351 results about "Domain analysis" patented technology

An on-demand manager provides an improved distributed data processing system for facilitating dynamic allocation of computing resources among multiple domains based on a current workload and service level agreements. Based on a service level agreement, the on-demand manager monitors and predicts the load on the system. If the current or predicted load cannot be handled with the current system configuration, the on-demand manager determines additional resources needed to handle the workload. If the service level agreement violations cannot be handled by reconfiguring resources at a domain, the on-demand manager sends a resource request to other domains. These other domains analyze their own commitments and may accept the resource request, reject the request, or counter-propose with an offer of resources and a corresponding service level agreement. Once the requesting domain has acquired resources, workload load balancers are reconfigured to allocate some of the workload from the requesting site to the acquired remote resources.

Certain aspects of the present disclosure provide techniques for autonomously testing a web-based application. The techniques generally include an analysis module searching a page of the web-based application for one or more fillable form fields and identifying a fillable form field in the page. The analysis module determines a field type associated with the fillable form field, determines a field data format based on the field type of the fillable form field and generates a test data entry based on the field data format. The analysis module then enters the test data entry into the respective fillable form field and submits the test data entry to a server.

The present invention discloses various embodiments of multiple domain anomaly detection systems and methods. In one embodiment of the invention, a multiple domain anomaly detection system uses a generic learning procedure per domain to create a “normal data profile” for each domain based on observation of data per domain, wherein the normal data profile for each domain can be used to determine and compute domain-specific anomaly data per domain. Then, domain-specific anomaly data per domain can be analyzed together in a cross-domain fusion data analysis using one or more fusion rules. The fusion rules may involve comparison of domain-specific anomaly data from multiple domains to derive a multiple-domain anomaly score meter for a particular cross-domain analysis task. The multiple domain anomaly detection system and its related method may also utilize domain-specific anomaly indicators of each domain to derive a cross-domain anomaly indicator using the fusion rules.

The invention discloses a locomotive wheelset bearing fault diagnosis method based on the angular domain-time domain-frequency domain, and belongs to the technical field of bearing testing. The method includes the steps that firstly, collected vibration acceleration signals of locomotive wheelset bearings are analyzed in the time domain and the frequency domain, whether the bearings are in a fault state or not is judged, the specific portions of the faults are judged, angular domain analysis is conducted on vibration acceleration creatively, and quantitative analysis data of the faults are acquired, so that the severity degrees of the faults are grasped, and basic data are provided for further fault monitoring. The analysis method in which the time domain, the frequency domain and the angular domain are combined is adopted, information such as fault occurrence, fault types and fault severity degrees of the bearings can be accurately provided, especially, the angular domain fault diagnosis method is creatively provided, an accurate monitoring mode is provided for the fault development degree, and more abundant reference data are provided for subsequent fault processing.

The invention provides a target tracking method which comprises: a step of obtaining a connected domain, carrying out three-dimensional connected domain analysis on an input initial depth image to obtain a list of the connected domain of the initial depth image; a step of determining an initial target, determining a target connected domain where the target is in the initial depth image according to a currently known current position of the target, and determining n feature points in the image part corresponding to the connected domain, wherein n is a natural number; a step of tracking, carrying out three-dimensional connected domain analysis in the subsequent depth image input after the initial depth image, identifying the target connected domain where the target is in each candidate connected domain in the connected domain list of the subsequent depth image; and a step of determining the target position, namely tracking the n feature points in the target connected domain identified by the tracking step to update the current position of the target. A target tracking device is also correspondingly provided.

A Linguistic Assistant For Domain Analysis Methodology to help a user define object models from documents such as requirements documents and validate object models against such documents. The approach is domain-independent and language-independent, mainly relying on widely available linguistic resources for the text analysis.

A BOTDA system based on pulse coding and coherent detection comprises a narrow linewidth laser device (10), a first polarization-maintaining coupler (11), a second polarization-maintaining coupler (12), a microwave signal source (17), testing optical fibers (18), an optical circulator (19), a 3dB coupler (20), a balance photoelectric detector (21), a scrambler (16), a spectrum analyzer (22) and a digital signal processing unit (23), wherein continuous light emitted by the arrow linewidth laser device (10) is divided into two channels of continuous light, namely, a first channel of the continuous light and a second channel of the continuous light, through the first polarization-maintaining coupler (11); and the system further comprises a frequency shifter (9), a first electrooptical modulator (13), a pulse signal source (14) and a second electrooptical modulator (15). The system adopts a pulse coding technology and a coherent detection method, so that the signal to noise ratio of the BOTDA and the measurement accuracy can be improved, the sensing distance is increased, and the system has the function of breakpoint detection.

