1539results about "Photogrammetry/videogrammetry" patented technology

A system, apparatus and method of obtaining data from a 2D image in order to determine the 3D shape of objects appearing in said 2D image, said 2D image having distinguishable epipolar lines, said method comprising: (a) providing a predefined set of types of features, giving rise to feature types, each feature type being distinguishable according to a unique bi-dimensional formation; (b) providing a coded light pattern comprising multiple appearances of said feature types; (c) projecting said coded light pattern on said objects such that the distance between epipolar lines associated with substantially identical features is less than the distance between corresponding locations of two neighboring features; (d) capturing a 2D image of said objects having said projected coded light pattern projected thereupon, said 2D image comprising reflected said feature types; and (e) extracting: (i) said reflected feature types according to the unique bi-dimensional formations; and (ii) locations of said reflected feature types on respective said epipolar lines in said 2D image.

A noncontact optical three-dimensional measuring device that includes a first projector, a first camera, a second projector, and a second camera; a processor electrically coupled to the first projector, the first camera, the second projector, and the second camera; and computer readable media which, when executed by the processor, causes the first digital signal to be collected at a first time and the second digital signal to be collected at a second time different than the first time and determines three-dimensional coordinates of a first point on the surface based at least in part on the first digital signal and the first distance and determines three-dimensional coordinates of a second point on the surface based at least in part on the second digital signal and the second distance.

An integrated system generates a model of a three-dimensional object. A scanning laser device scans the three-dimensional object and generates a point cloud. The points of the point cloud each indicate a location of a corresponding point on a surface of the object. A first model is generated, responsive to the point cloud, that generates a first model representing constituent geometric shapes of the object. A data file is generated, responsive to the first model, that can be inputted to a computer-aided design system.

An automated system and/or method is disclosed for rapidly, accurately, and efficiently processing bulk three-dimensional digital image data of both path/corridor and area scenes to discriminate different structures or classifications of objects from within the image. The method first decomposes the three-dimensional digital imagery coordinate points into simple local structures and then extracts the globally complex structures from the local structures. The system and/or method incorporates procedures for sub-dividing the three-dimensional image data into rectilinear and/or ellipsoidal finite element cells, mathematically analyzing the contents (point coordinates) of each individual cell to classify/define the local structure, and extracting the globally complex structure or object from the image. The system and/or method applies accepted mathematical formulas to filter or classify large volumes of apparently random three-dimensional point coordinate spatial data into simpler structures and then to extract more globally complex objects generally encountered within the real world imagery scene being investigated.

The method according to the invention gene rates an aerial image mosaic viewing a larger area than a single image from a camera can provide using a combination of computer vision and photogrammetry. The aerial image mosaic is based on a set of images acquired from a camera. Selective matching and cross matching of consecutive and non-consecutive images, respectively, are performed and three dimensional motion and structure parameters are calculated and implemented on the model to check if the model is stable. Thereafter the parameters are globally optimised and based on these optimised parameters the serial image mosaic is generated. The set of images may be limited by removing old image data as new images are acquired. The method makes it is possible to establish images in near real time using a system of low complexity and small size, and using only image information.

An optical imaging system and associated methods for capturing images from an aircraft, such as a UAV. A camera unit on-board the aircraft is remotely controlled from an image control station. The image control station receives image data from the camera unit, and also delivers control signals for determining a viewing mode of the image.

A method and apparatus for performing wide area terrain mapping. The system comprises a digital elevation map (DEM) and mosaic generation engine that processes images that are simultaneously captured by an electro-optical camera (RGB camera) and a LIDAR sensor. The image data collected by both the camera and the LIDAR sensor are processed to create a geometrically accurate three-dimensional view of objects viewed from an aerial platform.

A navigation apparatus with image recognition, includes: an imaging section for obtaining a stereo image of a target spot; an inertial information detecting section for measuring an attitude angle of a body and an acceleration of the body; an image process calculating section for calculating a relative position of the body with respect to the target spot based on the stereo image and the attitude angle; and a navigation calculating section for calculating navigation information based on the attitude angle, the acceleration and the relative position.

Methods for classifying plants by remote sensing and image analysis technology are presented. These methods are useful for evaluating plants and for selecting plants for a plant breeding program which has as its goal to selectively alter phenotype. The methods combine the newer techniques of remote sensing technology to obtain indirect correlates of the traits of interest, with classical pedigree breeding strategies. Thermal and infrared reflectance measures of plant canopies are examples of energy values measured by remote sensing, used to indirectly predict the selected traits.

