1491 results about "Extraction algorithm" patented technology

An optically-based rigid-body 6-DOF motion tracking system optimized for prospective (real-time) motion correction in Magnetic Resonance Imaging (MRI) applications using a single camera with an on-board image processor, an IR illuminator and optical fiducial targets affixed to a patient. An angle extraction algorithm operated by the on-board image processor utilizes successive approximation to solve the 3-point pose problem for angles close to the origin to achieve convergence to sub-microradian levels. A motion alarm is enabled by a monitor and GUI application in communication with the motion tracking system. A motion correction is enabled for MR scan images taken while operating the motion tracking system wherein an MRI controller is in communication with the motion tracking system.

This invention provides an identification method and a device for countenance based on the video, which applies the ASM profile pick-up algorithm in the pick-up of character vectors and picks up the man-face image based on the position of the eyes to generate a normalized character face from the chin and picks up the most effective character in the character face to identify the countenance, which can eliminate the influence of illumination to make the right and left gray value almost the same with the variance.

The invention discloses an indoor scene 3D reconstruction method based on Kinect and solves the technical problem of the real-time reconstruction of an indoor scene 3D model and avoidance of excessive redundant points. The method comprises steps of: obtaining the depth data of an object by using Kinect and de-nosing and down-sampling the depth data; obtaining the point cloud data of a current frame and calculating the vector normal of each point in the frame; using a TSDF algorithm to establish a global data cube, and using a ray casting algorithm to calculate predicted point cloud data; calculating a point cloud registration matrix by using an ICP algorithm and the predicted point cloud data, fusing the obtained point cloud data of each frame into the global data cube, and fusing the point cloud data frame by frame until a good fusion effect is obtained; rendering the point cloud data with an isosurface extraction algorithm and constructing the 3D model of the object. The method improves the registration speed and the registration precision, is fast in fusion speed and few in redundancy points, and can be used for real-time reconstruction of the indoor scene.

A vehicle environment monitoring system is provided that is based on a three-dimensional vector model. The three-dimensional vector model of the vehicle's environment is generated on the basis of the image data captured by at least one three-dimensional camera. Out of the image data, particular data are extracted for generating the three-dimensional vector model in order to reduce the data volume. For data extraction, a data extraction algorithm is applied that is determined in accordance with at least one parameter that relates to the situation of the vehicle. Therefore, targeted data extraction is performed for generating a three-dimensional model that is particularly adapted for an application that is desired in the current vehicle situation. The applications of the vector model include driver assistance, external monitoring and vehicle control, as well as recording in an event data recorder. In one implementation, a sequence of three-dimensional vector models, representing a three-dimensional space-and-time model, is generated.

The present invention provides an FMCW broadband life detection radar breathing and heartbeat signal extraction algorithm. Compared with the prior art, the algorithm has the advantages that breathing and heartbeat signals of multiple persons can be obtained simultaneously, the boundaries and energy of reconstructed breathing signals can be very well kept by using Coiflets wavelets compared with traditional frequency-domain filtering, especially processing conducted on short-time signals is obvious, higher harmonics of the breathing signals are filtered out by adopting a double-coefficient based LMS self-adaptive filtering algorithm, and the self-adaptive filtering algorithm does not need additional reference signals. Due to the fact that a degressive search step size coefficient is adopted in the algorithm, the heartbeat signals can be better retained while breathing signal harmonics are filtered out, the heartbeat signals can be rapidly converged by selecting the appropriate search step size coefficient and adopting the double-coefficient based LMS self-adaptive filtering algorithm, and smaller stable imbalance is kept in longer time, so that finally separated heartbeat signals are more accurate in frequency component within a long time.

The invention relates to an electroencephalogram feature extracting method based on brain function network adjacent matrix decomposition. The current motion image electroencephalogram signal feature extraction algorithm mostly focuses on partially activating the qualitative and quantitative analysis of brain areas, and ignores the interrelation of the bran areas and the overall coordination. In light of a brain function network, and on the basis of complex brain network theory based on atlas analysis, the method comprises the steps of: firstly, establishing the brain function network through a multi-channel motion image electroencephalogram signal, secondly, carrying out singular value decomposition on the network adjacent matrix, thirdly, identifying a group of feature parameters based on the singular value obtained by the decomposition for showing the feature vector of the electroencephalogram signal, and fourthly, inputting the feature vector into a classifier of a supporting vector machine to complete the classification and identification of various motion image tasks. The method has a wide application prospect in the identification of a motion image task in the field of brain-machine interfaces.

