Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

47 results about "Pinhole camera model" patented technology

The pinhole camera model describes the mathematical relationship between the coordinates of a point in three-dimensional space and its projection onto the image plane of an ideal pinhole camera, where the camera aperture is described as a point and no lenses are used to focus light. The model does not include, for example, geometric distortions or blurring of unfocused objects caused by lenses and finite sized apertures. It also does not take into account that most practical cameras have only discrete image coordinates. This means that the pinhole camera model can only be used as a first order approximation of the mapping from a 3D scene to a 2D image. Its validity depends on the quality of the camera and, in general, decreases from the center of the image to the edges as lens distortion effects increase.

Methods for improved hand-eye calibration based on structured light cameras

Provided is a method for improved hand-eye calibration method based on a structured light camera. The method includes: step 1: establishing a pinhole camera model, and using a depth camera to detect a three-dimensional (3D) coordinate to obtain a physical coordinate of each point in an image coordinate system with a known depth relative to a camera coordinate system; step 2: establishing a Denavit-Hartenberg (DH) model of a robotic arm, and moving the robotic arm to a determined coordinate using inverse kinematics; step 3: collecting n sets of point cloud data, applying depth scaling coefficients to the n sets of point cloud data to perform Singular Value Decomposition (SVD), and solving for an optimal depth scaling coefficient using a Nelder-Mead algorithm; and step 4: completing the hand-eye calibration of the robotic arm based on the solved optimal depth scaling coefficient. The method offers strong operability and robustness.
Owner:GUANGDONG UNIV OF TECH

Non-rigid registration method and device for point cloud processing, equipment and storage medium

The invention provides a non-rigid registration method, device and equipment for point cloud processing and a storage medium, and relates to the field of three-dimensional reconstruction, and the method comprises the steps: carrying out the point cloud reconstruction of a depth image through a pinhole camera model, and generating a virtual data set; performing model training through a preset training loss function to obtain a hierarchical matching fusion network; performing fine adjustment on the hierarchical matching fusion network through a preset reasoning loss function; inputting the source point cloud and the target point cloud into the fine-tuned hierarchical matching fusion network to register an overlapping region; and performing rotation interpolation processing on the non-overlapping areas to register the non-overlapping areas. According to the invention, after the non-overlapping region of the source point cloud and the target point cloud is determined based on the overlapping region, the rotation interpolation processing is carried out on the non-overlapping region to register the non-overlapping region; the overlapping region registration and the non-overlapping region registration correspond to different stages, so that the influence of the non-overlapping region registration on the overlapping region registration result is avoided, and the point cloud registration precision is improved.
Owner:HEFEI UNIV OF TECH

Method for constructing infrared imaging dataset of gas leakage based on computational fluid dynamics

A method for constructing an infrared imaging dataset of gas leakage based on computational fluid dynamics includes steps of: establishing a three-dimensional physical model of a gas leakage field scene; meshing and simulating based on the computational fluid dynamics to obtain leaking gas mole fractions of each mesh under time steps, and constituting three-dimensional gas concentration data corresponding to each frame; using optical gas imaging based on a pinhole camera model, imaging the three-dimensional gas concentration data to obtain initial images, and calculating gas concentration path-lengths corresponding to pixel points in each frame of the initial images; and performing maximum-minimum value normalization and generating grayscale images, thereby constructing the infrared imaging dataset of the gas leakage. The method can not only be used in leakage classification tasks and localization tasks, but can also be used in training tasks related to the leakage concentration.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Omnidirectional image processing method and device and computer readable storage medium

The invention provides an omnidirectional image processing method, an omnidirectional image processing device and a computer readable storage medium. The method comprises the following steps: acquiring an omnidirectional image; projecting the omnidirectional image to a pinhole camera model to obtain a pinhole image; setting a mask value of a pixel point with a corresponding projection point in the pinhole image in the omnidirectional image as a first preset value, and setting mask values of other pixel points of the omnidirectional image as a second preset value; and performing mask processing on the omni-directional image by using the mask value of each pixel point in the omni-directional image. Through the mode, the processing device uses the abstract pinhole camera model to describe the mapping relation of the omnidirectional camera, image information can be reserved as far as possible, and pixel distortion is reduced.
Owner:SHANGHAI SENSETIME INTELLIGENT TECH CO LTD

In-vivo flexible rapid three-dimensional reconstruction method and system based on digital elevation model

