Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

133 results about "Camera placement" patented technology

Method and apparatus for processing three-dimensional images

A camera placement determining unit determines a position at which a real, camera is placed in an object space, based on a z-value acquired in a frame immediately preceding a current frame and a user's appropriate parallax. After a projection processing, a parallax image generator generates parallax images based on viewpoint images. The z-value is acquired, in the immediately preceding frame, by at least one real camera positioned by the camera placement determining unit. Using this z-value in the current frame, the high-speed processing of three-dimensional images as a whole can be achieved.
Owner:SANYO ELECTRIC CO LTD

Telepresence communication system

A telepresence communication system for group meeting rooms and personal home and office systems provides improved human factor experience through substantially life size images with eye level camera placement. The system provides switched presence interfaces so that conferees can select when to transmit their images during a conference and optionally provides individual microphones for each of conferee. Switched presence between presets of conferees are viewed on multipoint windows overlaying life-size images upon eye contact camera regions and eliminate seeing camera image movement during pan, tilt and zoom operations. An ambient light rejecting filter system enables an eye level camera to be hidden behind a projection screen and provides bright, high contrast images under normal meeting room and office environments. A telepresence organizational enablement system brings all the features of a corporate office complex and its social and organizational benefits, into a virtual community eliminating the need to centralize employees.
Owner:VIDEOTRONIC SYST

System and method for camera calibration

A system and method for determining the adjustments that must be made to the individual images recorded by a multi-lens camera so that the images will fit together into a panorama. The camera is placed in the center of a structure, the edges of which have at least one row on indicia. Each camera records an image which includes the indicia along each edge that will be seamed with an edge of another image in order to form a panorama. Each edge of the structure which is along a seam that will be seamed with an edge of another image is recorded by two lenses on the camera. The amount of adjustment required to make the indicia in the two images fit together is then determined. The values of these adjustments are recorded along with an identification of the camera which recorded the images. Subsequent sets of images recorded by this same camera can then be seamed using the same adjustments.
Owner:IMMERSIVE LICENSING

Method for eliminating error in camera having angular velocity detection system

An error in a camera having angular velocity sensors is eliminated. A camera is placed on a rotating table and rotated, angular velocities are detected by angular velocity sensors, and a CZP chart is photographed. The motion of the camera is computed as a locus of motion of a point light source on an imaging plane from the outputs from the angular velocity sensors. The inclination of the locus motion is compared with the inclination of a zero-crossing line which has been obtained by subjecting the photographed image to Fourier transformation, to thus compute angles of relative inclination of the angular velocity sensors with respect to the image sensor. Further, when no coincidence exists between the zero-crossing line of the data into which a PSF has been Fourier-transformed and a zero-crossing line of the data into which a photographed image has been Fourier-transformed, a computer computes a correction coefficient from a proportion of an interval between the zero-crossing lines, on condition that an error is included in the angular velocity sensors or the focal length of a photographing lens, and the error is eliminated.
Owner:INTELLECTUAL VENTURES FUND 83 LLC

System to freely configure video conferencing camera placement

Embodiments of the present invention are directed to cordless video conferencing camera adaptors and video conferencing systems including the camera adaptors. Embodiments of the present invention overcome some of the inherent problems of known video conferencing products by being a part of a portable and configurable video conferencing system, which can be used in various meeting rooms, laboratories, training rooms, and conference halls. For example, embodiments of the invention allow use of low cost (e.g., under $100) cameras to provide any angle of video coverage in any conference room setting.
Owner:ALCATEL LUCENT SAS

Merged laser and photogrammetry measurement using precise camera placement

The surface of a part is measured using a combination of laser tracking and Photogrammetry processes. Cameras used in the Photogrammetry process are mounted on a carriage for movement to positions along a predetermined path where images of the part surface are recorded and then converted to surface measurements. Laser tracking is used to both measure the part surface and track the position of the cameras. The measurements made by Photogrammetry and laser tracking processes are combined with the camera position to produce highly accurate part surface measurements.
Owner:THE BOEING CO