The invention discloses an image stitching method based on unmanned aerial vehicle POS information and image SURF feature combination and relates to the digital image processing field, the GIS field,the survey field and other relevant fields. According to the method, first, geometric correction is performed on images; second, geographic coordinates of four corners of each image are calculated; based on the geographic coordinates of the first image, a position relation of homonymy matching target positions is obtained by extracting SURF features of adjacent image overlapping regions, and therefore the geographic coordinates of the following images are sequentially corrected; and last, an adaptive gradual-in-gradual-out fusion algorithm is adopted, a panoramic image with a good visual effect is obtained, and good stitching of the images is completed. Through the method, an image feature extraction algorithm and the geographic coordinates of the images are combined, and stitching efficiency and the visual effect are both improved greatly compared with traditional feature extraction and stitching algorithms; and the image obtained after stitching contains geographic information, so that the image has certain practical value.

System and method for compact model algorithms to accurately account for effects of layout-induced changes in nitride liner stress in semiconductor devices. The layout-sensitive compact model algorithms account for the impact of large layout variation on circuits by implementing algorithms for obtaining the correct stress response approximations and layout extraction algorithms for obtaining the correct geometric parameters that drive the stress response. In particular, these algorithms include specific information from search “buckets” that are directionally-oriented and include directionally-specific distance measurements for analyzing in detail the specific shape neighborhood of the semiconductor device. The algorithms are additionally adapted to enable the modeling and stress impact determination of a device having single stress liner film and dual-stress liners (two different liner films that abut at an interface).

Embodiments of the invention provide a framework for traffic classification that bridges the gap between the packet content inspection and the flow-based behavioral analysis techniques. In particular, IP packets and / or IP flows are used as an input, network nodes are associated to specific network applications by leveraging information gathered from the web, and packet-level and / or flow-level signatures are extracted in an off-line fashion using clustering and signature extraction algorithms. The signatures learned are systematically exported to a traffic classifier that uses the newly available signatures to classify applications on-the-fly.

The invention relates to a precise registration method of ground laser-point clouds (ground base) and unmanned aerial vehicle image reconstruction point clouds (aerial base). The method comprises generating overlapping areas of the ground laser-point clouds and the unmanned aerial vehicle image reconstruction point clouds on the basis of image three-dimensional reconstruction and point cloud rough registration; then traversing ground base images in the overlapping areas, extracting ground base image feature points through a feature point extraction algorithm, searching for aerial base point clouds in the neighborhood range of the ground base point clouds corresponding to the feature points, and obtaining the aerial base image feature points matched with the aerial base point clouds to establish same-name feature point sets; according to the extracted same-name feature point sets of the ground base images and the aerial base images and a transformation relation between coordinate systems, estimating out a coordinate transformation matrix of the two point clouds to achieve precise registration. According to the precise registration method of the ground laser-point clouds and the unmanned aerial vehicle image reconstruction point clouds, by extracting the same-name feature points of the images corresponding to the ground laser-point clouds and the images corresponding to the unmanned aerial vehicle images, the transformation parameters of the two point cloud data can be obtained indirectly to accordingly improve the precision and the reliability of point cloud registration.

The invention provides a full-automatic anti-intrusion intelligent video monitoring alarm system for an unattended villa, which relates to the technical field of intelligent monitoring systems. The anti-intrusion intelligent video monitoring alarm system comprises a video intelligent analysis system, an anomalous event analysis system and an anomalous event alarm system. The video intelligent analysis system particularly refers to automatically detecting an object through a subregion autonomous non-reference threshold algorithm and an object key information secondary extraction algorithm and automatically tracking the object by adopting a movement trend tracking algorithm merging Kalman filtering and particle filtering. By detecting and tracking the movement objective track information, the movement direction, the horizontal and vertical displacement, and the object center position of the object are determined. The anomalous event analysis system particularly refers to analyzing video signals acquired by a villa monitoring camera through a machine vision algorithm, judging anomalous and dubious behaviors of the objects (personnel) around and in a villa through a preset rule, and notifying information on pictures, characters and the like of the anomalous behaviors and events to a proprietor or a security department in time.

Embodiments of the invention are directed to human challenge response test delivery systems and methods. Specifically, embodiments of the present invention are directed to secure human challenge response test delivery services of configurable difficulty for user devices. One embodiment of the present invention is directed to methods and systems for implementing a familiar and dynamic human challenge response test challenge repository created from transaction data. The dynamic human challenge response test challenge repository may be created by a server computer receiving a plurality of transaction data. Challenge items may be extracted from the transaction data using an extraction algorithm. Furthermore, in some embodiments a challenge message may be sent to a requestor, a verification request may be received, and the verification request may be compared to the challenge message. Another embodiment may be directed at using user information in a human challenge response test to mutually authenticate a user and a service provider.