ActiveCN119074218AExpand surgical field of viewSuture equipmentsInternal osteosythesisColor imageColour image
The invention provides an in-vivo flexible rapid three-dimensional reconstruction method and system based on a digital elevation model, and relates to the field of in-vivo flexible rapid three-dimensional reconstruction. The method comprises the following steps: firstly, acquiring a color image frame sequence of a laparoscopic surgery and a corresponding depth map sequence; using a pinhole camera model to restore the color image frame and the depth map thereof into a color point cloud; constructing a local three-dimensional model by using the improved digital elevation model again; acquiring a deformation field composed of a series of deformation nodes; warping the last fused three-dimensional model by using the current deformation field to obtain a warped three-dimensional model; and finally, fusing the warped three-dimensional model and the current local three-dimensional model to obtain a current fused three-dimensional model. A three-dimensional model of an in-vivo three-dimensional scene can be generated in real time, and a doctor is helped to observe a fine tissue structure in an operation process; and color image frames of a time sequence can be spliced, so that a relatively complete three-dimensional scene is formed, and the surgical field of view is expanded.
Owner:HEFEI UNIV OF TECH

Manipulator micro-pen direct writing tool calibration method, device and system based on machine learning and monocular vision

PendingCN121104999AProgramme-controlled manipulatorImage analysisPinhole camera modelRobot hand
The invention belongs to the technical field of manipulator tool calibration, and particularly relates to a manipulator micro-pen direct writing tool calibration method, device and system based on machine learning and monocular vision. Comprising the steps that an industrial camera and a direct-writing micro pen are installed under a manipulator tail end coordinate system, the manipulator and the industrial camera are connected to a PC end to complete hand-eye calibration, and a hand-eye matrix is obtained; installing different direct-writing micro-pens, collecting data, and obtaining a plurality of groups of micro-pen central point pixel coordinates and space coordinates in a tail end coordinate system to form point pair data; the hand-eye matrix parameters are optimized through the point pair data; establishing an error compensation model through a pinhole camera model and the single-pixel step length adjustment factor, and carrying out collaborative optimization on the single-pixel step length adjustment factor by adopting point pair data and the optimized hand-eye matrix in combination with the error compensation model; and calculating space coordinates under pixel coordinates by using the optimized hand-eye matrix and parameters to complete calibration. According to the invention, high-efficiency and high-precision calibration can be carried out on different models of manipulators and different specifications of micro-pen printing heads.
Owner:HUAZHONG UNIV OF SCI & TECH

Distortion correction method, device, equipment and medium for inspection image of railway communication base station

ActiveCN120655550AImage enhancementImage analysisPinhole camera modelImage extraction
The invention relates to a distortion correction method and device for a railway communication base station inspection image, equipment and a medium. The method comprises the following steps: extracting real distortion pixel coordinates based on images shot by a camera on a mark point at a plurality of preset positions; determining a first calibration pixel coordinate of the mark point based on a pinhole camera model; converting the first calibration pixel coordinate to a normalized plane to obtain a first calibration plane coordinate; distortion forward transformation is carried out on the first calibration plane coordinates, and expected distortion pixel coordinates are obtained through pixel coordinate reduction transformation; respectively calculating a target deviation between the expected distortion pixel coordinate and the real distortion pixel coordinate at each preset position; and taking target deviation minimization as an optimization target, iteratively updating the distortion parameter by using a nonlinear optimization algorithm until a preset convergence condition is met, and obtaining a target distortion parameter. According to the invention, the accuracy of distortion parameters can be improved, so that the accuracy of image distortion correction is improved.
Owner:CHINA RAILWAY CONSTR ELECTRIFICATION BUREAU GRP CO LTD +2

Depth detection method and device, storage medium and electronic equipment

The embodiment of the invention discloses a depth detection method and device, a storage medium and electronic equipment, and the method comprises the steps: firstly, carrying out the detection of a current head posture of a user, obtaining the first coordinates of a plurality of total feature points of a user face in a reference coordinate system, and then, carrying out the detection of the first coordinates; and calculating a difference value between a preset axial numerical value in the first coordinate of the first feature point and a preset axial numerical value in the first coordinate of the second feature point, determining a target feature point in the plurality of feature points based on the difference value, and finally determining the target feature point in the plurality of feature points based on the first coordinate of the target feature point and a pinhole camera model imaging equation. And calculating the depth from the eyes of the user to the terminal screen. According to the embodiment of the invention, the current head posture of the user is detected to select the target feature points for calculating the depth from the human eyes to the screen, and then the depth from the human eyes to the terminal screen is calculated according to the target feature points, so that the accuracy of measuring the depth from the human eyes to the screen is improved.
Owner:GUANGZHOU SHIYUAN ELECTRONICS CO LTD +1

