the cross-domain student model, updating parameters of the target domain teacher model through index moving average of the weight of the cross-domain student model, generating a pseudo label to supervise the multi-level domain adaptive adversarial training of the cross-domain student model, and optimizing the cross-domain student model in combination with a designed loss function. Obtaining a final cross-domain student model; and detecting pedestrians in the overlooking fisheye image to be detected based on the final cross-domain student model. According to the technical scheme of the invention, the requirements of people flow statistics, safety monitoring and people flow guidance on rapid and accurate detection of pedestrians in a scene can be met.

The invention discloses a method, a system, a medium and equipment for panoramic display of underground facilities, and belongs to the technical field of augmented reality visualization. The method comprises the following steps: real picture data of a real camera in a target area is acquired in real time, and the real picture data of the real camera are acquired based on pose data of the real camera; synchronously adjusting the pose state of a virtual camera configured in the fused three-dimensional model; wherein the fused three-dimensional model is obtained by performing space alignment based on an underground facility three-dimensional model and a ground three-dimensional model; according to the pose state, performing perspective projection rendering and image matting processing on the fused three-dimensional model to obtain an underground facility image only containing a view angle corresponding to the current pose state; and carrying out picture fusion on the real picture data and the underground facility image to obtain a virtual-real fused perspective image, and displaying the virtual-real fused perspective image. By implementing the method and the device, the problem that the underground facility shielded by the ground cannot be accurately and stably displayed in a real-time picture of a common camera in the prior art can be solved.

To provide a head-mounted display (HMD) for use in a virtual reality (VR) environment in which a user can view the real world without removing the head-mounted display.SOLUTION: The HMD104 includes a display 108 for providing virtual content and / or images to the user 100 and image capture devices, such as the first camera 110 and / or the second camera 112. The first camera 110 and / or the second camera 112 are disposed in or near the front of the MD104 to capture images of the surroundings 102 and pass through the images of the surroundings to the user for viewing on the display. The environment 102 includes a computer 150 that communicatively couples to the HMD, the controller 106, the tracking system 122, and / or the remote computing resources 142 via a network 124 and / or wired technologies.SELECTED DRAWING: Figure 1

The invention discloses a quantitative detection method for anti-perspective performance of a textile in a complex light environment, and belongs to the technical field of new material detection, a micro gap is arranged between the textile to be detected and a variable-frequency gray scale target to simulate a non-clinging state when clothes are worn and excite Fresnel diffraction and subsurface scattering effects, and the anti-perspective performance of the textile is detected. Complex illumination conditions such as backlight and sidelight are simulated by adjusting the light intensity ratio, and after a target perspective image is acquired by using an image acquisition unit, the modulation transfer function attenuation rate of a to-be-detected textile to the target is calculated, so that the anti-perspective performance of the textile is quantitatively represented; the interference of glare on the surface of the high-gloss fabric is effectively eliminated by introducing an orthogonal polarization modulation technology, and a detection result is highly consistent with the visual perception of human eyes by adopting a specific light source spectrum simulating the skin color of a human body; compared with a traditional light transmittance method, the method has the advantages that the dimension crossing from luminous flux measurement to image information fidelity evaluation is realized, and the accuracy, reliability and practicability of detection are remarkably improved.

The invention relates to a front sight laser aiming auxiliary device which is used for guiding a kirschner wire to present a point-shaped perspective shadow on a C-arm screen in an orthopedic operation, and belongs to the technical field of medical instruments. The device aims at solving the problems that in traditional Kirschner wire perspective point forming operation, repeated perspective depends on the experience of an operator, radiation exposure is large, and operation precision is difficult to guarantee. The device mainly comprises a front sight base which can be fixed on the surface of a receiver of the C-arm machine, wherein a ball head base is arranged in the center of the front sight base; and the ball head laser indicator is arranged on the base and is adjustable in laser direction. When in use, the perspective image is adjusted to the central position of the front sight on the screen by moving the metal point on the operating table. Installing a laser lamp, adjusting the laser lamp to irradiate on a metal point on an operating table, and screwing a nut to fix the position of the laser lamp at the moment. Therefore, a visible laser guide line coinciding with the path of the target X-ray beam is established. And an operator only needs to adjust the guide needle along the laser ray and place the guide needle, so that the guide needle can be stably developed in a point shape in a perspective image, and accurate and rapid screw guide needle placement is realized. The device is simple in structure, low in cost, intuitive in operation, capable of remarkably reducing intraoperative radiation and reducing dependence on experience of operators, and suitable for being used in hospitals of all levels to carry out precise orthopedic surgery under perspective guidance.

