4293results about How to "Accurate extraction" patented technology

A voice recognition device, method, and program for operating a plurality of control objects recognizing a plurality of user-provided verbal commands. The voice recognition device determines a control object and control content from predefined types of control objects and contents, based on a recognition result of the input verbal command. A voice recognition unit converts input verbal commands into a text expressed with a series of words, a first parsing unit performs an identification process of a first control candidate group as a control candidate for the control object and control content, a second parsing unit performs an identification process of a second control candidate group as a control candidate for the control object and control content, and a control candidate identification unit identifies a final control candidate group for determining the control object and control content from the first control candidate group and the second control candidate group.

The invention provides a body-worn system that continuously measures pulse oximetry and blood pressure, along with motion, posture, and activity level, from an ambulatory patient. The system features an oximetry probe that comfortably clips to the base of the patient's thumb, thereby freeing up their fingers for conventional activities in a hospital, such as reading and eating. The probe secures to the thumb and measures time-dependent signals corresponding to LEDs operating near 660 and 905 nm. Analog versions of these signals pass through a low-profile cable to a wrist-worn transceiver that encloses a processing unit. Also within the wrist-worn transceiver is an accelerometer, a wireless system that sends information through a network to a remote receiver, e.g. a computer located in a central nursing station.

The present invention detects a moving object by generating the distance information of the moving object, detecting the object motion, determining the object distance, detecting the object image area and the object contour from the video image that includes the object image and contour, and provides a moving object detection apparatus to carry out such detection as well as detecting a contour of the specific moving object by detecting the center of the moving object in high precision.

An inductive algorithm, denominated STALKER, generating high accuracy extraction rules based on user-labeled training examples. With the tremendous amount of information that becomes available on the Web on a daily basis, the ability to quickly develop information agents has become a crucial problem. A vital component of any Web-based information agent is a set of wrappers that can extract the relevant data from semistructured information sources. The novel approach to wrapped induction provided herein is based on the idea of hierarchical information extraction, which turns the hard problem of extracting data from an arbitrarily complex document into a series of easier extraction tasks. Labeling the training data represents the major bottleneck in using wrapper induction techniques, and experimental results show that STALKER performs significantly better than other approaches; on one hand, STALKER requires up to two orders of magnitude fewer examples than other algorithms, while on the other hand it can handle information sources that could not be wrapped by prior techniques. STALKER uses an embedded catalog formalism to parse the information source and render a predictable structure from which information may be extracted or by which such information extraction may be facilitated and made easier.

An image processing apparatus and method, which can appropriately extract an object even when the focus of a camera having an automatic focus adjustment function shifts from the background to the object. To this end, frame images which are sensed by an image sensing unit and are sequential in the time axis direction are input from an input unit. The input frame images are smoothed by a filter unit. A background image generation unit generates an average image of a predetermined number of smoothed frame images as a background image. An image differential unit generates a differential image between the predetermined smoothed frame image and the background image. An object extraction unit extracts an object region where a predetermined object is sensed, on the basis of the differential image.

The invention provides a multi-sensor system that uses an algorithm based on adaptive filtering to monitor a patient's respiratory rate. The system features a first sensor selected from the following group: i) an impedance pneumography sensor featuring at least two electrodes and a processing circuit configured to measure an impedance pneumography signal; ii) an ECG sensor featuring at least two electrodes and an ECG processing circuit configured to measure an ECG signal; and iii) a PPG sensor featuring a light source, photodetector, and PPG processing circuit configured to measure a PPG signal. Each of these sensors measures a time-dependent signal which is sensitive to respiratory rate and, during operation, is processed to determine an initial respiratory rate value. An adaptive digital filter is determined from the initial respiratory rate. The system features a second sensor (e.g. a digital 3-axis accelerometer) that attaches to the patient's torso and measures an ACC signal indicating movement of the chest or abdomen that is also sensitive to respiratory rate. This second signal is processed with the adaptive filter to determine a final value for respiratory rate.

The invention provides a multi-sensor system that uses an algorithm based on adaptive filtering to monitor a patient's respiratory rate. The system features a first sensor selected from the following group: i) an impedance pneumography sensor featuring at least two electrodes and a processing circuit configured to measure an impedance pneumography signal; ii) an ECG sensor featuring at least two electrodes and an ECG processing circuit configured to measure an ECG signal; and iii) a PPG sensor featuring a light source, photodetector, and PPG processing circuit configured to measure a PPG signal. Each of these sensors measures a time-dependent signal which is sensitive to respiratory rate and, during operation, is processed to determine an initial respiratory rate value. An adaptive digital filter is determined from the initial respiratory rate. The system features a second sensor (e.g. a digital 3-axis accelerometer) that attaches to the patient's torso and measures an ACC signal indicating movement of the chest or abdomen that is also sensitive to respiratory rate. This second signal is processed with the adaptive filter to determine a final value for respiratory rate.

