1496results about "Picture interpretation" patented technology

A powerful, scaleable, and reconfigurable image processing system and method of processing data therein is described. This general purpose, reconfigurable engine with toroidal topology, distributed memory, and wide bandwidth I/O are capable of solving real applications at real-time speeds. The reconfigurable image processing system can be optimized to efficiently perform specialized computations, such as real-time video and audio processing. This reconfigurable image processing system provides high performance via high computational density, high memory bandwidth, and high I/O bandwidth. Generally, the reconfigurable image processing system and its control structure include a homogeneous array of 16 field programmable gate arrays (FPGA) and 16 static random access memories (SRAM) arranged in a partial torus configuration. The reconfigurable image processing system also includes a PCI bus interface chip, a clock control chip, and a datapath chip. It can be implemented in a single board. It receives data from its external environment, computes correspondence, and uses the results of the correspondence computations for various post-processing industrial applications. The reconfigurable image processing system determines correspondence by using non-parametric local transforms followed by correlation. These non-parametric local transforms include the census and rank transforms. Other embodiments involve a combination of correspondence, rectification, a left-right consistency check, and the application of an interest operator.

The present invention provides a system (method and apparatus) for creating photorealistic 3D models of environments and/or objects from a plurality of stereo images obtained from a mobile stereo camera and optional monocular cameras. The cameras may be handheld, mounted on a mobile platform, manipulator or a positioning device. The system automatically detects and tracks features in image sequences and self-references the stereo camera in 6 degrees of freedom by matching the features to a database to track the camera motion, while building the database simultaneously. A motion estimate may be also provided from external sensors and fused with the motion computed from the images. Individual stereo pairs are processed to compute dense 3D data representing the scene and are transformed, using the estimated camera motion, into a common reference and fused together. The resulting 3D data is represented as point clouds, surfaces, or volumes. The present invention also provides a system (method and apparatus) for enhancing 3D models of environments or objects by registering information from additional sensors to improve model fidelity or to augment it with supplementary information by using a light pattern projector. The present invention also provides a system (method and apparatus) for generating photo-realistic 3D models of underground environments such as tunnels, mines, voids and caves, including automatic registration of the 3D models with pre-existing underground maps.

Systems are arranged to provide a user information which relates to objects of interest. A user may point a device toward an object to address it. The device determines which objects are being addressed by reference to an internal database containing preprogrammed information relating to objects. Information relating to objects being addressed can then be presented at a user interface. A device of the system may include a point reference, a direction reference, a position determining support, attitude determining support, a computer processor and database, and a user interface. Methods of systems include the steps of addressing an object, determining position and attitude, searching a database, and presenting information to a user.

“Path-enhanced” multimedia (PEM) data may be viewed, modified, or interacted with according to user selected views which determine the manner in which at least a portion of the PEM data is displayed. The PEM data is stored in a data structure as a scrapbook object including first data object types corresponding to the PEM data and second object types corresponding to the different view types. The scrapbook object data structure lends itself to displaying portions of the PEM data according to selected views that correspond to a particular time and place or to a particular time ordered sequence of locations (i.e., a particular path segment) and/or can be enhanced with other multimedia content related to that time and place or to that path segment, thereby providing a more interesting and effective display of the “path-enhanced” recorded events. For example, the time and location of a particular point on the path may be used to locate and append other recorded sounds and images associated with that time and/or that location, to thereby provide an enhanced presentation of a trip or other path-oriented experience. Moreover, the data defining any such associated path may also be edited to thereby define a new or modified path.

Directions normal to images of an object captured by at least two cameras from different points of view are aligned with each other to form corrected object images, and a correspondence is determined between at least one pixel position on a horizontal line in one of the corrected object images and at least one pixel position on the same horizontal line in another of the corrected object images. The correspondence is determined by determining a similarity in brightness and color components at the pixel positions and a parallax between the corrected object images A robust, accurate image matching can be done by making dynamic matching between all pixels on a scan line in the images captured by the cameras.

A navigation system and a navigation method inside of a building using Visible Light Communications (VLC) are provided. The navigation system includes a map server, in which map information required to provide a navigation function is stored, for transferring the map information to each lamp, a plurality of lamps, installed in each zone inside of the building and having their respective identifiable and unique IDentifications (IDs), for receiving the map information required to provide the navigation function from the map server, and for generating a visible light signal in response to the received map information by using a VLC module, and a mobile terminal, equipped with a visible light Rx module, for being provided with the map information upon receiving the visible light signal generated from the lamp, and for displaying a map image in response to the provided map information.