METHODS AND APPARATUS FOR ESTIMATION OF THE DISTANCE OF THE OBJECTS IN EUCLIDEAN SPACE USING FUSION OF CAMERA POSE INFORMATION and SCENE PRIOR INFORMATION'S AND THEREOF

ActiveKR103043885B1Image enhancementImage analysisPinhole cameraPinhole camera model
The present invention discloses a real-time distance estimation method and apparatus (100) for a fisheye lens camera as well as a pinhole camera. The present invention utilizes camera pose information as well as scene prior information to estimate the distance of an object from a camera (160). The camera pose information is estimated with the help of extrinsic camera correction, which essentially utilizes intrinsic camera correction information. Fisheye lens cameras and any other camera models introduce distortion into the acquired input image. Therefore, an additional step of image non-distortion or pixel point non-distortion is required. The above additional step is necessary to ensure that the input image or its pixel points follow the pinhole camera model before applying distance estimation to any input image or its random pixel points.
Owner:HL KLEMOVE CORP

IMPROVED METHOD FOR ASSISTING WITH THE LANDING OF AN AIRCRAFT AND SYSTEM CONFIGURED TO EXECUTE THE METHOD.

PendingFR3149416A1Image enhancementImage analysisPinhole camera modelFlight vehicle
The invention relates to a method for assisting the landing of an aircraft (1) adapted to determine as many probable theoretical positions (POS1, POS2, POS3) of the aircraft facing a plurality of runways (100a, 100b, 100c) of a destination airport facility (100); to operate reprojections (102a, 102b, 102c) of said runways in an image (F) obtained by a camera (10c) of the aircraft (1) by means of a theoretical camera model (e.g., "pinhole camera model"), each with reference to one of the determined theoretical positions (POS1, POS2, POS3); and to establish for each of the projections operated a consistency score enabling the subsequent provision of an estimated position (POSA) of the aircraft (1). Advantageously, this allows us to confirm or refute whether the runway seen from the camera (10c) of the aircraft (1), and positioned facing the aircraft (1), is indeed the intended destination runway (100b) for landing. Fig. 1
Owner:AIRBUS OPERATIONS (SAS)

Visual servo formation control method for mobile robots

The invention discloses a mobile robot formation finite time control method based on visual servo. According to the method, firstly, a relative kinematics model between a navigation robot and a following robot is established under a world coordinate system, the relative kinematics model is converted into a relative vision kinematics model in an image space in combination with a pinhole camera model, and an image error vector is obtained through normalization; for the error model, a non-linear observer is designed to estimate the unknown speed of the piloting robot, a parameter adaptive updating law is provided to process the uncertain feature height, and a finite time controller based on the linear speed and the angular speed is further designed to realize accurate tracking of the piloting robot. The information required by the method can be acquired from the image, the method does not depend on local communication or GPS between the robots, the communication and sensor loads are small, the tracking control precision is good, the system response speed is high, and the method is suitable for efficient cooperative control in the multi-robot formation task.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA ZHONGSHAN INST

Geometry-aware augmented reality effects with real-time depth map

ActiveUS12236541B2Image enhancementImage analysisPinhole camera modelDepth map
Techniques of introducing virtual objects into a physical environment of AR system include displacing vertices of a mesh representing the physical environment based on a live depth map. For example, an AR system generates a mesh template, i.e., an initial mesh with vertices that represents a physical environment and a depth map that indicates a geometry of real objects within the physical environment. The AR system is configured to represent the real objects in the physical environment by displacing the vertices of the mesh based on depth values of the depth map and parameter values of a pinhole camera model. The depth values may be taken from the perspective of an illumination source in the physical environment.
Owner:GOOGLE LLC