The invention provides a body-worn system that continuously measures pulse oximetry and blood pressure, along with motion, posture, and activity level, from an ambulatory patient. The system features an oximetry probe that comfortably clips to the base of the patient's thumb, thereby freeing up their fingers for conventional activities in a hospital, such as reading and eating. The probe secures to the thumb and measures time-dependent signals corresponding to LEDs operating near 660 and 905 nm. Analog versions of these signals pass through a low-profile cable to a wrist-worn transceiver that encloses a processing unit. Also within the wrist-worn transceiver is an accelerometer, a wireless system that sends information through a network to a remote receiver, e.g. a computer located in a central nursing station.

The invention discloses a crossroad traffic event automatic detection system based on multi-source information fusion. The invention aims at urban crossroad traffic management, establishes audio-video traffic information acquisition, traffic information analytical processing and traffic event automatic alarming three subsystems. The invention mainly comprises: designing and realizing an acquisition subsystem of multi-source traffic information (traffic audio information, traffic video information, multi-angle video information, elevation angle video information); realizing a traffic parameter automatic extractive technique based on traffic audio and traffic video; realizing a traffic event (car crash, illegal parking, jam and retrograde motion) automatic detection technique based on the multi-source information fusion; and realizing a software system for traffic event report, traffic event associated video information transmission, and traffic control center display and processing, and forming an integrated crossroad traffic event automatic detection system.

The invention provides a non-contact free space eye-gaze tracking method suitable for man-machine interaction. The method comprises the steps of positioning and tracking a face and eyes in real time, extracting eye movement biological characteristic information, building an eye movement model based on the eye movement biological characteristic information, building a mapping relational model of the eye movement model and an eye-gazed object and the like. The non-contact free space eye-gaze tracking method suitable for the man-machine interaction relates to multiple crossed fields of image processing, computer vision, pattern recognition and the like and has wide application prospect in the fields of new-generation man-machine interaction, disabled people assisting, aerospace relating field, sports, automobile and airplane driving, virtual reality, games and the like. In addition, the method has great practical significance for improvement of the life and self-care level of disabled people, building of a harmonious society and improvement of independent innovative capability in the national high-and-new technical fields of the man-machine interaction, unmanned driving and the like.

An obstacle recognition apparatus is provided which can recognize an obstacle by accurately extracting a floor surface. It includes a distance image generator (222) to produce a distance image using a disparity image and homogeneous transform matrix, a plane detector (223) to detect plane parameters on the basis of the distance image from the distance image generator (222), a coordinate transformer (224) to transform the homogeneous transform matrix into a coordinate of a ground-contact plane of a robot apparatus (1), and a floor surface detector (225) to detect a floor surface using the plane parameters from the plane detector (223) and result of coordinate transformation from the coordinate transformer (224) and supply the plane parameters to an obstacle recognition block (226). The obstacle recognition block (226) selects one of points on the floor surface using the plane parameters of the floor surface detected by the floor surface detector (225) and recognizes an obstacle on the basis of the selected point.

A method and apparatus for conversion of traffic information based on traffic information element knowledge base are provided. According to the present invention, a road network is described using roads, intersections and sections as traffic information elements and a correspondence between these elements and a road topological network in a digital map is established, so that a universal traffic information describing model, which is compatible with language used in people's daily life, can be established. Further, a traffic information element knowledge base can be generated based on the roads, intersections and sections, their respective attributes and the relationship between them, to support inter-conversion between road topological network traffic information and text-based traffic information. With the universal traffic information describing model and the traffic information element knowledge base according to the present invention, it is possible to support fusion and conversion for traffic data from various sources and to support various forms of presentation and interaction for traffic information, such as presentation of traffic information on digital navigation map, textual description of traffic information, map presentation of traffic information for urban trunk roads, interaction for natural language queries of traffic information, etc.

Devices, systems and methods for use in separating sample materials into different sample components and then isolating one or more of the sample components for further processing or analysis are disclosed. Devices employ configurations that optionally allow a sample material to be electrophoretically separated into sample components in a separation matrix within a separation conduit. The sample components may then be detected in a detection zone in the separation conduit, and then selected components shunted to a component collection conduit within the device downstream of the detection zone for further processing or analysis based on information received at the detection zone. Methods of using these devices, and systems that incorporate these devices are also envisioned.