The invention provides a human falling detection method based on machine vision. Under the conditions that all detected objects are people in indoor environment and the activities of all people can be captured by a depth camera, the method comprises the following steps of: (1) acquiring an image by using the depth camera; (2) subtracting a background from the image which is acquired, and extracting a foreground from the image; (3) acquiring a foreground contour by using a binary image contour extraction algorithm; (4) performing convolution computation on the foreground contour and Gaussian functions in different scales, mapping a contour image to a curvature scale space (CSS) to form a CSS image, extracting peak points of the CSS image, and thus obtaining a video word bag based on curvature scale characteristics by the peak points in different scales; and (5) training an extreme learning machine classifier by using the video word bag which is obtained. By adoption of the method, under the condition of few training samples, an accurate falling detection result can be obtained within a short training time.

The present invention provides a system and a method for identifying an agricultural disaster scope based on a high-resolution remote sensing image. The system comprises an image preprocessing module, a characteristic inversion module and a disaster identification module. The method comprises the steps of: obtaining a high-resolution remote sensing image and performing image preprocessing; obtaining characteristic parameters representing disaster characteristics through disaster characteristic parameter inversion; performing boundary identification and extraction for the preprocessed high-resolution remote sensing image according to the characteristic parameters, identifying a disaster scope, and obtaining disaster scope information. Through adoption of the system and the method of the present invention, the insured subjects of an agricultural insurance can be identified and extracted in a remote sensing survey link of underwriting and claiming of the agricultural insurance, and an accurate disaster scope can be further obtained based on a land type classification and boundary identification and extraction algorithm for the insured subjects of an agricultural insurance.

Disclosed herein is a method and apparatus for editing an image using an object contour extracted from an input image. The method of editing an image using a contour-extracting algorithm includes: inputting image data; extracting an object contour from the input image data; optimizing the extracted contour using the characteristics of the input image data; editing the input image data using the optimized contour; and outputting the edited image data.

The invention discloses a phishing website detection method based on uniform resource locator (URL) classification. Firstly, a modeling is performed for URL characteristics, a method specific to a domain name imitation phenomenon of the characteristics is provided for calculating the similarity between a suspicious domain name and a protected domain name by a dynamic programming thought, in order to collect phishing URL high frequency suspicious character features, a suspicious character extraction algorithm based on a generalized suffix tree is provided, then on the basis of characteristic modeling, a support vector machine (SVM) algorithm is utilized to perform classified training for experimental training set, a SVM classification model is obtained after the training, the SVM classification model is used for classifying the URL to be detected, and a server for detecting a phishing website updates the current SVM classification model according to a specific online incremental learning strategy.

The invention discloses an object-oriented remote sensing image coastline extraction method which belongs to the field of full automatic remote sensing image coastline extraction. The steps are as follows: carrying out filtering treatment on a remote sensing image; selecting the segmentation algorithm to segment the remote sensing image; utilizing sample points for classifying the remote sensing image after segmentation; utilizing the seed growth method for extracting a seawater region; and finally utilizing the corresponding judgment criterion to extract a coastline. By utilizing the method disclosed by the invention, the accuracy of the existing coastline extraction algorithm can be improved, the correct rate of seawater extraction after segmentation and classification treatment throughthe object-oriented method is improved and the accuracy of the coastline extraction is ensured. As the coastline changes frequently, the method can provide convenience for maintenance and updating ofcoastline information of all levels of national fundamental geographic information databases.

The invention discloses a generation method and a generation device of frequent position trajectory based on moving target, which relates to the technical field of positioning. The main purposes are to solve such problems as massive position data with various degrees of accuracy and being unable to determine the correct position trajectory of the moving target, of which the target track emerges frequently. The generation method of frequent position trajectory based on moving target includes the following steps. Information about the position of the moving target is obtained. According to locus fragment correlation function, correlation operations between locus fragments, which are in correspondence with the information about the position, are implemented. According to a pre-set method of dividing a grid, the information about the position after the correlation operations is divided. According to an established motion state filter and a default feature point extraction algorithm, the feature point of the information about the position after the division of the grid is extracted and a resampling trajectory. According to time attributes, position attributes, direction attributes and a default space clustering algorithm, the resampling trajectory of the feature point is clustered in the form of sub-trajectory. After scanning and clustering, the sub-trajectory becomes the frequent position trajectory.

