163 results about "Image tracing" patented technology

Apparatus is described for imaging a portion of a body of a subject that moves as a result of cyclic activity of a body system of the subject and that also undergoes additional motion. An imaging device acquires a plurality of image frames of the portion. A sensor senses a phase of the cyclic activity of the body system. A control unit generates a stabilized set of image frames of the portion by identifying a given phase of the cyclic activity, and outputting a set of the image frames corresponding to image frames of the portion acquired during the given phase, and by image tracking at least the set of image frames to reduce imaged motion of the portion associated with the additional motion. A display displays the stabilized set of image frames of the portion. Other embodiments are also described.

A surgical navigation system has a computer with a memory and display connected to a surgical instrument or pointer and position tracking system, so that the location and orientation of the pointer are tracked in real time and conveyed to the computer. The computer memory is loaded with data from an MRI, CT, or other volumetric scan of a patient, and this data is utilized to dynamically display 3-dimensional perspective images in real time of the patient's anatomy from the viewpoint of the pointer. The images are segmented and displayed in color to highlight selected anatomical features and to allow the viewer to see beyond obscuring surfaces and structures. The displayed image tracks the movement of the instrument during surgical procedures. The instrument may include an imaging device such as an endoscope or ultrasound transducer, and the system displays also the image for this device from the same viewpoint, and enables the two images to be fused so that a combined image is displayed. The system is adapted for easy and convenient operating room use during surgical procedures.

Camera registration and / or sensor data is updated during a live event by determining a difference between an estimated position of an object in an image and an actual position of the object in the image. The estimated position of the object in the image can be based on an estimated position of the object in the live event, e.g., based on GPS or other location data. This position is transformed to the image space using current camera registration and / or sensor data. The actual position of the object in the image can be determined by template matching which accounts for an orientation of the object, a shape of the object, an estimated size of the representation of the object in the image, and the estimated position of the object in the image. The updated camera registration / sensor data can be used in detecting an object in a subsequent image.

The present invention relates to a system and method for processing a video input signal providing for tracking a selected portion in a predefined audiovisual presentation and integrating selected user images into the selected portion of the predefined audiovisual presentation.

A surgical navigation system has a computer with a memory and display connected to a surgical instrument or pointer and position tracking system, so that the location and orientation of the pointer are tracked in real time and conveyed to the computer. The computer memory is loaded with data from an MRI, CT, or other volumetric scan of a patient, and this data is utilized to dynamically display 3-dimensional perspective images in real time of the patient's anatomy from the viewpoint of the pointer. The images are segmented and displayed in color to highlight selected anatomical features and to allow the viewer to see beyond obscuring surfaces and structures. The displayed image tracks the movement of the instrument during surgical procedures. The instrument may include an imaging device such as an endoscope or ultrasound transducer, and the system displays also the image for this device from the same viewpoint, and enables the two images to be fused so that a combined image is displayed. The system is adapted for easy and convenient operating room use during surgical procedures.

A method for identifying facial features comprises following steps: An image tracing step is performed to receive video data of a plurality of face images and to obtain a real-time background image from the video data by a video tracing technique.A data calculating step is performed to calculate a video data difference between a current face image and the real-time background image.A process setting step is performed to set an iteration number according to the video data difference.A coordinate requesting step is performed to obtain facial feature coordinates of a previous face image,the previous one of the current face image,serving as initial facial feature coordinates.A localization step is performed to obtain current facial feature coordinates of the current image by conducting an iterative calculation according to the iteration number and based on the initial facial feature coordinates.

An imaging device for recognition (100) includes an image pickup unit (101) that sequentially generates a plurality of images by shooting an object, a face recognition unit (105) that recognizes, in each of the plurality of images, an object region in which the object is located in the image, a face tracking unit (106) that tracks the object region across the plurality of images, an area calculation unit (109) that calculates an area of the object region, and an exposure control unit (102) that sets a first exposure time for the image pickup unit (101) in the case where the area is smaller than a first threshold, and sets a second exposure time longer than the first exposure time in the case where the area is equal to or larger than the first threshold.

