66 results about "3d tracking" patented technology

Disclosed is a method and system for efficiently and accurately tracking three-dimensional (3D) human motion from a two-dimensional (2D) video sequence, even when self-occlusion, motion blur and large limb movements occur. In an offline learning stage, 3D motion capture data is acquired and a prediction model is generated based on the learned motions. A mixture of factor analyzers acts as local dimensionality reducers. Clusters of factor analyzers formed within a globally coordinated low-dimensional space makes it possible to perform multiple hypothesis tracking based on the distribution modes. In the online tracking stage, 3D tracking is performed without requiring any special equipment, clothing, or markers. Instead, motion is tracked in the dimensionality reduced state based on a monocular video sequence.

Methods and apparatus are described for monocular 3D human pose estimation and tracking, which are able to recover poses of people in realistic street conditions captured using a monocular, potentially moving camera. Embodiments of the present invention provide a three-stage process involving estimating (10, 60, 110) a 3D pose of each of the multiple objects using an output of 2D tracking-by detection (50) and 2D viewpoint estimation (46). The present invention provides a sound Bayesian formulation to address the above problems. The present invention can provide articulated 3D tracking in realistic street conditions.

The present invention provides methods and apparatus for people detection and 2D pose estimation combined with a dynamic motion prior. The present invention provides not only 2D pose estimation for people in side views, it goes beyond this by estimating poses in 3D from multiple viewpoints. The estimation of poses is done in monocular images, and does not require stereo images. Also the present invention does not require detection of characteristic poses of people.

A bracket for use on an ultrasound transducer to releasably mount at least one 3D tracking sensor on the transducer. Each sensor has a pair of axially aligned pins projecting outward from its body. The bracket includes at least one socket having a pair of spaced-apart wall portions, each of which includes a slot arranged to receive a respective one of the pins of the sensor when the sensor is in a first position. From this position the sensor's body can be rotated to a second position, whereupon the spaced apart wall portions releasably engage (snap-fit about) a portion of the body of the sensor to deter the accidental displacement of the sensor with respect to the transducer.

An object recognition system is described that incorporates swarming classifiers. The swarming classifiers comprise a plurality of software agents configured to operate as a cooperative swarm to classify an object in a domain as seen from multiple view points. Each agent is a complete classifier and is assigned an initial velocity vector to explore a solution space for object solutions. Each agent is configured to perform an iteration, the iteration being a search in the solution space for a potential solution optima where each agent keeps track of its coordinates in multi-dimensional space that are associated with an observed best solution (pbest) that the agent has identified, and a global best solution (gbest) where the gbest is used to store the best location among all agents. Each velocity vector changes towards pbest and gbest, allowing the cooperative swarm to concentrate on the vicinity of the object and classify the object.

The present invention relates to a pixel detector (10), comprising a semiconductor sensor layer (12), in which charges can be generated upon interaction with particles to be detected. The semiconductor layer defines an X-Y-plane and has a thickness extending in Z-direction. The detector further comprises a read-out electronics layer (14) connected to said semiconductor layer (12), said read-out electronics layer (14) comprising an array of read-out circuits (20) for detecting signals indicative of charges generated in a corresponding volume of said semiconductor sensor layer (12). The neighbouring read-out circuits (20) are connected by a relative timing circuit configured to determine time difference information between signals detected at said neighbouring read-out circuits (20). The time difference information is indicative of a difference in the Z-components of the locations of charge generations in the corresponding neighbouring sensor volumes caused by a particle trajectory that is inclined with respect to the X-Y-plane.

A lithotripsy system capable of 3D tracking monitors the acoustic reflection from the stone in order to focus the shock wave on the stone regardless of shock wave displacement or stone movement. The tracking and focusing is based on a phased array concept, allowing the lithotripsy head to remain stationary and well coupled to the body. An alternate shock wave steering is based on refraction by a variable liquid wedge.