Novel solutions for position measurement, including without limitation tools and techniques that can be used for land surveying and in similar applications. One such tool is a greatly enhanced position measurement system that takes the form of a surveying rod with substantial independent functionality, which can be used with or without a total station or similar device.

A flying vehicle guiding system, which comprises a remotely controllable flying vehicle system, a surveying instrument being able to measure distance, angle, and track, and a ground base station for controlling a flight of the flying vehicle system based on measuring results by the surveying instrument, wherein the flying vehicle system has a retro-reflector as an object to be measured, wherein the surveying instrument has a non-prism surveying function for performing distance measurement and angle measurement without a retro-reflector, a prism surveying function for performing distance measurement and angle measurement with respect to the retro-reflector, and a tracking function for tracking the retro-reflector and for performing distance measurement and angle measurement, wherein the surveying instrument performs non-prism measurement on a scheduled flight area, the ground base station sets a safe flight area based on the results of the non-prism measurement, and controls so that the flying vehicle system flies in the safe flight area based on the results of tracking measurement by de surveying instrument.

A system for guided geospatial image capture, registration and 2D or 3D mosaicking, that employs automated imagery processing and cutting-edge airborne image mapping technologies for generation of geo-referenced Orthomosaics and Digital Elevation Models from aerial images obtained by UAVs and/or manned aircraft.

The scene matching method for raising navigation precision includes the following steps: 1. for the topographic scene matching module in combined navigation system to read in topographic data based on the digital topographic picture; 2. to search mapping point in the topographic picture based on the current geographic location the inertial navigation system obtains; 3. to intercept the reference map data from the topographic picture around the mapping point; 4. matching the measured map and the reference map; and 5. correcting inertial navigation with the matched result so as to raise the precision of inertial navigation system greatly. One simulating combined navigation system is also disclosed, which includes an aviation trace planning module, a flight control module, an aviation trace generator, an inertial navigation module, a topographic scene matching module matching module and an image displaying module. It has high locating precision, high autonomy and excellent man-computer operation interface.

An image registration method and apparatus for automatically registering images of different perspectives, and where a sensor image is registered with a more precise reference image such that the geocoding of the reference image can be transferred to the sensor image.

The invention provides a joint measurement method based on a laser radar and a binocular visible light camera to obtain accurate and dense three-dimensional information simply and efficiently. The joint measurement method comprises assuming that the laser radar is a camera device with a fixed internal reference; directly projecting three-dimensional point cloud data into a two-dimensional image, calculating rotation and translation relationships between the laser radar device and the binocular camera by using an image processing method and the matching between the two-dimensional images; creatively introducing an idea for obtaining a matrix norm and a matrix trace to solve a rotation matrix; finally fusing laser radar and binocular stereo vision point cloud data. The method not only can obtain an accurate position and attitude information, but also can reconstruct the special texture and feature information of a target surface, which has a high application value for spacecraft dockingand hostile satellite capture in the military field and workpiece measurement and unmanned driving in the civilian field.

A method and system are disclosed for creating a real-time, high accuracy mosaic from an aerial video image stream by applying orthorectification of each original video image frame using known ground control points, utilizing a photogrammetric model resolving the object image into pixilation, applying shading to the pixellation, and mosaicking the shaded pixilation of several orthorectified images into a mosaicked image where the mosaicked image is then scaled to the known original image dimensions.

The invention provides a composite three-dimensional point laser measurement system and a measurement method, comprising three-dimensional scanning and three-dimensional detection. Normal optical scanning is adopted so as to obtain the profile information of the article quickly and establish a three-dimensional model; motion trajectory planning is carried out by the profile data; and a point laser probe is guided to carry out more precise measurement so as to obtain the three-dimensional point cloud data of higher precision and higher quality. The three-dimensional non-contact detection to the characteristic position, appointed section line and integer of the workpiece is obtained further on the basis of comparing the point cloud and model data. The system and the method have the advantages that the non-contact measurement can obtain the point cloud of good quality and high precision, the article can be positioned freely, precise clamping devices are not needed, the measurement speed is quick, the process is automatic and the measured article has wide applicable range.

A method for quickly identifying lanes-change condition of object vehicle includes utilizing machine vision and radar to collect horizontal and longitudinal distances, relative speed and the same lane possibility between object vehicle and local vehicle, making comparison and quantization on said data collected each time, making compensation and tracking prediction on relevant data, calculating confidence of each vehicle by using two layers of neural network training to obtain object vehicle weight and setting object vehicle to be dangerous object once calculated confidence coefficient is over confidence threshold.