The invention discloses a general video flexibility measurement system insensitive to ambient light. The general video flexibility measurement system comprises a black-and-white industrial camera (1), an industrial fixed-focus lens (2), an electronic theodolite (3), a distance measurement machine (4), a tripod (4), a high brightness monochromatic LED target (6), a narrow bandpass filter sheet (7) corresponding to monochromatic light source wavelength and a computer (8); a monochromatic LED target is installed on a tested point; a video flexometer with the narrow bandpass filter sheet installed on the lens is utilized to record the video image of the LED target in real time; and flexible data is obtained in real time through an image tracking algorithm on the basis of image gray correlation matching or characteristic points extraction. The general video flexibility measurement system is insensitive to the change of ambient light, can realize high precision measurement for displacement or flexibility at daytime or nigh, can calculate multiple object positions in one image, and realizes real-time dynamic measurement of displacement or flexibility of multiple detected points.

Imaging systems in which an undedicated optical component—i.e., a component that would be present in the system even in the absence of image stabilization—is configured to undergo corrective motion and / or other correction of image data, and thus to function as a stabilization component. The stabilization component may be a mirror and / or a lens, and a positioner may be provided to tilt, rotate, and / or otherwise precisely adjust the position and orientation of the stabilization component to improve image resolution, compensate for platform motions such as platform vibration, and / or improve image tracking. Because an undedicated optical component functions as the stabilization component, the stabilization occurs upstream, rather than downstream, from separation (if any) of the incoming image data into two or more beams. As a result, only one stabilization component is required regardless of whether the system is configured to split the image data into multiple data channels, and imaging systems as described herein therefore may be particularly well-suited for integration into a shared-aperture imaging system. In some embodiments, the coefficients of thermal expansion of selected system components—including optics, optical support structures, and / or positioners—may be substantially the same or closely matched.

The invention discloses an image tracking system and an image tracking algorithm for a double-cylinder multi-FOV (field of view) sun photometer. The image tracking system for the double-cylinder multi-FOV sun photometer comprises an image forming photic cylinder, a CCD (charged coupled device) image sensor, an image capturing module, a movement control module, an industrial personal computer, and a rotary table. The movement control module is controlled by the industrial personal computer to enable the rotary table to correctly return to an initial position in two degrees of freedom in horizontal and elevated directions. After a broad-tracking command is issued by a user via the industrial personal computer, the rotary table is controlled by the movement control module to enable the image forming photic cylinder to align to the sun, parallel sunlight forms an image on a target surface of the CCD via the image forming photic cylinder, the image capturing module is commanded, by the industrial personal computer via a procedure, to capture a sun image output by the CCD image sensor and transmits the sun image to the industrial personal computer, then an accurate-tracking command is issued by the industrial personal computer so that the movement control module can control the rotary table to accurately track the sun, and the tracking accuracy is higher than one arc-second. By the aid of the image tracking system and the image tracking algorithm for the double-cylinder multi-FOV sun photometer, the limitation problem that a conventional sun photometer, in the presence of uneven clouds, cannot accurately track the sun by utilizing distribution of four-quadrant light intensity is solved.

Methods and apparatus are provided for selecting a touchdown point for a vertical takeoff and landing aircraft. The eye movements of a user are tracked relative to an image being rendered on a display screen. An updated touchdown point location is determined from the tracked eye movements, and an updated touchdown point is rendered at the updated touchdown point location on the display screen.