The invention aims to provide a method for analyzing and evaluating measure point precision of a gearbox in a vibration acceleration sensor, aiming at analyzing a plurality of sets of collected sample data at different measure point positions and a certain fixed position under various working conditions. The method comprises the following steps of: performing synchronous data collection of a vibration signal and a rotation speed signal of the gearbox by taking the rotation speed signal as the main control through the vibration acceleration sensor; extracting time domain characteristic values,analyzing and the evaluating the time domain characteristic values, and drawing an RMS (root mean square)-Peak picture and a box plot; calculating an order time spectrum and analyzing and evaluating the order time spectrum; and analyzing the result through time domain analysis and frequency domain analysis methods to form an analysis and evaluation result of the measure point precision of the gearbox. According to the method disclosed by the invention, the order time analysis on the vibration signal of a gearbox shell can be realized; optical positions better representing various fault characteristics can be obtained by analyzing the time domain and frequency domain characteristics; the measurement error is reduced; the installation position of the vibration sensor is determined; and an assurance is provided for the accuracy of the fault diagnosis.

The invention relates to fields of a vehicle plate character segmenting method based on horizontal projection and connected domain analysis and pattern recognition. The method comprises the following steps of: 1) locating a vehicle plate subimage; 2) computing the optimal threshold value of the subimage; 3) binarizing the image to obtain a binarized image; 4) rotating the binarized image at an optimal angle; 5) performing slant correction on the rotated image; 6) performing horizontal projection on the binarized image; 7) performing connected domain analysis on the binarized image to obtain a character block; 8) verifying the character block by using priori knowledge and removing a false character block; 9) performing character segmentation by combining the horizontal projection in the step 6) and the connected domain result in the step 7) so as to obtain the horizontal position of each character; 10) computing an upper border and a lower border of the vehicle plate character according to the binarized image in the step 5); 11) computing each border of a character rectangle according to the upper border and the lower border and the central position of the character; and 12) performing fine adjustment according to a horizontal projection curve to obtain a character-segmenting result. By the method, the segmentation of the vehicle plate character is reliable and stable, the resistance to image noise and interference is high, and the segmenting efficiency is high.

By collecting or creating information written in a specific descriptive system, making a real model defining the concept handled in the organization activity, analyzing the domain for defining the words by stratifying each concept on the model of each basic concept of at least person, organization, article, document, meeting and event for composing the organization activity, analyzing the sentence pattern for defining the context by stratifying on the model of the concept of action, and by fitting and integrating the word defined by domain analysis and sentence pattern analysis into the context, a logical model corresponding to the real model is created. Thereby an organization activity database, in which information about various events necessary for organization activity and information of achievements resulting organization activity are integrated, is constructed.

The present invention discloses a method and a device for touching character segmentation in character recognition, and belongs to the character recognition field. The method comprises the steps of carrying out preprocessing to obtain connected domains, an average character width and an average character height of a row image; carrying out connected domain analysis, marking touching connected domains, carrying out stroke extraction for selected touching connected domains, carrying out segmentation point detection of the touching connected domains to obtain pre-segmentation points, and saving character blocks for non-touching connected domains; merging extracted strokes according to the pre-segmentation points to obtain the character blocks; saving the character blocks and turning to a next connected domain for carrying out touching determination, and outputting a character block sequence after all connected domains having been traversed; and merging the character blocks according to reference information and outputting recognition result. The method and the device provided in the invention merge the strokes according to the pre-segmentation points to obtain the character blocks, guaranteeing that segmentation points in a larger scope can be detected, and take the mode that contour information is used to predetect the segmentation points as a parameter in merging, avoiding merging mistakes caused by merging correct segmentation points.

The invention provides a binocular vision-based power transmission line online detection method for a patrol robot. The method comprises the steps of establishing a data sample set of a power transmission line component by utilizing an acquired original image, and then performing convolutional neural network and feature pyramid network training according to the established data sample set; and fora to-be-detected image shot by the patrol robot, performing detection by utilizing a trained power transmission line detection model; performing detection segmentation on a power transmission line, the component and the like in the image; through connected domain analysis of pixel-by-pixel segmentation, judging whether a foreign matter exists on the power transmission line or not; and obtaining adistance between the component and the foreign matter in combination with images in a left camera and a right camera. The method has high accuracy and high robustness, has high accuracy for various power transmission line components including the power transmission line, an insulator, a vibration-proof hammer and a tower, and has an extremely good detection effect for the foreign matter; and themeasured distance between the component and the foreign matter is accurate.

