612 results about "Fiducial points" patented technology

This invention involves apparatus and methods for relating image scan data of a patient's anatomy from an imaging scanner to a device attached to said patient's anatomy or to an apparatus located nearby said patient's anatomy. In one embodiment it includes identification of fiducial points or markers on or near the patient's anatomy in the image scan data, and subsequently relating these fiducial points to reference points or structures connected to an apparatus attached to or nearby the patient's body. Such an apparatus might be a surgical head clamp or stereotactic frame or arc which has been attached to the patient's head at the time of surgery. A mapping is made between the coordinate frame data of the scan image to the coordinate reference frame of the patient attachment means or external apparatus by physically referencing the fiducial points to the patient attachment means or external apparatus. In one embodiment, such registration can be in the form of distance or coordinate measurements between the fiducial points on the patient's body and the reference points on the external apparatus. Applications are given in the field of frameless stereotaxy, radiosurgery, and stereotactic frame application.

A method for registration of cardiac image data in an interventional system includes inserting a first plurality of fiducial points on an acquired 3D anatomical image and exporting the 3D anatomical image, with the first plurality of inserted fiducial points thereon, to an interventional system. A second plurality of fiducial points is inserted on the exported 3D anatomical image using the interventional system, and the first and said second plurality of fiducial points are aligned to one another so as to register the exported 3D anatomical image with the interventional system.

A method is provided for localizing parts of an object in an image by training local detectors using labeled image exemplars with fiducial points corresponding to parts within the image. Each local detector generates a detector score corresponding to the likelihood that a desired part is located at a given location within the image exemplar. A non-parametric global model of the locations of the fiducial points is generated for each of at least a portion of the image exemplars. An input image is analyzed using the trained local detectors, and a Bayesian objective function is derived for the input image from the non-parametric model and detector scores. The Bayesian objective function is optimized using a consensus of global models, and an output is generated with locations of the fiducial points labeled within the object in the image.

The present invention provides a method and system for characterizing one beat of a patient's supraventricular rhythm. A plurality of templates is provided and updated using a plurality of qualified beats. Updating occurs by temporally aligning the shock channel waveforms of the template beats using rate channel fiducial points. The template beats are combined by point-by-point addition of the shock channel waveforms. The resultant updated template characterizes one of the patient's supraventricular conducted cardiac beats.

Provided is an electronic device to monitor a user's biological measurements, where a sensor is configured to acquire a first signal from a user, and a diagnostic processor is configured to pre-process the first signal to generate a second signal, segment the second signal to form signal segments, determine at least one event location for each of the signal segments, match adjacent signal segments for feature alignment, and provide a third signal using results of the feature alignment.

The invention relates to a datum point positioning method based on machine vision, which belongs to the field of image processing and aims to solve the problems of poor datum point positioning accuracy and high cost of surface mounting equipment. The method comprises the following steps that a vision obtaining device is adjusted to obtain a datum point regional image; the image is preprocessed, and a threshold is set to establish a binary image; connected region labeling is performed on the binary image, so as to find out the largest connected region as a target region of a datum point; Canny edge detection is performed on an original image, so as to preliminarily determine coarse edge points; Hough transformation processing is performed on the coarse edge points, and an optimal existing circle in the image is found out; the distance between each edge point and the center of the circle is calculated; the position of a sub-pixel level of the edge point is obtained; and circular least-square fit is performed on the edge point in the position of the sub-pixel level, and then an accurate center and radius of the datum point are obtained and sent to a control system. The datum point positioning method can be widely applied to accurate positioning of the datum point.

An implantable medical device for optically sensing action potential signals in excitable body tissue. The device includes an elongated tubular lead body carrying an optical fiber extending from a proximal lead end to a distal lead end to position the optical fiber at a target site. The lead body additionally carries a conduit for dispensing a voltage-sensitive fluorescent dye into tissue surrounding the target site. The optical fiber transmits excitation light to the fluorescent dye to cause the dye to fluoresce with varying intensity as the transmembrane potentials of local tissue cells vary due to passing depolarization wavefronts. The optical fiber transmits the fluorescence signal to the device to generate an action potential signal or fiducial points of an action potential signal for use in accurately measuring and characterizing electrical activity of excitable tissue.

A method and system for automatically determining ischemia detection parameters are provided. The method includes obtaining a baseline trace indicative of a cardiac behavior, determining an ischemia detection window based on at least one physiologic state indicator within the baseline trace, and automatically identifying a fiducial point based on the baseline segment trace. The baseline trace includes a baseline segment within the ischemia detection window; where the ischemia detection window and the fiducial point may constitute ischemia detection parameters.

A laser projection system scans an output laser light beam onto an object to detect features. A high-sensitivity optical feedback system receives and detects a feedback beam of the output beam light diffusely reflected from the object. The feedback light and projected output beam share the same beam path between beam-steering mirrors of the projector and the object. The laser projection system has light suppression components to control stray scattered light, including ambient light, from being detected. A computer of the laser projection system calculates fiducial points on the object from detected features to align the projection system with the object without using targets. This feature detection is used in a process to guide assembly and fabrication on or to the object, and to verify the accurate placement of parts and fabrication steps in place after they are assembled or processed. In one form, the detected feature is a light spot on the object produced by a second light source.