Effortless Navigation Across Cameras and Cooperative Control of Cameras

This application discloses a system and related methods (called Fast Track) to effortlessly navigate across multiple cameras, e.g. video surveillance cameras distributed in a facility. Fast Track simplifies the act of following a suspicious individual roaming in a facility, e.g. by eliminating the need for security operators to memorize camera placement and coverage, and to manually control pan-tilt-zoom (hereinafter “PTZ”) cameras, and by simplifying the process to reduce the risk of operator error. Combinations of novel scoring and control methods generally provide an automatic identification of optimal cameras and pre-emptive re-direction of PTZ cameras. Extensions to these methods enable two new capabilities: Cooperative PTZ Control (e.g. coordinating PTZs to cover a 3D map viewport optimally) and Self-Healing Perimeters, to automatically reassign and redirect multiple PTZ cameras to fill gaps in a security perimeter.
Owner:FORTEM SOFTWARE INC

Angular velocity calibration method

Inclinations of angular velocity sensors attached to a camera are detected, and outputs from the angular velocity sensors are calibrated. A camera is placed on a rotating table and rotated, angular velocities are detected by angular velocity sensors, and a CZP chart is photographed. The motion of the camera is expressed as a locus of motion of a point light source on an imaging plane from the outputs from the angular velocity sensors. The inclination of the locus motion is compared with the inclination of a zero-crossing line which has been obtained by subjecting the photographed image to Fourier transformation, to thus compute angles of relative inclination of the angular velocity sensors with respect to the image sensor.
Owner:EASTMAN KODAK CO

Position and posture optimization method and position and posture optimization system based on multi-map fusion

The invention discloses a position and posture optimization method and a position and posture optimization system based on multi-map fusion. The method includes the steps: calibrating wide-angle lenses of a plurality of cameras to obtain calibration parameters of the wide-angle lenses of the cameras; correcting wide-angle images of the wide-angle lenses corresponding to the calibration parametersaccording to the calibration parameters to obtain normal visual-angle images; placing the cameras at the same coordinate positions in a world coordinate system, and initializing the cameras; trackingand acquiring a moved normal visual-angle image of each camera, and calculating a key frame position and posture of each camera to generate a key frame position and posture set; optimizing each key frame position and posture in the key frame position and posture set to generate an optimized key frame position and posture set, and generating a fusion map according to the optimized key frame position and posture set. According to the method, positions and postures of a plurality of cameras can be unified into the same coordinate system, and the same maps are built, so that a plurality of maps can be fused.
Owner:BEIJING HUAJIE IMI TECH CO LTD

Calibration approach for camera placement

ActiveUS20180339386A1Reduces or prevents object position errorsImage enhancementProgramme-controlled manipulatorDocumentation procedureCamera placement
Multiple cameras are used for tool positioning, as-built documentation, and / or personnel monitoring in construction site. A camera unit comprises one or more imaging devices, a processing computer, and a communication device. The camera units are placed at multiple locations in a construction site to cover an area. The camera units are self-positioned by detecting a calibration target that moves within a working volume. The camera units can detect and calculate positions of objects, including measurement sticks, tools, personnel, etc., in the area.
Owner:TRIMBLE INC

A surveillance camera placement method based on the importance of a substation area

The invention provides a surveillance camera distribution method based on the importance degree of a substation area, which comprises the following steps: (1) obtaining a plane distribution map of thewhole substation and rasterizing the plane distribution map; (2) Setting the importance of monitoring each small area; (3) performing a set of small areas where cameras can be installed in a given substation; (4) Taking the minimum average difference between the actual camera coverage and the expected coverage as the objective function, and taking the given number of cameras installed as the costconstraint, the camera placement optimization model is established; (5) Genetic algorithm is used to solve the optimal model of surveillance camera placement, and the optimal installation scheme of camera placement is obtained. The invention provides a surveillance camera distribution method based on the importance degree of the substation area, which can be used for determining the installationdistribution position of the surveillance camera in the substation, enhancing the monitoring degree of the key equipment and the key area in the substation, and realizing the optimal configuration under the condition of limited surveillance camera resources.
Owner:QINGYUAN POWER SUPPLY BUREAU OF GUANGDONG POWER GRID CO LTD