The invention relates an abnormal voice detecting method based on time-domain and frequency-domain analysis. The method includes computing the background sound intensity of a monitored scene updated in real time at first, and detecting and extracting suddenly changed fragments of the sound intensity; then extracting uniform filter Mel frequency cepstrum coefficients of the suddenly changed fragments; and finally using the extracted Mel frequency cepstrum coefficients of sound of the abnormal fragments as observation sequences, inputting a trained modified hidden Markov process model, and analyzing whether the abnormal fragments are abnormal voice or not according to frequency characteristics of voice. Time sequence correlation is improved when the hidden Markov process model is added. The method is combined with time-domain extraction of suddenly changed energy frames and verification within a frequency-domain range, the abnormal voice can be effectively detected, instantaneity is good, noise resistance is high, and robustness is fine.

The invention discloses an optical fiber Brillouin optical time domain analyzer, which is made based on optical fiber broadband nonlinear light amplification effect and strain, temperature effect and optical light domain analysis principle of coherent amplified Brillouin scattering. The optical fiber Brillouin optical time domain analyzer comprises a narrowband single-frequency fiber laser, a fiber beam splitter, a pulse modulator, two optical fiber circulators, a heterodyne receiver, a digital signal processor, a fiber-grating filter, a monomode fiber and a continuous-operating fiber Raman pump laser. The continuous-operating high-power fiber Raman pump laser is used as the pump light source of the Brillouin optical time domain analyzer, which can overcome the difficulty in strictly locking the frequency of a detection laser and the pump laser of the Brillouin optical time domain analyzer; and boardband fiber nonlinear scattering amplification is used for substituting for narrowband Brillouin amplification to increase the gain of stimulated Brillouin scattering with back amplification, thus improving the S / N ratio of the system, increasing the measurement length, and improving the accuracy for simultaneous measurement of stain and temperature.

The invention relates to a distributed optical fiber sensing system, and in particular relates to a chaos Brillouin optical coherence domain analysis distributed optical fiber sensing device and method. According to the invention, the problems of unavailable spatial resolution and sensing distance combination, severely limited sensing distance and low spatial resolution of the existing distributed optical fiber sensing system are solved. The chaos Brillouin optical coherence domain analysis distributed optical fiber sensing device comprises a wide spectrum chaos semiconductor laser, a 1*2 optical fiber coupler, an optical scrambler, an optical isolator, a first optical amplifier, a variable optical delay line, a second optical amplifier, an optical circulator, a sensing optical fiber, a tunable optical filter, a broadband gain photodetector, a data acquisition device, a signal processing device and a display device. The device and the method, which are provided by the invention, are applicable to the field of distributed optical fiber sensing.

The invention provides a video image character detecting method based on sparse expression, which comprises the following steps of: S1, resampling a video sequence to obtain a color video image, and converting the gray level and the multi-scale of the color video image to obtain a multi-scale gray level image; S2, performing edge detection and morphological closed operation to the multi-scale gray level image with an improved Sobel operator to obtain an edge image and filter the edge density of the edge image; obtaining a candidate character region through connected domain analysis and regular analysis; and S3, performing vertical projection and horizontal projection to the candidate character region, diving a vertical projecting image and a horizontal projecting image to obtain candidate character lines, dividing the candidate character lines into small regions through sliding windows, extracting the edge characteristics of the small regions, respectively classifying each small region with a classifying method based on the sparse expression, judging whether the small regions are character regions, judging the candidate character lines according to the judging result of the small regions to obtain and output a final character line region.

Development of domain-specific analytic applications having predefined data mining models, including identifying a business problem to be solved; selecting a data mining algorithm appropriate for solving the business problem; defining data schema for use as inputs and outputs to and from the mining algorithm, the data schema including input data schema and output data schema; and defining a mining model based on the data schema to solve the business problem; whereby a domain-specific analytic application is developed, the analytic application having at least one predefined data mining model, the analytic application having the capabilities of: populating the input data schema with sample historical data; production training the mining model using the sample historical data in the input data schema, whereby a production trained mining model is created; and production scoring production data using the production trained mining model, production scoring further comprising applying the production trained mining model to production data.

