1549 results about "Prior information" patented technology

A system and method are provided for receiving speech and/or non-speech communications of natural language questions and/or commands and executing the questions and/or commands. The invention provides a conversational human-machine interface that includes a conversational speech analyzer, a general cognitive model, an environmental model, and a personalized cognitive model to determine context, domain knowledge, and invoke prior information to interpret a spoken utterance or a received non-spoken message. The system and method creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech or non-speech communication and presenting the expected results for a particular question or command.

Systems and methods are provided for receiving speech and non-speech communications of natural language questions and/or commands, transcribing the speech and non-speech communications to textual messages, and executing the questions and/or commands. The invention applies context, prior information, domain knowledge, and user specific profile data to achieve a natural enviromnent for one or more users presenting questions or commands across multiple domains. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context of the speech and non-speech communications and presenting the expected results for a particular question or command.

Systems and methods for receiving natural language queries and/or commands and execute the queries and/or commands. The systems and methods overcomes the deficiencies of prior art speech query and response systems through the application of a complete speech-based information query, retrieval, presentation and command environment. This environment makes significant use of context, prior information, domain knowledge, and user specific profile data to achieve a natural environment for one or more users making queries or commands in multiple domains. Through this integrated approach, a complete speech-based natural language query and response environment can be created. The systems and methods creates, stores and uses extensive personal profile information for each user, thereby improving the reliability of determining the context and presenting the expected results for a particular question or command.

Optical character recognition (OCR) for images such as a street scene image is generally a difficult problem because of the variety of fonts, styles, colors, sizes, orientations, occlusions and partial occlusions that can be observed in the textual content of such scenes. However, a database query can provide useful information that can assist the OCR process. For instance, a query to a digital mapping database can provide information such as one or more businesses in a vicinity, the street name, and a range of possible addresses. In accordance with an embodiment of the present invention, this mapping information is used as prior information or constraints for an OCR engine that is interpreting the corresponding street scene image, resulting in much greater accuracy of the digital map data provided to the user.

A prior information collecting unit transmits in advance a SYN/ACK frame to an address of a client in an external network, and monitors a response to the SYN/ACK frame. If there is no response, the prior information collecting unit determines that the address is a valid attack address. If there is a response with a RST frame, the prior information collecting unit determines that the address is an invalid attack address. An address holding unit stores a responding state of the client. A valid attack identifying unit detects a valid attack frame having a valid attack address as a source address from among frames addressed to the server, based on information stored in the address holding unit. A flow rate limiting unit limits a flow rate at the time of transferring the valid attack frames to the server.

A tomographic reconstruction method and system incorporating Bayesian estimation techniques to inspect and classify regions of imaged objects, especially objects of the type typically found in linear, areal, or 3-dimensional arrays. The method and system requires a highly constrained model M that incorporates prior information about the object or objects to be imaged, a set of prior probabilities P(M) of possible instances of the object; a forward map that calculates the probability density P(D|M), and a set of projections D of the object. Using Bayesian estimation, the posterior probability p(M|D) is calculated and an estimated model M_EST of the imaged object is generated. Classification of the imaged object into one of a plurality of classifications may be performed based on the estimated model M_EST, the posterior probability p(M|D) or MAP function, or calculated expectation values of features of interest of the object.

Disclosed is a method and system for object detection and tracking. Spatio-temporal information for a foreground/background appearance module is updated, based on a new input image and the accumulated previous appearance information and foreground/background information module labeling information over time. Object detection is performed according to the new input image and the updated spatio-temporal information and transmitted previous information over time, based on the labeling result generated by the object detection. The information for the foreground/background appearance module is repeatedly updated until a convergent condition is reached. The produced labeling result from objection detection is considered as a new tracking measurement for further updating on a tracking prediction module. A final tracking result may be obtained through the updated tracking prediction module, which is determined by the current tracking measurement and the previous observed tracking results. The tracking object location at the next time is predicted. The returned predicted appearance information for the foreground/background object is used as the input for updating the foreground and background appearance module. The returned labeling information is used as the information over time for the object detection.