Full-space AMR forklift obstacle avoidance method and AMR forklift

The invention relates to a full-space AMR forklift obstacle avoidance method and an AMR forklift. The method comprises the steps that depth information of a measured object is obtained through a sensor array; analyzing the depth information by using a deep learning framework so as to identify the category of the tested object; according to the position coordinates of each sensor in the sensor array and the pixel point coordinates of the depth information, a pinhole camera model and inverse projection transformation are utilized, and multi-view distance data are obtained through fusion; for the multi-view distance data, an improved iterative nearest point algorithm model is adopted for analysis, a shape constraint condition is introduced, and size information of the measured object is obtained through iterative solution; and outputting an obstacle avoidance result based on the category of the measured object, the position of the measured object, the size information of the measured object and the real-time environment dynamic state, and generating an obstacle avoidance action sequence in combination with the dynamic constraint of AMR. Therefore, through the highly integrated sensor array, the advanced deep learning algorithm and the complex path planning strategy, accurate and efficient obstacle avoidance operation is realized.
Owner:HANGZHOU LANXIN TECH CO LTD

In vivo flexible rapid 3D reconstruction method and system based on digital elevation model

The present invention provides a method and system for flexible and rapid three-dimensional reconstruction in vivo based on a digital elevation model, and relates to the field of flexible and rapid three-dimensional reconstruction in vivo. The present invention first obtains a color image frame sequence of laparoscopic surgery and its corresponding depth map sequence; secondly, uses a pinhole camera model to restore the color image frame and its depth map into a color point cloud; again, uses an improved digital elevation model to construct a local three-dimensional model; obtains a deformation field composed of a series of deformation nodes; then uses the current deformation field to warp the last fused three-dimensional model to obtain a warped three-dimensional model; finally, fuses the warped three-dimensional model and the current local three-dimensional model to obtain the current fused three-dimensional model. A three-dimensional model of a three-dimensional scene in vivo can be generated in real time to help doctors observe small tissue structures during surgery; and a color image frame of a time sequence can be spliced ​​to form a relatively complete three-dimensional scene, expanding the scope of the surgical field of view.
Owner:HEFEI UNIV OF TECH

A submarine cable defect detection method and device based on multi-modal perception spatial correlation

The application relates to a submarine cable defect detection method and device based on multi-modal perception space correlation, which comprises the following steps: synchronously acquiring submarine cable observation data by using an underwater detection platform, preprocessing the submarine cable observation data, and correlating the submarine cable observation data through a three-dimensional space transformation matrix; adopting a residual network as a backbone network, performing multi-scale fusion through a feature pyramid network structure, and acquiring fusion features; in the multi-scale fusion, a water quality prior parameter is introduced as a gate factor to adjust feature weights, and the water quality prior parameter comprises a light attenuation coefficient of a current water area and a sonar signal-to-noise ratio; the fusion features are input into a pre-trained target detection head, the submarine cable defect category and a bounding box are acquired, laser ranging information is combined, the actual physical size of the defect is calculated according to a pinhole camera model, and submarine cable defect three-dimensional detection results are output, so that submarine cable defect detection is completed. Compared with the prior art, the application realizes automatic identification of submarine cable defects in a complex underwater environment and is suitable for underwater submarine cable defect detection tasks.
Owner:TONGJI UNIV

Visible light three-dimensional positioning system based on virtual beacons

PendingCN120949163APosition fixationClose-range type systemsPinhole camera modelEngineering
The invention discloses a visible light three-dimensional positioning system based on a virtual beacon. The visible light three-dimensional positioning system comprises a signal transmitting end and a positioning terminal, the signal transmitting end encodes and modulates the unique identifier LED-UID of the LED lamp in a world coordinate system set in an indoor scene, and drives the LED lamp to emit UID modulated light by outputting a voltage signal; and the positioning terminal obtains the UID modulation light through a camera on the mobile device, and interprets and calculates the three-dimensional coordinates of the positioning terminal in the world coordinate system so as to obtain the three-dimensional coordinates of the mobile device. According to the system, a high-precision single-lamp three-dimensional positioning scheme is provided on the basis of a pinhole camera model and a perspective projection principle, and height and angle parameters necessary for positioning are solved through combined comparison of a virtual beacon for positioning reference constructed by a simulation modeling platform and actual camera imaging; the positioning terminal can realize accurate three-dimensional positioning without additional auxiliary equipment, and the anti-interference capability of the system is improved.
Owner:JINAN UNIVERSITY