Embodiments of the invention relate to a method and apparatus to produce a flightplan for a sUAS. Embodiments can produce such a flightplan for a variety of environmental and/or geographical parameters. A specific embodiment produces an optimal flightplan based on one or more metrics and/or one or more assumptions or boundary conditions. Embodiments take in vehicle parameters and/or the properties of the sensor systems used for imaging, and compute a partial, or complete, flightplan. Such a flightplan can include altitude, airspeeds, flight paths encompassing the target area, and/or the direction and/or path to turn in-between flightlines. Embodiments can improve the flight planning procedure compared to a manual process, which can be completely dependent on the operator, to implement a partially, or totally, automated process. Specific embodiments can produce a flightplan that results in the optimal data collection path.

A method for tracking device orientation on a portable device is disclosed. The method comprises initializing a device orientation to a sensor orientation, wherein the sensor orientation is based on information from an inertial measurement unit (IMU) sensor. It also comprises initiating visual tracking using a camera on the portable device and capturing a frame. Next, it comprises determining a plurality of visual features in the frame and matching the frame to a keyframe, wherein capture of the keyframe precedes capture of the frame. Subsequently, it comprises computing a rotation amount between the frame and the keyframe. Responsive to a determination that a rotational distance between the frame and the keyframe exceeds a predetermined threshold, promoting the frame to a keyframe status and adding it to a first orientation map and adjusting the frame with all prior captured keyframes.

A method of acquiring data uses multiple sensors in an aircraft. The method includes the steps of: (a) turning ON a DIAL sensor to detect a target of interest during a first flight pass over a region of interest (ROI), wherein the target of interest is a gas or oil pipeline leak; (b) detecting the target of interest using the DIAL sensor; and (c) storing location of the detected target in a look up table (LUT). The method also includes the steps of: (d) during a second flight pass over the ROI, triggering another sensor to turn ON at or about the location stored in the LUT; and (e) confirming presence of the target of interest using both ON-sensors. If necessary, a third flight pass over the ROI is conducted and yet another sensor is triggered to turn ON at or about the location stored in the LUT. Presence of the target of interest is confirmed using all three ON-sensors.

A three-dimensional rebuilding method based on laser and camera data fusion is characterized in that the rebuilding method comprises the following steps: (1) a C++ language is adopted to compile a laser data automatic collecting platform based on a radar principle; (2) a rotation matrix R and a translation vector T are arranged between a camera coordinate system and a laser coordinate system; (3) a motion object is extracted and subdivided by utilizing an optical flow field region merging algorithm, thus further subdividing the point cloud corresponding to the motion object; and (4) guarantee of point cloud and image texture on the precise positioning is provided for the three-dimensional image texture mapping, thus realizing the three-dimensional rebuilding system based on data fusion. The three-dimensional rebuilding method has the advantages of quickly and automatically collecting and processing laser data, quickly completing the external labeling of the laser and CCD, effectively extracting and subdividing effective point clouds of the object in complex environment and exactly completing the three-dimensional rebuilding of the laser and CCD data of the object.

The invention discloses a power line patrolling method which concretely comprises the following steps that: an unmanned aerial vehicle equipped with a photographing device and a navigation system is used for automatically recording the real-time image data of the power line according to a preset flight course and feeding back the data information of the flight point position at real time; and a suspected fault point on the power line is confirmed according to the analysis result of the image data and the corresponding flight point position data. With the power line patrolling method disclosed by the invention, the unmanned aerial vehicle can go deep into all areas of the power line to patrol without the limitations from complex landforms and conditions of a disaster area, so manpower and material resources can be greatly saved, the working efficiency of patrolling the power line is greatly improved and the danger level of manual operation is reduced.

The invention relates to a vehicle anti-impact alarm method and relative system, for alarming driver to avoid impact and accidence. The output of inverter power and one end of relay is connected with an output signal interface of an intelligent camera, the picture information collecting module, vehicle character extracting module, information analyzing module, vehicle position tracking module, ranging speed measuring module and anti-impact alarm module are embedded in the chip of the camera, while the intelligent camera via a mounting support is fixed in the front windscreen glass of cabin, and said six modules should started in serially to realize the alarm method.