The invention provides a body-worn system that continuously measures pulse oximetry and blood pressure, along with motion, posture, and activity level, from an ambulatory patient. The system features an oximetry probe that comfortably clips to the base of the patient's thumb, thereby freeing up their fingers for conventional activities in a hospital, such as reading and eating. The probe secures to the thumb and measures time-dependent signals corresponding to LEDs operating near 660 and 905 nm. Analog versions of these signals pass through a low-profile cable to a wrist-worn transceiver that encloses a processing unit. Also within the wrist-worn transceiver is an accelerometer, a wireless system that sends information through a network to a remote receiver, e.g. a computer located in a central nursing station.

The invention provides a multi-sensor system that uses an algorithm based on adaptive filtering to monitor a patient's respiratory rate. The system features a first sensor selected from the following group: i) an impedance pneumography sensor featuring at least two electrodes and a processing circuit configured to measure an impedance pneumography signal; ii) an ECG sensor featuring at least two electrodes and an ECG processing circuit configured to measure an ECG signal; and iii) a PPG sensor featuring a light source, photodetector, and PPG processing circuit configured to measure a PPG signal. Each of these sensors measures a time-dependent signal which is sensitive to respiratory rate and, during operation, is processed to determine an initial respiratory rate value. An adaptive digital filter is determined from the initial respiratory rate. The system features a second sensor (e.g. a digital 3-axis accelerometer) that attaches to the patient's torso and measures an ACC signal indicating movement of the chest or abdomen that is also sensitive to respiratory rate. This second signal is processed with the adaptive filter to determine a final value for respiratory rate.

The invention discloses a three-dimensional human body gait quantitative analysis system and method. The method comprises the following steps of: simultaneously using two inertia measurement nodes on feet, carrying out analyses fusion on the data of the two inertia measurement nodes, measuring a more accurate gait parameter, and obtaining information which can not be measured in a single-foot manner; and firstly storing the collected data in storage units of the measurement nodes in a walking process, and finally transmitting the collected data to an analytical calculation device in a wired or wireless manner after the walking process is ended. The high-speed acquisition of all gait information in the walking process can be realized and no characteristic gait information point is omitted. A foot part binding device of the designed inertia measurement node is adopted, a measuring error brought by fixed position shift of the measurement nodes in the walking process is eliminated, and the identity of fixed positions of the measurement nodes in a walking process is guaranteed through repeated measurement; and a gait analytical calculation program module adopts a moving window searching value method to definition a characteristic point of gait information, and can more exactly extract the gait diagnostic information.

A system and method of enhancing guitar instruction based on Tablature Plus encoding of playing techniques within a MIDI file or other data structure, that may be rendered on an associated player application that provides multimedia output of the piece being played including a number of playing techniques. The system hardware for encoding the information includes string motion monitoring, and optionally a hand motion and finger positioning sensor, such as a data glove or a video motion capture system, for simultaneously registering the actions of the guitarist while playing the piece. The software comprises algorithms for determining note pitch and duration, and for extracting playing techniques from the data being collected. Multimedia player software is also described which renders a visual and audio output for the Tablature Plus encoded file, wherein the encoded playing techniques are represented within the display output. The system is adaptable to instruction for any instrument.

The invention relates to the technical field of information, and particularly discloses a method for integrating and exchanging data on the basis of unique identification. The method includes building data element management models for business required to be integrated, exchanged and shared, and uniquely identifying each data item in each data element management model; mapping the identification in the data element management models with fields of multi-source heterogeneous databases; generating corresponding target SQL (structured query language) statements according to the fields corresponding to the identification; accessing the multi-source heterogeneous databases, executing the target SQL statements and returning result sets; fusing and processing the result sets by the aid of fusion algorithms. The method has the advantages that conflict examples in heterogeneous data sources can be effectively recognized and fused by the aid of the method, and accordingly data integration / data fusion effects can be improved on high level; the data exchange and integration accuracy can be effectively improved, and the data integration and exchange efficiency can be greatly enhanced.

A profile-manufacturing method based on multi-transducer integrated measurement includes utilizing CCD photographic measurement to make rough measurement on object to obtain rough 3-D geometric data of object, guiding said data into 3-D rebuilding module (RM) in universal format, rebuilding rough 3-D model of object by processing viewpoint group, using laser measuring head and contact measuring head to obtain accurate 3-D geometric data of object based on said rough 3-D model, guiding said accurate data into 3-D RM in UF to obtain accurate 3-D model of object then revising obtained model according to requirement.