The invention discloses a self-adaptive dead zone inverse model generating device of a visual servo mechanical arm system. The visual servo mechanical arm system is composed of a visual servo controller, a visual module, a motion control module, a driving module, a six-degree-of-freedom mechanical arm, a torque feedback module, a speed and position collecting module and a detecting module. The self-adaptive dead zone inverse model generating device of the visual servo controller is used for eliminating dead zone non-linear constraint and comprises a dead zone inverse model module, a self-adapting module and an operating module, wherein the dead zone inverse model module is used for structuring a smooth dead zone nonlinear inverse model; the self-adapting module adjusts estimated dead zone parameters through self-adaptive laws and transmits the parameters into the dead zone inverse model module to change the parameters of the inverse model; by means of the signal communication of the modules, a closed-loop control system can be formed inside the visual servo mechanical arm system. The self-adaptive dead zone inverse model generating device of the visual servo mechanical arm system can effectively eliminate the influence of the dead zone nonlinear restraint and achieve high image tracing precision.

An image tracking device and an image tracking method thereof are provided. The image tracking device includes an image capture interface, a storage means, and a processor means. The storage means has a multi-dimensional storage space for storing a plurality of first images, each dimension of the multi-dimensional storage space being corresponding to a feature-related variance of a multi-dimensional variance. The processor means is configured to execute the following operations: marking a second image in the picture frame; calculating a multi-dimensional variance between the second image and each of the first images separately; determining whether the second image contains the object according to the multi-dimensional variance calculated; and if the second image is determined as one containing the object, storing the second image as one of the first images, in a specific subspace of the multi-dimensional storage space according to the multi-dimensional variance calculated.

The invention relates to a digital intelligent alarming linkage system. The invention solves the technology problem that: providing a digital intelligent alarming linkage system which can realize the smooth linking, fluent cooperation, integral dispatching of alarming-word recording-voice warning-image tracing-point locating. The digital intelligent alarming linkage system includes a synthesis alarm state processing device, network databank, uniform dispatching platform, audio frequency image supervising device, GIS geology information device. The invention can be applied to police supervising field, especially the 110 alarm receiving and processing arrangement system, at the same time, it can be extended to path supervising, electric supervising, environment supervising, power supervising.

A method for implementing complementation and fusion of image tracking measurement data and radar measurement data includes the steps of firstly, conducting demodulation to obtain position information of a target and driving an image tracking system to aim at the target when receiving target data through radar from a distance; secondly, pulling the target to an effective area of a screen, collecting video image information to conduct image tracking measurement, and perfecting a command and guide map; thirdly, assisting in distance measurement judgment through a coaxial laser distance measurement instrument while conducting image tracking measurement, and conducting demodulation to obtain the accurate position information of the target; fourthly, replacing drive data of the command and guide map with identified high-accuracy data after data accuracy verification and judgment are conducted on radar detection target parameters, extrapolation data images and tracking measurement data; fifthly, using an optimized secondary radar signal for guiding an aircraft monitoring, guiding and tracking system to more accurately aim at the target, and expanding the action distance of the aircraft monitoring, guiding and tracking system. By means of the method, fake tracks of the target in near-field flight can be identified and processed, and blind area coverage can be achieved.

A Pseudo Bipolar Junction Transistor(Pseudo-BJT) based retinal focal-plane sensing system is an instant image sensing and front-end processing system with the advantages of high dynamic range and instant image processing. In addition, the system proposes a Pseudo-BJT based retinal focal-plane sensor with adaptive current Schmitt trigger and smoothing network for applying a new Pseudo-BJT circuit structure to mimic parts of functions of the cells in the outer plexiform layer of the real retina. It is suitable to resolve the existing technical drawbacks performing major functions in optical image detecting circuits, such as image recognition, image tracing, robot vision, bar-code / character readers, etc.

A real-time, semi-automatic method for discriminant track initialization in thermal imagery is very critical for tracking since it determines what to track for the tracker. Therefore, any insignificant or false information may result in redundant features or deceptive appearance that can cause premature track losses. To achieve long-term tracking, a real-time, semi-automatic track initialization methodology for images is proposed which takes a single image coordinate as input, then generates target bounding box for the most salient segment. The present invention is designed for real-time applications in which erroneous user input is unavoidable. Therefore, error compensation capability of present invention both introduces many practical advantageous together with performance boost. Low computational cost and requirement of only a point coordinate as input in the vicinity of the target make this approach preferable in real-time tracking applications.

