618 results about "Angle of view" patented technology

The invention relates to a light and miniature big-target-surface low-light lens, and the lens comprises a front lens group A, a diaphragm B and a rear lens group C, wherein the front lens group A, the diaphragm B and the rear lens group C are sequentially arranged in an incident direction of an optical path. The front lens group A includes a positive meniscus lens A1, a negative meniscus lens A2,a biconcave lens A3 and a biconvex lens A4, wherein the positive meniscus lens A1, the negative meniscus lens A2, the biconcave lens A3 and the biconvex lens A4 are sequentially arranged in an incident direction of the optical path. The biconcave lens A3 and the biconvex lens A4 are in close connection with each other as a first bonding group. The rear lens group C includes a biconcave lens C1, abiconvex lens C2, a biconvex lens C3, a plano-convex lens C4 and a negative meniscus lens C5, wherein the biconcave lens C1, the biconvex lens C2, the biconvex lens C3, the plano-convex lens C4 and the negative meniscus lens C5 are sequentially arranged in an incident direction of the optical path. The biconcave lens C1 and the biconvex lens C2 are in close connection with each other as a secondbonding group. The invention also relates to an imaging method of the lens. The lens is reasonable in design, effectively improves the imaging quality under the requirement of the large target surfaceof the lens, reduces the number of optical lenses, and realizes light and miniature lens. The lens has strong light collecting and light transmitting ability, and the target surface of the lens is large. The lens is high in optical resolution, is large in angle of view, and is large in observable range.

This invention proposes a security risk detection method based on visual temporal evolution analysis, comprising: acquiring a continuous video sequence of a target scene; extracting visual security elements from each frame and quantifying them into security feature vectors; constructing a temporal feature sequence by associating the security feature vectors of multiple consecutive frames based on a preset time window; calculating the change in security feature vectors at adjacent moments as the change in security status at the current moment; calculating the security risk value at the current moment based on historical security risk values ​​and the change in security status at the current moment; comparing the security risk value at the current moment with a preset risk threshold; and determining whether a persistent security risk exists based on the comparison result. This invention models the security status from a temporal evolution perspective, accurately capturing the accumulation process and evolution trend of security risks, and solving the core defects of existing technologies that cannot distinguish between instantaneous and occasional anomalies and long-term persistent risks, and are prone to false alarms due to short-term interference.

This invention relates to an online testing method for engine assembly status, belonging to the field of engine testing technology. Addressing the problems of low efficiency and poor consistency in existing technologies, such as the difficulty in simultaneously assessing spatial installation and appearance using single-image testing methods, and the tendency to miss measurements in complex structural areas, this invention proposes acquiring color and depth images of the engine under test. Based on the component characteristics, it selects a camera mode from color-only testing, depth-only testing, and collaborative testing. Multi-view image acquisition is performed according to a preset testing scheme, and the results of each test item are obtained through a preset testing algorithm. Finally, the results are fused and judged to generate an overall result. This invention improves the targeting, accuracy, and coverage of the inspection, and is applicable to the field of online testing of engine assembly quality.

The present application relates to the field of dam inspection, especially to a kind of image processing method and system for dam inspection, the present application is by controlling unmanned aerial vehicle to fly over detection area according to predetermined trajectory, when unmanned aerial vehicle is pre-entered detection area, continuously obtain image information and carry out multidimensional analysis, based on the result of multidimensional analysis and mirror surface reflection index, calculate to obtain spectral characteristic interference representation value, set interference label for detection area, subsequent interference label based on the control of unmanned aerial vehicle in detection area adaptively obtains spectral information in monitoring area, subsequent generation perspective adjustment instruction, by sampling determination selection confidence sampling position obtains spectral information, the present application is by image information in advance sensing interference situation of spectral information extraction in detection area, adaptively select spectral information capture mode, under the premise of guaranteeing inspection efficiency, improve the quality and reliability of the obtained spectral information, provide effective data support for subsequent analysis dam potential anomaly.

1. Name of the product in this design: Elevator Car (Smoke Dye). 2. Purpose of this design: for interior decoration of elevator cars. 3. The key design features of this product are the combination of shape and pattern. 4. Images or photos that best illustrate the design key points: usage status reference diagrams. 5. Other situations requiring explanation: The product protected by this design is an elevator car, therefore, all six views in this application are views from inside the car.