Lead Tracking of Implantable Cardioverter-Defibrillator and Cardiac Resynchronization Therapy Devices improve upon the process of implantation of ICD-CRT devices, placing their leads, and improving the information fed back to the device and/or clinician. Tracking of the placement of the leads during implantation is accomplished along with monitoring the leads once implanted. Benefits include reducing the risk and complication rate, simplifying implantation procedure, and enabling the extraction of vital data not previously available. Leads are tracked to at least minimize the need to use fluoroscopy. Three dimensional tracking (10) is employed to facilitate obtaining of data that allows the surgeon to better visualize lead insertion and placement. Placement of the leads during a procedure requires use of an external tracking component along with means and method for tracking the implantable leads. Transmitting antennas (10, 110) are provided, equal in number to the number of degrees of freedom of tracking required. A link (50) between the sensor (70) and the computation unit (40) can be wired or wireless. Once leads are implanted, heart wall motion must be monitored via the tracking of the leads within a clinical or home environment. Such tracking of the leads may be accomplished in real time.

The present invention relates to the field of the optical 3D contour measuring technology. Two video cameras are used to collect the image of some objects and the two CCD cameras are in some certain distance, the 3D measurement is performed based on double-eye stereo visual principle. The measured object is marked with the geographic shapes in different color and in specific range order so that matching point can be found out in the images the two CCD cameras obtain. The position of some point in the 3D space is calculated according to the parallex of a matching point in two images. It can beused to track moving human body and has wide application in 3D motion picture production, selection and training of athlete, etc.

A lithotripsy system capable of 3D tracking monitors the acoustic reflection from the stone in order to focus the shock wave on the stone regardless of shock wave displacement or stone movement. The tracking and focusing is based on a phased array concept, allowing the lithotripsy head to remain stationary and well coupled to the body.

The virtual scalpel unit includes micro controller, scalpel, force transferring device connecting the scalpel and proportional electromagnet for transmitting the drive force from the proportional electromagnet, repositioning spring connected across the force transferring device, force sensor on the scalpel handle for detecting the upward force of the scalpel, and 3D tracking device for detecting the position and posture of the scalpel. The 3D tracking device and the force feeding back mechanism are small and light and has no influence on the action of the operator. The present invention maybe used in virtual operation.

Systems and methods for performing behavioral detection using three-dimensional tracking and machine learning in accordance with various embodiments of the invention are disclosed. One embodiment of the invention involves a the classification application that directs a microprocessor to: identify at least a primary subject interacting with a secondary subject within a sequence of frames of image data including depth information; determine poses of the subjects; extract a set of parameters describing the poses and movement of at least the primary and secondary subjects; and detect a social behavior performed by at least the primary subject and involving at least the second subject using a classifier trained to discriminate between a plurality of social behaviors based upon the set of parameters describing poses and movement.

A method and apparatus are used to compare in real-time an intended radiation treatment plan with a delivered plan. Markers are arranged, on a subject receiving radiation, at three-dimensional (3D) positions between a two dimensional radiation detector and a radiation source and are used to reconstruct the actual position of a high dose rate (HDR) source in three-dimensional (3D) space. The detected position is compared with the intended radiation path of the treatment plan. Adjustments can be made to the treatment plan if the detected position and the intended path do not correspond.

A centering and locating method for machining the end face of the segment of steel cable tower includes such steps as using numeral controlled hydraulic locating system to support said segment and locate it to a machining position, centering the first end face by using 3D tracking measurer to measure machine and 3 laser markers for determining the position relation between machine and workpiece and regulating and locking the position of workpiece, centering the second end face by transporting the segment to machining position, creating the coordinate system of machine, measuring and processing the machined first end face, and checking its position in said coordinate system.

The invention discloses a 3D target detection and tracking method based on a camera and a laser radar. The method comprises the following steps: firstly, performing target detection on an image acquired by a camera to obtain a 2D detection frame and assign a number; meanwhile, carrying out feature point detection, descriptor extraction and feature point matching on the image; then, performing ground segmentation on the point cloud data, and projecting the non-ground point cloud into a corresponding image according to the external parameters of the laser radar and the camera; then, screening and clustering the point clouds according to the 2D detection frame in the image to obtain an object 3D detection frame; and finally, according to the matched feature points, performing matching association on the detection frames of the front and rear frames of images, and replacing numbers to realize 3D tracking of the object. According to the method, the advantages of the laser radar and the camera data are fully fused, the defects that the laser radar classification capability is weak and the camera lacks depth information are overcome, 3D target tracking of the object is realized, and the method can be used for unmanned 3D target detection and tracking tasks.