A tunable auscultation system includes a heart sound acquirer for sensing heart sounds from at least one chest location of the patient. An initial conditioner then conditions the heart sounds through pre-amplification and anti-aliasing. The heart sounds are transduced into electrical signals by a signal processor. The electric heart signals are then tuned by an analysis tool. The analysis tool includes an interaction tuner, a processing tuner and an output tuner. The interaction tuner includes a preset tuning selector and a dynamic range tuning selector. The processing tuner includes a band pass filter and an algorithmic extraction engine which applies extraction algorithms to the electric heart signals, segments them and extracts signals of interest. Signals of interest may be correlated to specific pathologies. The output tuner includes a signal strength indicator, a diagnosis indicator, an overlapping cardiac cycle display and a display configuration engine. A display module provides output.

The invention provides a quick traffic signal lamp detection method based on depth characteristic learning, and relates to the fields of image processing, deep learning and intelligent traffic. The method comprises the steps: extracting a traffic signal lamp candidate region from a detected image; and carrying out the classification of the traffic signal lamp candidate region through a convolutionneural network. The adding of the training data can enable a network to apply to various types of complex scenes, thereby improving the recall rate of traffic signal lamps and the detection accuracy.Because a traffic signal lamp candidate region extraction algorithm and a classification network can achieve the higher recall rate and the classification accuracy, the classification network is enabled to adapt to various types of complex scenes. The method is high in detection rate, and meets the real-time requirements of an unmanned vehicle. The number of candidate regions is reduced, the subsequent calculation burden of the classification network is reduced, and the whole detection rate of a system is reduced. The method can be suitable for the traffic signal lamps in various complex scenes, and improves the detection accuracy.

The invention belongs to the field of image processing methods, and discloses a three-dimensional roof reconstruction method based on LiDAR data and ortho images. The method comprises the following steps of: (1) LiDAR point roof facets segmentation based on a triangular cluster; (2) roof ridge extraction based on LiDAR data nad ortho images; (3) three-dimensional roof model reconstruction. In the method, for meeting the requirement on accurate reconstruction of the three-dimensional roof model, the LiDAR data and the high-resolution images are integrated, the complementary advantages of the elevation characteristic of the LiDAR data and the high-resolution characteristic of the images are comprehensively used, 'roof facets segmentation, ridge extracton and three-dimensional roof model reconstruction' is taken as a principal line, a LiDAR point roof facets segmentation algorithm based on the triangular cluster and a roof ridge extraction algorithm based on the LiDAR data and the ortho images are realized, and a new method for three-dimensional roof model reconstruction is formed. Tests show that the method of the invention has high automation degree, higher accuracy and integrity and high location precision in modeling, and meets the needs of actual application.

The invention discloses an ocean environment visualization method. Based on the combination of the ocean environment three-dimensional scene and a parallel coordinate method, the method comprises the concrete steps of modeling the three-dimensional scene and the parallel coordinates of ocean environment; secondly establishing a multi-dimensional element integrated rendering and interactive extraction algorithm based on the three-dimensional scene and the parallel coordinates of the ocean environment; thirdly expressing the multi-dimensional ocean environment data linked features and cluster features. The method can be used for knowledge discovery of ocean phenomena such as storm tides, red tides, ENSO circulation and the like, and provides a new idea for understanding, rebuilding and discovering ocean phenomena.

The invention relates to the field of the computer visual technology, in particular to a fast 3D skeleton model detecting method based on a depth camera. The fast 3D skeleton model detecting method based on the depth camera comprises the steps that a whole human body is shot by using the depth camera, human face detection is carried out in the image by using an Adaboost algorithm, and thus depth information of the human face is obtained; the body silhouette is extracted based on the depth information of the human face; detection verification is carried out on the detected body silhouette through a 'convex template' verification algorithm; after the verification succeeds, image smoothness processing is carried out on the body silhouette, and the skeleton line of the body silhouette is obtained through a detailing algorithm; characteristic points on the skeleton line of the body silhouette are extracted, the number and the positions of the characteristic points are corrected, and interference points are removed; the corrected characteristic points are verified, and accurate joint points and other characteristics are obtained by adopting a fast joint point extracting algorithm if the verification succeeds. The fast 3D skeleton model detecting method based on the depth camera is high in operating speed, low in computing complexity and adaptive to various complex backgrounds, and each frame of image only needs 5ms.