A method for converting digital images of an actuated breast into an accurate description of breast surface motion from a digital image-based elasto-tomography system comprises the steps of artificially placing a high density of fiducial markers on the breast surface, whereby the fiducial markers have different qualities and are placed in different proportions according to their quality; utilizing motion invariant properties of the fiducial markers to form a global motion invariant signature; tracking the markers on the actuated breast surface from image to image in each digital camera using the global motion invariant signature; and using the cameras calibration to measure the breast surface motion.

The invention relates to the field of image identification and tracking, and provides an AR augmented reality) algorithm based on real-time tracking. The AR algorithm comprises the following steps of: setting a target image; computing a feature code of the target image; setting a maximum tracking point number; obtaining a frame of novel image, and judging whether the novel image has a target tracking point or not, and continuing the tracking if the novel image has the target tracking point; otherwise, computing the target tracking point; computing novel image tracking data; computing a mapping quadrilateral; supplementing a tacking point; updating target tracking image data; and synthesizing an image and displaying the synthesized image on a screen. The AR algorithm is suitable for effective tracking of the target tracking image, so that real-time performance and reliability of tracking are strengthened, and the computing accuracy is improved.

The invention designs an image tracking method based on multi-neighborhood-aided two-dimensional ultrasonic deformed microstructure, which comprises the steps as follows: a two-dimensional ultrasonic cardiogram of a tested heart object is collected under a high frame frequency condition and used for offline analysis firstly; then any visible image is used as a selected initial frame of a region of interest (ROI) so that the ROI includes cardiac muscular tissues, simultaneously the interferences of grey scale signals is eliminated; after the ROI of the initial frame on an initial image I is completely selected, the original ROI is set as a center; moreover, the ROI and eight areas coating the surrounding of the original ROI and having same sizes are used as a new searching source region, the tracking vectors of all subregions with the sizes the same as the size of the original ROI in the searching area are traversed through an SAD (Sum of Absolute Differences) arithmetic; and weighted average is implemented on each tracking vector finally, thus obtaining the tracking result of the original ROI. Compared with the traditional SAD tracking method, the neighborhood tracking result of the ROI is sufficiently considered; therefore, the image tracking method based on multi-neighborhood-aided two-dimensional ultrasonic deformed microstructure has excellent noise immunity, and is especially beneficial for movement estimation and parameter calculation on movement issues.

The invention discloses a binocular AR (Augmented Reality) head-mounted device information display method. On the premise of presetting mapping relations fc-s and fd-i in the head-mounted device, the position of a target object on an image photographed by a camera is acquired in real time through an image tracking method, the position is mapped to a screen coordinate system of the head-mounted device, and a left image / right image display position is calculated; and then, through a monocular vision distance measurement method, a camera imaging ratio is used for calculating the distance between the target object and the camera in real time, the distance between the left image and the right image is thus calculated, and the display position of an image at the other side is further calculated. Correspondingly, the invention also provides a binocular AR head-mounted device information display method and an augmented reality information display system. The method of the invention is high in reliability and low in cost. The traditional field depth adjustment starts from changing the image distance of an optical component, the traditional thinking is broken, the optical device structure is not changed, field depth adjustment is realized through calculating the left image / right image display position, creativity is realized, and compared with a method of changing an optical focal length, the method is more practical.

The embodiment of the invention discloses a trajectory tracking and three-dimensional reconstruction method, system and device, relates to the technical field of image processing, and solves the problems of poor trajectory tracking stability and low precision in the prior art and low accuracy of a three-dimensional scene reconstruction effect in the prior art. According to the specific scheme, themethod comprises the steps of using a trajectory tracking and three-dimensional reconstruction device for extracting a first view image frame corner point and a second view image frame corner point of a target acquired by a binocular camera; generating a three-dimensional point cloud and a key frame; and tracking the front and rear frames of images by using a multi-plane fitting-based mode to continuously update the three-dimensional point cloud and the key frame set, solving a camera pose, obtaining a dense depth map according to the camera pose and the three-dimensional point cloud, performing confidence judgment on the depth map, and finally obtaining a three-dimensional reconstruction model of the scene. The embodiment of the invention is used in the process of image tracking and three-dimensional scene reconstruction.