A computerized system for displaying, geolocating, and taking measurements from captured oblique images includes a data file accessible by the computer system. The data file includes a plurality of image files corresponding to a plurality of captured oblique images, and positional data corresponding to the images. Image display and analysis software is executed by the system for reading the data file and displaying at least a portion of the captured oblique images. The software retrieves the positional data for one or more user-selected points on the displayed image, and calculates a separation distance between any two or more selected points. The separation distance calculation is user-selectable to determine various parameters including linear distance between, area encompassed within, relative elevation of, and height difference between selected points.

An illumination channel, a stereoscopic optical channel and another optical channel are held and positioned by a robotic surgical system. A first capture unit captures a stereoscopic visible image from the first light from the stereoscopic optical channel while a second capture unit captures a fluorescence image from the second light from the other optical channel. An intelligent image processing system receives the captured stereoscopic visible image and the captured fluorescence image and generates a stereoscopic pair of fluorescence images. An augmented stereoscopic display system outputs a real-time stereoscopic image comprising a three-dimensional presentation of a blend of the stereoscopic visible image and the stereoscopic pair of fluorescence images.

A method of generating a geodetic reference database product is disclosed The method comprises acquiring mobile mapping data captured by means of digital cameras, range sensors and position determination means including GPS and IMU mounted to a vehicle driving across the earth surface, the mobile mapping data comprising simultaneously captured image data, range data and associated position data in a geographic coordinate system. Linear stationary earth surface features are derived from the mobile mapping data by processing the image data, range data and associated position data. 3D-models are generated for the linear stationary earth surface features in the geographic coordinate system from the image data, range data and associated position data and stored in a database to obtain the geodetic reference database product. A 3D-model could include an image representing the colors of the surface of the 3D model or a set of smaller images representing photo-identifiable objects along the model. The 3D-models could be used to rectify aerial imagery, to correct digital elevation models and to improve the triangulation of digital elevation models.

The invention provides a calibration method for a binocular stereo measurement system, and belongs to the technical field of measurement and test. The invention adopts a plane calibrating board having a characteristic dot array with an accurate given distance between the centers of two characteristic dots; the calibrating board is shot from more than three angles; initial values of the intrinsic and extrinsic parameters of two cameras are solved by using the linear method under a pinhole model; the distortion effect is considered; the intrinsic and extrinsic parameters of the two cameras are taken as optimization variables for a first optimization; the space coordinates of the centers of the characteristic dots on the calibrating board are taken as optimization variables for a second optimization; the translation vector between the cameras is scaled to the ratio of the calculated distance to the given accurate distance, thus getting a calibration result of the parameters; the result of the second optimization is got by using the intrinsic parameters and the relative attitude parameters of the two cameras. Considering the influence of the geometrical errors of the calibrating board, the method reduces the manufacturing, measurement and calibration requirement of the calibrating board and gets calibration result of high precision.

Embodiments of the invention relate to a determination method and apparatus for the position and orientation of a mobile robot. The method comprises the following steps: in virtue of simultaneous localization and mapping (SLAM) technology, establishing a global map of an environment where the mobile robot plays a navigation role by using a laser scanner; when the mobile robot is energized, establishing a local map of an environment in the energization moment of the mobile robot by using a laser scanner in virtue of SLAM technology; and subjecting the local map to image matching in the global map so as to obtain the initial position and orientation of the mobile robot in the global map. According to the embodiments of the invention, the absolute position and orientation of the mobile robot in the global map in the moment the mobile robot is energized and started can be obtained, thereby realizing initialization of the position and orientation of the mobile robot; moreover, determined position and orientation of the mobile robot can be further corrected.

The invention discloses a method for measuring the three-dimensional position and the stance of an object with a single camera. The method comprises the following steps of: acquiring an image of a target to be measured by utilizing a single camera; confirming the real-time three-dimensional position and stance information of the target to be measured by accurately identifying marking points on the target to be measured; selecting a suitable camera according to a detection scene and a range and calibrating the camera to acquire inner and outer parameters of the camera; designing target marking points according to the target to be measured and reasonably arranging the marking points; then, detecting the target, identifying characteristic points according to the image shot by the camera, and matching the detected characteristic points with the marking points; and finally, solving the three-dimensional position and stance information of the target to be measured according to the corresponding relation between the measuring points and the object marking points. Whether a non-rigid object is deformed or not can also be detected by using the method. In the invention, the single camera is adopted to realize three-dimensional measurement, acquire the information of the target in a three-dimensional space, such as space geometrical parameters, position, stance, and the like, decrease the measuring cost and the size of a measuring system, and facilitate the operation.