A digital receiver automatically detects and non-coherently demodulates a multiplicity of interfering digitally modulated signals transmitted simultaneously at approximately the same carrier frequency. The receiver includes one or more antenna inputs (e.g., polarization and/or space diverse), a parameter estimator module, and a multiuser detector for estimating the data transmitted by each interfering signals and adapted to operate with at least one of a MUD algorithm with partially quantized prior information and a MUD algorithm based on prewhitened data.

The invention discloses an unmanned aerial vehicle multi-overlapped-remote-sensing-image method for extracting a building contour line. The unmanned aerial vehicle multi-overlapped-remote-sensing-image method includes the steps that three-dimensional point cloud is generated with an aerial-triangulation and dense-matching combined method and filtered, and a building is detected from the point cloud; after the walls of the detected building are canceled, the general contour of the building is extracted from building top face information; the general contour of the building serves as a buffering area to be overlapped on spliced images and serves as shape prior information, evolution is carried out in the buffering area with a level set algorithm, and finally an accurate contour of the building is obtained. By means of the unmanned aerial vehicle multi-overlapped-remote-sensing-image method, as point cloud three-dimensional information generated by the multiple overlapped images is sufficiently used, and meanwhile the high-accuracy geometrical information of the high-resolution remote sensing images is used in a combined mode, the building contour extracting accuracy is remarkably improved, and the complexity of the method is lowered.

A noninvasive image measuring method of measuring internal organ/tissue temperature using an MRI system. Temperature measurement insusceptible to body motion and spatial variation of magnetic field is realized by utilizing the position and size of a temperature change region as a priori information to determine the phase distribution of the complex magnetic resonance signal of water proton at a given temperature point and by subtracting the phase distribution before the temperature change estimated (self-referred) from the phase distribution in the peripheral region for each pixel of the image, thereby eliminating the subtraction process of image before and after temperature change. The precision of temperature measurement can be enhanced by estimating a complex curved surface formed of the peripheral region in each temperature change region of the real-part and imaginary-part images of the complex magnetic resonance signal, and calculating the phase difference between an actually measured complex signal distribution and the estimated complex signal distribution of the complex signal distribution for each pixel, thereby reducing the estimation error due to phase transition from −π to +π occurring in a phase distribution. Furthermore, temperature can be measured through optimal imaging following up body motion by using an optical positioning system in combination even if the part being measured is shifted.

The invention discloses a CT image pulmonary parenchyma three-dimensional semantic segmentation method based on a deep neural network. The segmentation method comprises an offline part and an online part. The offline part comprises four steps: preprocessing a data set; Constructing a full convolutional neural network framework; Constructing a GRU cyclic convolutional neural network framework; Network training. The online part comprises the following five steps: preprocessing an image; Extracting and fusing pixel features; Extracting and fusing voxel characteristics; Performing segmented output; Segmentation result evaluation. The feature fusion comprises feature fusion between an encoding layer and a decoding layer and feature fusion between anatomical structure layers. A deep neural network model with a gating circulation unit is designed, and spatial features are extracted by using anatomical structure prior information of a lung to effectively represent an apparent evolution relationship between fault sequences, so that accurate three-dimensional semantic segmentation is carried out on lung parenchyma in a CT image.

In a method and control device to control a slice image acquisition system, a scan protocol is initially selected from a number of scan protocols, and then an automatic control of the slice image acquisition system (13) ensues on the basis of the selected scan protocol by automatic receipt of previous information regarding the examination subject, automatic synchronization of the previous information with information regarding scan protocol-specific parameters of scan protocols, and automatic selection of the scan protocol, from among the number of scan protocols, that has parameters exhibiting the greatest compatibility with the received previous information according to an established rule.