The patent application provides a complex environment three-dimensional scene reconstruction method based on a multi-view neural network, and the method mainly comprises two steps: scene information capturing: obtaining scene data from a plurality of views through a high-resolution camera, and ensuring that all details of a complex scene are covered; the captured image is standardized, including color correction and noise removal, to ensure image quality and consistency. And three-dimensional model reconstruction: performing three-dimensional reconstruction on the acquired scene data by using a neural network. Firstly, light sampling is performed on a scene through camera parameters and pose information, and an occupancy grid is created to optimize the sampling efficiency. Thirdly, decomposing the sampling data into feature vectors and inputting the feature vectors into a neural network which is divided into a density network and a color network and is used for generating volume density and color information of the scene; and finally, obtaining a three-dimensional scene model through a volume rendering technology. The method has the advantage that a high-precision three-dimensional model can be quickly generated in a complex environment through an efficient sampling and data processing technology.

This application provides a method, system, medium, and device for human-centered video scene reconstruction and separation. The method includes: for a first-person perspective video sequence, initializing a 3D Gaussian set covering the background, hands, and objects based on a priori knowledge of structure recovery from motion; assigning a learnable dynamic category probability vector to each Gaussian point in the 3D Gaussian set; constructing a dedicated deformation branch; according to the learnable dynamic category probability vector of each Gaussian point, assigning each Gaussian point to the dedicated deformation branch for processing through a preset soft-hard two-stage routing mechanism, determining the Gaussian points processed by the dedicated deformation branch; rendering the Gaussian points processed by the dedicated deformation branch to determine the 4D scene reconstruction image and the decomposed reconstruction images of the background, hands, and objects. This application achieves 4D scene reconstruction of human-centered video and explicit, fine-grained separation of the background, hands, and objects.

The application relates to a kind of city building agent reconstruction methods based on aerial image.The method comprises: obtaining the multi-view image corresponding to target building;Multi-view image includes near vertical view image and inclined view image;According to near vertical view image, the bottom contour of target building is determined;Determine the first depth difference between each pixel point in inclined view image;According to the camera pose parameter of multi-view image and the current predicted height of target building, rendering is carried out, and the rendering depth map of target building under the current predicted height is obtained;With the distance between the second depth difference of each pixel point in the rendering depth map and the first depth difference as the optimization target, the current predicted height is optimized, and according to the bottom contour and target measurement height, the three-dimensional building model corresponding to target building is constructed.Using the method can improve the efficiency and accuracy of city building agent reconstruction.

A combined convolutional neural network driven automobile flow field excitation prediction method comprises the following steps: 1) constructing a plurality of automobile deformation models with continuous geometric feature changes, and sampling multi-view images of all automobile deformation models to construct an image dataset; 2) simulating transient flow fields of all automobile deformation models, obtaining corresponding fluid dynamic pressure excitation and sound pressure excitation, and labeling corresponding multi-view images in the image dataset with excitation labels to construct a training set; 3) constructing a combined convolutional neural network model; 4) taking multi-view images as input and excitation labels as output, and training the combined convolutional neural network model by using the training set; and 5) obtaining multi-view images of a to-be-predicted automobile, inputting the multi-view images of the to-be-predicted automobile into the trained combined convolutional neural network model, and obtaining predicted fluid dynamic pressure excitation and sound pressure excitation. The application can significantly reduce the dependence of automobile flow field excitation calculation on supercomputing services and reduce wind noise development costs.

The application discloses a reverse making method of terraced rice picture and belongs to the field of straw picture, and comprises the following steps: S1, breeding color rice varieties with different color and plant height, and carrying out planting and management according to the characteristics of terraces; S2, designing a plane pattern by using PS and AI; S3, importing the plane pattern into CAD and adjusting the angle and perspective; S4, measuring the position and range of the rice field picture area field plot and the height difference of the field ridge; S5, discharging the whole pattern in the reverse direction of the field ridge by using the Ovi interactive map, and adjusting the position and angle of the field ridge in the picture to be optimal; and S6, placing the converted pattern in the rice field by using a positioning instrument and placing and planting. The terraces are curved, the field ridge is high, the field plot surface is small, and the rice field picture cannot be made like the basin or the plain, the application adopts a reverse terraced picture making technology, the technology overcomes the disorder and the broken feeling caused by the large height difference of the terraces, the small field plot and the large bending degree, and improves the overall viewing effect of the picture.

The present application relates to the field of three-dimensional reconstruction, and provides a pig weight estimation method, device, equipment, medium and computer program product.The method comprises the following steps: acquiring multi-view image data of a pig to be detected; generating sparse point cloud data based on the multi-view image data; generating a multi-view rendering image based on the sparse point cloud data and three-dimensional Gaussian data; the three-dimensional Gaussian data is converted from the sparse point cloud data; inputting the three-dimensional Gaussian data into a weight estimation model to obtain pig feature information, and estimating the weight of the pig to be detected based on the pig feature information.The present application improves the accuracy of pig non-contact weight estimation and reduces the implementation cost through individual weight posture correction, weight scene three-dimensional reconstruction and the associated weight estimation method of fusing body posture semantics.