The invention relates to an extraction method for early failure sensitive characteristics based on ensemble empirical mode decomposition (EEMD) and wavelet packet transform. The extraction method for the early failure sensitive characteristics based on the EEMD and the wavelet packet transform includes the following steps: (1), collected original vibration signals of mechanical and electrical equipment are decomposed according to the EEMD, white noise is added, and intrinsic mode function (IMF) components are obtained through decomposition; (2), the sensitive IMF components closely related to failure are chosen, and other irrelative IMF components are ignored; (3), the sensitive IMF components chosen through step (2) are decomposed in an orthogonal wavelet packet mode, and a wavelet coefficient of each node is obtained; and (4), envelopes are extracted from the obtained wavelet packet coefficients by adoption of the Hilbert transform and the Fourier transform, power spectrums are calculated, the power spectrum corresponding to each wavelet packet coefficient is obtained and serves as the early failure sensitive characteristic , and the sensitive characteristics are automatically obtained. Self-adapting signals can be decomposed, the sensitive characteristics can be convenient to obtain automatically, diagnosis precision and speed are improved, and a mechanical and electrical system can be diagnosed quickly, accurately and stably. The extraction method for the early failure sensitive characteristics based on the EEMD and the wavelet packet transform can be applied to the field of mechanical and electrical equipment failure diagnosis.

A synchronous quick calibration method of a plurality of video cameras in a three-dimensional scanning system, which includes: (1) setting a regular truncated rectangular pyramid calibration object, setting eight calibration balls at the vertexes of the truncated rectangular pyramid, and respectively setting two reference calibration balls at the upper and lower planes; (2) using the video cameras to pick-up the calibration object, adopting the two-threshold segmentation method to respectively obtain the corresponding circles of the upper and lower planes, extracting centers of the circles, obtaining three groups of corresponding relationships between circle center points in the image and the centres of calibration ball in the space, solving the homography matrix to obtain the internal parameter matrix and external parameter matrix and obtaining the distortion coefficient, taking the solved video camera parameter as the initial values, and then using a non-linear optimization method to obtain the optimum solution of a single video camera parameter; (3) obtaining in sequence the external parameter matrix between a plurality of video cameras and a certain video camera in the space, using the polar curve geometric constraint relationship of the binocular stereo vision to establish an optimizing object function, and then adopting a non-linear optimization method to solve to get the optimum solution of the external parameter matrix between two video cameras.

The invention discloses a track obstacle detection system based on machine vision, and belongs to the field of railway safety. Black and white video images are obtained by an on-board camera installed at the head of a train, and the track is similarly linear or bent is judged according to that whether the camera is over travel. Manual detection of bend states is achieved by fixing a high definition camera and a wireless transmitting device at a bend for receiving wireless images. A similar straightway analyzes the obtained real-time image sequence, and divides forward obstacles into a non-dangerous class (including static small obstacles, moving objects quickly crossing the track) and a dangerous class (static large obstacles, moving obstacles influencing pass of the train) by adopting a track edge extraction algorithm based on hood conversion and Otsu threshold value, combining an inter-frame difference method based on mathematical morphology improvement with a background difference method and adopting an angular point feature matching tracking algorithm. The track obstacle detection system based on machine vision can quickly process track images, more effectively and accurately extract track edges, and is high in detection precision of track obstacles.

A system and method of enhancing guitar instruction based on Tablature Plus encoding of playing techniques within a MIDI file or other data structure, that may be rendered on an associated player application that provides multimedia output of the piece being played including a number of playing techniques. The system hardware for encoding the information includes string motion monitoring, and optionally a hand motion and finger positioning sensor, such as a data glove or a video motion capture system, for simultaneously registering the actions of the guitarist while playing the piece. The software comprises algorithms for determining note pitch and duration, and for extracting playing techniques from the data being collected. Multimedia player software is also described which renders a visual and audio output for the Tablature Plus encoded file, wherein the encoded playing techniques are represented within the display output. The system is adaptable to instruction for any instrument.

The invention discloses a road boundary detecting and tracking method. The road boundary detecting and tracking method comprises acquiringpolar coordinate data of radar scanning points of the surroundings of an unmanned vehicle through radar scanning, and converting the polar coordinate data into rectangular coordinates; mapping radar points into a polar coordinate grid, and according to the height of extending vertexes in the grid, extracting ground points; extracting road boundary points through the radial distance of the scanning points from a road boundary under the same scanning line as well as the height mutation properties of the neighboring scanning points and by combining with a road extending direction; performing filtering through the random sampling consensus algorithm, fitting the filtered road boundary points through the least square method; performing tracking through a Kalman filter. The road boundary detecting and tracking method can effectively extract road boundaries in an actual scenario when obstacles exist on roads, and by means of the Kalman filter, enhances the boundary detecting accuracy and reliability. The road boundary detecting and tracking method involves no complex computation, thereby being high in practicality and applicable to wide application to unmanned navigation modules.