The invention discloses a heartbeat type classification method and device, and electrocardiogram equipment and belongs to the field of medical apparatuses. The method comprises steps that heartbeat waveform characteristic parameters are extracted from ECG signals, heartbeat and template heartbeat matching degree characteristic parameters are further extracted, analysis is carried out through a decision tree classifier, and the heartbeat type analysis result can be acquired through measurement. An extracted characteristic vector can be better present difference of the ECG signals, and disadvantages of utilizing only a waveform analytical method or a template analysis method are avoided. The invention further comprises the electrocardiogram equipment comprising the method. The method is advantaged in that the characteristic vector extraction algorithm is simple and easy for realization, the operation speed is fast, classification accuracy is high, and the method is suitable for a wearable electrocardiogram real-time monitoring automatic analysis diagnosis system.

Embodiments of the invention provide a framework for traffic classification that bridges the gap between the packet content inspection and the flow-based behavioral analysis techniques. In particular, IP packets and / or IP flows are used as an input, network nodes are associated to specific network applications by leveraging information gathered from the web, and packet content signatures are extracted in an off-line fashion using clustering and signature extraction algorithms. The signatures learned are systematically exported to a traffic classifier that uses the newly available signatures to classify applications on-the-fly.

The invention relates to a speech information hiding secret communication system which organically integrates techniques, such as information hiding, passwords, communication, and the like. In the invention, MELP2.4KBps secret speech is hidden in the public speech of G.721, G.728, GSM and G.729 of a code-excited linear prediction code by connecting a public telephone network PSTN, mobile communication GSM / CDMA, videoconferences and a VoIP network and utilizing a speech information hiding and extraction algorithm, and a private channel is established in a public communication channel to carry out the real-time secret communication of secret speech information. The system adopts an embedded type technique based on DSP, and designs corresponding functional modules, such as speech coding and decoding, speech encryption and decryption, speech information hiding and extraction, and the like. Under the condition that a certain communication rate and a certain speech quality are ensured, secret speech real-time communication is carried out on various public channels, and the communication quality reaches the requirement of a communication standard.

The invention relates to a method for detecting the welding seam segmentation and defects of digital X-ray images, belonging to the field of nondestructive testing. In the invention, aiming at the defect detection of a series of vertical bar-shaped X-ray welding seam images with a specific width range, when the welding seam segmentation is carried out, a segmentation method based on the welding seam horizontal width and vertical continuity in the welding images is adopted, and the segmentation method comprises the following steps: filtering, intensifying the images, segmenting a threshold, looking for the welding seam position, extracting the welding seam and carry out other steps. In the extraction of the defects, a method for combining edge detection and a subtraction method are utilized. The method provided by the invention can be used for rapidly and effectively segmenting the welding seam in the images, and the syncretic defect extraction algorithm can be used for better detecting the defects.

The invention pertains to the technical field of machine vision and provides a method for automatically extracting elliptic image features from a complex background image. In the invention, firstly a Canny edge extraction method is utilized to obtain the sub-pixel image coordinates of an image edge, and the adjacent edge pixels are connected to an edge fragment via an edge connection method; arc fragments in the edge fragments which meet constraints of the central distance and the constraints of the radius are fused through using an edge split fusion algorithm based on the arc approximate fit; the arc fragments which pertain to the same ellipse are clustered on the basis of a random sampling consistency robust estimation algorithm; and finally an elliptic parameter equation is obtained by carrying out the least square fitting of the clustered arc fragments in the same category. The proposed elliptic automatic extraction algorithm effectively eliminates the interference of the noise edge in the image, solves the problems of identification and clustering of the elliptic edge of the complex background image, and realizes the automatic extraction of the elliptic image features.

The invention relates to an inertia / vision integrated navigation method for a deep-space detection patrolling device. The method comprises the steps that a state model of inertia / vision integrated navigation of the patrolling device is established according to a serial inertial navigation mechanical arrangement in a fixed coordinate system of a planet; a binocular vision camera is used for shooting a surrounding environment of the patrolling device; a stereoimage sequence is obtained; pixel coordinates of characteristic points are obtained by an image characteristic extraction algorithm; a measurement model by taking the pixel coordinates of the characteristic points as measurement vectors is established; and a position, a speed and a state of the deep-space detection patrolling device are estimated by using Unscented kalman filter. The method can effectively correct a position error of inertial navigation and improve the navigation accuracy, is very applicable to autonomous navigation of the deep-space detection patrolling device, belongs to the technical field of space navigation, can provide high-precision navigational parameters for the deep-space detection patrolling device, and can provide references for the design of an autonomous navigation system of the deep-space detection patrolling device.