This invention provides an intelligent detection and classification method for oil and gas pipeline defects based on pseudo-color images, belonging to the field of pipeline safety inspection. First, multi-dimensional magnetic flux leakage data of the oil and gas pipeline in the axial, circumferential, and radial directions are obtained through a tensile experiment. The detection data is converted into visualized pseudo-color images, and image defect annotation is completed to construct a standardized pipeline defect dataset. In the detection stage, the dataset is input into a pre-trained YOLOv11 model to achieve accurate identification and location of potential pipeline defect areas. In the multi-view fusion stage, the defect bounding box output by the model is used to extract the target area of ​​the original pseudo-color image. Images of the same defect from multiple directions are stitched together to generate a multi-view pseudo-color image of the defect. In the classification stage, the Patch preprocessing module is used to complete image resizing and filling, and then the image is fed into a finely tuned DINOv3 classification model to efficiently complete the intelligent identification and classification of various pipeline defects.

This application discloses a method and related products for training a generative model for generating three-dimensional aneurysms. The method includes: extracting at least one perspective of two-dimensional image data from original three-dimensional image data; semi-transparentizing the aneurysm-bearing artery region in the two-dimensional image data and marking the centerline of the aneurysm-bearing artery to obtain preprocessed data; extracting aneurysm-related two-dimensional and three-dimensional features using a pre-trained image encoder and shape encoder based on the preprocessed data and the original three-dimensional image data; and training the generative model using the two-dimensional and three-dimensional features as the input and output, respectively, so that the generative model outputs a three-dimensional aneurysm containing the aneurysm-bearing artery region and surrounding vessels. Using the solution of this application, high-precision three-dimensional aneurysm reconstruction can be achieved without original DICOM data, providing a reliable aneurysm-assisted diagnosis and treatment decision-making solution.

This invention provides a system and method for synthesizing novel viewpoints in complex scenes (e.g., outdoor scenes). [Solution] In some implementations, the system and method may include or use a machine learning model that can learn from unstructured and / or unconstrained collections of images, such as “wild” photographs. In particular, exemplary implementations of this disclosure can learn volume scene density and luminance represented by a machine learning model such as one or more multilayer perceptrons (MLPs).

This invention discloses a method and system for large-scale federated 3D Gaussian sputtering scene reconstruction for resource-constrained edge networks. The method includes: constructing a resource-aware federated 3D-GS system consisting of a single edge cloud server and a set of ubiquitous edge sensing devices; on the edge sensing device end-to-edge side, based on the collected local multi-view real-scene image dataset and an adaptive lightweight mechanism, under given GPU memory budget and maximum latency constraints, adaptively selecting the optimal Gaussian point subset for local training, obtaining updated local spatial features, position gradients, and binary masks, and transmitting them back to the single edge cloud server via a wireless network; on the single edge cloud server end, using the local spatial features, position gradients, and binary masks uploaded by the device, mapping the structurally heterogeneous local model back to the global index space, performing structural consistency restoration, and then performing weighted aggregation to generate a 3D real-scene map.

This invention relates to the field of image processing technology and discloses a method for target 3D reconstruction and automated model generation. The method includes: acquiring multi-view original point cloud data of the target object, and obtaining a simplified point cloud dataset through voxel filtering and downsampling; dividing the data into smooth regions and sharp edge feature sets based on curvature characteristics, performing smooth fitting and edge-preserving reconstruction respectively, and then generating a composite mesh model through vertex merging and mesh stitching; performing topological structure analysis on the model, detecting and optimizing non-manifold elements and topological holes to obtain an initial mesh model; parametrically mapping and automatically unfolding the texture of the model surface geometric manifold characteristics, and fusing and binding the unfolded texture map with the initial mesh model to finally complete the 3D reconstruction of the target object; this invention can improve the efficiency of target 3D reconstruction and automated model generation.

This invention provides a method and apparatus for 3D tooth reconstruction based on multi-view geometric priors and specular Gaussian representation. The method first acquires multi-view image data containing teeth and gingiva. A multi-view geometric estimation module predicts and globally aligns dense 3D point maps to obtain an initial point cloud, camera intrinsic and extrinsic parameters, and a depth map. Based on this, a Gaussian primitive set is initialized and input into a specular Gaussian reconstruction module, where relevant parameters are combined to optimize the reconstruction. This module introduces depth and normal losses based on the color target, supervises and reduces the weight of highlight regions within the region of interest, and finally outputs the 3D reconstruction result. This invention can improve the stability and geometric accuracy of tooth reconstruction under high reflectivity and weak texture, enhance specular reflection and highlight expression capabilities, and balance the detailed reconstruction of tooth hard tissue with the geometric and appearance effects of gingival soft tissue, thereby improving the integrity of oral scene reconstruction and its clinical application value.