A system and method for imaging a three-dimensional scene having one or more objects. The system includes a light source, a detector array, a timing circuit, an inertial guidance system and a processor connected to the timing circuit and the inertial guidance system. The light source generates an optical pulse and projects the optical pulse on an object so that it is reflected as a reflected pulse. The detector array includes a plurality of detectors, wherein the detectors are oriented to receive the reflected pulse. The timing circuit determines when the reflected pulse reached detectors on the detector array. The inertial guidance system measures angular velocity and acceleration. The processor forms a composite image of the three-dimensional scene as a function of camera position and range to objects in the three-dimensional scene.

In one embodiment, an aerial collection system includes an image collection field vehicle that travels at street level and an image collection aerial vehicle that travels in the air above the street. The aerial vehicle collects image data including at least a portion of the field vehicle. The field vehicle includes a marker, which is identified from the collected image data. The marker is analyzed to determine an operating characteristic of the aerial vehicle. In one example, the operating characteristic in the marker includes information for a flight instruction for the aerial vehicle. In another example, the operating characteristic in the marker includes information for the three dimensional relationship between the vehicles. The three dimensional relationship is used to combine images collected from the air and images collected from the street level.

A camera calibration device capable of simply calibrating a stereo system consisting of a base camera and a detection camera. First, distortion parameters of the two cameras necessary for distance measurement are presumed by the use of images obtained by shooting a patterned object plane with the base camera and the reference camera at three or more view points free from any spatial positional restriction, and projective transformation matrixes for projecting the images respectively onto predetermined virtual planes are calculated. Then internal parameters of the base camera are calculated on the basis of the projective transformation matrixes relative to the images obtained from the base camera. Subsequently the position of the shot plane is presumed on the basis of the internal parameter of the base camera and the images obtained therefrom, whereby projection matrixes for the detection camera are calculated on the basis of the plane position parameters and the images obtained from the detection camera. According to this device, simplified calibration can be achieved stably without the necessity of any exclusive appliance.

A computerized aircraft system, such as an unmanned aircraft system (UAS) is provided with a cloud detection system. The UAS includes a monocular electro-optic or infra-red camera which acquires consecutively, in real time, a plurality of images within a field of view of the camera. The system identifies feature points in each of the consecutive images, and generates macro representations of cloud formations (3D representations of the clouds) based on tracking of the feature points across the plurality of images. A cloud avoidance system takes in nominal own-ship waypoints, compares those waypoints to the 3D cloud representations and outputs modified waypoints to avoid the detected clouds.

A system for aerial image detection and classification is provided herein. The system comprising_an aerial image database storing one or more aerial images electronically received from one or more image providers, and an object detection pre-processing engine in electronic communication with the aerial image database, the object detection pre-processing engine detecting and classifying objects using a disparity mapping generation sub-process to automatically process the one or more aerial images to generate a disparity map providing elevation information, a segmentation sub-process to automatically apply a pre-defined elevation threshold to the disparity map, the pre-defined elevation threshold adjustable by a user, and a classification sub-process to automatically detect and classify objects in the one or more stereoscopic pairs of aerial images by applying one or more automated detectors based on classification parameters and the pre-defined elevation threshold.

The present invention relates to a system and a method for monitoring/tracking the movement of an object in a location which is difficult to access, such as the movement of a patient in a clinical MRI scanner. This is achieved by an optical motion tracking system for determining the movement of an object at least partly located in a volume of difficult access and/or at least partly located in an electromagnetic field, said system comprising a borescope for imaging a pattern on the object or a surface part of the object with a camera, said pattern or surface part located adjacent to a distal end of the borescope and said camera attached to a proximal end of said borescope, and image processing means for calculating the movement of said pattern or surface part relative to the distal end of the borescope based on a plurality of frames/images captured by the camera. The invention further relates to the use of a borescope for motion tracking of an object and a marker plate suitable for use in the motion tracking system.