The present invention relates to a respiratory gas consumption monitoring method and monitoring device that is portable and has high measurement accuracy, for enabling the analysis and prediction of the respiratory behavior of subjects employing a variety of different types of breathing apparatuses in water, etc. Respiratory gas consumption monitoring device (20), for monitoring the respiratory gas consumption of the user of a breathing apparatus (1) in which a respiratory gas (G) inside a high pressure gas container (2) is reduced in pressure at pressure regulator (4) and supplied to a breathing mask (10), is provided with:a primary pressure sensor (21) for detecting the pressure prior to pressure reduction at pressure regulator (4);a temperature sensor (22) for correction;an environmental pressure sensor (23) for detecting the environmental pressure;an amplifier (24) for amplifying the signals from the aforementioned sensors;an A / D converter (25) for performing analog / digital conversion of the amplified signal;a data logger (26) for recording and storing the analog / digital converted signals; anda display (27) for display.In addition, as needed, a computer (X) for calculating, analyzing, and predicting data may be housed in housing (28), and connected to breathing apparatus (1) by connecting primary pressure sensor (21) to a high pressure opening (8) of pressure regulator (4) using a high pressure hose (29).

The invention provides a multi-sensor system that uses an algorithm based on adaptive filtering to monitor a patient's respiratory rate. The system features a first sensor selected from the following group: i) an impedance pneumography sensor featuring at least two electrodes and a processing circuit configured to measure an impedance pneumography signal; ii) an ECG sensor featuring at least two electrodes and an ECG processing circuit configured to measure an ECG signal; and iii) a PPG sensor featuring a light source, photodetector, and PPG processing circuit configured to measure a PPG signal. Each of these sensors measures a time-dependent signal which is sensitive to respiratory rate and, during operation, is processed to determine an initial respiratory rate value. An adaptive digital filter is determined from the initial respiratory rate. The system features a second sensor (e.g. a digital 3-axis accelerometer) that attaches to the patient's torso and measures an ACC signal indicating movement of the chest or abdomen that is also sensitive to respiratory rate. This second signal is processed with the adaptive filter to determine a final value for respiratory rate.

Provided is a method and apparatus for processing an image, in which an image is removed from the entire photographed image and synthesized with another image using distance information to a photographed object regardless of colors or patterns of the image. The method includes the steps of photographing images using two cameras, extracting distance information to a photographed object using a disparity between the images, and processing the images of the photographed object at a predetermined distance using the extracted distance information.

The invention discloses an object contour extraction method based on mask-RCNN. The method comprises the steps: firstly obtaining a mask-RCNN model through trianing, inputting the RGB image under object contour extraction into mask-RCNN model for semantic segmentation, obtaining the corresponding binary mask image of the RGB image through processing of the mask-RCNN network, and inputting the RGBimage and the corresponding binary mask image into a contour refinement module. A contour feature description method is proposed to accurately represent the direction and angle information of the object contour, and the binary mask image contour obtained based on mask-RCNN is modified adaptively through the contour correction algorithm, and finally real-time accurate extraction of the image instance contour is realized under the condition of low image quality, low resolution, blurred object and low time and space complexity.

The embodiment of the invention provides a method and a device for extracting a keyword based on a graph model. The method comprises the steps of acquiring a to-be-processed text, and segmenting words of the to-be-processed text to obtain candidate keywords corresponding to the to-be-processed text; finding out word vectors corresponding to the candidate keywords from a word vector model, wherein the word vector model includes the word vectors of the candidate keyword; constructing a word similarity matrix of the candidate keywords according to the word vectors; acquiring a language database corresponding to the to-be-processed text, calculating global information of the candidate keywords in the language database to obtain a global weight of the candidate keywords, and taking the global weight as an initial weight of the candidate keywords, wherein the global information represents the importance degree of the candidate keywords in the language database, and the language database at least includes a search log and a network document; and ranking the candidate keywords according to the initial weight and the word similarity matrix of the candidate keyword, and extracting the keyword of the to-be-processed text. By use of the embodiment, the keyword extraction accuracy rate is effectively improved.