Embodiments of the present application disclose a display panel and a display device. The display panel comprises a driving substrate, a plurality of light emitting elements, a first pixel defining structure and a second pixel defining structure. The plurality of light emitting elements are located on one side of the driving substrate. The first pixel defining structure is located on one side of the driving substrate, and the first pixel defining structure comprises a pixel opening part and a pixel defining part. The light emitting elements are located in the pixel opening part, and the pixel defining part surrounds at least part of the light emitting elements. The second pixel defining structure surrounds at least part of the light emitting elements, and a undercut structure is arranged on one side of the second pixel defining structure facing the light emitting elements. In this way, the position and opening size of the light emitting elements are defined by the first pixel defining structure, so as to achieve a better large-viewing-angle light emission effect, and the adjacent light emitting elements are blocked by the second pixel defining structure, so as to reduce the horizontal leakage.

The application discloses a three-dimensional Gaussian sputtering initialization method based on Fast3R, which performs Fast3R fast reasoning on an input image sequence under low resolution; calculates Anchor scores of each view based on the product combination of quality scores and mutual view coverage scores, takes Fast3R output as initialization, performs feature extraction and matching, triangulation to obtain sparse trajectory constraints, introduces dense consistency constraints based on point graph projection, constructs a joint geometric optimization model, and robustly iteratively solves camera external parameters and internal parameters. The QSP strategy is introduced, high-confidence and strong cross-view consistency point clouds are preferentially retained under uniform spatial voxel constraints, the point cloud size is controlled, and outlier and floating points are reduced, thereby providing high-integrity, high-precision and controllable-scale initialization for three-dimensional Gaussian sputtering. The sensitivity of Fast3R to the selection of the first frame is effectively reduced, the stability and point cloud quality of large-scale scene reconstruction are improved, and the 3DGS training convergence and rendering effect are improved under the premise of ensuring the initialization efficiency.

Embodiments of the present application disclose a kind of appearance defect detection method, equipment, medium and program based on image, wherein, method includes: different exposure acquisition image of target detection object under the same angle of view is obtained;Different exposure acquisition image of the target detection object under the same angle of view is synthesized into the pseudo-color image of the target detection object;According to the pseudo-color image of the target detection object, inference image data is generated;According to the inference image data, defect recognition and classification are carried out, and the appearance defect detection result of the target detection object is obtained.The technical scheme of the embodiment of the present application can improve the generality and detection precision of the appearance defect detection method based on image.

This application provides an action determination method and apparatus, a robot system, a storage medium, and an electronic device, relating to the field of robotics. The method includes: acquiring task instructions and multi-view image data, wherein the multi-view image data includes image data collected by the robot from M views, where M is an integer greater than or equal to 2; determining a feature set based on the multi-view image data, wherein the feature set includes a semantic feature subset, a geometric feature subset, and a three-dimensional spatial feature subset corresponding to the M views; and determining the robot's execution action based on the feature set and the task instructions. This solves the problem of inaccurate robot execution actions in related technologies, enabling action generation based on accurate three-dimensional spatial understanding and improving the accuracy of execution actions.

This imaging device includes an imaging unit that is provided to face a window glass of a building and is capable of imaging an outdoor side of the window glass. A light source, positioned adjacent to the imaging unit and facing the window glass of the building, is capable of emitting light toward the window glass. In a cross-sectional view in a plane including the window glass, the imaging unit, and the light source, a first angle including an object located on the outdoor side of the window glass within the angle of view of the imaging unit, and a second angle at which glare caused by the reflection of the light of the light source on the window glass occurs within the angle of view of the imaging unit, overlap each other. Denoting the first angle as χ and the overlap angle at which the first angle and the second angle overlap each other as δ, the conditions δ / (χ−δ)<1 and χ–δ>0 are satisfied.