Systems and methods are disclosed for generating a digital flight path within complex mission boundaries. In particular, in one or more embodiments, systems and methods generate flight legs that traverse a target site within mission boundaries. Moreover, one or more embodiments include systems and methods that utilize linking algorithms to connect the generated flight legs into a flight path. Moreover, one or more embodiments include systems and methods that generate a mission plan based on the flight path. In one or more embodiments, the generated mission plan enables a UAV to traverse a flight area within mission boundaries and capture aerial images with regard to the target site. Furthermore, in one or more embodiments, systems and methods capture digital aerial images of vertical surfaces of a structure by generating a reference surface and flight legs corresponding to the reference surface.

The present invention is in-situ visual measurement system calibrating equipment and process. The calibrating equipment is 3D coordinate measuring system and stereo target, and the stereo target set inside the work range of the 3D coordinate measuring system consists of base plate as well as sensor calibrating target and system measured target, which are standard balls, set on two sides of the base plate. The 3D coordinate measuring system may be an industrial theodolite measurement system or a laser tracking instrument. The calibrating process includes calibrating the stereo target in the coordinate measuring system, acquiring the image of the sensor calibrating target, obtaining the conversion relation between the system measured target and the sensor calibrating target via coordination conversion, and other steps. The present invention can realize the in-situ measurement element calibration and overall system calibration.

The invention discloses a multi-angle unmanned aerial survey system. The multi-angle unmanned aerial survey system is provided with a six-rotor-wing unmanned aerial vehicle, and each multi-view-angle inclined camera composed of five camera lenses is carried on the six-rotor-wing unmanned aerial vehicle. Each multi-view-angle inclined camera comprises a shooting unit, a controlling unit and a hanging unit. The six-rotor-wing unmanned aerial vehicle comprises an unmanned aerial vehicle flying platform system, a GPS, a flying controlling system, a remote sensing shooting system, a ground controlling system and a signal transmitting system. Ground images can be collected at the same time at multiple angles, in this way, the defect that according to a traditional aerial photography technology, shooting can be performed only at a vertical angle is overcome, the actual conditions of a ground feature can be reflected more really, and the defects in orthophotography are overcome; through integrating POS data, DSM data, vectors and others, a three-dimensional model establishing technology based on image intensive matching is established, a digital city model is rapidly and efficiently established, and therefore the working cost for three-dimensional model establishing is greatly lowered.

The system relates to an indoor positioning method, an indoor positioning apparatus and an indoor positioning system. The method comprises the steps of taking an indoor picture; acquiring characteristic information of an image of an LED light source according to the picture; taking at least preset number of communication images of the LED light source at a speed of a preset frame to acquire identification information uniquely corresponding to the LED light source; determining a position of a picture-taking spot in relative to the LED light source according to the characteristic information corresponding to the LED light source and an image-forming principle; determining an indoor position of the LED light source according to the identification information of the LED light source and an indoor layout diagram; and acquiring the indoor position of the picture-taking spot according to the indoor position of the LED light source and the position of the picture-taking spot in relative to the LED light source. Electromagnetic interference can be prevented because the indoor positioning method is in no need of installing wireless signal transmitting device. The indoor positioning system for realizing the indoor positioning method is simpler in structure and lower in cost.

The invention discloses an underground space high-precision positioning method based on laser scanning and sequence encoded graphics. Aiming at the rapid high-precision positioning, orientation, altitude determination and navigation of moving targets in a GPS signal-free underground well of a mine, the method can make the breakthrough in key directions from the design, decoding and optimized layout of the encoded graphics, the economical and rapid acquisition of a fine and accurate road network-a three-dimensional well network space model consisting of underground tunnels of mine, a high-precision positioning algorithm of the moving targets in well restraint spaces (precise resolving of position, direction, altitude parameters), a three-dimensional well network space matching algorithm, athree-dimensional navigation technology to a final navigation platform and terminal control system, and the like, thus key technologies for underground rapid high-precision positioning and navigationas well as software and hardware systems are formed to eventually achieve the leaping-development of a underground unmanned mining technology for the mine in our country. Besides, the method disclosed in the invention can also meet the application demands of large urban underground space, deep and long traffic tunnel, large grotto, large building interior, large overpass and subway space on the rapid high-precision positioning and navigation of the moving targets, thereby pushing forward the development of the underground space positioning technology in our country.

A system for capturing aerial images, the system comprising at least one camera unit, the camera unit comprising a plurality of steerable detail camera modules, each steerable detail camera module comprising a detail camera and a beam-steering mechanism in the optical path of the camera whereby the pointing direction of the camera is time-multiplexed to provide a wider effective field of view.