Tracheal Intubation Device

A tracheal intubation device for placing an endotracheal tube in the trachea of a patient is disclosed. The tracheal intubation device includes a bar-shaped camera, a handle portion, a guiding portion, and a display device. The bar-shaped camera for capturing images is placed inside the endotracheal tube. The display device is electrically connected to the bar-shaped camera for displaying images captured by the bar-shaped camera. The guiding portion connected to the handle portion has a front end and a rear end, wherein the rear end is connected to the handle portion, and the bar-shaped camera and the endotracheal tube are movably situated in the guiding portion.
Owner:CHEN TIEN SHENG

A system and method for optimizing fiducial marker and camera positions/orientations

A method for optimizing fiducial marker and camera positions / orientations is realized to simulate camera and fiducial positions and pose estimation algorithm to find best possible marker / camera placement comprises the steps of: acquiring mesh data representing possible camera positions and feasible orientation boundaries of cameras on the environment of tracked object; acquiring mesh data representing possible active marker positions and feasible orientation placements of markers on a tracked object; pose data representing possible poses of tracked object under working conditions; initializing the control parameter for camera placement; create initial solution strings for camera placement; solving marker placement problem for the current camera placement; evaluating the quality of the current LED and camera placement taking pose coverage, pose accuracy, number of placed markers, number of placed camera etc. into account; determining if a stopping criterion is satisfied.
Owner:ASELSAN ELEKTRONIK SANAYI & TICARET ANONIM SIRKETI

Device for use in identifying or authenticating a subject

A device for use in identifying or authenticating a subject positioned in an acquisition volume on the basis of at least one biometric characteristic of the subject, the device including in succession, in offset manner along a camera placement axis: a first camera; a second camera; and a third camera; the optical axes of the first and second cameras forming between them an angle strictly less than 10°, and the optical axis of the third camera intersecting the optical axes of the first and second cameras, the optical axes of the first and second cameras each forming an angle less than or equal to 5° relative to a normal axis perpendicular to the camera placement axis.
Owner:IDEMIA IDENTITY & SECURITY FRANCE

Product quality detection device based on machine vision

The invention discloses a product quality detection device based on machine vision. By arranging an intermittent driving mechanism at one side of a conveying mechanism and then arranging a pushing mechanism which takes the reciprocating motion, the pushing mechanism can be matched with the intermittent driving mechanism to work, the intermittent driving mechanism intermittently drives the drivingmechanism to work so as to implement intermittent movement of a conveying belt, facilitate enabling a space between two adjacent separators to reach an auxiliary table when the conveying belt stops moving, the pushing mechanism is enabled to push a pushing plate onto the conveying belt so as to push a product placed on the conveying belt onto a supporting table in a detection room, and then the pushing mechanism is enabled to drive the pushing plate to move back onto the auxiliary table without influencing continuous movement of the conveying belt; and by arranging a movement mechanism in thedetection room and arranging a lens frame on the movement mechanism, a camera can be placed in the lens frame so as to achieve a quality detection effect of machine vision, and working of the movement mechanism can enable the lens frame to move on an X axis, a Y axis and a Z axis.
Owner:陕西众策网络科技发展有限公司

Camera for automobile

The invention discloses a camera for an automobile. The camera comprises a shell. Positioning installing holes are formed in the two ends of the shell, a boss is arranged at the front end of the shell, the upper end of the boss is a slope, strip-shaped convex plaid is arranged on the slope of the boss, a camera placement groove is formed in the center of the front end of the boss, a camera device is arranged in the camera placement groove and comprises a rear view camera body and lighting light compensation lamps, the lighting light compensation lamps are arranged at the two ends of the rear view camera body, and a sealing cover is arranged on the camera placement groove. By the adoption of the mode, rainwater can be effectively blocked on rainy days, and normal use of the camera for the automobile is not affected on the rainy days.
Owner:范绍明