The invention provides a fast magnetic resonance imaging method and device based on a deep convolution neural network. The fast magnetic resonance imaging method comprises steps of constructing a deep convolution neural network, obtaining an offline magnetic resonance image data, training the deep convolution neural network, learning a mapping relation between an undersampled magnetic resonance image and a full sampled image, using a deep convolution neural network learned through the S2 to reconstruct a resonance image. The fast magnetic resonance imaging method and device based on deep convolution neural network learn an offline deep convolution neural network through using substantial sampled magnetic resonance data, learns a mapping relation between the sampled magnetic resonance image and the full sampled image, fully uses offline substantial the magnetic resonance images to develop the prior information, enables the offline network to recover more fine structure and image characteristics from the undersampled resonance data and improves the magnetic resonance multiple and the imaging accuracy.

The invention provides a method for recognizing indoor and outdoor scenes. The method comprises the following steps: collecting data which are related to the current state of a mobile terminal and the scene, in which the mobile terminal is, through one or more of an optical sensor, an acceleration sensor, a gyroscope, a magnetic sensor, an air pressure sensor, a temperature sensor and/or a global positioning system component of the mobile terminal; and judging whether the current scene, in which the mobile terminal is, is indoor or outdoor on the basis of the collected data. According to the method, data collection and analysis and indoor and outdoor scene reorganization are carried out by using the sensor of a mobile phone instead of any prior information; and the method can be used as lightweight service capable of running on the background of the mobile phone, and has the characteristics of high accuracy rate, short detection time delay, low energy consumption and wide universality.

The invention discloses a method for positioning and recognizing a vehicle logo. The method comprises the following steps of: collecting the vehicle head image of a vehicle by a high-definition camera; positioning the vehicle and positioning and recognizing a vehicle registration plate according to the vehicle head image, and generating the estimated position region of the vehicle logo according to the prior information of the vehicle logo and the vehicle registration plate; in the estimated position region of the vehicle logo, filtering the background region disturbance of the vehicle logo according to extracted texture information, carrying out binaryzation on the texture grey-scale map of the vehicle logo, on which the background region disturbance of the vehicle logo is filtered, accurately positioning the vehicle logo on the generated binary image through a method of finding connected domains in the estimated position region of the vehicle logo and generating the accurate position information of the vehicle logo; according to the accurate position information of the vehicle logo, extracting the accurate grey-scale map of the vehicle logo, carrying out binaryzation on the accurate grey-scale map of the vehicle logo, and generating a binary map corresponding to the vehicle logo; and matching the binary map corresponding to the vehicle logo with a prestored vehicle logo format, carrying out weighing calculation according to the position information, and viewing the vehicle logo type corresponding to the highest score obtained by calculation as the recognizing result of the vehicle logo.

A method for imaging is presented. The method includes receiving a first image data set and at least one other image data set. Further the method includes adaptively selecting corresponding regions of interest in each of the first image data set and the at least one other image data set based upon apriori information associated with each of the first image data set and the at least one other image data set. Additionally, the method includes selecting a customized registration method based upon the selected regions of interest and the apriori information corresponding to the selected regions of interest. The method also includes registering each of the corresponding selected regions of interest from the first image data set and the at least one other image data set employing the selected registration method.

The invention discloses a visual information based real-time calculation method of spatial position of a flying unmanned aircraft, belonging to the technical field of digital video image processing. The method is mainly based on aerial photography image information, elevation information, combines unmanned aircraft flight parameter information to analyze and identify the spatial position of an unmanned aircraft. According to the method, images are rectified by using aerial photography images of an unmanned aircraft and combining flight parameters such as the elevation information of the unmanned aircraft, comparative analysis with prior information is conducted, so that the present location information of the unmanned aircraft can be obtained via the aerial photography images through inverse computation. The visual information based unmanned aircraft flight spatial location real-time calculation method aims to the characteristics of the unmanned aircraft, fully utilizes the visual information and improves the independence of the unmanned aircraft.