This invention relates to visual frequency speed testing method, which comprises the following steps: testing movement, track description; even speed computer, super speed judging and car flow statistics and is based on movement test technique according to image process technique, image trace technique and computer technique. This invention uses hardware platform as cameral machine and computer hardware to realize this invention widely used in road automotive speed testing and other situations.

An image tracking device comprises an image pickup device that takes an image formed by an imaging optical system and outputs image information, a focus detector that detects a focusing state of the imaging optical system, a recognizer that stores reference information related to a reference image and recognizes a position of an image corresponding to the reference information, within an image corresponding to the image information, and a controller that performs first focus detection in which the focusing state is detected by the focus detector, before the position is recognized by the recognizer, and second focus detection in which the focusing state is detected for the position that has been recognized by the recognizer.

The invention provides a multi-point touch interaction splicing method for realizing ultra-large size and ultra-high resolution display. The method comprises the following steps: (1) constructing a large-scale spliced touch screen; (2) fusing multi-projection images, wherein each splicing unit corresponds to a projector, and the images of a plurality of projectors are fused into a high-resolution large image through projection fusing software; (3) splicing a plurality of sensor images, wherein an infrared sensor is placed behind each splicing unit for capturing reflected light, the images of the sensors are spliced into an ultra-wide viewing field image by adopting image tracing software, and a large splicing screen is captured; (4) tracing contacts; (5) touching to response; (6) calibrating split screens. According to the method, the ultra-large size and ultrahigh resolution display is realized through screen splicing and multi-image fusion and splicing, so as to meet the requirements of people on the visible size and display resolution of a displayed image.

The invention provides an anti-interference contour tracing method based on prior model constraint. The method comprises the following steps: establishing an initial prior model of a video image to be traced as a target model by using an SLIC algorithm and a mean shift clustering algorithm; carrying out level set evolution on a current frame of image by target feature distribution of the target model; determining a target region of the current frame of image by the SLIC algorithm and the mean shift clustering algorithm; and updating the prior model according to an occlusion condition of the current image. By the method, interference of non-target information in the image in an image tracing process is removed, so that description of the prior model to a target is accurate. Accuracy of the model is guaranteed.

The embodiment of the invention provides an image tracking method and device. The method comprises the steps that a smart bracelet detects a radio frequency signal of a radio frequency chip on a current page of a smart book in real time and sends the radio frequency signal to a voice broadcast terminal; an image tracker tracks and photographs an eyeball image of a reader in real time and sends theeyeball image to the voice broadcast terminal; the voice broadcast terminal obtains book content currently read by the reader based on the radio frequency signal and the eyeball image, and carries out voice broadcast on the currently read book content according to a preset rule. The image tracking method and device provided by the invention are convenient for use; the book content currently readby a child can be automatically analyzed without any operation, the automatic voice broadcast is carried out on the book content, a learning effect is greatly improved, the enjoyment is high, and thepreschool enlightenment education is facilitated.

A ray tracing method of two-dimensional images in space is used to simulate three-dimensional space in two-dimensional space. The three-dimensional space has five faces of a first plane, a second plane intersects with the first plane, a third plane, a fourth plane and a fifth plane which is parallel to the first plane. The method comprises selecting one area on the first plane to fill the actual color of the plane to serve as a natural color layer, superposing a grey scale layer on the natural color layer of the first plane, superposing an image tracing layer on the grey scale layer of the first plane, superposing an illumination layer on the image tracing layer of the first plane, and the second plane, the third plane, the fourth plane and the fifth plane are superposed in the order of the first plane processing, then jointing the corresponding layers of all planes. The invention can realistically display three-dimensional images in two-dimensional space.