The application provides a pose estimation method and device, a computer device and a storage medium. The method comprises: acquiring a monocular image, a target mask image corresponding to a target to be measured in the monocular image, and a three-dimensional model of the target to be measured; sampling a plurality of initial pose data of the target to be measured under a determined view direction; determining initial position data of the target to be measured under each initial pose data based on the target mask image; wherein the initial pose data and the initial position data constitute initial pose data, and the plurality of initial pose data constitute an initial pose estimation set; selecting target quantity candidate pose data from the initial pose estimation set, adjusting the target quantity candidate pose data, and generating a plurality of intermediate pose data; constructing a loss function, and iteratively optimizing each intermediate pose data by using the loss function to generate optimized pose data; and determining pose estimation data corresponding to the target to be measured from the plurality of optimized pose data.

This invention relates to the field of image segmentation technology and discloses a construction site risk behavior recognition system based on big data. The system constructs a multi-view spatiotemporal representation of construction by uniformly aligning multi-view video streams, personnel positioning information, equipment operating status, and construction space area data at the construction site. Simultaneously, it constructs a segmentation model including an image encoder and a Bayesian mask decoder, and introduces a dynamic evidence adaptation mechanism based on Set Transformer and Hypernetwork to achieve dynamic segmentation of construction targets and hazardous areas in complex construction scenarios. Furthermore, by combining spatial posterior distribution, semantic posterior distribution, and a visual language model, it achieves reliability analysis and semantic discrimination of risk behaviors, thereby improving the reliability and adaptability of risk behavior recognition in complex construction scenarios.

The present application relates to the technical field of flight safety monitoring, in particular to a kind of aircraft icing real-time detection and evaluation method and system, method includes: collecting icing image obtains original image data, and it is carried out enhancement processing and obtains enhanced image data;Semantic segmentation model carries out icing area detection to enhanced image data, obtains multi-view icing mask two-dimensional image data;Deep learning three-dimensional reconstruction model carries out feature extraction and multi-view information fusion to multi-view icing mask two-dimensional image data, obtains icing surface triangular mesh model;Through three-dimensional grid boolean addition operation, icing surface triangular mesh model is fused with the existing wing three-dimensional model, and fusion model containing ice layer morphology is generated;Fusion model is input into aerodynamic force evaluation model and carries out aerodynamic evaluation of ice wing, obtains evaluation result.The present application can realize end-to-end closed loop from icing detection to aerodynamic performance evaluation, real-time output evaluation result, support flight safety decision.

This invention discloses an optimization method and system for smoke screen chaff deployment based on a view cone masking model, belonging to the field of signal jamming technology. The method includes the following steps: S1, constructing an adversarial kinematic model of the missile, target, and chaff; S2, establishing a view cone masking quantitative evaluation model with masking completeness as the core; S3, defining a fitness function with the maximum effective masking time as the objective; and S4, using an adaptive genetic algorithm to solve for the optimal deployment strategy that satisfies spatiotemporal constraints. This invention solves two major bottlenecks in existing technologies: the disconnect between effect evaluation and decision control, and the excessive reliance of advanced decision models on preset conditions. It achieves accurate, direct, and decision-driven quantitative evaluation of masking effects from the first-person perspective of the missile seeker.

The present application relates to the field of processing measurement technology, and more particularly to a kind of automatic measurement method and system for engine box class part machining aperture.The method includes the following steps: obtaining original aperture image;Using local gradient sliding window to locate initial edge point set, determining the tilt angle of viewing axis and the deflection azimuth angle of major axis based on fitting method, to realize the independent separation of the two;Using the deflection azimuth angle of major axis to construct rotation relationship to obtain spindle alignment point set;Using the tilt angle of viewing axis to carry out projection transformation to obtain orthogonal projection point set;Based on the tilt angle of viewing axis, determine the local object distance drift of each edge pixel point, and then determine the non-uniform magnification correction gain, carry out numerical compensation restoration on orthogonal projection point set, to obtain the final machining aperture size;Output compensation signal to drive machine tool compensation actuator to adjust tool offset value.The present application solves the non-uniform magnification distortion problem caused by probe rod droop, and realizes the true value restoration of space light field.

The application belongs to the technical field of computer vision and intelligent control, and discloses a load device cooperative control system and method based on visual identification, which comprises a data acquisition module, an industrial camera is arranged in a work area, multi-view image acquisition of a load device and a work target is carried out, visual image data is acquired, time sequencing is carried out, and work visual data flow is formed; a pose analysis module is used for image analysis of the work visual data flow, extraction of load device structure characteristics, calculation of the spatial pose of each load device in combination with camera calibration parameters, determination of the work target position, generation of load device pose information; a shielding modeling module is used for equivalent of the geometric shape of each load device to a space bounding box changing with time according to the load device pose information, determination of the position and scale of the bounding box based on preset size parameters, formation of a space shielding body set, and improvement of the efficiency and safety of multi-load device cooperative work.