A Portal Assessment Design System includes a system for designing assessment models and assessments (e.g., standardized tests). In assessment design, specifications are organized around three basic elements: 1) what knowledge, skill or abilities are important to measure; 2) what is necessary evidence of that knowledge, skill or ability; 3) what performance situations are needed to elicit the required evidence from students and other assessment users. The system includes three modules (i.e., Domain Analysis, Domain Modeling, Conceptual Assessment Framework), each of which targets a specific phase of the design process, for designing an assessment in accordance with the three basic elements. The sequence of modules represents the structure of a design process that helps assessment developers work through successive stages or phases of assessment design, from the gathering of raw information to the creation of a complete set of specifications for an assessment product. Each module has its own set of objects for organizing information, such as knowledge skills and abilities of interest of the students being tested, evidence of these, and situations structured to elicit this evidence. The modules and objects of the system are implemented as a software application executing in a client-server environment.

The invention relates to a multi-target tracking system in a dynamic video sequence, belonging to the technical field of image processing. The multi-target tracking system comprises an input module, a moving target detection module, a PHD (Probability Hypothesis Density) filter module and an output module, wherein the moving target detection module comprises a background area initialization submodule, a background area updating submodule, a foreground image extraction submodule, a morphology processing submodule and a connected domain analysis submodule; and the PHD filter module comprises a Gauss element parameter prediction submodule, a Gauss element updating submodule, a Gauss element trimming submodule and a state extraction submodule. The invention provides more reliable measurement information for the video tracking system through the improved moving target detection module, solves the problems of possible complex computation of particle filters and probability hypothesis density filters and unreliable state extraction under the condition that targets are crossed, ensures the effectiveness and the reliability of the video tracking system, avoids the data association computation and is widely used in various fields of multi-target video monitoring.

The invention belongs to the technical field of machine vision, and particularly relates to a vision-based method of detecting defects on the end surface of a bearing finished product, aiming at solving the problem of on-line detection of defects such as rust, scratches, pressed marks and bumps which probably exist on the end surface of the bearing finished product. The method comprises the following steps of: acquiring an original acquired image; acquiring a first workpiece image of the end surface of the bearing to be detected; performing edge extraction, obtaining the precise positioning ofthe bearing workpiece by using the fitting algorithm of a circle, and obtaining a second workpiece image; and based on the second workpiece image, expanding an annular workpiece drawing into a rectangular workpiece drawing; dividing the rectangular workpiece drawing into a plurality of end surface region drawings by adopting a unidirectional projection segmentation method; carrying out binarization segmentation through an adaptive gray threshold to obtain a defect candidate region; and as to the defect candidate region, obtaining a detect region by using a connected domain analysis method according to the defect position and shape information. The method realizes the on-line detection of the bearing end surface, improves the detection efficiency and the detection stability.

An audio restoration apparatus which restores an audio to be restored having a missing audio part and being included in a mixed audio. The audio restoration apparatus includes: a mixed audio separation unit which extracts the audio to be restored included in the mixed audio; an audio structure analysis unit which generates at least one of a phoneme sequence, a character sequence and a musical note sequence of the missing audio part in the extracted audio to be restored, based on an audio structure knowledge database in which semantics of audio are registered; an unchanged audio characteristic domain analysis unit which segments the extracted audio to be restored into time domains in each of which an audio characteristic remains unchanged; an audio characteristic extraction unit which identifies a time domain where the missing audio part is located, from among the segmented time domains, and extract audio characteristics of the identified time domain in the audio to be restored; and an audio restoration unit which restores the missing audio part in the audio to be restored, using the extracted audio characteristics and the generated one or more of phoneme sequence, character sequence and musical note sequence.

The invention discloses a chromosome karyotype image cutting method, and belongs to the technical field of chromosome image processing. An existing image segmentation method is used for segmenting a chromosome image, due to the fact that the chromosome image has a lot of noise, the phenomenon of wrong segmentation can occur, and errors are caused to bring interference to subsequent analysis. According to the method, chromosome image segmentation is mainly carried out based on connected domain segmentation and skeleton extraction modes, after independent single chromosomes are extracted throughconnected domain analysis, skeleton extraction and skeleton analysis are carried out on remaining cross chromosomes to find possible segmentation points, and segmentation of the cross chromosomes isrealized through the segmentation points; compared with the prior art, direct segmentation of the preprocessed image is changed, the segmentation effect is clear, errors caused by segmentation are reduced to the maximum extent, the process is simple and reasonable, large-scale popularization and application can be conducted outwards, and deployment is simple.