The present invention discloses a BEV spatial target detection method and device for multi-perspective images. The method inputs the multi-perspective images into a preset BEV target detector, generates a corresponding perspective image feature map through an image feature extractor, inputs the perspective image feature map into a built-in depth feature extractor and foreground and background mask extractor, generates a depth feature map through the depth feature extractor, and generates a foreground and background mask feature map through the foreground and background mask extractor. The features of foreground pixels are then projected based on the perspective image feature map, the foreground and background mask feature map, and the depth feature map to generate a BEV feature map. Based on the BEV feature map, the position and category information of the target to be detected are detected. The implementation of the embodiments of the present invention can reduce the amount of computation and improve the efficiency and accuracy of target detection.

The application provides a perspective image reconstruction method and a readable storage medium. The perspective image reconstruction method comprises the following steps: setting a plurality of calculation nodes in series based on a perspective image reconstruction process, and the plurality of calculation nodes work in parallel; inputting a view data to a first calculation node of the plurality of calculation nodes in a time period; and outputting a perspective image by a last calculation node of the plurality of calculation nodes. In this way, each calculation node operates independently and does not interfere with each other, and each calculation node processes one view data at a time, the data amount involved in each execution is small, the scheduling is convenient, the view data can be discarded immediately after being used, and the consumption of memory and display memory is reduced. Thus, the problem that the reconstruction method in the prior art has a long delay, a low refresh frequency and cannot meet the real-time requirement of the perspective image in special occasions is solved.

The present invention enables more accurate estimation of a three-dimensional structure including an internal structure of a target without requiring a large number of captured images. A three-dimensional structure estimation device (10) includes: an acquisition unit (111) that acquires a plurality of fluoroscopic images obtained by imaging a target from mutually different directions; a learning unit (112) that, using the plurality of fluoroscopic images, learns a learning model to which input data indicating three-dimensional coordinates of an arbitrary point inside the target is input and which outputs first output data indicating a signed distance of the arbitrary point with respect to a surface of an internal structure possessed by the target and second output data indicating a first attenuation coefficient at the arbitrary point; a calculation unit (113) that inputs, to the learning model, input data indicating respective points inside the target and, by correcting the first attenuation coefficient indicated by the second output data on the basis of the signed distance indicated by the first output data, calculates second attenuation coefficients at the respective points inside the target; and an estimation unit (114) that estimates a three-dimensional structure of the target on the basis of the second attenuation coefficients at the respective points inside the target.

Provided is an X-ray imaging apparatus that enables an operator to freely manually move an X-ray source along a rail installed on a ceiling or a floor, and can capture a fluoroscopic image. An X-ray control unit continuously emitting X-rays from an X-ray source and permits fluoroscopy only in a case in which one or more predetermined conditions, including a condition in which the X-ray source is stopped at a predetermined position on a rail corresponding to a position at which an X-ray detector is held, are satisfied. Specifically, the X-ray control unit enables an operation of a fluoroscopy switch, and continuously supplies a tube current and a tube voltage to the X-ray tube in a case in which the operator operates the fluoroscopy switch.

Embodiments of systems and methods for generating see-through images include a vision sensor configured to generate an image of an environmental scene surrounding a vehicle, and one or more processors operable to generate, using a pre-trained neural network, a depth map of the environmental scene based on the image, determine whether the environmental scene includes a blocking object by comparing the depth map with historical depth information of the environmental scene, in response to determining that the environmental scene includes the blocking object, update, using the pre-trained neural network, the depth map by replacing depth information of the blocking object with the historical depth information of the environmental scene at an area of the blocking object, and project the updated depth map into a see-through image of the environmental scene.

Provided are an information processing method and the like that appropriately associate an image captured by an image acquisition catheter with an image captured by angiography even for a bent blood vessel.　The information processing method causes a computer to execute a process for: acquiring cross-sectional image information related to a plurality of cross-sectional images (71) of a blood vessel; acquiring, in perspective images (61), sensor position information related to the positions of a sensor used for capturing the respective cross-sectional images (71); acquiring designation of the visual field direction; and outputting either the shape of the blood vessel seen through in the acquired visual field direction or the angle relating to the visual field direction on the basis of the cross-sectional image information and the sensor position information.