An improved hand-eye calibration method based on structured light camera

The present invention belongs to the technical field of hand-eye calibration, and specifically relates to an improved hand-eye calibration method based on a structured light camera, comprising the following steps: Step 1: Establish a pinhole camera model, then use a depth camera to detect three-dimensional coordinates, and obtain the physical coordinates of each point in the image coordinate system of known depth relative to the camera coordinate system; Step 2: Establish a robot arm DH model, and then use inverse kinematics to move to determine the coordinates; Step 3: Collect n groups of point cloud data, substitute the depth scaling coefficient for SVD decomposition, and use Nelder‑Mead to solve the optimal coefficient; Step 4: Complete the hand-eye calibration of the robot arm according to the solved optimal coefficient. The present invention has the advantages of strong operability and strong robustness for hand-eye calibration based on a structured light camera.
Owner:GUANGDONG UNIV OF TECH

A method for correcting laser radar and camera external parameter drift

PendingCN123032807AData setCalibration result
A laser radar and camera external parameter drift correction method, comprising the following steps: step (1): the three-dimensional point cloud of the laser radar is preprocessed by the pinhole camera model, and a depth map is obtained; step (2): a full-resolution feature fusion module based on FPN; all hierarchical features including the highest resolution layer are extracted and fused respectively, and paired features with consistent semantics and retaining fine-grained geometric details are output; step (3): the rotation and translation components are estimated; step (4): the regression loss is used to constrain the drift prediction value in the parameter space, and the mixed loss is used to weight the re-projection error pixel by pixel according to the distance from the optical center and the point cloud depth in the imaging geometry space; step (5): a once wide-range correction is decomposed into three times of fine correction by a coarse-to-fine multi-range iteration, and the single prediction ability is converted into the final high-precision calibration result. The present application has high precision, strong robustness and good cross-dataset generalization in the estimation of translation and rotation drift.
Owner:GUANGDONG LAB OF ARTIFICIAL INTELLIGENCE & DIGITAL ECONOMY (SZ)

Method and device for identifying and tracking auricular points in three-dimensional space

The invention provides an auricular point position identification and tracking method and device in a three-dimensional space, and belongs to the technical field of intelligent detection, identification and tracking of auricular points in traditional Chinese medicine. The method comprises the following steps: S1, constructing an ear three-dimensional point cloud model based on an obtained human ear image sequence; s2, positioning the three-dimensional space position of each auricular point in the ear three-dimensional point cloud model, and taking the three-dimensional space position of each auricular point as a positioning reference basis of each auricular point under different visual angles; and S3, mapping the three-dimensional space position of each auricular point in the ear three-dimensional point cloud model to a two-dimensional view under the to-be-tracked view angle based on a pinhole camera model according to the camera parameter of any to-be-tracked view angle, so as to realize cross-view-angle auricular point identification and tracking. According to the method, continuous, stable and accurate tracking of the auricular point under multiple view angles can be realized, the method has strong robustness and occlusion recovery capability, and meanwhile, the method does not need to label samples of different angles, so that the labeling cost is reduced, and the efficiency is improved.
Owner:HENAN MECHANICAL & ELECTRICAL ENG COLLEGE

Fatigue detection system, method, medium and detection equipment based on facial skeleton model

ActiveCN113920491BSolve the convenienceSolve the problem of inconvenient wearingCharacter and pattern recognitionPattern recognitionFace detection
The present invention discloses a driving fatigue detection system, method, medium and detection equipment based on a facial skeleton model, and relates to the field of image recognition technology. The obtained image is recognized by using a human posture detection model; the obtained recognition image is 3D skeletonized by a pinhole camera model, and the head posture features and facial features are extracted by using a face detection model, and fatigue features are calculated by using the extracted head and facial posture features; the obtained fatigue features are detected by using a classifier, and a fatigue detection model is obtained, and fatigue is graded and determined by using the fatigue detection model, and an APP is used to interact with the user. The present invention analyzes fatigue behavior, extracts fatigue recognition features, and obtains a fatigue detection model integrating multiple fatigue features by using a random forest algorithm. The entire system is implemented on a Raspberry Pi, and the development of the backend and the APP end is completed. The entire fatigue detection system has a high integrity.
Owner:HARBIN INST OF TECH AT WEIHAI

Method for constructing infrared imaging dataset of gas leakage based on computational fluid dynamics