Method and system for reducing impulsive burst noise in less delayed reception in pilot based OFDM systems, especially using DVB-T standard such as Digital Video Broadcasting (DVB) is provided. The method contains following steps: 1) recognition of the impulse position and possibly length in the time domain symbol, 2) blanking of those samples of the symbol where significant amount of impulse noise is present, 3) calculating the first estimate of the received signal from the blanked symbol, 4) deriving correction values for the carrier estimates by applying prior information (pilot carriers), and 5) the corrected estimate of the received symbol is derived by subtracting the correction values of step 4 from the first estimate of carriers derived in step 3. The method and arrangement allow correction of fairly long bursts of impulse noise with minor degradation only. The complexity of the scheme and the additional energy consumption are fairly low. The method provides considerably more effective more simple and less delay in broadcast data reception than previously known solutions in interfered multi-carrier signal reception.

A non-contact imaging apparatus for examining an object having complex surfaces or shape deformations. The imaging apparatus includes at least one imaging device for obtaining a scanned image of the exterior surfaces of the object being examined. A predetermined reference image) of an ideal model for the object is stored in a memory. An image register is coupled to the imaging device and to the memory containing the reference image of the ideal model for the object. A transformation estimator compares the scanned image to the reference image and provides a transform which maps the scanned image to the reference image and provides a set of registered object data points. One or more filter modules process the registered object data points with a priori information to reduce noise and to further enhance the accuracy and precision of the registration. A gauge estimator is coupled to the filter module. The gauge estimator utilizes the processed and registered object data to determine deformation parameters of the object, which are then displayed to an operator as gauging information.

The invention discloses an airborne radar clutter suppression method, belonging to the technical field of radar signal processing and aiming at solving the problems of the current clutter suppression technology such as high sample requirement, large calculation amount and poor real-time performance. The implementation steps are as follows: firstly, carrying out clutter pre-processing on the received data according to the prior information of the clutter spectrum distribution to realize dimensional reduction of the space-time bidimensions and reduce the clutter freedom degree; then carrying out cascade connection low-rank adaptive processing and performing multiple filtering and multiple dimensional reduction of the space-time bidimensions on the echoed signal to realize the clutter suppression and target detection of the signals. Indicated by the results of computer simulation analysis and actually measured data processing, the invention has remarkably reduced sample requirement and calculation amount under the precondition of good performance and the filtering performance is greatly improved under the circumstance of equivalent sample requirement, thus the invention can be used in dynamic target detection.

The invention discloses a detecting tracking integrated method for a multi-target scene, and belongs to the technology of radar detecting and tracking. The method is a multi-target tracking method coupling Bayes detection and joint probabilistic data association (JPDA) filtering. The method includes the steps that position distribution information of targets at the current moment is calculated according to prediction of a JPDA tracking filter at the previous moment; a Bayes detector takes the distribution information as prior information for detecting a judgment and detects the targets; finally, the JPDA tracking filter is used for detecting obtained measurement trace points and carries out data correlation on the measurement trace points and the targets to finish position estimation and track updating of the targets at the current moment, and position distribution information of the targets at the next moment is predicted. The method can be used in detection and tracking of adjacent targets, and has good performance and good practicality.

This invention presents an innovative framework for the application of machine learning for identification of alloys or composites with desired properties of interest. For each output property of interest, we identify the corresponding driving (input) factors. These input factors may include the material composition, heat treatment, process, microstructure, temperature, strain rate, environment or testing mode. Our framework assumes selection of optimization technique suitable for the application at hand and data available, starting with simple linear, or quadratic, regression analysis. We present a physics-based model for predicting the ultimate tensile strength, a model that accounts for physical dependencies, and factors in the underlying physics as a priori information. In case an artificial neural network is deemed suitable, we suggest employing custom kernel functions consistent with the underlying physics, for the purpose of attaining tighter coupling, better prediction, and extracting the most out of the—usually limited—input data available.