A system to detect the presence or absence of T wave alternans is described based on statistical tests and periodicity transform. T wave and ST segment boundaries are detected in multi-lead ECG signals acquired from the regular clinical leads. Once the fiducial point and the above boundaries are delineated, computation of regular parameters like T wave amplitude, area under the T waves or segments of T wave, ST segment slope and/or the curvature of T wave are performed. Each parameter forms a rolling array of values with each successive beat. The array of values, or the time series, is used to make the decision about the T wave alternans. Two different methods are employed based on periodicity transforms and statistical tests. A set of numerical values (e.g. norm of the projection on to p-2 space, sums of adjacent terms after the trend removal, t-value, and number of deviations from alternans pattern) are all computed and compared to threshold values. Threshold values are computed from past information and experience with clinical databases and simulations. Final system comprises a software module, which can be part of the existing ECG monitoring programs as well as external defibrillator modules, apart from being stand-alone algorithms.

In order to improve the efficiency of vehicle positioning to meet the real-time requirements for vehicle type identification, the present invention provides a vehicle type identification method and system based on a deep neural network. The method comprises: integrating candidate target extraction and target identification into a network, and using end-to-end detection/identification methods to integrate feature extraction, target location, and target detection into a single network. According to the method and system provided by the present invention, target extraction t is no longer extracted from the original image, but is extracted from the high-dimensional feature map with very small dimensions by using the reference point and multi-dimensional coverage manner, and at the same time, the method for sharing the deep convolutional network parameters is used in the feature extraction layer, so that repetitive calculation of features is avoided, the identification efficiency is greatlyimproved, 20fps is reached in reality, the effect of the processing efficiency of a single server reaches 2 million sheets/day, and the requirement for real-time vehicle type identification is satisfied.

A system and automated method for assessing ventricular synchrony in ambulatory patients is provided including at least one mechanical sensor (e.g., accelerometer, tensiometric sensor, force transducer, and the like) operatively coupled to a first myocardial location in order to measure a wall motion signal of a first chamber, and a second mechanical sensor operatively coupled to a second myocardial location in order to measure a wall motion signal of a second chamber. The wall motion signals are processed in order to identify the time at which a fiducial (e.g., an inflection point, a threshold crossing, a maximum amplitude, etc.) occurs for each respective signal. The temporal separation between the fiducial points on each respective signal is measured as a metric of ventricular synchrony and can be optionally utilized to adjust pacing therapy timing to improve synchrony.

An in-building location system for detecting the location of individuals or items within a building utilizes a scanner carried by an individual or an item and RFID tags to provide fiducial points for assisting in the location process, with the tags being scanned by the scanner and in which tag proximity to a scanner provides for accurate in-building location. Accurate location of the scanner relative to multiple tags may be ascertained utilizing triangulation.

The invention discloses a worker safety helmet wearing real-time detection method based on video analysis. The method comprises the steps that captured video frames are read in real time from a camera in a monitoring area; a Viola-Jones detector is used to classify the image of the current frame to identify the upper body of a human body; a detected target is located, and the highest point of the detected upper body of the human body is determined; the highest point is used as a reference point to extract a corresponding area; and finally the color of the image area is determined according to color characteristics to determine whether a detected worker wears a helmet; and if a worker who does not wear a helmet is in the detection area, an alarm is given to ensure the safety of workers entering the work area. According to the invention, the influence of the background environment on helmet detection can be reduced; the helmet wearing detection accuracy of workers in the identification area is greatly improved; and the method has the advantages of fast detection speed and good instantaneity.

A novel, unified technique for analyzing, synthesizing, and recognizing faces captured by various modalities, and under a variety of often seen real-world circumstances, using thin-plate splines for densification of points of a face from an initial set of fiducial points.

The invention provides a sub-pixel-level PCB board defect reference point detection method. The method comprises the following steps: reading in a PCB grayscale image 1; preprocessing the PCB image, wherein self-adaptive median filtering denoising is used to remove pepper-and-salt-type noises to obtain a denoised image 2, a method of maximum inter-class variance is used to carry out binary segmentation of the image to obtain a binarized image 3, and a mathematical morphology method is used to process the image to further remove small interference points and holes to obtain an image 4; using acommunicate-domain algorithm to obtain a position and a scale of a preprocessed image feature region; and then enabling reference circle extraction and positioning efficiency and precision to be improved through a sub-pixel edge detection algorithm and fitting of a least square method. Requirements of high-precision reference point extraction and positioning are effectively satisfied, defects of low precision and low speed of previous reference point positioning are overcome, and the method has the characteristics of high applicability and high accuracy.

A coordinate input apparatus has a generally rectangular, flat coordinate input area and a set of at least first and second detectors for detecting arrival/non-arrival of light from an object to be detected present at any position in the coordinate input area. Coordinates indicating the position are output on the basis of outputs from the first and second detectors. The first and second detectors are placed at positions where coordinate resolution in the vicinity of a point, within the coordinate input area, nearest to the midpoint of a line segment connecting fiducial points of the two detectors is substantially equal to coordinate resolution in the vicinity of a point, within the coordinate input area, farthest from the midpoint.

The invention relates to a data processing method for carrying out static correction on transient electromagnetic data. The method comprises the following steps: ensuring that influences of field electromagnetic interference and a frame effect are eliminated, calculating late period apparent resistivity according to a late period apparent resistivity formula, calculating apparent depth according to an apparent depth empirical formula, selecting a reference point and a correction mode according to measuring point elevation data, determining a static correction factor d through a ratio between each measuring point apparent depth and reference point apparent depth, correcting values of V and t by utilizing relations between the static correction factor d and cube and square of V and t, substituting obtained corrected Vc into the late period apparent resistivity formula to calculate new rho[c], substituting the new rho[c] into the apparent depth empirical formula to obtain corrected apparent depth, and adding reference point elevation to the depth to complete a static correction process. According to the invention, false abnormity generated by landform fluctuation in qualitative interpretation can be rapidly and effectively eliminated, transient electromagnetic method data processing speed and interpretation precision are substantially raised, and large scale development and application of the method technology are promoted.