A method for constructing an infrared imaging dataset of gas leakage based on computational fluid dynamics includes steps of: establishing a three-dimensional physical model of a gas leakage field scene; meshing and simulating based on the computational fluid dynamics to obtain leaking gas mole fractions of each mesh under time steps, and constituting three-dimensional gas concentration data corresponding to each frame; using optical gas imaging based on a pinhole camera model, imaging the three-dimensional gas concentration data to obtain initial images, and calculating gas concentration path-lengths corresponding to pixel points in each frame of the initial images; and performing maximum-minimum value normalization and generating grayscale images, thereby constructing the infrared imaging dataset of the gas leakage. The method can not only be used in leakage classification tasks and localization tasks, but can also be used in training tasks related to the leakage concentration.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

A method for constructing a gas leakage infrared imaging dataset based on computational fluid dynamics

The present invention discloses a method for constructing a gas leakage infrared imaging data set based on computational fluid dynamics, which belongs to the technical field of gas leakage detection and prevention and control, and specifically comprises the following steps: establishing a three-dimensional physical model of a gas leakage field scene, simulating it based on the principle of computational fluid dynamics after grid division, obtaining the mole fraction of the leaked gas of each grid under the time step, and forming the three-dimensional gas concentration data corresponding to each frame; using optical gas imaging based on a pinhole camera model, the three-dimensional gas concentration data is imaged and processed into an initial image, and the gas concentration path length corresponding to each pixel point in each frame of the initial image is calculated, and after normalization to the maximum and minimum values, each frame of grayscale image is synthesized, thereby constructing a gas leakage infrared imaging data set. The present invention is not only used for leakage classification tasks and positioning tasks, but also for training tasks related to leakage concentration. The synthesized grayscale image is more reliable and authentic, which solves the problem of the small number of public data sets for gas leakage infrared imaging and significantly reduces the cost of data set production.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Non-rigid registration method, device, equipment and storage medium for point cloud processing

ActiveCN119090930BImage enhancementImage analysisPinhole camera modelData set
The present application provides a non-rigid registration method, device, equipment and storage medium for point cloud processing, which relates to the field of three-dimensional reconstruction. The method includes: reconstructing the point cloud of the depth map through a pinhole camera model to generate a virtual data set; training the model through a preset training loss function to obtain a hierarchical matching fusion network; fine-tuning the hierarchical matching fusion network through a preset inference loss function; inputting the source point cloud and the target point cloud into the fine-tuned hierarchical matching fusion network to align the overlapping areas; performing rotational interpolation processing on the non-overlapping areas to align the non-overlapping areas. After determining the non-overlapping areas of the source point cloud and the target point cloud based on the overlapping areas, the present application performs rotational interpolation processing on the non-overlapping areas to align the non-overlapping areas; the overlapping area registration and the non-overlapping area registration correspond to different stages, avoiding the influence of the non-overlapping area registration on the overlapping area registration results, and improving the accuracy of point cloud registration.
Owner:HEFEI UNIV OF TECH

Apparatus and method for generating speech synthesis image

PCT designated stageWO2026023736A1Image enhancementImage analysisHead movementsPinhole camera model
An apparatus and a method for generating a speech synthesis image are provided. The apparatus for generating a speech synthesis image, according to one embodiment, comprises: a head movement prediction module, which estimates three-dimensional geometric transformation of a head movement of a person between a first image and a second image of the person, calculates, on the basis of a pinhole camera model, a plurality of transformation matrices for applying the three-dimensional geometric transformation at a plurality of preset depths, and predicts the head movement of the person between the first image and the second image by using the plurality of transformation matrices; a facial expression movement prediction module for predicting a facial expression movement of the person between the first image and the second image on the basis of a pre-trained facial expression movement prediction model; and a movement generation module for transforming the first image on the basis of the predicted head movement and facial expression movement.
Owner:DEEPBRAIN AI INC

Visual identification method of intelligent ball picking robot

The invention discloses an intelligent ball picking robot visual identification method, and relates to the technical field of robot visual identification and automatic control. Tennis recognition precision is low in a complex light environment. The upper computer converts the RGB image of the tennis area into an HSV image and then processes the HSV image into a black and white binary image; converting the RGB image of the tennis ball area into a grayscale image, dividing the grayscale image into a background image and an image containing a tennis ball, and detecting all round object contours from the image containing the tennis ball by adopting a Hough circle detection method; fusing the processed black and white binary image and all circular object contours to obtain an image containing all circular objects, and selecting a circular object image of which the radius pixel accords with a preset radius pixel from the image as a candidate target; the pinhole camera model adopts a similar triangle principle to obtain the distance from a small hole of the pinhole camera model to each actual tennis ball; the pinhole camera model obtains an included angle between each actual tennis ball and the horizontal plane by adopting a lens transformation principle; therefore, tennis ball position identification is realized. And identifying tennis balls.
Owner:JINHUA HUIYAN TECHNOLOGY CO LTD