The invention discloses a detection method and a detection system for video image text and relates to the technical field of image text detection. The method comprises the following steps of coarse positioning of video image text areas and verification of video image text areas. The specific steps are as follows: (A) coarse positioning of video image text area: the gaussian pyramid multi-scale image of a video image is calculated, the image text area is segmented by threshold segmentation, text areas are combined by the inflation and corrosion technology in mathematical morphology, and candidate text areas are analyzed and positioned by connected domain analysis, text line segmentation and elimination rules; and (B) verification of video image text areas: an adaboost classifier is trained by adopting harr characteristics, and the adaboost classifier is utilized to detect whether text exists in the candidate text areas and the candidate text areas the text of which is not detected are eliminated. The method and the system can improve the accuracy and the recall ratio of video image text detection.

The invention provides a Mean shift moving object tracking method based on compressed domain analysis; in the method, the compressed domain analysis and a Mean shift tracking algorithm are combined, probability statistics analysis is carried out to motion vector generated in the video coding process, so as to obtain estimated value of object moving direction and moving speed, so as to correct the central position of a Mean shift moving candidate region and lead the candidate central position to close to the central position of the practical object when the searching starts at each time. In the technical proposal, the tracking precision of the rapid moving object is improved, the searching iteration times of the algorithm are reduced, and the operation efficiency is improved. The proposal is particularly suitable for situation that the video coding and object tracking in the intelligent video monitoring equipment are carried out at the meantime.

The invention provides an abnormity behavior detection method in combination with the depth data and an abnormity behavior system. The method comprises steps that a monitoring video image of a target area is acquired, a scene background model on the basis of the monitoring video image is established, the motion target prospect of a two-dimensional image is extracted, and communication domain analysis and target segmentation are carried out; a depth background graph of an original visual angle is acquired according to the monitoring video image, a motion target prospect of a three-dimensional image is extracted from the depth background graph, and two times of target prospect segmentation on the original visual angle and a downward-view visual angle after projection transformation is carried out; the effective person target information is extracted; according to the acquired person target information, tracking and behavior analysis on person targets are realized, whether behaviors of the person targets are abnormal can be determined according to preset abnormal behavior rules, if yes, alarm starts. Through the method and the system, abnormal events and abnormal behaviors are automatically identified, detection precision of the abnormal events is improved, and timely response can be realized on the unattended condition.

The invention discloses a detection method for remnants in the complex environment. The detection method comprises the following steps: comparing prospect targets obtained on the basis of both a partial updated Gaussian mixture background modeling method and a modified three-frame difference method; in combination with the YCbCr color space based shadow elimination method and the connected domain analysis, dividing to obtain temporary static briquettes within a scene; carrying out the centroid distance judging method on each frame of an image, and counting the rest time of each briquette; marking the static briquettes reaching to the temporal threshold as the remnants after eliminating the possibility of pedestrian residence through the HOG (Histograms of Oriented Gradients) pedestrian detection algorithm, and eliminating the possibility of pedestrian residence through the FAST (Features from Accelerated Segment Test) feature point detection algorithm. The detection method can improve detection accuracy of the remnants, lowers calculation complexity, can be better suitable for the complex environment crowded and frequent in shielding, and enhances the anti-interference capability.

Automated data mining using domain-specific analytic applications for solving predefined problems, including populating input data schema, the input data schema having a format appropriate to solution of a predefined problem. Production training a predefined data mining model to produce a trained data mining model, the predefined data mining model comprising a predefined data mining model definition, production training having an output of a knowledge base. Executing a preselected data mining algorithm in production training mode. Production scoring input data from the input data schema. The method typically includes scheduling the steps of populating input data schema, production training, and production scoring. Typically the analytic application includes predefined problems, predefined data mining algorithms, predefined data schema, and at least one predefined data mining model definition.

The invention discloses a computer simulation method of human-computer engineering design of a vehicle cab, comprising the following steps of: firstly, establishing a human parameter database; subsequently carrying out three-dimensional operation domain analysis: inputting or calling existing human dimensions and setting the position of a manipulator to work out the sphere of activity of a human body in each plane; determining the three-dimensional operation domain of the human body by a multi-plane superposition method and judging whether the position of the manipulator is reasonable or not; if reasonable, ending the analysis; otherwise, redesigning the manipulator and carrying out the analysis again; then carrying out visual field analysis: inputting or calling existing eyellipse parameters and setting the position of an indicating instrument to work out the projected outline of the eyellipse and the projective point of the judgment point of the indicating instrument; analyzing the range of the visual field in which the judgment point of the indicating instrument is located; judging whether the position of the indicating instrument is reasonable or not; if reasonable, ending the analysis; otherwise, redetermining the position of the indicating instrument and analyzing again; and finally ending the whole design process. The invention has wide sphere of application and can improve the design efficiency.