Monocular camera pose measurement device and method based on iterative updating

The invention provides a position and posture measuring device and a method of a monocular camera based on iterative updating, belonging to the field of image processing and high-precision measurement. In the monocular camera pose measuring device based on iterative updating, the camera bracket is fixedly connected with the industrial camera, the industrial camera is arranged above the target to be measured, the target to be measured is two-dimensional translated and one-dimensional rotated on the moving platform, the signal output end of the industrial camera is connected with the signal input end of the image acquisition card, and the output end of the image acquisition card is connected with the input end of the industrial control computer for position and posture measurement. The specific steps of the monocular camera pose measurement method based on iterative updating are as follows: according to the two-dimensional measurement data extracted from the measurement image, the three-dimensional world coordinates are deduced; the posture measurement of the object to be measured is realized by the way of posture iterative updating. The device and the method for calibrating the measurement accuracy of the posture measurement system provided by the invention can obtain a large amount of measurement data only by taking a measurement picture once, thereby greatly simplifying the calibration process of the measurement accuracy.
Owner:HARBIN INST OF TECH

Panoramic structured light vision measurement system and universal distortion model parameter calibration method

ActiveCN108917602AAvoid tuningAvoiding Global Calibration ProblemsImage analysisUsing optical meansModel reconstructionModel parameters
The invention discloses a panoramic structured light vision measurement system and a universal distortion model parameter calibration method. The panoramic structured light vision measurement system is composed of a camera, a structured light projector, a glass tube and a computer. A panoramic structured light vision measurement model is established by using light bar points located on both an imaging light path and a structured light. According to the refraction distortion of glass tube, a universal distortion model is established, and spatial coordinates of target feature points are reconstructed based on the model, the spatial coordinates are represented by X<r>; meanwhile, an auxiliary camera is placed outside the glass tube to reconstruct the corresponding spatial coordinates of the target feature points, the corresponding spatial coordinates are represented by X<c>; and based on the X<r>and X<c> which are in one-to-one correspondence, the objective function is established and optimized to obtain universal distortion model parameters. When the parameters of the structured light vision model are calibrated, the spatial coordinates of the light bar points are obtained based on the universal distortion model, and the structured light equation is fitted. The panoramic structured light vision measurement system and the universal distortion model parameter calibration method caneffectively correct distortion and have that characteristic of good stability and higher precision.
Owner:BEIHANG UNIV

Portable bacterial colony automatic counting device and method based on a smart phone

The invention discloses a portable bacterial colony automatic counting device and method based on a smart phone. A lighting and control circuit board is arranged above a height adjusting plate. A light source diffusing plate is positioned above the lighting and control circuit board. A culture dish limiting plate is arranged above the light source diffusing plate. A bracket shell is arranged on the culture dish limiting plate. The culture dish limiting plate is provided with a through hole. A bacteriological culture dish is arranged in the through hole and on the light source diffusing plate.The bracket shell is provided with a smart phone placement position in which a smart phone is placed. The smart phone placement position is provided with a phone camera placement hole in which a camera is placed. The lighting and control circuit board provides backlight for the bacteriological culture dish to keep the bacteriological culture solution stable. The camera collects an image. The counting result is obtained by preprocessing the image through a specific algorithm. Bacterial colony counting operation commonly used in biochemical samples detection is realized. High accuracy and full automation are achieved at low cost. The device and the method can be conveniently used both in the laboratory and in the field.
Owner:ZHEJIANG UNIV

Pipeline measurement method based on multi-view vision

The invention discloses a pipeline measurement method based on multi-view vision. The method is composed of four parts of image acquisition and preprocessing, center line and outer diameter extraction, camera calibration and camera matrix conversion, pipeline center line matching and outer diameter expansion. A camera is placed on a built measurement frame to carry out image acquisition and preprocessing and acquire a pipeline gray scale picture. The method comprises the following steps of acquiring a pipeline center line by applying distance transformation and a minimum path method, extracting feature points of the pipeline center line, and discretizing the feature points; calibrating the corresponding binocular cameras (a front side camera and a rear side camera), and obtaining a conversion matrix from a rear side camera coordinate system to a front side camera coordinate system; and recovering three-dimensional information of the pipeline center line by adopting a dynamic matchingmethod according to the obtained center line feature points and the camera calibration parameters, expanding outer diameter information obtained by processing pictures shot from different viewing angles on the three-dimensional pipeline center line, and finally obtaining the spatial position of the pipeline center line and the corresponding outer diameter information.
Owner:NANJING UNIV