The invention relates to a system for three-dimensionally modeling and restitution a subject, the system comprising a housing suitable for being carried in the hand by an operator, the housing having an optical unit with stereoscopic digital video cameras co-operating with an inertial navigation unit having a trihedron of optical fiber gyros and a trihedron of accelerometers for generating position and displacement signals in a frame of reference. The housing may also include, in particular, a telemeter laser, an infrared video camera, a GPS unit, inclinometers, and tri-flux magnetometers. A second subassembly connected to the housing by an optical and/or electrical connection cable contains an electrical power supply, electronic circuits, and a microcomputer for processing signals delivered by the housing and for generating a three-dimensional model of the subject, implementing a photogrammetric technique.

Images of an object viewed from a plurality of points of view is input through an image inputting unit. Change of orientation of the image inputting means, occurring when the images of the object are input, is detected. Change of position of point of view, occurring when the images of the object are input, is detected. Characteristic points are extracted from the image which is input previously, each of the characteristic points corresponding to a respective one of objects points on the object. Corresponding points are extracted from the image which is input currently, each of the corresponding points corresponding to a respective one of the characteristic points. The three-dimensional position of each of the object points is calculated, based on the change of orientation and the change of position of point of view of the image inputting unit and the data of the characteristic points and the corresponding points.

A position measurement device is provided that can precisely measure the photographing position or posture of a photographing device or the coordinates of an object based on sequentially changing photographed images. A position measuring device 100 of the invention comprises: an image acquisition section 2 for acquiring a series of photographed images changing continuously or little by little along with position displacement relative to an object to be photographed; a positional relationship measurement section 9 for measuring position displacement and posture change of the image acquisition section 2; a feature extraction section 3 for extracting feature points from the photographed images obtained with the image acquisition section 2; a feature point tracking section 4 for tracking the feature points by searching corresponding points corresponding to the feature points on a plurality of the photographed images; an image selection section 61 for selecting an image to be processed from the series of photographed images based on a measurement result made with the positional relationship measurement section 9; and a position measurement section 7 for measuring the photographing position and the photographing posture of the image acquisition section 2 based on the image to be processed selected with the image selection section 61.

The invention relates to a dynamic target position and attitude measurement method based on monocular vision at the tail end of a mechanical arm and belongs to the field of vision measurement. The method comprises the following steps: firstly calibrating with a video camera and calibrating with hands and eyes; then shooting two pictures with the video camera, extracting spatial feature points in target areas in the pictures by utilizing a scale-invariant feature extraction method and matching the feature points; resolving a fundamental matrix between the two pictures by utilizing an epipolar geometry constraint method to obtain an essential matrix, and further resolving a rotation transformation matrix and a displacement transformation matrix of the video camera; then performing three-dimensional reconstruction and scale correction on the feature points; and finally constructing a target coordinate system by utilizing the feature points after reconstruction so as to obtain the position and the attitude of a target relative to the video camera. According to the method provided by the invention, the monocular vision is adopted, the calculation process is simplified, the calibration with the hands and the eyes is used, and the elimination of error solutions in the measurement process of the position and the attitude of the video camera can be simplified. The method is suitable for measuring the relative positions and attitudes of stationery targets and low-dynamic targets.

A method for deriving three-dimensional measurement information and/or creating three-dimensional models and maps, from single images of at least one three-dimensional object is provided. The method includes the steps of: (a) obtaining at least one two-dimensional single image of the object, the image consisting of image data and being associated with an image geometry model (IGM); (b) deriving three-dimensional coordinate information associated with the image, based on the IGM, and associating the three-dimensional coordinate information with the image data; (c) analyzing the image data so as to: (i) measure the projection of the object using the IGM to derive measurement data including the height and/or point-to-point distances pertaining to the object; and/or (ii) measure the shadow of the object to derive measurement data including the height and/or point-to-point distance pertaining to the object; and (d) obtaining three-dimensional measurements based on the projection and/or shadow measurements of the object. In another aspect of the method, the method includes the further step of creating three-dimensional models or maps based on the projection and/or shadow measurements. A series of algorithms are also provided for processing the method of the invention. A computer system and related computer program for deriving three-dimensional measurement information and/or creating three-dimensional models and maps, from single images of at least one three-dimensional object is provided based on the disclosed method is also provided.