Method, system and device for detecting personnel in forbidden zone under cantilever and storage medium

The invention discloses a method, a system and equipment for detecting personnel in a forbidden area under a cantilever and a storage medium, and relates to the technical field of image processing and safety monitoring, and the method comprises the steps: obtaining a video image collected by a monocular camera, recognizing a preset area in the video image through a target detection model, and outputting a bounding box corresponding to the preset area; based on a pinhole camera model and camera internal parameters, performing monocular back projection on pixel points in the bounding box, and mapping the pixel points to a ground coordinate system to obtain three-dimensional space position information; and constructing a forbidden zone based on the three-dimensional space position information, identifying whether the person enters the forbidden zone illegally by judging whether the three-dimensional projection point of the person falls into the forbidden zone, and outputting an alarm signal. According to the method, automatic extraction of key targets in a working site is realized, three-dimensional position information of the targets is acquired under the condition of no depth sensor assistance, and real-time identification and early warning response of illegal intrusion behaviors in a working area are realized.
Owner:LUCULENT SMART TECHNOLOGIES CO LTD

A method for estimating the height of urban buildings using street view images under severe occlusion

The present invention provides a method for estimating the height of urban buildings using street view images under severe occlusion conditions: first, obtain building footprint data and street view panoramic images; second, use a spherical panoramic camera as an intermediary to establish a projection conversion model of two-dimensional street view targets and three-dimensional geographic entities to achieve the correspondence between street view panoramic images and buildings in geographic space; then, in view of the widespread occlusion of buildings in street view images, a method for eliminating pseudo-height feature points of buildings based on slope mutation test is proposed to identify the real building height feature points under severe occlusion conditions; finally, project the two-dimensional image coordinates of the true height feature points into three-dimensional geographic space to estimate the height of the building. On the one hand, the present invention solves the perspective deformation problem of street view images in the traditional pinhole camera model, and on the other hand, eliminates the influence of severe occlusion in street view images on the extraction of building height feature points, significantly improving the accuracy and stability of building height estimation.
Owner:HUAZHONG NORMAL UNIV

Image deblurring method based on IMU (Inertial Measurement Unit) enhanced double-branch codec network and application

The invention discloses an image deblurring method based on an IMU (Inertial Measurement Unit) enhanced double-branch codec network. The method comprises the following steps: synchronously acquiring an RGB (Red, Green, Blue) blurred image and IMU original data in a global blurred scene; preprocessing the IMU original data to obtain camera motion parameters between adjacent image frames; generating an IMU (Inertial Measurement Unit) expected optical flow field of an image plane based on a pinhole camera model; and acquiring a trained dual-branch codec network model based on IMU enhancement, and inputting the RGB blurred image and the expected optical flow field as the trained dual-branch codec network model based on IMU enhancement to obtain a deblurred image and a pixel-level motion prediction field. According to the method, image deblurring can be efficiently achieved, the method is further used for SLAM, and the problem of SLAM performance degradation in a global blurred scene is solved.
Owner:KUNMING UNIV OF SCI & TECH

Camera Fast and Robust Calibration Method, Device and Equipment for Outdoor Visual Measurement

The present invention discloses a method, device and equipment for rapid and robust calibration of a camera for outdoor visual measurement. The method includes: obtaining a pinhole camera model corresponding to the camera to be calibrated, and constructing an initial linear equation in combination with preset construction information; performing transformation on the initial linear equation based on a preset transformation strategy to obtain a homogeneous equation, and performing zero-point analysis processing on the homogeneous equation based on a zero-point analysis strategy to obtain a zero-point analysis result set; screening the zero-point analysis result set based on a screening strategy to obtain a screened zero-point analysis result and determining a current initial translation vector; and performing iterative optimization on the current initial translation vector based on an iterative optimization strategy to obtain an optimized translation vector for calibrating the camera. The embodiment of the present invention can start from the pinhole camera model, directly construct constraints without relying on intermediate variables, thereby improving the robustness to the point distribution; moreover, by adopting a null space analysis framework based on rotation matrix constraints, the camera to be calibrated can be calibrated more quickly and with high precision.
Owner:CHINA CONSTR SCI & IND CORP LTD +1