An image pair comprising angiographic image data and bone image data showing the same area of a patient and taken from the same viewing direction onto the patient is acquired and overlaid over a live fluoroscopic image. In order to increase the perceivability of information in the angiographic image and / or the live fluoroscopic image in the overlay, a part of the bone image data is altered, for example attenuated, when the overlay is calculated. (Fig. 1)

The present invention provides a method and device for three-dimensional modeling of an interventional medical needle based on a medical perspective image. The method is applicable to the field of medical imaging. The method comprises: obtaining a two-dimensional medical perspective image of a target interventional medical needle; obtaining the two-dimensional pixel coordinates of the needle tip and needle tail on the two-dimensional medical perspective image; performing coordinate conversion based on the two-dimensional pixel coordinates of the needle tip and needle tail to obtain the three-dimensional world coordinates of the needle tip and needle tail; generating a three-dimensional centerline of the needle tract of the target interventional medical needle based on the three-dimensional world coordinates of the needle tip and needle tail; obtaining radius information of the target interventional medical needle; determining a direction vector based on the coordinates of two adjacent points on the three-dimensional centerline of the needle tract; generating a spatial circular surface based on the coordinate points and radius information on the three-dimensional centerline of the needle tract; and constructing a three-dimensional volume model of the target interventional medical needle based on the spatial circular surface and the direction vector. The present invention improves the accuracy and efficiency of three-dimensional modeling of the target interventional medical needle.

Embodiments of systems and methods for generating see-through images include a vision sensor configured to generate an image of an environmental scene surrounding a vehicle, and one or more processors operable to generate, using a pre-trained neural network, a depth map of the environmental scene based on the image, determine whether the environmental scene includes a blocking object by comparing the depth map with historical depth information of the environmental scene, in response to determining that the environmental scene includes the blocking object, update, using the pre-trained neural network, the depth map by replacing depth information of the blocking object with the historical depth information of the environmental scene at an area of the blocking object, and project the updated depth map into a see-through image of the environmental scene.

Object detection including receiving a fluoroscopic video including a plurality of fluoroscopic images captured by a fluoroscope rotated about a patient, generating a three-dimensional (3D) volumetric reconstruction from the fluoroscopic images, deleting values in the 3D volumetric reconstruction beyond a region of interest about an object, generating 2D images from a remaining 3D volumetric reconstruction following the deleting of values: detecting the object in the 2D images to determine an initial position of the object, and refining the detected initial position of the object.

A method performed by a computing system comprises receiving a fluoroscopic image of a patient anatomy while a portion of a medical instrument is positioned within the patient anatomy. The fluoroscopic image has a fluoroscopic frame of reference. The portion has a sensed position in an anatomic model frame of reference. The method further comprises identifying the portion in the fluoroscopic image and identifying an extracted position of the portion in the fluoroscopic frame of reference using the identified portion in the fluoroscopic image. The method further comprises registering the fluoroscopic frame of reference to the anatomic model frame of reference based on the sensed position of the portion and the extracted position of the portion.

The invention discloses a connector internal defect detection method and device and a medium, and the method comprises the steps: obtaining first X-ray exposure time corresponding to different types of metals in a to-be-detected connector, and obtaining second X-ray exposure time corresponding to different types of plastics; performing X-ray shooting on a metal area in the to-be-detected connector by using the first X-ray exposure time to obtain a metal perspective image, and performing X-ray shooting on a plastic area in the to-be-detected connector by using the second X-ray exposure time to obtain a plastic perspective image; fusing the metal perspective image and the plastic perspective image to generate an X-ray feature image corresponding to the to-be-detected connector; and positioning a defect region in the X-ray feature image through edge detection and a morphological segmentation algorithm, and identifying a defect type of the positioning region based on a convolutional neural network model.

The present disclosure relates to an X-ray fluoroscopy image generation method and device, and an X-ray fluoroscopy system. The generation method comprises determining a target line-of-sight vector for a target organ according to an observation requirement and a target position of the target organ of a biological subject to be detected; determining a primary rotation angle and a secondary rotation angle of an imaging arm in an X-ray fluoroscopy device and determining a primary rotation matrix and a secondary rotation matrix based on the target line-of-sight vector; determining a target projection matrix that conforms to a target projection geometry based on the primary rotation matrix and the secondary rotation matrix; and performing volume rendering based on the target projection matrix and pre-acquired three-dimensional computed tomography (CT) data of the target organ to obtain a two-dimensional target X-ray fluoroscopy image under a target observation view angle. The X-ray fluoroscopy image generation method and device and the X-ray fluoroscopy system of the present disclosure can freely generate an X-ray fluoroscopy image under a desired observation view angle based on pre-acquired three-dimensional CT data.