Method for generating 3D panoramic image from dense point cloud

InactiveCN107545537AReal depth of field feelingCorrect disparity informationImage analysisGeometric image transformationParallaxPoint cloud
The invention discloses a method for generating a 3D panoramic image from dense point cloud. In the method, a 360-degree panoramic image and a corresponding 360-degree depth image are used for rendering a correct image a virtual camera should see through deploying one virtual camera in each direction, after the panoramic image and the corresponding depth image are acquired, a pair of 3D panoramicimages can be generated, a correct parallax error relation can be generated for any direction, depth perception is not changed along with a difference between a viewing angle and an original camera placement angle, a vertical parallax error causing discomfort of human eyes is avoided, and thus immersion and comfort level of a user when the user watches panoramic 3D by using VR head-mounted equipment can be greatly improved. In addition, a base line distance B of the virtual camera can also be adjusted according to sizes of shooting scenes, and thus different levels of 3D feeling is achieved.
Owner:嘀拍信息科技南通有限公司

Target crowd tracking and monitoring method based on limited range scene

ActiveCN112200021ARealize intensive monitoringRealize no dead angle identification tracking monitoringImage analysisCharacter and pattern recognitionPattern recognitionMulti target tracking
The invention discloses a target crowd tracking and monitoring method based on a limited range scene, and the method comprises the steps: S1, designing and achieving a whole set of camera placement and collection device based on a limited visual field range, so as to meet the demands of a target crowd activity scene and the full coverage of a visual field; S2, modifying the size and proportion ofan anchor frame of a detection network model according to the body type and face type proportion of the target crowd, and modifying a loss function of the detection network to improve the detection accuracy; S3, recognizing the human face by adopting a specific recognition network while detecting the human face, so as to improve the detection and recognition precision while not reducing the speedunder the condition that the detection network and the human face recognition network are used at the same time; and S4, improving a multi-target tracking monitoring model, and improving the model adaptability of target crowd tracking monitoring through extraction of specific features and pruning of a specific scene. According to the design scheme, in a visual scheme of nursing the target crowd and preventing accidents, the monitoring accuracy and the positioning speed are improved while no leakage and real-time performance are realized.
Owner:YANSHAN UNIV

System to freely configure video conferencing camera placement

Embodiments of the present invention are directed to cordless video conferencing camera adaptors and video conferencing systems including the camera adaptors. Embodiments of the present invention overcome some of the inherent problems of known video conferencing products by being a part of a portable and configurable video conferencing system, which can be used in various meeting rooms, laboratories, training rooms, and conference halls. For example, embodiments of the invention allow use of low cost (e.g., under $100) cameras to provide any angle of video coverage in any conference room setting.
Owner:ALCATEL LUCENT SAS

Six-sided detection device used for plate production

PendingCN107966102ASolve the problem of not being able to take picturesInvestigating moving sheetsUsing optical meansImaging processingImage manipulation
The invention relates to a six-sided detection device used for plate production. The device comprises a top and bottom detection section, a left and right detection section, a support plate, a servo motor, guide devices, a cylinder, a module, a CCD camera, an upper board detection camera, an optical lens, a lower board detection camera, a placement frame and a support plate. The servo motor is arranged on the left side of the module. Two groups are symmetrically arranged on left and right sides of the cylinder. The cylinder is fixedly connected with the module through the guide devices. The CCD camera is arranged on the upper end of the module. The upper board detection camera is arranged on the top of the placement frame. The optical lens is arranged on the lower side inside a rack. The lower board detection camera is arranged on the lower end of the placement frame. The device integrates servo control, line scan cameras, image processing, laser sensing, distance sensing, informatization software and other frontier technologies in many neighborhoods, and solves the problem that the side of a moving plate cannot be photographed. Moving detection is carried out on various sizes of plates, including profiled plates, on the same device.
Owner:GUANGDONG XG INTELLIGENT SYST CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products