An image processing device is provided that can precisely measure the photographing position or posture of a photographing device or the coordinates of an object based on sequentially changing photographed images. A series of sequentially photographed images are acquired, from which feature points are extracted. The feature points are tracked and correlated to each other. Stereo images are selected from the series of photographed images correlated, and subjected to an orientation and a 3D measurement. The error range of corresponding points obtained by the 3D measurement is calculated. Based on the calculated error range, it is determined whether or not the corresponding points are appropriate for 3D measurement. Those corresponding points determined as inappropriate are deleted. Another orientation and another 3D measurement are performed using those corresponding points excluding the deleted ones, thus improving the measurement precision.

An endoscope with a stereoscopic optical channel is held and positioned by a robotic surgical system. A first capture unit captures: a visible first color component of a visible left image combined with a fluorescence left image from first light from one channel in the endoscope; a visible second color component of the visible left image from the first light; and a visible third color component of the visible left image from the first light. A second capture unit captures: a visible first color component of a visible right image combined with a fluorescence right image from second light from the other channel in the endoscope; a visible second color component of the visible right image from the second light; and a visible third color component of the visible right image from the second light. An augmented stereoscopic outputs a real-time stereoscopic image including a three-dimensional presentation including the visible left and right images and the fluorescence left and right images.

An endoscope with a stereoscopic optical channel is again held and positioned by a robotic surgical system. A capture unit captures (1) at a first time, a first image from light from the channel; and (2) at a second time different from the first time, a second image from the light. Only one of the first image and the second image includes a combination of a fluorescence image and a visible image. The other of the first image and the second image is a visible image. An intelligent image processing system generates an artificial fluorescence image using the captured fluorescence image. An augmented stereoscopic display system outputs an augmented stereoscopic image of at least a portion of the tissue comprising the artificial fluorescence image.

The invention relates to the field of indoor navigation and discloses an indoor location method and an indoor location system. In the invention, vision road signs (artificial or natural road signs) are deployed in fixed indoor positions. During the location process, a movable robot photographs images from surrounding environment, wherein the images are subjected to pretreatment and character extraction. A characteristic image after the character extraction is matched with the road signs in a road sign character library to obtain a road sign which can be used for location in the image. Through a vision distance measurement scheme on the basis of the characteristic road sign, real-time location is carried to the movable robot. In the embodiment, with the vision road signs (passive road sign), the road sign itself does not emit a wireless signal and has low cost. Through the vision distance measurement scheme, only one road sign is required to deploy within in vision range of the robot, so that the method and the system need fewer road signs, thereby reducing deployment cost of indoor navigation.

The invention provides a method for barrier perception based on airborne binocular vision. The method comprises the following steps of setting a coordinate system of an airborne binocular vision camera, calculating a formula for conversion between the coordinate system and computer image coordinates of an image obtained by the airborne binocular vision camera according to the coordinate system, wherein the airborne binocular vision camera comprises a left camera and a right camera, extracting characteristic points of an image obtained by the airborne binocular vision camera, carrying out a characteristic vector description process on the characteristic points, carrying out stereo matching of left and right images according to characteristic vectors of the characteristic points to obtain preliminary matching point pairs, eliminating error matching in the preliminary matching point pairs to obtain final matching point pairs, creating a disparity map according to the final matching point pairs, and carrying out barrier perception according to the disparity map. The method for barrier perception based on airborne binocular vision has the advantages of strong adaptability, good instantaneity and good concealment performance.

Novel tools and techniques for monitoring railway track geometry. In one aspect, some such tools and techniques can determine a location of a platform along a railway, capture one or more images of the railway, and/or analyze the rail configuration at that point. In another aspect, some solutions might employ photogrammetric techniques to analyze the rail configuration and thereafter store data about the rail configuration, perhaps correlated with the location of the images, in a data store.

A wall area estimation system generates an estimated wall area measurement of a building based on the received roof measurements (e.g., those generated by, received from or found in a three dimensional model of the roof) and a reference distance. The reference distance is a measurement indicative of a distance between a reference point on the roof and a ground surface. This reference distance may be used to determine how for down to extend the walls of the building (e.g., to a ground level) when building a three dimensional digital model of the building to aid in generating wall area measurements. The resulting wall measurements, roof measurements, measurements of areas missing from the wall used to generate a wall estimate report, or a combined roof and wall estimate report including various different identifiers indicating the different features and measurements based on the three dimensional model.