There is a robotic mower (100) configured to plan a path (190) to be followed in a working area (200) of the robotic mower. The mower (100) comprises an image sensor arrangement (130) for capturing images of obstacles in the working area (200), and a processor (141) for planning the path based on image data of the captured images. The image sensor arrangement (130) comprises a monocular camera (131) configured to capture a perspective image (10) of a scene (30) comprising at least one obstacle (300). The processor (141) is configured to generate an inverse perspective mapping [IPM] source image (20) from the captured perspective image (10), generate an IPM image (40) depicting a bird's-eye view of the scene (30) by applying an IPM transformation to the IPM source image (20), determine a distance (d) to the obstacle (300) from image data of the IPM image (40), and adapt the path (190) to be followed based on the determined distance (d).

The invention provides a self-adaptive viewpoint rendering method for a fixed display space, and belongs to the technical field of computer graphics and virtual reality. The method comprises the following steps: S1, performing hardware deployment and system preprocessing operation; s2, acquiring viewpoint position data of two eyes of an observer in the space in real time; s3, generating perspective image data corresponding to the display screen; s4, carrying out self-adaptive rendering image generation operation; and S5, synchronously outputting the display picture and dynamically updating the display picture. The method has the beneficial effects that radar and camera dual data sources and dual-confidence judgment can effectively cope with various complex scenes, and the accuracy under severe working conditions is ensured; weight correction can improve the adaptation degree of fusion data in different scenes; and due to the introduction of the resolution sensitivity coefficient, the resource investment can be reduced in a low-attention area, the cost is reduced, and the efficiency is improved.

To detect the body movement of a subject during photographing a fluoroscopic image.SOLUTION: An image of a subject is captured by a camera provided in the X-ray imaging apparatus. First, the skeleton of a human figure included in an image is detected, and the skeleton of a subject placed on the top plate of an X-ray imaging apparatus is extracted based on the detected skeleton. A movement amount (optical flow) of corresponding pixels is calculated between the captured image and an image acquired by the camera at a timing earlier than a timing at which the captured image is acquired by a predetermined time. A plurality of regions of interest are set in the image of the subject based on the position of the skeleton of the subject. The number of regions of interest in which the movement amount of the pixel of the subject in the region of interest is larger than a predetermined threshold is obtained, and when the obtained number of regions of interest is larger than a predetermined value, it is determined that the body movement occurs in the subject.SELECTED DRAWING: Figure 8

The present invention provides a distance measurement method and device based on the characteristics of adjacent track trains, which belongs to the field of rail transportation. It includes: obtaining the target characteristics of the adjacent track train; determining the depth value from each characteristic corner point to the vehicle based on the internal parameter matrix of the on-board shooting device, the coordinates of each characteristic corner point of the target characteristics in the pixel reference coordinate system in the adjacent track train image, and the geometric constraints of the target characteristics; projecting the side image into a non-perspective image based on the inverse perspective transformation, and determining the depth value from the target position of the adjacent track train occupying the switch to the vehicle based on the vertical points of different characteristic corner points on the lower straight line and the depth value from the characteristic corner point to the vehicle. The distance measurement method and device based on the characteristics of adjacent track trains provided by the embodiment of the present invention do not require changes to the existing active train collision avoidance system, and can also serve as a heterogeneous supplement to the laser radar scanning ranging, providing a more accurate depth value for the train operation control system to control train collision avoidance.

The invention provides an X-ray fluoroscopic imaging apparatus and an image processing method. The present invention addresses the problem of making it possible to reduce the amount of X-ray radiation by increasing the ratio of an interpolated image when the accuracy or real-time performance of a perspective image is not required, and to maintain a display frame rate equivalent to when the accuracy or real-time performance of the perspective image is required. The X-ray fluoroscopic imaging device can change the irradiation rate according to the operation of an operator. The X-ray fluoroscopic imaging device displays a fluoroscopic image generated at an irradiation rate on an image display device when the irradiation rate is equal to or greater than a reference rate, and generates an interpolated frame so that the display rate becomes equal to the reference rate when the irradiation rate is lower than the reference rate. And displaying the perspective image generated at the irradiation rate and the interpolated frame on an image display device.